Next Issue
Volume 14, August
Previous Issue
Volume 14, June
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.1
3.0
Journals
Machines
Volume 14
Issue 7
share announcement

Machines, Volume 14, Issue 7 (July 2026) – 122 articles

Cover Story (view full-size image): How can robots safely transport objects for which physical properties are not precisely known? This work introduces a dual-phase manipulation framework that combines uncertainty-aware trajectory planning and nonlinear predictive control to enable robust tray delivery. Objects are first positioned through intentional sliding on a tray and then transported while preventing undesired motion, even in the presence of modeling uncertainties. The proposed strategy enhances safety, accuracy, and energy efficiency, bringing service robots closer to performing reliable delivery and assistance tasks in real-world environments such as hospitals, healthcare facilities, and domestic settings. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
26 pages, 6616 KB  
Article
Integrated FEM Evaluation and Optimization of Excavation, Loading, and ROPS/FOPS Systems in a Skid-Steer Loader
by Diego Andrés Duque-Sarmiento, Gustavo Morocho, Juan José Molina-Campoverde and Xavier Narváez
Machines 2026, 14(7), 833; https://doi.org/10.3390/machines14070833 - 22 Jul 2026
Viewed by 448
Abstract
This study proposes an integrated finite element methodology for evaluating and redesigning three critical subsystems of an XCMG XC740K skid-steer loader: the excavation attachment, the arm–bucket charging system, and the ROPS/FOPS operator protection cab. The components were reconstructed by reverse engineering and 3D [...] Read more.
This study proposes an integrated finite element methodology for evaluating and redesigning three critical subsystems of an XCMG XC740K skid-steer loader: the excavation attachment, the arm–bucket charging system, and the ROPS/FOPS operator protection cab. The components were reconstructed by reverse engineering and 3D scanning, modeled in CAD, and simulated in ANSYS Workbench/Mechanical under load cases derived from hydraulic parameters, soil–tool interaction, and international safety standards. The novelty of the work lies in applying a single FEM-based workflow to three interacting subsystems of the same compact machine, rather than optimizing isolated components independently. The original configuration showed critical effort concentrations in the cab and charging system. Localized geometric reinforcements and the use of high-strength and wear-resistant steels improved stiffness and safety margins in the excavation bucket, loading bucket, and ROPS/FOPS cab. However, the arm–quick coupler region remained the controlling weak point of the loading assembly, indicating the need for further redesign. The proposed approach provides a transferable computational framework for identifying structural vulnerabilities and prioritizing redesign actions in compact earthmoving machinery. Because the study is numerical, future experimental validation is required before certification or field implementation. Full article
(This article belongs to the Section Machine Design and Theory)
►▼ Show Figures

Figure 1

30 pages, 23708 KB  
Article
Impact Parameter Inversion and Quantitative Damage Assessment of Helicopter Tail Drive Shafts Based on Stress Wave Characteristics and Physics-Guided Hierarchical Gaussian Process Regression
by Qizhou Wu, Yiping Shen, Songlai Wang, Yanfeng Peng and Jian Li
Machines 2026, 14(7), 832; https://doi.org/10.3390/machines14070832 - 22 Jul 2026
Viewed by 508
Abstract
The helicopter tail drive shaft is vulnerable to failure from projectile impacts during low-altitude flight. Stress wave-based inversion of impact parameters and quantitative damage assessment remain insufficiently explored. To address small-sample and nonlinear challenges, a framework based on stress wave characteristics and physics-guided [...] Read more.
The helicopter tail drive shaft is vulnerable to failure from projectile impacts during low-altitude flight. Stress wave-based inversion of impact parameters and quantitative damage assessment remain insufficiently explored. To address small-sample and nonlinear challenges, a framework based on stress wave characteristics and physics-guided hierarchical Gaussian process regression is proposed. Four key features, namely first-arrival wave trough amplitude, frequency standard deviation, ratio of low-frequency to high-frequency root mean square, and wavelet energy entropy, are extracted from transient signals to construct a hierarchical progressive architecture for damage mode discrimination, parameter inversion, and quantitative assessment. Perforation is identified using a wavelet energy entropy-based adaptive threshold. Incidence angle inversion is achieved by an adaptive composite kernel and Bayesian physical prior correction. Damage degree is assessed through residual learning guided by a physical prior surface mean function. Results show an incidence angle inversion root mean square error (RMSE) of 3.02°, with entry and exit hole equivalent failure area RMSEs of 13.32 mm2 and 12.98 mm2, respectively. The 95% prediction interval maintained reliable coverage across the validation samples. This framework provides a new method with both physical interpretability and uncertainty quantification for the assessment of impact damage in thin-walled tube structures. Full article
(This article belongs to the Section Machines Testing and Maintenance)
►▼ Show Figures

Figure 1

35 pages, 3685 KB  
Review
A Review of Modern Excitation Strategies for Wound Field Synchronous Motors: An Electric Vehicle Perspective
by Pragya Raghav and Himavarsha Dhulipati
Machines 2026, 14(7), 831; https://doi.org/10.3390/machines14070831 - 22 Jul 2026
Viewed by 816
Abstract
Wound Field Synchronous Motors (WFSMs) offer precise control over the rotor magnetic field, making them well suited to electric vehicle (EV) traction applications that require adjustable excitation, wide constant-power operation, and freedom from rare-earth permanent magnets. The excitation system (ES) governs the rotor [...] Read more.
Wound Field Synchronous Motors (WFSMs) offer precise control over the rotor magnetic field, making them well suited to electric vehicle (EV) traction applications that require adjustable excitation, wide constant-power operation, and freedom from rare-earth permanent magnets. The excitation system (ES) governs the rotor field strength and therefore directly influences motor efficiency, dynamic response, and operational stability. This paper reviews modern excitation strategies for WFSMs in EV traction, with particular emphasis on contactless approaches based on wireless power transfer (WPT). The fundamental principles of inductive power transfer (IPT) and capacitive power transfer (CPT) are presented, together with their design considerations, compensation topologies, power electronic interfaces, control strategies, and practical challenges, followed by a discussion of hybrid IPT–CPT systems. Representative experimental studies in each category are compared on the basis of power level, efficiency, operating frequency, and misalignment tolerance. A capacitive power coupler is also designed for a WFSM, which requires a 6-amp DC field current, where the geometry of the coupler is constrained by the WFSM rotor geometry. The review identifies open challenges—including misalignment sensitivity, electromagnetic interference, thermal constraints, and air-gap variability under rotation—and outlines research directions for compact, efficient, and reliable WPT-based excitation systems for next-generation EV traction motors. Full article
(This article belongs to the Section Electrical Machines and Drives)
►▼ Show Figures

Figure 1

21 pages, 17691 KB  
Article
Preload-Loss State Identification of Bolted Joints Using Multi-Sensor Electromechanical Impedance Signals and a Distance-Weighted Graph Convolutional Network
by Lu Li, Xingyu Fan, Yuxuan Wang, Tong Zhao and Jin Mao
Machines 2026, 14(7), 830; https://doi.org/10.3390/machines14070830 - 21 Jul 2026
Viewed by 275
Abstract
To address the insufficient fusion of electromechanical impedance (EMI) response features from multiple sensors and the limited characterization of spatial relationships between sensors and bolt nodes in four-bolt connection structures, this study proposes an improved graph convolutional network (GCN) model integrating Batch Normalization [...] Read more.
To address the insufficient fusion of electromechanical impedance (EMI) response features from multiple sensors and the limited characterization of spatial relationships between sensors and bolt nodes in four-bolt connection structures, this study proposes an improved graph convolutional network (GCN) model integrating Batch Normalization (BN) and Distance Weighting (DW) strategies for bolt preload-loss state identification. First, PZT sensor nodes and bolt nodes are jointly represented as a graph structure, and the correlation coefficient deviation (CCD) is extracted as the EMI response feature. Then, a weighted adjacency matrix is constructed according to the geometric distances between sensor nodes and bolt nodes to describe the spatial coupling relationships among different nodes. Subsequently, the weighted adjacency matrix and node features are input into the GCN, and a BN layer is introduced after the graph convolutional layers to reduce the influence of multi-channel feature distribution variations on model training stability. Experimental results on a four-bolt connection structure show that the proposed GCN-BN-DW model outperforms the Basic GCN, GCN-BN, GCN-DW, and several benchmark models in terms of prediction accuracy and stability. Under the strict five-fold cross-validation protocol, the proposed model achieves a test MAE of 2.400±0.100, RMSE of 3.302±0.239, MASE of 0.300±0.013, and R2 of 0.821±0.033. These results indicate that the proposed model can effectively integrate multi-sensor EMI features and sensor–bolt spatial relationships, providing a feasible graph-based modeling approach for bolt preload-loss state identification. Full article
(This article belongs to the Section Electromechanical Energy Conversion Systems)
►▼ Show Figures

Figure 1

26 pages, 58326 KB  
Article
Numerical Investigation of Rock-Cutting Mechanics and Energy Efficiency of an Oscillating Disc Cutter
by Yuxuan Zhang, Huijun Liang, Zhibin Li, Zhipeng Fang and Bijuan Yan
Machines 2026, 14(7), 829; https://doi.org/10.3390/machines14070829 - 21 Jul 2026
Viewed by 394
Abstract
Conventional roadheader cutting tools are subjected to substantial forces, intense impacts, and friction during rock excavation, resulting in excessive energy consumption and accelerated tool wear. To address these challenges, undercutting technology has emerged as a promising alternative for integrating disc cutters into roadheaders. [...] Read more.
Conventional roadheader cutting tools are subjected to substantial forces, intense impacts, and friction during rock excavation, resulting in excessive energy consumption and accelerated tool wear. To address these challenges, undercutting technology has emerged as a promising alternative for integrating disc cutters into roadheaders. In this study, a comprehensive mechanical investigation is conducted on an Oscillating Disc Cutter (ODC) based on the undercutting principle to enhance fragmentation efficiency and minimize energy requirements. A high-fidelity numerical framework, coupling the Finite Element Method (FEM) and Smoothed Particle Hydrodynamics (SPH), is established to simulate the dynamic ODC cutting process. This model is rigorously validated against both theoretical analyses and experimental data. Results demonstrate that the ODC can reduce the minimum specific energy by 78% compared to conventional non-eccentric cutters and attenuates the average rolling, side, and normal forces by 70.9%, 59.4%, and 67.9%, respectively. Furthermore, parametric analysis reveals a strong sensitivity of cutting performance to oscillation frequency and feed rate. These findings confirm that the ODC mechanism effectively mitigates cutting resistance and optimizes rock fragmentation, providing essential theoretical and practical guidance for the development of high-efficiency underground excavation equipment. Full article
(This article belongs to the Section Machine Design and Theory)
►▼ Show Figures

Figure 1

27 pages, 535 KB  
Article
Robust Adaptive Cooperative Tracking Control for Multi-Train Systems with State Constraints, Collision Avoidance, and Time-Varying Parametric Uncertainties
by Yi Huang, Zuguo Chen, Chaoyang Chen and Biao Luo
Machines 2026, 14(7), 828; https://doi.org/10.3390/machines14070828 - 21 Jul 2026
Viewed by 272
Abstract
This paper investigates cooperative tracking control for virtually coupled multi-train systems subject to nonlinear running resistance, bounded time-varying resistance parameters, state constraints, and actuator saturation. The theoretical contribution is not the separate use of barrier Lyapunov functions, adaptive control, anti-windup compensation, or distributed [...] Read more.
This paper investigates cooperative tracking control for virtually coupled multi-train systems subject to nonlinear running resistance, bounded time-varying resistance parameters, state constraints, and actuator saturation. The theoretical contribution is not the separate use of barrier Lyapunov functions, adaptive control, anti-windup compensation, or distributed cooperative control. Instead, the revised analysis establishes a coupled safety-and-boundedness certificate for the actual saturated closed-loop vector field. The closing-speed-aware spacing variable and actuator-authority condition support a first-exit proof of forward invariance, after which a composite Lyapunov analysis couples the saturation residual, anti-windup state, cooperative tracking error, and time-varying parameter-estimation error to establish uniform ultimate boundedness without persistent excitation. This proof architecture distinguishes the proposed controller from recent constrained train-control methods focused separately on velocity/input bounds, distance-oriented full-state barriers, or iteration-indexed learning. Numerical studies with heterogeneous trains, stronger time-varying aerodynamic perturbations, normalized actuator limits, tracking-bound verification, constrained baselines, a near-boundary safety-allocation case, and a quantitative one-factor-at-a-time parameter-sensitivity study are provided. Full article
(This article belongs to the Special Issue Motion Planning and Control in Autonomous Robotic Systems)
►▼ Show Figures

Figure 1

33 pages, 5530 KB  
Article
Study on Performance Testing and Evaluation of Adaptive Cruise Control Systems Based on a Self-Constructed Comprehensive Performance Evaluation Index Model
by Hongtao Zhang, Wanyou Huang, Yan Wang, Xuesong Tian, Wenjun Fu, Ruixia Chu and Fangyuan Qiu
Machines 2026, 14(7), 827; https://doi.org/10.3390/machines14070827 - 21 Jul 2026
Viewed by 350
Abstract
Adaptive cruise control (ACC) performance is affected by multiple coupled factors, including safety margin, dynamic response, spacing regulation, target-transition behavior, and ride comfort. A single indicator is therefore insufficient for comprehensive ACC evaluation. This study proposes an adaptive cruise control comprehensive performance evaluation [...] Read more.
Adaptive cruise control (ACC) performance is affected by multiple coupled factors, including safety margin, dynamic response, spacing regulation, target-transition behavior, and ride comfort. A single indicator is therefore insufficient for comprehensive ACC evaluation. This study proposes an adaptive cruise control comprehensive performance evaluation index model (ACC-CPEIM) for scenario-oriented ACC testing and diagnosis. The model links functional objectives, six typical ACC scenarios, measurable longitudinal indicators, hierarchical weights, and scenario-specific scoring rules into a unified evaluation chain. Time-domain response data are converted into scenario-level, criterion-level, and overall performance scores, while the results remain traceable to specific weak scenarios and performance dimensions. The proposed model was evaluated using a CarSim/Simulink co-simulation platform and further applied to vehicle-test data. The co-simulation results yielded an overall score of approximately 3.32 and identified weak acceleration-following response, insufficient spacing reserve during deceleration, and limited cut-in safety margin as the main limitations. The vehicle-test application produced an overall score of approximately 2.98 and showed that comfort and steady-state control were relatively stronger, whereas target-transition adaptability, safety margin, and dynamic response remained limiting dimensions. The results indicate that the ACC-CPEIM can provide quantitative, interpretable, and engineering-oriented support for ACC performance testing and diagnosis. Full article
(This article belongs to the Section Automation and Control Systems)
►▼ Show Figures

Figure 1

31 pages, 4463 KB  
Article
A Tool Wear Prediction Network Fusing Visual-Acoustic Cross-Attention and Interval Guidance
by Xilu Zhang, Ruying Pang, Ruikun Zhou and Zhiping Wang
Machines 2026, 14(7), 826; https://doi.org/10.3390/machines14070826 - 21 Jul 2026
Viewed by 312
Abstract
To address the limitations of single-modality feature characterization in tool wear monitoring, as well as the susceptibility of deep regression models to local optima and their poor robustness under complex working conditions, this paper proposes a tool wear prediction method based on a [...] Read more.
To address the limitations of single-modality feature characterization in tool wear monitoring, as well as the susceptibility of deep regression models to local optima and their poor robustness under complex working conditions, this paper proposes a tool wear prediction method based on a multimodal attention mechanism and interval guidance. First, a Region of Interest (ROI) algorithm removes visual background redundancy, constructing an adaptive ROI-based visual stream feature model to achieve spatial alignment across image dimensions. Concurrently, the Gramian Angular Field (GAF) is introduced to encode one-dimensional acoustic emission signals into two-dimensional time-frequency feature maps. Subsequently, utilizing the EfficientNetV2 backbone network, Bi-Directional Cross-Attention (BCA) is employed to facilitate deep interaction between visual and acoustic features, ensuring cross-modal semantic alignment. Second, interval classification is introduced as an auxiliary constraint to guide the model toward precise localization within the fine-grained regression space, while a priori constraints are applied to this feature space. To mitigate task weight uncertainty, a Stable Kendall Loss is utilized to adaptively balance the weights among the global regression, interval classification, and structured regression tasks. Finally, the proposed model is experimentally validated using the MATWI dataset. Experimental results demonstrate a classification accuracy of 94.58% and a minimum mean absolute error (MAE) of 6.6183 μm. Compared to state-of-the-art prediction methods and official benchmarks, the proposed model achieves superior performance across all evaluation metrics. Notably, it reduces prediction errors by approximately 65% relative to the benchmark model, fully validating its high accuracy and robust performance under complex working conditions. Full article
(This article belongs to the Section Advanced Manufacturing)
►▼ Show Figures

Figure 1

24 pages, 5115 KB  
Article
Automated Drive Curve Offset Strategy for Corner Cleaning Based on Enhanced Principal Component Analysis
by Chaoqian Zhang, Dongyue Li, Chunming Yuan, Liyong Shen, Hongyu Ma, Ling Liu and Shuopeng Chen
Machines 2026, 14(7), 825; https://doi.org/10.3390/machines14070825 - 20 Jul 2026
Viewed by 368
Abstract
Corner cleaning is a critical sub-stage of finishing and is used to remove residual material left by previous machining operations, thereby ensuring the designed dimensional precision and surface quality. Although essential in CNC machining, many current industrial CAM software like UG NX, PowerMill [...] Read more.
Corner cleaning is a critical sub-stage of finishing and is used to remove residual material left by previous machining operations, thereby ensuring the designed dimensional precision and surface quality. Although essential in CNC machining, many current industrial CAM software like UG NX, PowerMill systems were largely developed based on early-stage theoretical frameworks. Meanwhile, the geometric shapes of machined workpieces are becoming increasingly complex, making such software gradually unable to meet the growing requirements for tool path quality. This paper establishes a rigorous mathematical framework to bridge the gap between industrial practice and theoretical modeling. Based on this framework, an enhanced Principal Component Analysis (PCA) method is proposed to generate an optimal drive curve by integrating geometric variance maximization with vector field guided directional optimization. Furthermore, a robust offset strategy is presented, incorporating self-intersection detection, critical-point trimming, and segment connection mechanisms to ensure path continuity and smoothness. Experimental results and real machining cases demonstrate that the proposed method outperforms the widely used commercial software in terms of robustness and path smoothness, validating its effectiveness and practical applicability. Full article
(This article belongs to the Section Advanced Manufacturing)
►▼ Show Figures

Figure 1

28 pages, 7528 KB  
Article
Dual-Rotor Straight Blade Vertical-Axis Wind Turbine for Farm Settings: A Numerical Study
by Belal H. Shanab and Alexandrina Untaroiu
Machines 2026, 14(7), 824; https://doi.org/10.3390/machines14070824 - 20 Jul 2026
Viewed by 271
Abstract
Vertical-axis wind turbines (VAWTs) are recognized as a viable option for wind energy farms due to their compact design and suitability for different wind settings, such as urban and offshore environments. VAWT wind farms have been studied with respect to various turbine spacing [...] Read more.
Vertical-axis wind turbines (VAWTs) are recognized as a viable option for wind energy farms due to their compact design and suitability for different wind settings, such as urban and offshore environments. VAWT wind farms have been studied with respect to various turbine spacing and configurations that demonstrate that the VAWT wind farm is well-suited for improving efficiency while requiring less land, compared to horizontal-axis wind turbines (HAWTs). Moreover, the use of combined dual-rotor configurations has recently given attention as a passive strategy to enhance the aerodynamic performance of VAWTs. Despite these advances, the optimal arrangement of VAWT farms, including inter-turbine distances, clustering configurations, and land-use efficiency of such dual rotors, has yet to be explored. This study investigates different clustering scenarios, including vertically aligned pairs and staggered clusters of three turbines, to evaluate their impact on power capture and land usage for a dual-rotor straight-blade vertical-axis wind turbine (DR-SBVAWT). The 2D-dimensional transient (URANS) numerical simulations are conducted using the k-ω SST turbulence model. Performance indices, namely, total power coefficient and improvement relative to standalone turbines, are analyzed. Wake effects are investigated through detailed velocity contour plots of the wind field. Results reveal that a DR-SBVAWT turbine arrangement can enhance wind farm performance by approximately 25% for two turbines and about 20% for three staggered turbines, with required spacing of 1.5 D and 2.5–3 D, respectively (Here, D is the outer diameter of the DR-SBVAWT). The study overall provides insights into the optimal placement and configuration of DR-SBVAWTs for maximizing energy output while minimizing land usage, offering guidance for the design of more efficient VAWT farms. Full article
(This article belongs to the Special Issue Aerodynamic Analysis of Wind Turbine Blades)
►▼ Show Figures

Figure 1

35 pages, 10861 KB  
Article
Short-Time Fourier Transform-Based Multi-Scale Attention ResNet for Phase Resistance Unbalance Diagnosis in an Industrial Robotic Joint Drive System
by Huanqing Han, Zhili Lin, Dongqin Li and Fengshou Gu
Machines 2026, 14(7), 823; https://doi.org/10.3390/machines14070823 - 20 Jul 2026
Viewed by 346
Abstract
Phase resistance unbalance in robotic joint drive systems can alter electromagnetic torque generation and degrade motion accuracy, but its early diagnosis is challenging because fault-related signatures are weak and coupled with operating dynamics. This study proposes a short-time Fourier transform (STFT)-based multi-scale attention [...] Read more.
Phase resistance unbalance in robotic joint drive systems can alter electromagnetic torque generation and degrade motion accuracy, but its early diagnosis is challenging because fault-related signatures are weak and coupled with operating dynamics. This study proposes a short-time Fourier transform (STFT)-based multi-scale attention ResNet for phase resistance-unbalance diagnosis using synchronized multi-sensor signals from a single industrial robotic joint. Controlled resistance-unbalance states were generated on an eRob70F100I-BM-18EN joint module by inserting 0.05 Ω and 0.1 Ω series resistors into one motor phase with a nominal single-phase resistance of 0.75 Ω. Current, acceleration, rotational speed, and torque signals were segmented and converted into four-channel STFT log-amplitude maps. A modified ResNet18 backbone was integrated with feature pyramid network (FPN)-style multi-scale fusion and a convolutional block attention module (CBAM) to enhance discriminative time–frequency features. Under a window-level stratified split, the proposed model achieved 98.97% accuracy and 98.97% macro-F1, outperforming raw-signal, fast Fourier transform (FFT), wavelet, STFT-ResNet18, STFT-VGG11-BN, STFT-MobileNetV2, and STFT-ShuffleNetV2 baselines. Grouped validation was conducted using file-level, leave-one-speed-out, and leave-one-load-out splits to assess robustness under stricter data partitions. The proposed model achieved 91.75% macro-F1 under file-level splitting and average macro-F1 values of 89.77% and 84.22% under leave-one-speed-out and leave-one-load-out validation, respectively. Grad-CAM visualization further indicates that the model relies on non-uniform local time–frequency regions rather than uniformly using the entire spectrogram. These results demonstrate effective robotic-joint resistance-unbalance discrimination while revealing that unseen operating conditions, especially specific speed and load settings, remain challenging for robust cross-condition deployment. Full article
(This article belongs to the Special Issue Tool Wear Condition Monitoring in Smart Manufacturing: Sensors, Analytics, and Decision-Making)
►▼ Show Figures

Figure 1

23 pages, 3799 KB  
Article
Intelligent Condition Monitoring for Machining Processes Under Cross-Domain Scenarios via Semi-Supervised Feature Separation
by Yue Zhao, Qi Chen, Long Gao and Hengchang Liu
Machines 2026, 14(7), 822; https://doi.org/10.3390/machines14070822 - 20 Jul 2026
Viewed by 316
Abstract
Tool wear state classification under varying working conditions remains challenging due to domain discrepancy and the scarcity of labeled target samples. To address this issue, this paper proposes a Semi-Supervised Domain-Adaptive Feature Separation framework (SS-DAFS) for intelligent condition monitoring in machining processes. Experiments [...] Read more.
Tool wear state classification under varying working conditions remains challenging due to domain discrepancy and the scarcity of labeled target samples. To address this issue, this paper proposes a Semi-Supervised Domain-Adaptive Feature Separation framework (SS-DAFS) for intelligent condition monitoring in machining processes. Experiments are conducted on the PHM2010 milling dataset, where tool conditions are categorized into three health states, including initial wear, normal wear, and severe wear. The proposed framework separates shared domain-invariant features from private domain-specific features to enhance feature representation capability and reduce domain-specific interference. Meanwhile, Maximum Mean Discrepancy (MMD) is incorporated to further align feature distributions between source and target domains. Semi-supervised transfer tasks under one-shot and three-shot settings are constructed to evaluate the effectiveness of the proposed framework with extremely limited labeled target samples. Experimental results demonstrate that the proposed framework consistently outperforms several representative domain adaptation methods under both settings. The average accuracy of the proposed method under three-shot and one-shot achieves 95.68% and 94.34%, respectively. The results verify the effectiveness of the proposed framework for intelligent condition monitoring for machining processes under cross-domain machining scenarios. Full article
(This article belongs to the Special Issue Tool Wear, Monitoring, and Life Prediction in Machining Processes)
►▼ Show Figures

Figure 1

17 pages, 3422 KB  
Article
Mechanical Design and Simulation Testing of Rope Pollination Equipment for Hybrid Rice Seed Production
by Zhide Ma, Jianbo Zhou, Jibing Chen and Yiping Wu
Machines 2026, 14(7), 821; https://doi.org/10.3390/machines14070821 - 19 Jul 2026
Viewed by 357
Abstract
In view of the urgent need for pollination equipment for existing hybrid rice and the practical problems of traditional manual pollen-driving, such as high labor intensity, low efficiency, and easy-to-break rice stems, an automatic pollen-driving system combining traditional manual and mechanical auxiliary control [...] Read more.
In view of the urgent need for pollination equipment for existing hybrid rice and the practical problems of traditional manual pollen-driving, such as high labor intensity, low efficiency, and easy-to-break rice stems, an automatic pollen-driving system combining traditional manual and mechanical auxiliary control was designed. According to the analysis of the driving process, the driving speed v and the rope height h are the main factors affecting the bending degree of rice stems (the cross-section angle θ of rice stems). Through shear and extrusion tests, the characteristic parameters of rice stems and the bonding parameters of the rice stem bonding model were obtained. The test results showed that when the bending angle of the rice stem was 47°, the maximum shear force of the rice stem was 5.42 N. A quadratic orthogonal rotation combination simulation test was carried out using the discrete element method (EDEM), and the optimal parameter combination of powder driving speed and rope height was determined. The angle error between the measured angle value and that obtained by the constraint solving tool of Design-Expert software was less than 5%. Furthermore, combined with field experiments, through the optimization of the pollen-driving operation parameters, the phenomenon of rice breakage was reduced in the process of pollen-driving. Therefore, the research in this paper can provide certain references for the design of hybrid rice powder-driven systems and the optimization of operating parameters. Full article
(This article belongs to the Special Issue Intelligent and Cooperative Agricultural Machines: Adapting Robots and AI to Agricultural Environments)
►▼ Show Figures

Figure 1

26 pages, 12592 KB  
Review
Pump Turbines Under Near-Zero Flow Conditions: A Review of Flow Instabilities, Guide Vane Dynamics, and Mitigation Strategies
by Hui Zeng, Yuhao Yan, Bin Wang, Zhengwei Wang, Jingyu Wan and Xuezhi Zhou
Machines 2026, 14(7), 820; https://doi.org/10.3390/machines14070820 - 19 Jul 2026
Viewed by 418
Abstract
The grid volatility caused by the integration of wind and solar power poses challenges to power systems, where Pumped Storage Hydropower (PSH) plays an irreplaceable role. During start-up, shutdown, and mode transition of pump turbines, near-zero flow conditions frequently occur, leading to severe [...] Read more.
The grid volatility caused by the integration of wind and solar power poses challenges to power systems, where Pumped Storage Hydropower (PSH) plays an irreplaceable role. During start-up, shutdown, and mode transition of pump turbines, near-zero flow conditions frequently occur, leading to severe hydraulic instability, guide vane vibration, and abnormal noise. This review synthesizes field observations from multiple high-head pumped storage stations together with recent experimental, numerical, and theoretical studies. The review indicates that hydraulic instability is primarily associated with the coupled effects of clearance leakage flow, bi-stable flow, and Rotor–Stator Interaction (RSI). The review suggests that self-excited vibration, rather than forced resonance, dominates guide vane vibration and abnormal noise under near-zero flow conditions. Four mainstream regulation strategies are summarized, including Misaligned Guide Vanes (MGVs), start-up/shutdown sequence optimization, structural-parameter adjustment, and operating range avoidance. The applicability and limitations of each strategy are discussed. These findings provide support for the design and operation of high-head, large-capacity pump turbines. Full article
(This article belongs to the Section Turbomachinery)
►▼ Show Figures

Graphical abstract

32 pages, 2183 KB  
Article
Power-Smoothing Control Strategy for a Slope-Track Gravity Energy Storage System in Wind-Farm Applications
by Su Wang and Liye Xiao
Machines 2026, 14(7), 819; https://doi.org/10.3390/machines14070819 - 18 Jul 2026
Viewed by 313
Abstract
With the increasing penetration of renewable energy, smoothing wind-farm-level power fluctuations at the point of common coupling has become an important requirement for maintaining grid stability. However, the dynamic power-tracking mechanism of large-inertia slope-track solid gravity energy storage systems remains insufficiently understood. This [...] Read more.
With the increasing penetration of renewable energy, smoothing wind-farm-level power fluctuations at the point of common coupling has become an important requirement for maintaining grid stability. However, the dynamic power-tracking mechanism of large-inertia slope-track solid gravity energy storage systems remains insufficiently understood. This paper presents a theoretical and control-oriented study of a slope-track solid gravity energy storage system by establishing a low-speed-branch electromechanical coupling model, deriving its steady-state power-speed characteristics, and formulating several feedforward-feedback electromagnetic torque control laws. Pure feedforward control, power feedback, speed feedback, and a gain-scheduled speed feedback law are analyzed within a unified framework. The results show that, for a given power command and under sufficient torque-control authority, increasing the moving load or slope angle enhances the gravity-driven torque and reduces the required operating speed, acceleration, and cumulative displacement. This mechanism indicates that systems with heavier loads or steeper slopes have an advantage in smoothly responding to wind-power fluctuations at a fixed power scale. Frequency-response analysis further shows that the low-speed branch is suitable for slow and medium time-scale power smoothing, whereas rapidly varying commands remain constrained by the closed-loop response time and inertial correction terms. To demonstrate a finite-track implementation of the theory, a single-track multi-unit scheme with 30 standard load units is designed and numerically tested for wind-farm-side smoothing and slow-varying command tracking. This analysis provides a theoretical basis for prototype design and parameter selection before costly full-scale experimental validation. Full article
(This article belongs to the Section Electromechanical Energy Conversion Systems)
►▼ Show Figures

Figure 1

22 pages, 11908 KB  
Article
Full-Space Modeling of Geometric Variation Propagation in a Multi-Axis Milling System Considering Local Parallel Chains
by Shun Liu, Yang Xiang, Qunfei Gu, Yongqiao Jin and Sun Jin
Machines 2026, 14(7), 818; https://doi.org/10.3390/machines14070818 - 18 Jul 2026
Viewed by 279
Abstract
The end-effector accuracy of a multi-axis milling system is primarily affected by assembly errors and deformation errors induced by low structural stiffness. This accuracy exhibits spatially nonlinear and non-uniform variations with changes in system pose, especially in robotic milling systems. Therefore, full-space accuracy [...] Read more.
The end-effector accuracy of a multi-axis milling system is primarily affected by assembly errors and deformation errors induced by low structural stiffness. This accuracy exhibits spatially nonlinear and non-uniform variations with changes in system pose, especially in robotic milling systems. Therefore, full-space accuracy modeling that accounts for manufacturing and assembly processes is crucial, particularly for machining workspace optimization. However, existing assembly deviation models are generally limited to error fluctuation simulations under fixed poses and lack the capability to analyze accuracy variations across the entire motion space of kinematic mechanisms, often requiring remodeling for different poses. To address this issue, this paper proposes a full-space geometric variation propagation modeling method for multi-axis robotic machining systems, considering local parallel chains. In the proposed model, the effects of manufacturing tolerances of multiple axes and their propagation on the geometric accuracy of a multi-axis milling system are considered in the spatial domain during the milling motion process. Firstly, three-dimensional tolerance expressions of joint and shaft-hole features are defined using small displacement Torsors, which can represent small feature variations within their tolerance ranges. Then, feature-to-feature Jacobian matrices are defined to characterize geometric variation propagation in multi-axis assemblies. Consequently, an overall Jacobian–Torsor-based expression model can be generated through the construction of a dimensional chain diagram. Based on the proposed model, case studies are conducted on a multi-axis robotic milling system to validate its effectiveness in modeling geometric variation propagation. The proposed method provides a comprehensive understanding of the mechanism of geometric variation propagation in robotic milling processes. Full article
(This article belongs to the Special Issue Intelligent Design and Application of Parallel Robots)
►▼ Show Figures

Figure 1

22 pages, 781 KB  
Article
A Fault-Tolerant Finite-Control-Set MPC Architecture with Asymmetry-Aware Thermal Balancing for Switched Reluctance Motor Drives
by Franklin Sánchez, María Isabel Milanés-Montero and Enrique Romero-Cadaval
Machines 2026, 14(7), 817; https://doi.org/10.3390/machines14070817 - 18 Jul 2026
Viewed by 240
Abstract
Switched reluctance motors (SRMs) are attractive for fault-tolerant drives because their rare-earth-free rotor and intrinsic phase isolation support continued operation after a converter fault. Realising this requires a post-fault control policy that preserves both torque tracking and per-phase thermal balance, with the latter [...] Read more.
Switched reluctance motors (SRMs) are attractive for fault-tolerant drives because their rare-earth-free rotor and intrinsic phase isolation support continued operation after a converter fault. Realising this requires a post-fault control policy that preserves both torque tracking and per-phase thermal balance, with the latter being a safety-relevant design consideration motivated by—though not herein verified against—ISO 26262. This paper proposes and evaluates, by simulation, a three-layer fault-tolerant finite-control-set model predictive control (FCS-MPC) architecture for a four-phase 8/6 SRM under a single open-phase converter fault. The layers are (i) a vector-set reconfiguration from the eight healthy, active vectors to the twenty-six admissible post-fault vectors, which restores controllability of the reduced converter; (ii) soft commutation expressed as a position-dependent penalty inside the MPC cost; and (iii) asymmetry-aware balancing that evens out the accumulated thermal load across the three healthy phases. We additionally analyse an activated-on-demand max-penalty thermal limiter and show, both analytically and in simulation, that it shares its optimiser with the variance-based balancing term and therefore confers no measurable benefit over it; it is consequently retained only as an optional on-demand limiter rather than a separate layer. The architecture is benchmarked against a fault-blind baseline, a rule-based hard fault-tolerant reference (Hard-FT), and intermediate configurations through a deterministic ablation across three critical operating points, complemented by a robustness assessment under measurement noise and parameter mismatch. A six-criteria fault-tolerance scorecard is reported as a methodological observation on the transferability of healthy-mode SRM specifications to post-fault operation. Full article
(This article belongs to the Special Issue Dynamics and Control of Electric Vehicles)
►▼ Show Figures

Figure 1

16 pages, 16673 KB  
Article
A Novel Method for Compensating Pitch and Tooth Thickness Deviations in Face Gear Worm Grinding
by Haiyu He, Yuansheng Zhou, Chao Li and Jinyuan Tang
Machines 2026, 14(7), 816; https://doi.org/10.3390/machines14070816 - 18 Jul 2026
Viewed by 262
Abstract
Worm grinding is an effective approach for the precision manufacturing of face gears. However, pitch deviation and tooth thickness deviation inevitably arise during the grinding process. To reduce these deviations, this study proposes a compensation method applicable to complex topological surfaces in face [...] Read more.
Worm grinding is an effective approach for the precision manufacturing of face gears. However, pitch deviation and tooth thickness deviation inevitably arise during the grinding process. To reduce these deviations, this study proposes a compensation method applicable to complex topological surfaces in face gear grinding. Based on the structural configuration of a CNC face gear grinding machine, the dressing path of the grinding worm using the dressing wheel is first planned, followed by the generation of the grinding path for the face gear. Considering the tooth surface characteristics of the face gear, evaluation methods for single pitch deviation, cumulative pitch deviation, and tooth thickness error are established. The linkage polynomial method of the CNC machine tool is then employed to optimize the face gear grinding path and compensate for pitch deviation. Subsequently, a meshing tooth surface mapping method between the grinding worm and the face gear is developed to compensate for tooth thickness deviation. A compensation case study is conducted to verify the proposed method. The results indicate that the proposed compensation strategy effectively reduces both pitch and tooth thickness deviations in the face gear, with reduction rates ranging from 48.57% to 96.80%. Full article
(This article belongs to the Special Issue Advanced Manufacturing Processes and Technologies: Trends and Innovations)
►▼ Show Figures

Figure 1

35 pages, 9895 KB  
Article
Failure Mechanism of Tip-Trailing-Edge Fracture in a Thin-Walled Single-Crystal Turbine Blade: An Uncertainty-Based Vibration Analysis
by Wenting Jiang, Di Liu, Lilun Geng, Yizhou Long, Wanchao Sun, Yinli Feng and Enliang Huang
Machines 2026, 14(7), 815; https://doi.org/10.3390/machines14070815 - 18 Jul 2026
Viewed by 238
Abstract
To resolve the fatigue fracture occurring at the tip trailing edge of thin-walled single-crystal turbine rotor blades for a specific aero-engine, this paper derives the relationship between the single-crystal constitutive stiffness matrix and crystal orientation, and clarifies the influence mechanism of crystal orientation [...] Read more.
To resolve the fatigue fracture occurring at the tip trailing edge of thin-walled single-crystal turbine rotor blades for a specific aero-engine, this paper derives the relationship between the single-crystal constitutive stiffness matrix and crystal orientation, and clarifies the influence mechanism of crystal orientation on blade-vibration characteristics. The influence rules and degrees of uncertain parameters on the vibration characteristics of thin-walled and thickened-profile blades are comparatively investigated. The results reveal that blade dynamic frequency is strongly affected by both blade profile thickness and crystal orientation, and blade profile optimization can effectively weaken the effects of crystal orientation and blade thickness on the dynamic frequency of critical modes. Based on the above results, the hazardous resonance overlooked in conventional engineering approaches is detected using uncertainty-based vibration analysis. The corresponding failure mechanism is illustrated, the resonant speed range is determined, and the risk of bending–torsion coupled flutter is detected. The outcomes provide valuable guidance for the frequency tuning design of turbine blades. Full article
(This article belongs to the Special Issue Structural Dynamics, Optimization, and Vibration Assessment in Turbomachinery)
►▼ Show Figures

Figure 1

28 pages, 5029 KB  
Article
An Energy-Efficient Constant-Speed Downhill Control Approach for Heavy-Duty Electric Trucks with Hydraulic Retarders
by Xuebo Li, Yanli Feng, Shiwei Xu and Yixi Zhang
Machines 2026, 14(7), 814; https://doi.org/10.3390/machines14070814 - 18 Jul 2026
Viewed by 335
Abstract
Constant-speed control of hydraulic retarders is essential for improving driving safety and reducing driver workload on long downhill roads. For heavy-duty battery electric trucks (BETs), regenerative braking provides a fast-response braking source and enables energy recovery, offering the potential to improve both speed [...] Read more.
Constant-speed control of hydraulic retarders is essential for improving driving safety and reducing driver workload on long downhill roads. For heavy-duty battery electric trucks (BETs), regenerative braking provides a fast-response braking source and enables energy recovery, offering the potential to improve both speed regulation and energy efficiency. This study proposes a two-mode constant-speed downhill control framework for BETs. In the retarder braking mode, a variable-argument proportional–integral–derivative (VAPID) controller is employed to regulate the hydraulic retarder, with its parameters optimized by an improved seeker optimization algorithm (ISOA). In the cooperative braking mode, a parallel dual-controller structure is adopted, where the retarder is governed by ISOA-VAPID and regenerative braking is regulated by a fuzzy-tuned PD controller according to real-time battery states. To further improve energy recovery, an optimization-based AMT gear-shifting schedule and coordinated strategy are incorporated. The proposed framework is validated through offline simulations, sensitivity analysis, and driver-in-the-loop experiments under constant-slope, variable-slope, and real-world downhill road conditions. Results show that the retarder braking mode outperforms benchmark methods in steady-state accuracy and dynamic response. In the cooperative braking mode, braking energy is effectively recovered while the battery charging load under unfavorable battery states is reduced. Moreover, AMT gear shifting improves energy recovery efficiency with negligible influence on constant-speed performance. Full article
(This article belongs to the Section Vehicle Engineering)
►▼ Show Figures

Figure 1

25 pages, 4114 KB  
Article
Trajectory Planning and Robustness Analysis for Mars Helicopters Under Uncertain Wind Fields
by Chaoqun Zhang, Yi Wei, Tianle Yu, Yi Luo and Jianbo Li
Machines 2026, 14(7), 813; https://doi.org/10.3390/machines14070813 - 17 Jul 2026
Viewed by 300
Abstract
Wind disturbances in the thin Martian are highly stochastic and spatially correlated, posing significant challenges to rotorcraft flight safety. Meanwhile, limited onboard computational resources make real-time safe trajectory planning difficult. This paper proposes a trajectory planning and analysis framework based on composite wind [...] Read more.
Wind disturbances in the thin Martian are highly stochastic and spatially correlated, posing significant challenges to rotorcraft flight safety. Meanwhile, limited onboard computational resources make real-time safe trajectory planning difficult. This paper proposes a trajectory planning and analysis framework based on composite wind modeling and differential flatness theory. The proposed method decouples deterministic trajectory generation from stochastic robustness evaluation, enabling efficient trajectory planning in uncertain wind environments with planning-stage robustness evaluation. First, a composite wind model is constructed by combining multi-scale decomposition with Gaussian process regression, where a local kernel strategy is introduced to improve computational efficiency. Second, based on differential flatness theory and the MinCo method, a high-order polynomial trajectory is formulated. A multi-dimensional cost function is designed under wind field constraints to generate a nominal trajectory, incorporating trajectory smoothness, flight time, energy consumption, risk avoidance, and state feasibility. Finally, wind uncertainty is propagated via Monte Carlo sampling, and trajectory performance is quantitatively evaluated. Simulation results show the proposed method can generate safe, feasible, and risk-aware trajectories under the uncertain Martian wind conditions. Across all test scenarios, the mean terminal deviation, average deviation, and maximum deviation remain within 2.1%, 1.6%, and 3.6% of the trajectory length, respectively, indicating strong robustness in the evaluated scenarios. Full article
(This article belongs to the Section Automation and Control Systems)
►▼ Show Figures

Figure 1

31 pages, 12128 KB  
Article
An Unsupervised Anomaly Detection Method for Drones Based on a 1-D Selective Kernel Convolutional Autoencoder with Bayesian Optimization
by Junjie He, Boyang Zhong, Simin Wang, Lin Song, Li Guo, Pengfei Wang and Fei Wang
Machines 2026, 14(7), 812; https://doi.org/10.3390/machines14070812 - 17 Jul 2026
Viewed by 352
Abstract
The widespread application of drones in complex environments imposes higher demands on flight safety. However, traditional anomaly detection methods often rely on mathematical models or large amounts of labeled samples, which makes them ill suited to address practical challenges such as unmanned aerial [...] Read more.
The widespread application of drones in complex environments imposes higher demands on flight safety. However, traditional anomaly detection methods often rely on mathematical models or large amounts of labeled samples, which makes them ill suited to address practical challenges such as unmanned aerial vehicle systems, which exhibit strong nonlinear characteristics, a scarcity of fault samples, and highly variable operating conditions. To overcome the above difficulties, this work puts forward a one-dimensional selective kernel convolutional autoencoder (1-D SKCAE) based on Bayesian optimization for unsupervised drone anomaly detection. Relying solely on normal operation data, this model achieves accurate anomaly identification by leveraging the sudden changes in reconstruction error. For the model architecture, this paper designs a multi-scale selective kernel convolution module and combines an attention mechanism to achieve adaptive feature weighting for various receptive fields. This method effectively improves the model’s ability to represent complex operational conditions and subtle fault characteristics. Simultaneously, Bayesian optimization is embedded into the model training process as a hyperparameter search strategy, enabling the adaptive configuration of key hyperparameters to further enhance detection performance. Extensive experiments were conducted using the RflyMAD simulation dataset and the 3DR Solo real flight dataset. The results demonstrate that the 1-D SKCAE outperforms multiple comparative models, exhibiting superior robustness particularly in complex scenarios such as mixed multi-fault superposition. This method enables drone anomaly detection without fault labels, showcasing strong potential for engineering applications. Full article
(This article belongs to the Special Issue AI-Driven UAV Design, Control and Application)
►▼ Show Figures

Figure 1

21 pages, 4089 KB  
Article
Data-Driven Tool Condition Monitoring Platform for Grooving Operations with Chip Control Issues
by Iñigo Llanos, Anne Sanz, Irantzu Ermina, Ainhoa Robles and Jokin Munoa
Machines 2026, 14(7), 811; https://doi.org/10.3390/machines14070811 - 17 Jul 2026
Viewed by 348
Abstract
Accurate Tool Condition Monitoring (TCM) is key to maximizing tool life and minimizing downtime in machining. However, real-time tool wear assessment remains challenging, particularly in turning, due to non-periodic signals and chip entanglement issues. This study frames tool wear prediction in grooving operations [...] Read more.
Accurate Tool Condition Monitoring (TCM) is key to maximizing tool life and minimizing downtime in machining. However, real-time tool wear assessment remains challenging, particularly in turning, due to non-periodic signals and chip entanglement issues. This study frames tool wear prediction in grooving operations as a supervised regression problem using machining monitoring data as inputs. Multi-source sensor data were acquired and processed using an edge platform during groove machining to train six machine learning regression models. Also, a feature and sensor importance analysis was performed to identify opportunities to simplify instrumentation and reduce industrial implementation. The results demonstrate that Random Forests and XGBoost consistently achieve high accuracy (R2 > 0.9), effectively handling the non-linear, noisy nature of turning data. Based on these results, a final ensemble model combining both approaches was defined and deployed at the industrial edge as part of a final condition tool monitoring system. To this end, the ensemble model was encapsulated within a Docker-based container and was executed on an edge computing platform, enabling reliable, portable, and scalable real-time deployment for TCM. Full article
(This article belongs to the Special Issue Monitoring and Control of Machining Processes)
►▼ Show Figures

Figure 1

22 pages, 13106 KB  
Article
Multi-Physics Design, Manufacturing, and Experimental Validation of a High-Efficiency IPMSM for Compact Electric Vehicles
by Hayatullah Nory, Ahmet Yildiz, Nesibe Sibel Akbulut, Abdurrahman Atila and Ahmet Orhan
Machines 2026, 14(7), 810; https://doi.org/10.3390/machines14070810 - 17 Jul 2026
Viewed by 322
Abstract
This study presents the design, manufacturing, and prototype-level evaluation of a high-efficiency interior permanent magnet synchronous motor (IPMSM) developed for compact electric vehicle traction applications. The proposed motor employs a 12-slot/10-pole spoke-type rotor topology and was evaluated in terms of electromagnetic performance, mechanical [...] Read more.
This study presents the design, manufacturing, and prototype-level evaluation of a high-efficiency interior permanent magnet synchronous motor (IPMSM) developed for compact electric vehicle traction applications. The proposed motor employs a 12-slot/10-pole spoke-type rotor topology and was evaluated in terms of electromagnetic performance, mechanical integrity, and thermal behavior. The slot–pole and winding configuration was assessed as part of the design evaluation, and the manufactured prototype was experimentally tested under different operating conditions. The experimental results were compared with numerical simulations using line-to-line back-EMF, efficiency maps, phase current–torque characteristics, and output power variation. At the nominal operating point of 7000 rpm and 3.5 Nm, the prototype delivered 2.5 kW output power with an experimental efficiency of 90.7%. The deviations between experimental and simulation results were 1.17% for phase current, 0.48% for line-to-line back-EMF, 1.18% for input power, and 1.20% for efficiency. Mechanical static structural finite element analysis indicated a rotor safety factor of 3.61 under the maximum centrifugal loading condition, while the resulting structural deformation remained sufficiently low to avoid adverse effects on air-gap alignment. In addition, the rotor incorporated an adhesive-free, mechanically disassemblable magnet-retention structure, which was mechanically evaluated under centrifugal loading and showed no magnet displacement, structural damage, or bolt-preload loss after testing. Thermal analysis and continuous-load experimental testing showed that the winding temperature remained around 80 °C under passive cooling conditions. Overall, the results demonstrate that the manufactured IPMSM prototype provides consistent electromagnetic performance, adequate mechanical reliability, and thermally safe operation for compact electric vehicle applications. Full article
(This article belongs to the Special Issue Design, Performance Optimization and Application of Permanent Magnet Motors)
►▼ Show Figures

Figure 1

42 pages, 7648 KB  
Article
FedAnchor: Anchored and Adaptive Federated Learning for Fault Diagnosis in Resource-Constrained Industrial IoT
by Yanxin Hu, Xiaoman Liu, Zhenzhen Xie, Junjie Pang and Chao Cheng
Machines 2026, 14(7), 809; https://doi.org/10.3390/machines14070809 - 16 Jul 2026
Viewed by 364
Abstract
Federated learning (FL) enables privacy-preserving fault diagnosis across distributed industrial devices, but most existing methods assume homogeneous model architectures and comparable client resources. This assumption is unrealistic in resource-constrained Industrial Internet of Things (IIoT) scenarios, where clients may have substantially different memory and [...] Read more.
Federated learning (FL) enables privacy-preserving fault diagnosis across distributed industrial devices, but most existing methods assume homogeneous model architectures and comparable client resources. This assumption is unrealistic in resource-constrained Industrial Internet of Things (IIoT) scenarios, where clients may have substantially different memory and computation capacities. To address this challenge, we propose FedAnchor, an anchored and adaptive FL framework for resource-heterogeneous fault diagnosis. FedAnchor decomposes each client submodel into a shared anchored core and a client-specific adaptive extension. The anchored core provides a common parameter subspace for consistent masked aggregation, while the adaptive extension is selected by a server-side reinforcement-guided policy under client memory budgets. This design couples resource-aware submodel allocation with structurally aligned aggregation. Experiments on four benchmark datasets and six heterogeneous memory configurations show that FedAnchor achieves competitive or superior accuracy compared with representative homogeneous and model-heterogeneous FL baselines. Under the evaluated non-IID settings, FedAnchor improves accuracy by up to 9.8 percentage points over the strongest baseline, while maintaining favorable communication–accuracy trade-offs and empirical stability. Full article
►▼ Show Figures

Figure 1

26 pages, 11676 KB  
Article
Machine Learning and Vibration-Based Method for Anti-Friction Bearing Fault Severity Estimation
by Haobin Wen, Khalid Almutairi, Jyoti K. Sinha and Long Zhang
Machines 2026, 14(7), 808; https://doi.org/10.3390/machines14070808 - 16 Jul 2026
Viewed by 395
Abstract
Anti-friction bearings are fundamental components in rotating machinery. Any bearing fault appearing during operation could lead to catastrophic damages and failures without proper maintenance. Numerous methods have been developed for bearing fault detection to reduce maintenance costs and avoid unscheduled downtime. However, once [...] Read more.
Anti-friction bearings are fundamental components in rotating machinery. Any bearing fault appearing during operation could lead to catastrophic damages and failures without proper maintenance. Numerous methods have been developed for bearing fault detection to reduce maintenance costs and avoid unscheduled downtime. However, once a bearing fault is detected, assessing defect severity may be of more critical concern to industries, as it determines the urgency of interventions such as replacement scheduling and maintenance strategies. This paper presents an efficient estimation method for bearing fault severity using vibration-based input parameters and machine learning. Based on modal characteristics, key input parameters, the vibration amplitudes at the bearing fault frequencies and their harmonics, are extracted from acceleration envelope spectra for their close correlations with physical defect conditions. The nonlinearity between these spectral parameters and bearing fault severity is revealed with experimental observations and is represented using artificial neural networks. The model is validated on experimental vibration data measured from a bearing rig, covering various defect scenarios of different sizes and shapes. The classification criteria of bearing fault severity levels, ranging from healthy to severe, are formulated based on physical defect sizes with maintenance recommendations. Robust and accurate fault severity estimation is achieved across three bearing datasets collected under different operating conditions. The proposed method addresses both fault detection and degradation assessment for anti-friction bearings using simple vibration-based parameters based on rotor and bearing dynamics, providing a practical framework for predictive maintenance in industrial applications. Full article
(This article belongs to the Special Issue AI-Driven Intelligent Maintenance and Health Management for Complex Industrial Systems)
►▼ Show Figures

Figure 1

23 pages, 27297 KB  
Article
CWT-PSDT-Based Identification of Electromagnetic-Related Stator Vibration Frequency Components in a Hydro-Generator
by Jiannan Zhao, Juan Duan, Kun Yang, Jianlan Wang, Junqing Wang, Xuan Yang and Jiacai Feng
Machines 2026, 14(7), 807; https://doi.org/10.3390/machines14070807 - 16 Jul 2026
Viewed by 344
Abstract
Accurate identification of electromagnetically induced stator vibration frequency components is essential for the online condition monitoring of hydro-generators, particularly for assessing the dynamic state of the stator core under normal operating conditions. In engineering practice, the fast Fourier transform (FFT) is widely used [...] Read more.
Accurate identification of electromagnetically induced stator vibration frequency components is essential for the online condition monitoring of hydro-generators, particularly for assessing the dynamic state of the stator core under normal operating conditions. In engineering practice, the fast Fourier transform (FFT) is widely used for vibration spectrum analysis; however, because the measured vibration response is simultaneously affected by electromagnetic excitation, mechanical rotation, hydraulic disturbance, and external harmonic interference, FFT-based spectra often contain multiple frequency components whose structural relevance is difficult to determine directly. To address this issue, this paper proposes a coupled continuous wavelet transform and power spectral density transmissibility (CWT-PSDT) method for identifying key vibration frequency components with stable time-frequency energy and inter-sensor transmissibility in hydro-generator stator vibration signals. In the proposed framework, the analytic Morlet wavelet is first employed to localize dominant energy bands in the time-frequency domain, and PSDT is then used to screen frequency components with relatively stable inter-sensor transmissibility characteristics, thereby reducing the ambiguity caused by excitation-dominated spectral components. A clamped-clamped beam model is first used for numerical validation, and the maximum identification error of the first five natural frequencies is 4.22%. Experiments on a Francis turbine-generator test rig under five operating conditions further show that the proposed method can distinguish the mechanical rotational component near 10.3 Hz from the electromagnetic-related component near 50.8 Hz, while retaining higher-order electromagnetic-related components around 150 Hz and 250 Hz. The results demonstrate that the proposed CWT-PSDT method provides a physically interpretable and data-efficient approach for extracting stator-core-related spectral features, and offers a theoretical basis for spectrum-based online monitoring and future abnormal-condition comparison of hydro-generator stator responses. Full article
(This article belongs to the Special Issue Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

17 pages, 7940 KB  
Article
The Effect of Using Tools with Protective Coatings on Changes in Surface Geometric Texture in High-Performance Machining of Cast Iron
by Piotr Stieler, Daniel Grochała and Rafał Grzejda
Machines 2026, 14(7), 806; https://doi.org/10.3390/machines14070806 - 16 Jul 2026
Viewed by 365
Abstract
Cast iron is a material widely used in mechanical engineering, the automotive industry and large-scale structures. Interest in cast iron remains strong, despite the widespread drive to manufacture ever lighter, cheaper and more durable machine parts from light metal alloys or titanium. This [...] Read more.
Cast iron is a material widely used in mechanical engineering, the automotive industry and large-scale structures. Interest in cast iron remains strong, despite the widespread drive to manufacture ever lighter, cheaper and more durable machine parts from light metal alloys or titanium. This is mainly due to the low cost of cast iron, its ease of recycling and its favourable mechanical properties, including its particular ability to dampen vibrations. There are numerous publications in the international literature on the principles for selecting machining parameters for high-performance machining of steel, light metal alloys and titanium. Research into modelling the effect of machining parameters on the surface roughness and wear of cutting tools when machining these materials is widely documented. However, there is considerably less literature available on the high-performance machining of cast irons. This is particularly true in the context of the use of tools with protective coatings. To fill this gap, a research project was undertaken, which identified the potential for using a single tool for high-performance machining of spheroidal cast iron. The machining process was investigated under industrial conditions (in the automotive sector), taking into account the specific nature of roughing and finishing operations integrated into a single operation. In addition to investigating efficiency in terms of material removal and surface quality, the degree of wear on the cutting inserts at which the quality of the machined surface does not deteriorate was determined. Full article
(This article belongs to the Special Issue Vibrations and Tool Wear in Metal Cutting)
►▼ Show Figures

Figure 1

19 pages, 11133 KB  
Article
Motion-State-Aware Adaptive Multi-Sensor Fusion Localization Using Sliding-Window Incremental Factor Graph Optimization
by Zhikuan Hou, Shuai Chen, Chao Xue, Jinling Wang, Changhui Jiang and Chuan Xu
Machines 2026, 14(7), 805; https://doi.org/10.3390/machines14070805 - 15 Jul 2026
Viewed by 392
Abstract
Accurate and real-time localization for unmanned vehicles in complex motion environments is challenged by asynchronous multi-sensor measurements, time-varying measurement quality, and the growing computational burden of long-term factor graph optimization. To address these problems, this study proposes AVFGO, a sliding-window incremental factor graph [...] Read more.
Accurate and real-time localization for unmanned vehicles in complex motion environments is challenged by asynchronous multi-sensor measurements, time-varying measurement quality, and the growing computational burden of long-term factor graph optimization. To address these problems, this study proposes AVFGO, a sliding-window incremental factor graph optimization framework for motion-state-aware adaptive multi-sensor fusion localization. IMU pre-integration is used as the primary state-propagation backbone, while asynchronous LiDAR odometry, AHRS, wheel odometry, and barometer measurements are uniformly represented as factor-graph constraints. A sliding-window marginalization mechanism bounds the optimization scale by retaining historical information as prior factors. A motion-state-aware fusion-rate strategy controls the insertion density of external factors, and a residual-driven vector-wise adaptive weighting model adjusts the covariance of heterogeneous sensors in different measurement dimensions. Field experiments on a GNSS-denied wheeled unmanned vehicle dataset show that AVFGO achieves a 3D position RMSE of 0.380 m, reducing the error by 65.36% relative to IFGO and 52.71% relative to SWIFGO. The mean single-step optimization time is 0.0389 s, corresponding to an 11.9× speedup over IFGO and a 75.81% reduction relative to SWIFGO. These results indicate that the proposed framework improves accuracy and real-time performance while remaining limited by the single-platform field-test scope, which is explicitly discussed as a direction for future validation. Full article
(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)
►▼ Show Figures

Figure 1

22 pages, 25099 KB  
Article
A Novel Field Routing Approach for Unmanned Ground Vehicles in Steep-Slope Vineyards
by Mhd Ali Alshikh Khalil and Maria Rita Palattella
Machines 2026, 14(7), 804; https://doi.org/10.3390/machines14070804 - 15 Jul 2026
Viewed by 339
Abstract
Autonomous ground vehicles operating in steep-slope vineyards must reason jointly about three coupled factors: the order of waypoints across multiple polygon sub-fields, the points at which the route crosses sub-field boundaries, and terrain-aware travel cost in a Digital Elevation Model (DEM). Existing planners [...] Read more.
Autonomous ground vehicles operating in steep-slope vineyards must reason jointly about three coupled factors: the order of waypoints across multiple polygon sub-fields, the points at which the route crosses sub-field boundaries, and terrain-aware travel cost in a Digital Elevation Model (DEM). Existing planners address one side at a time: Coverage Path Planning (CPP) libraries treat each field in isolation, vineyard-specific A* variants reason about terrain and rollover safety within one vineyard, and energy-aware planners optimise coverage within a single field. This paper presents a novel field-scale planner, which optimises a tour over the waypoints of all sub-fields with one Travelling Salesman Problem (TSP) whose travel costs come from three-dimensional polylines sampled from the DEM and a travel-cost model of rolling resistance, climbing work, and a differential-drive pivot-turn term. Transitions between sub-fields are routed through chains of adjacent sub-fields. Four strategies are evaluated: a greedy nearest-neighbour (NN) heuristic and three Simulated Annealing (SA) TSP variants minimising distance (SA-D), energy (SA-E), or time (SA-T). Evaluated on two Moselle sites in Luxembourg, the objective-matched variants reduce mission cost over the nearest-neighbour baseline by up to 21%, on average, and 40% on the best mission, within an integrated pipeline from public geodata to executable, terrain-aware routes. Full article
(This article belongs to the Special Issue New Advances in Robotics, Factory Automation and Intelligent Networked Systems)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-122
Previous Issue
Next Issue
Back to TopTop