Machines

36 pages, 15714 KB

Open AccessArticle

Surrogate-Assisted Coordinated Optimization of Mechanism Parameters and Motion Trajectories for a Variable-Link-Length Robotic Manipulator

by Jingdong Qu, Jinfei Liu, Hua Huang, Ming Chen and Yifan Zhu

Machines 2026, 14(9), 996; https://doi.org/10.3390/machines14090996 (registering DOI) - 1 Sep 2026

Abstract

Fixed-link manipulators have limited adaptability to changes in task locations and obstacle layouts, while sequential mechanism design and trajectory planning restrict their coordinated performance. This study proposes a surrogate-assisted bilevel optimization method for a four-degree-of-freedom PRRR variable-link-length manipulator. The three link lengths are [...] Read more.

Fixed-link manipulators have limited adaptability to changes in task locations and obstacle layouts, while sequential mechanism design and trajectory planning restrict their coordinated performance. This study proposes a surrogate-assisted bilevel optimization method for a four-degree-of-freedom PRRR variable-link-length manipulator. The three link lengths are treated as outer-layer mechanism variables, whereas B-spline control points and trajectory duration are optimized in the inner layer subject to joint, motion, endpoint, and collision constraints. An objective-decoupled surrogate predicts trajectory duration, path length, jerk cost, and minimum clearance, and is embedded in an adaptive reference vector-guided multi-operator multi-objective beluga whale optimization algorithm. The framework combines inverse-kinematics prescreening, surrogate evaluation, high-fidelity trajectory re-optimization, dense constraint verification, and preference-based decision-making. Blind-test, ablation, and high-fidelity verification results show that the method efficiently identifies high-quality, physically feasible mechanism–trajectory candidates. Factorial analysis of an obstacle-constrained handling task indicates that trajectory optimization primarily improves smoothness and clearance, whereas mechanism adaptation redistributes joint motion and further enhances overall trajectory quality. Physical experiments demonstrate the executability of the selected mechanism–trajectory solutions without observed cylinder collision or joint-limit activation in the tested trials. These results demonstrate that the proposed framework provides an effective approach to task-adaptive mechanism–trajectory co-optimization in constrained environments. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

38 pages, 13250 KB

Open AccessArticle

Static–Dynamic Performance Improvement of LV500 Horizontal CNC Lathe via Bed–Saddle Collaborative Optimization and Laser Interferometer Validation

by Lei Qin, Changyuan Sun, Luji Wu, Jinyu Geng, Longjie Li and Baozhou Shi

Machines 2026, 14(9), 995; https://doi.org/10.3390/machines14090995 - 1 Sep 2026

Abstract

To improve the static and dynamic stiffness of the LV500 horizontal CNC lathe and reduce machining errors, this study focuses on integrated structural simulation, bed–saddle collaborative optimization, and standardized precision evaluation. A whole-machine structural model is established in SolidWorks, and static, modal, and [...] Read more.

To improve the static and dynamic stiffness of the LV500 horizontal CNC lathe and reduce machining errors, this study focuses on integrated structural simulation, bed–saddle collaborative optimization, and standardized precision evaluation. A whole-machine structural model is established in SolidWorks, and static, modal, and harmonic response co-simulations are performed in ANSYS, followed by multi-objective optimization of the two key weak components. MATLAB is used to process the dynamic simulation data. Based on a Renishaw XL-80 laser interferometer and the accompanying CARTO software, axis accuracy detection and measurement uncertainty evaluation are performed, forming a reproducible full-process engineering analysis system applicable to similar machine tools. The simulation results show that the maximum structural deformation after optimization is 0.016 mm, and the first-order natural frequency increases from 86.99 Hz to 92.55 Hz. Experimental tests demonstrate positioning accuracies of 3.0 μm (U = 0.38 μm, k = 2) for the X-axis and 3.3 μm (U = 0.45 μm, k = 2) for the Z-axis. Owing to the enhanced static–dynamic stiffness after structural optimization, the workpiece machining error can be stably controlled within 0.01 mm. In this study, a unified whole-machine model enables continuous static and dynamic analysis. The coupling stiffness of assembled components is considered in the modeling process, and the static and dynamic performance of the whole machine is improved through dual-component collaborative optimization. The inclusion of metrological-level uncertainty evaluation enhances the reliability of the experimental data. The proposed method provides a standardized engineering scheme for the static and dynamic performance optimization of similar horizontal CNC lathes. Full article

(This article belongs to the Special Issue Advanced Design, Manufacturing, and Applications of Precision Machine Tools)

► Show Figures

Figure 1

24 pages, 13470 KB

Open AccessArticle

Research on the Characteristics of an Electro-Mechanical Direct Drive System for Heavy-Duty Manipulators

by Zepeng Li, Yuxin Yang, Long Quan, Xiangyu Wang, Yunxiao Hao and Lei Ge

Machines 2026, 14(9), 994; https://doi.org/10.3390/machines14090994 - 1 Sep 2026

Abstract

Heavy-duty manipulators are generally driven by hydraulic systems. The control valves in these systems cause substantial throttling losses, resulting in low overall system energy efficiency. To address this problem, this study proposes an electro-mechanical direct drive system (EMDDS) based on an electro-mechanical actuator [...] Read more.

Heavy-duty manipulators are generally driven by hydraulic systems. The control valves in these systems cause substantial throttling losses, resulting in low overall system energy efficiency. To address this problem, this study proposes an electro-mechanical direct drive system (EMDDS) based on an electro-mechanical actuator (EMA) for energy-efficient actuation of heavy-duty manipulators. A supercapacitor energy-management strategy combining current feedforward with voltage feedback is also developed to recover and reuse the gravitational potential energy of the manipulator efficiently. System parameters were selected for the boom of a 6 t excavator, after which a multidisciplinary co-simulation model was established and an experimental prototype was built for validation. The simulation and experimental results show that the proposed system incurs no throttling loss during operation and achieves high drive efficiency. The system recovers and reuses gravitational potential energy with an efficiency of up to 46.4%. Compared with the load-sensing (LS) system, the EMDDS reduces energy consumption over one boom raising and lowering cycle from 42.25 kJ to 16.86 kJ, a reduction of 60.1%. The analysis and experiments provide a basis for developing energy-efficient electric drives and potential-energy recovery technologies for heavy-duty manipulators. Full article

(This article belongs to the Section Electromechanical Energy Conversion Systems)

► Show Figures

Figure 1

29 pages, 5788 KB

Open AccessArticle

Study on the Influence of Structural Parameters on the Performance of an Internal Feedback Hydrostatic Bearing

by Xiaochen Song, Xinzhou Wang, Xiaosen Lv, Shuguo Zheng, Mingcheng Zhai, Rencheng Zheng and Jianbin Liu

Machines 2026, 14(9), 993; https://doi.org/10.3390/machines14090993 - 1 Sep 2026

Abstract

Hydrostatic spindles are key components in high-precision grinding machines. In this paper, an internal feedback radial–thrust combined hydrostatic bearing is proposed to improve the load-carrying performance of conventional hydrostatic spindles. The throttling structure is integrated into the bearing inner surface, and an internal [...] Read more.

Hydrostatic spindles are key components in high-precision grinding machines. In this paper, an internal feedback radial–thrust combined hydrostatic bearing is proposed to improve the load-carrying performance of conventional hydrostatic spindles. The throttling structure is integrated into the bearing inner surface, and an internal feedback throttling configuration is developed to enhance pressure regulation and reduce nterference between oil pockets. Based on fluid lubrication theory and the hydraulic resistance network method, a theoretical model of the combined bearing is established, and a systematic parameter design method is developed. The governing equations of flow, pressure, load-carrying capacity, and stiffness are derived for performance prediction and structural design. Furthermore, finite element simulations are conducted to investigate the effects of key parameters. The simulation results show that, at a supply pressure of 4 MPa, the radial stiffness reaches 2559.3 N/μm and the axial stiffness reaches 423.1 N/μm. The simulation results are compared with the theoretical predictions, showing good agreement and providing numerical verification of the proposed theoretical model. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

24 pages, 7187 KB

Open AccessArticle

Point Cloud-Based Measurement of Switch Rail-to-Sleeper Longitudinal Displacement with Multi-Bolt Reference

by Cuijun Dong, Qingzhou Mao, Shihao Zhang, Zongming Zhang, Yixuan Shi, Wei Hu, Jizhong Zheng and Dehui Lai

Machines 2026, 14(9), 992; https://doi.org/10.3390/machines14090992 - 1 Sep 2026

Abstract

The longitudinal displacement of the switch rail relative to the sleeper is a critical defect affecting the safety of railway switching operations, as the sleeper serves as the mounting base for the switch machine. Existing measurement methods that rely on the stock rail [...] Read more.

The longitudinal displacement of the switch rail relative to the sleeper is a critical defect affecting the safety of railway switching operations, as the sleeper serves as the mounting base for the switch machine. Existing measurement methods that rely on the stock rail as a reference are susceptible to reference drift and cannot directly capture the displacement of the switch rail relative to its actuation base. This paper proposes a measurement method for the longitudinal displacement of the switch rail relative to the sleeper using the centers of multiple anchor bolts as reference benchmarks. Based on the fact that both the anchor bolts and the switch machine are fixed to the sleeper, the displacement of the switch rail relative to the bolt centers is equivalent to its displacement relative to the switch machine. Multiple anchor bolt centers on the sleeper are used to establish a stable reference frame. A self-developed mobile measurement device is employed to acquire three-dimensional structured light point clouds of the switch rail area. The coordinates of multiple anchor bolt centers are extracted through hexagon fitting. Abnormal coordinates are eliminated via joint adjustment of the multi-bolt centers, establishing a stable spatial reference frame that enables precise measurement of the longitudinal displacement of the switch rail relative to the sleeper. Field experiments on an operational No. 18 turnout successfully extracted the switch rail tip position and a longitudinal misalignment of −2 mm between the two switch rails. In simulation experiments, a creep displacement of 10 mm and multiple gross errors were artificially introduced; after three iterations, the final measured creep was 9.65 mm, with a deviation of only 0.35 mm, verifying the method’s accuracy and robustness under adverse conditions. Additional experiments on a No. 12 turnout with straight and curved switching states demonstrated that the standard deviation of the longitudinal spacing measurements between bolt centers was 1.17 mm under track switching conditions, confirming the method’s stability in the presence of switch machine movement. The proposed method achieves non-contact, automated measurement of the switch-rail-to-sleeper relative displacement, providing a practical technical pathway for turnout condition monitoring. Full article

(This article belongs to the Special Issue Innovations in Railway Vehicle System: Design, Monitoring and Maintenance)

► Show Figures

Figure 1

19 pages, 5445 KB

Open AccessArticle

Geometric Improvement of High-Pressure Bifurcated Pipes for Enhanced Flow and Energy Characteristics Under Hydraulic Short-Circuit Operation

by Shang Zhu, Ming Xia, Shizhe Liu, Fangxu Ji, Jing Yang and Zhengwei Wang

Machines 2026, 14(9), 991; https://doi.org/10.3390/machines14090991 - 1 Sep 2026

Abstract

Hydraulic short-circuit (HSC) operation is an important approach to enhancing the operational flexibility of pumped-storage power plants (PSPPs). However, under this new operating mode, the flow characteristics in the bifurcated pipe deteriorate significantly, posing a threat to the efficiency of the piping system [...] Read more.

Hydraulic short-circuit (HSC) operation is an important approach to enhancing the operational flexibility of pumped-storage power plants (PSPPs). However, under this new operating mode, the flow characteristics in the bifurcated pipe deteriorate significantly, posing a threat to the efficiency of the piping system and potentially affecting the inflow conditions for the turbine. In this study, six improved bifurcated pipe models were designed, and their internal flows under pumping, generating, and HSC modes were numerically simulated. Entropy production theory and vortex identification method were employed for flow field analysis. The results show that local modifications confined to the bifurcation are insufficient to simultaneously improve energy characteristics across different modes. In contrast, the bypass pipe enables early flow diversion, weakening the original high-dissipation regions while introducing controllable additional losses. M6 achieves an average energy loss reduction of 47.85% in the mid-to-high flow split ratio range (FSR > 0.3). A strong correlation is observed between vortex suppression and energy loss reduction: the bypass pipe substantially shortens the main vortex length at the inlet section of the generating branch, while simultaneously inducing new shear vortices at the junction; adjustment of its installation position is expected to further shorten their extension, thereby ensuring the normal operation of the turbine. This study provides a new technical pathway for extending the operating range of HSC operation and contributes to enhancing the grid-regulation capability of PSPPs. Full article

(This article belongs to the Special Issue Health Condition Monitoring, Intelligent Operation and Maintenance of Wind Turbines)

► Show Figures

Figure 1

22 pages, 33864 KB

Open AccessArticle

A Novel Brushless Synchronous Generator Combining Series Hybrid-Excited and Salient-Pole Wound-Field Sections for Hydropower

by Jianglin Liu, Zhijun Jiang and Bing Shao

Machines 2026, 14(9), 990; https://doi.org/10.3390/machines14090990 - 31 Aug 2026

Abstract

This paper proposes a novel axially parallel salient pole hybrid excitation synchronous generator (PSPHESG) for small and medium hydropower (SMHP). To prevent irreversible demagnetization of the permanent magnets (PMs), while improving the power density and reducing the volume compared with those of a [...] Read more.

This paper proposes a novel axially parallel salient pole hybrid excitation synchronous generator (PSPHESG) for small and medium hydropower (SMHP). To prevent irreversible demagnetization of the permanent magnets (PMs), while improving the power density and reducing the volume compared with those of a conventional electrically excited synchronous generator equipped with an AC exciter, a salient pole series hybrid excitation machine is axially integrated with an electrically excited machine, with the latter serving as the power compensation section. The basic structure and operating principles of the proposed PSPHESG are introduced. Finite-element analysis (FEA) is used to investigate the magnetic field distribution and no-load characteristics. Moreover, the phase angle deviation characteristics and output performances under load are analyzed, showing favorable voltage output capability over a wide load range during steady-state operation. Finally, the anti-demagnetization capability of the PM is studied under field forcing (FF) and de-excitation (DE). The results confirm that the PSPHESG not only provides good constant-voltage capability but also effectively avoids irreversible PM demagnetization during FF and DE, indicating its promising applicability to SMHP systems. Full article

(This article belongs to the Section Electrical Machines and Drives)

► Show Figures

Figure 1

18 pages, 13718 KB

Open AccessArticle

EDM Knife-like Robotic End-Effector Driving Material Efficiency

by Sergio Tadeu de Almeida, John P. T. Mo and Songlin Ding

Machines 2026, 14(9), 989; https://doi.org/10.3390/machines14090989 - 31 Aug 2026

Abstract

Electric discharge machining (EDM) has a unique ability to accurately cut exotic, hard-to-cut materials such as titanium without physical contact, with negligible force and vibration. Such a characteristic makes it a promising machining technique to be combined with robot manipulators to maximise the [...] Read more.

Electric discharge machining (EDM) has a unique ability to accurately cut exotic, hard-to-cut materials such as titanium without physical contact, with negligible force and vibration. Such a characteristic makes it a promising machining technique to be combined with robot manipulators to maximise the flexibility of the working envelope. Such a combination enabled robots to make a more sustainable cut of large, monolithic, and complex workpieces used in relevant defence and aerospace industries. The concept has been proven through a feasibility study prototype using wire EDM, followed by rotational milling EDM configurations. The wire EDM configuration was challenging due to instability in the wire control system and tension. The milling EDM configuration has been proven successful for intricate geometries. However, it involves removing large amounts of material and is thus not ideal for large geometries or deep cuts. Thus, to further explore sustainable robotic EDM for large workpieces without vaporising significant amounts of scarce, exotic, hard-to-cut materials, new inventive tools are needed. Therefore, this research aims to present a new knife EDM (KEDM) end-effector concept as a pure simulation capable of making large, deep cuts on a titanium workpiece without interruption. Using the TRIZ algorithm, engineering constraints are overcome to propose a KEDM design that vibrates and operates like a large WEDM, without frequent wire breakage, setup, or restarts. This research further explores the proposed end-effector through a digital twin kinematic simulation to find and demonstrate the extent of the machined workpiece and the robot’s enlarged workspace. Full article

(This article belongs to the Special Issue Trends and Advances in Electric Discharge Machining)

► Show Figures

Figure 1

33 pages, 14817 KB

Open AccessArticle

Imbalanced Fault Diagnosis of Harmonic Reducers Using Vibration Signals Based on an Auxiliary Classifier WGAN-GP with Spectral Normalization

by Lingdong Wang, Ronggang Yang, Jianlong Wang, Kai Li, Jiawei Xiang and Lishan Gao

Machines 2026, 14(9), 988; https://doi.org/10.3390/machines14090988 - 30 Aug 2026

Abstract

Class imbalance is common in vibration-based fault diagnosis because normal-condition data are generally more abundant than fault data. This study proposes an auxiliary-classifier Wasserstein generative adversarial network with gradient penalty and spectral normalization, termed ACWGAN-SG, for fault-sample generation and progressive dataset augmentation. The [...] Read more.

Class imbalance is common in vibration-based fault diagnosis because normal-condition data are generally more abundant than fault data. This study proposes an auxiliary-classifier Wasserstein generative adversarial network with gradient penalty and spectral normalization, termed ACWGAN-SG, for fault-sample generation and progressive dataset augmentation. The method combines class-conditioned generation, Wasserstein adversarial learning, gradient penalty, spectral normalization, and PCC-CS-based sample screening. Experiments were conducted on the public CWRU bearing dataset and a self-built 12-class harmonic-reducer dataset, with the downstream diagnostic experiments covering balance ratios from 1:100 to 1:1. The CWRU and harmonic-reducer experiments were independently repeated five and three times, respectively. Under the balanced condition, ACWGAN-SG achieved mean diagnostic accuracies of 98.40% and 97.627% on the two datasets. On the harmonic-reducer dataset at BR = 1:2, the method obtained a Macro-F1 of 94.298%, a balanced accuracy of 94.333%, and an MCC of 0.9383. Repeated-run statistical analyses showed significant overall differences among the evaluated methods across the tested balance ratios. These results indicate that the proposed generation and progressive-augmentation procedure improves downstream diagnostic performance under the reported experimental settings. Full article

(This article belongs to the Special Issue AI-Driven Intelligent Perception and Diagnosis of Mechanical Equipment)

20 pages, 23811 KB

Open AccessArticle

Development and Experimental Assessment of a Reconfigurable Platform for Laser Processing Applications

by António J. O. Ferreira, Carlos Miranda, Daniel Monteiro, Lucas Martins, Pedro M. O. Duarte, António B. Pereira and Fábio A. O. Fernandes

Machines 2026, 14(9), 987; https://doi.org/10.3390/machines14090987 - 30 Aug 2026

Abstract

Commercial laser-processing systems are typically designed for a specific manufacturing process, limiting their adaptability in research and prototyping environments. This study presents the staged evolution of a laboratory-scale prototype originally conceived for metal powder bed fusion into a reconfigurable laser-processing platform. Successive mechanical, [...] Read more.

Commercial laser-processing systems are typically designed for a specific manufacturing process, limiting their adaptability in research and prototyping environments. This study presents the staged evolution of a laboratory-scale prototype originally conceived for metal powder bed fusion into a reconfigurable laser-processing platform. Successive mechanical, optical, electrical, and control developments are consolidated, including the integration and calibration of a 200 W fibre laser, a galvanometric scanning system, motorised powder feed and build platforms, a recoater mechanism, and a combined LabVIEW and weldMARK control architecture. The capabilities of the resulting platform were assessed through optical commissioning by laser marking and two experimental case studies involving single-layer fusion of AISI 316L powder and laser transmission welding of dissimilar thermoplastics. The marking trials provided qualitative confirmation of beam delivery, focal adjustment, and programmed path reproduction. In contrast, the powder experiments produced continuous fused regions, demonstrating controlled laser–powder interaction without constituting full multilayer powder-bed-fusion validation. Thermoplastic welding generated mechanically resistant joints, with failure occurring cohesively within the foam substrate rather than at the welded interface. These results demonstrate the potential of the developed system as a reconfigurable research platform for different laser-processing operations. Nevertheless, fully automated multilayer powder bed fusion still requires improvements in platform levelling, machine-zero integration, process synchronisation, and atmosphere monitoring. Full article

(This article belongs to the Section Advanced Manufacturing)

► Show Figures

Figure 1

45 pages, 16025 KB

Open AccessArticle

Fault Diagnosis of Cascaded NPC Inverter Based on Single Sensor

by Chao Wu, Yihao Wang, Pengcheng Han and Jiahui Lv

Machines 2026, 14(9), 986; https://doi.org/10.3390/machines14090986 - 29 Aug 2026

Abstract

Accurate and low-cost fault diagnosis is essential for improving the reliability of cascaded neutral-point-clamped (NPC) inverters. This paper proposes a single-sensor fault diagnosis method for a single-phase three-module cascaded NPC inverter. Only one DC-side current sensor is required for the diagnostic algorithm, while [...] Read more.

Accurate and low-cost fault diagnosis is essential for improving the reliability of cascaded neutral-point-clamped (NPC) inverters. This paper proposes a single-sensor fault diagnosis method for a single-phase three-module cascaded NPC inverter. Only one DC-side current sensor is required for the diagnostic algorithm, while the voltage sensor used in the outer voltage-control loop is not involved in fault-feature extraction. The measured DC-side current is decomposed via Fourier analysis, and a low-dimensional feature vector is constructed using the amplitudes of the zeroth, 2nd, 3rd, and 4th harmonics together with the phases of the 1st and 3rd harmonics. The six Fourier features are normalized using feature-wise Min–max parameters determined exclusively from the training data. A back-propagation (BP) neural network is then adopted to identify and locate 24 single-switch open-circuit faults in the three-module system. The investigated inverter produces 13 output-voltage levels under healthy operation, and the BP network converges after 5835 training iterations to an error threshold of 1 × 10⁻⁶. An adaptive confirmation criterion based on consecutive diagnosis-code consistency and inter-window feature convergence is introduced. For the nominal 25-class simulation test set, the accuracy, macro-precision, macro-recall, and macro-F1-score are all 100%. In addition, 134 of the 136 dynamic-condition simulation runs are correctly diagnosed, corresponding to an overall robustness-test accuracy of 98.53%. One confirmed, but incorrect final code occurs under the load disturbance applied at 90° of the output-voltage fundamental, and another occurs at an SNR of 20 dB, while no unconfirmed run is observed. Under the severe RL-load condition with τ/T₀ = 1, the mean and maximum diagnostic delays are 41.7 ms and 52 ms, respectively. Full article

(This article belongs to the Special Issue Research Progress and Prospects of Multi-Level Converters)

► Show Figures

Figure 1

28 pages, 16414 KB

Open AccessArticle

A Field-Feasible Early Warning Framework for Excavation Threat Detection near Underground Petrochemical Pipelines Using Vibration Spectrograms

by Gi-Uk Yeom, Soon-Hyun Lim, Dae-Hwan Kim, Jae-Young Kim and Jong-Myon Kim

Machines 2026, 14(9), 985; https://doi.org/10.3390/machines14090985 - 29 Aug 2026

Abstract

Underground petrochemical pipelines face severe risks from unreported third-party damage during excavation. Existing monitoring systems based on supervised deep learning or distributed acoustic sensing often require expensive hardware and large volumes of labeled defect data, and they exhibit high false-alarm rates in noisy [...] Read more.

Underground petrochemical pipelines face severe risks from unreported third-party damage during excavation. Existing monitoring systems based on supervised deep learning or distributed acoustic sensing often require expensive hardware and large volumes of labeled defect data, and they exhibit high false-alarm rates in noisy urban environments. To overcome these limitations, this study proposes a cost-effective, field-feasible early warning framework utilizing attached acceleration sensors. High-frequency transient vibrations from physical impacts are demodulated into low-frequency rhythms using a Hilbert transform-based envelope algorithm, and these rhythms are then converted into 2D spectrograms via the Short-Time Fourier Transform. A 2D Convolutional Neural Network-Variational Autoencoder (2D CNN-VAE) is employed for unsupervised anomaly detection, trained specifically on normal background data. Furthermore, a hierarchical alarm classification logic is implemented to evaluate the reconstruction error, incorporating impulse noise rejection and temporal continuity checks. In a field demonstration, the proposed framework effectively suppressed false alarms caused by severe continuous noise, such as ground compacting, while reliably detecting sustained asphalt-breaking threats. This methodology demonstrates practical feasibility for isolating genuine excavation activities from transient environmental noise, offering a promising predictive maintenance approach that reduces alarm fatigue without requiring labeled defect data. Full article

(This article belongs to the Special Issue Advances in Condition Monitoring of Distributed Energy Equipment and Systems)

► Show Figures

Figure 1

35 pages, 2712 KB

Open AccessArticle

WrenchBuddy: A Governance Framework for Human-Centered Industrial AI Fault Diagnostics

by Mowffq M. Alsanousi, Po-Chien Huang and Vittaldas V. Prabhu

Machines 2026, 14(9), 984; https://doi.org/10.3390/machines14090984 - 29 Aug 2026

Abstract

Industrial artificial intelligence (AI) fault-diagnostic systems can identify plausible causes under uncertainty, but their outputs alone do not determine how diagnostic support should be delivered during maintenance. This paper presents WrenchBuddy, a human-centered governance framework that manages three decisions during a fault episode: [...] Read more.

Industrial artificial intelligence (AI) fault-diagnostic systems can identify plausible causes under uncertainty, but their outputs alone do not determine how diagnostic support should be delivered during maintenance. This paper presents WrenchBuddy, a human-centered governance framework that manages three decisions during a fault episode: how much diagnostic structure to expose, what assistance posture to provide, and which first confirmatory question to prioritize. The framework is method-agnostic. In this illustration, its roles are instantiated using capped Bayesian-network views, a Comprehensive Operational Cost burden proxy, Fault-Situation Difficulty, a scenario-level physiological readiness input, Data Envelopment Analysis, a Help/Escalate rule, and Value of Information query ranking. A maintenance corpus from approximately 300 remotely monitored uninterruptible power supply machines provides 429 tagged incidents, while an independent physiological dataset provides the scenario-level readiness input. The reconstructed cause–alarm graph has 35 nodes and 34 edges. The Bounded view retains approximately 85% of Baseline coverage with approximately 57% of its interpretability burden. At the selected operating point, three alarms are escalated; bootstrap analysis shows that the two highest-difficulty decisions are stable, whereas the third is a borderline result based on seven incidents. Because the two datasets are not synchronized, the study evaluates governance-policy behavior rather than operational-outcome improvement. WrenchBuddy therefore provides an auditable framework for governing diagnostic exposure, assistance, and first-query selection, while synchronized human-subject validation remains future work. Full article

(This article belongs to the Special Issue AI-Enabled Industrial Robotics and Production Automation for Smart Manufacturing Transformation)

► Show Figures

Figure 1

19 pages, 8904 KB

Open AccessArticle

SHGCN: An Industrial Fault Diagnosis Model Integrating Simplicial Hierarchical Topology

by Guoqing Li and Weijun Zhang

Machines 2026, 14(9), 983; https://doi.org/10.3390/machines14090983 - 29 Aug 2026

Abstract

Fault diagnosis of complex industrial systems is challenging due to the intricate interactions among multiple components and the limitations of conventional graph-based models in capturing higher-order dependencies. To address this issue, this paper develops a Simplicial Hierarchical Graph Convolutional Network (SHGCN) for multivariate [...] Read more.

Fault diagnosis of complex industrial systems is challenging due to the intricate interactions among multiple components and the limitations of conventional graph-based models in capturing higher-order dependencies. To address this issue, this paper develops a Simplicial Hierarchical Graph Convolutional Network (SHGCN) for multivariate sensor-based fault diagnosis. By representing industrial systems as simplicial complexes, the proposed framework extends pairwise relationships to higher-order topology. A Flower-Petal (FP)-based bipartite reconstruction strategy is introduced to efficiently model these structures without explicitly constructing computationally expensive higher-order topologies. Furthermore, a multi-order spectral convolution module is designed to extract hierarchical representations from different topological levels and integrate them for fault classification. The proposed method is evaluated on the Three-Phase Flow Facility (TFF) and Secure Water Treatment (SWaT) datasets. Comparative experiments with representative graph learning approaches, together with feature visualization and ablation studies, demonstrate that SHGCN achieves improved diagnostic performance and more separable feature representations. Specifically, SHGCN achieves accuracies of 98.41% and 94.64% on the TFF and SWaT datasets, respectively, outperforming existing graph-based methods and verifying the effectiveness of higher-order topological modeling for capturing complex interactions in industrial fault diagnosis. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

29 pages, 20769 KB

Open AccessArticle

Multi-Objective Optimization Design of High-Power-Density BLDC Motors Based on Surrogate Models

by Xia Yang, Ruihu Li, Yuhan Zheng, Yiyun Peng, Dingfeng Yu, Xiong Deng, Yan Luo and Yanyang Wu

Machines 2026, 14(9), 982; https://doi.org/10.3390/machines14090982 - 29 Aug 2026

Abstract

Aiming at insufficient rated torque and excessive magnet thermal loss of vehicle high-power-density BLDC motors, a multi-objective optimization framework integrating a surrogate model and NSGA-II is proposed. An eight-pole 48-slot finite-element model is built to analyze initial electromagnetic defects. Taguchi experiments conduct parameter [...] Read more.

Aiming at insufficient rated torque and excessive magnet thermal loss of vehicle high-power-density BLDC motors, a multi-objective optimization framework integrating a surrogate model and NSGA-II is proposed. An eight-pole 48-slot finite-element model is built to analyze initial electromagnetic defects. Taguchi experiments conduct parameter sensitivity screening to reduce simulation cost. Two surrogate models (RSM, BP neural network) are quantitatively compared via R² and MSE; the BP network achieves R² = 0.995 for magnet loss with overall error below 5%. Combined with NSGA-II, Pareto-optimal structural parameters are obtained. Simulation results show that optimized motor rated torque rises by 9.01% and peak magnet loss drops by 16.5%, while torque ripple and cogging torque meet engineering standards. This method features high efficiency and precision, providing references for automotive BLDC optimal design. Full article

(This article belongs to the Section Electrical Machines and Drives)

► Show Figures

Figure 1

17 pages, 10333 KB

Open AccessArticle

Preliminary Experimental Characterization of Pressure-Dependent Stiffness of a Granular Jamming Structure

by Christopher Quach, Yuanli Bai, Siddhartha Aryal, Pranish Pradhan, Mahesh Khadka and Sangeun Song

Machines 2026, 14(9), 981; https://doi.org/10.3390/machines14090981 - 29 Aug 2026

Abstract

Granular jamming enables switchable stiffness modulation through vacuum-induced particle confinement and has attracted increasing interest in variable-stiffness robotic systems. However, quantitative characterization of pressure-dependent mechanical behavior remains limited. This study experimentally investigates the relationship between vacuum pressure and structural stiffness using a cylindrical [...] Read more.

Granular jamming enables switchable stiffness modulation through vacuum-induced particle confinement and has attracted increasing interest in variable-stiffness robotic systems. However, quantitative characterization of pressure-dependent mechanical behavior remains limited. This study experimentally investigates the relationship between vacuum pressure and structural stiffness using a cylindrical granular-jamming specimen subjected to impact and static three-point bending tests. Coffee granules enclosed within an elastomeric membrane were evaluated under vacuum pressures ranging from 0 to −10 kPa. Under quasi-static loading, beam deflections were converted to equivalent Young’s modulus using classical beam theory, whereas the impact measurements were used to derive an apparent impact-response metric for relative comparison. Both loading conditions exhibited pressure-dependent increases in stiffness accompanied by reduced beam deflection. The static loading configuration showed an approximately linear pressure–stiffness relationship, whereas the impact tests exhibited nonlinear behavior at higher pressure levels, indicating that the apparent mechanical response depends on the loading condition. The results demonstrate that loading conditions influence the measured stiffness characteristics and should therefore be considered when evaluating granular-jamming structures. The presented methodology provides preliminary experimental characterization data that may support the design and evaluation of pressure-controlled variable-stiffness mechanisms for robotic and adaptive mechanical systems. Full article

(This article belongs to the Special Issue Robotic Intelligence Developments Regarding Artificial Intelligence in Robot Perception, Learning and Decision—2nd Edition)

► Show Figures

Figure 1

32 pages, 13011 KB

Open AccessArticle

Feasibility-Aware Visibility-Risk Navigation for Mobile Robots in Industry 4.0: Visual Servoing, CBF Safety Filtering, and Bounded ELR Replanning

by Atef M. Ghaleb, Ali S. Allahloh, Mohammad Sarfraz, Abdalla Alrashdan, Mohammed A. H. Ali, Fahad M. Alqahtani and Adel Al-Shayea

Machines 2026, 14(9), 980; https://doi.org/10.3390/machines14090980 - 28 Aug 2026

Abstract

A collision-free path is not sufficient for visibility-dependent mobile robot tasks: a moving obstacle can block the camera–target line of sight and cause inspection or visual-servoing failure even when the robot remains physically safe. Maintaining visual contact with targets is therefore important in [...] Read more.

A collision-free path is not sufficient for visibility-dependent mobile robot tasks: a moving obstacle can block the camera–target line of sight and cause inspection or visual-servoing failure even when the robot remains physically safe. Maintaining visual contact with targets is therefore important in Industry 4.0 environments, yet visibility-preserving maneuvers can conflict with navigation progress and collision avoidance. This work presents the Visibility-Informed Safety and Target Awareness framework with control barrier function filtering and occlusion-evasive local replanning (VISTA-CBF+ELR). The architecture combines visibility-risk planning, target-bearing control, an ELR supervisor, and a CBF quadratic program that keeps collision constraints hard while relaxing field-of-view and occlusion requirements through slack. Counterproductive interventions are limited through persistence, benefit–cost and feasibility gates, progress protection, bounded dwell, recovery, and cooldown. In locked factory simulations, redesigned VISTA achieved 67% and 73% strict-goal success under clean and nominal sensing, whereas Visibility-CEM-2D achieved 87% and 86% but with lower clearance. In matched Gazebo trials, strict success was 19/30 for redesigned VISTA, 26/30 without ELR, and 16/30 for Nav2 Smac+MPPI; zero-clearance collisions were 8/30, 3/30, and 14/30, with no difference surviving multiplicity correction. A separate CEM stress test sustained 6.875 Hz optimization, missed 26.31% of 100 ms deadlines, and held commands on 31.35% of ticks. The results demonstrate repair of the ELR pathology and conditional visibility-risk reduction while exposing safety–visibility trade-offs, transfer limitations, and real-time constraints. Full article

(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)

► Show Figures

Graphical abstract

36 pages, 1244 KB

Open AccessArticle

A Multi-Time-Scale Guaranteed-Cost Coordination Strategy for Networked Integrated Energy Systems over Directed Communication Graphs

by Chao Qin, Jiancheng Zhang, Lingyu Ma and Shanchen Pang

Machines 2026, 14(9), 979; https://doi.org/10.3390/machines14090979 - 28 Aug 2026

Abstract

The coordinated control of networked integrated energy systems (IESs) is complicated by the different response speeds of the electrical, gas, and thermal subsystems and by information exchange over directed communication graphs. Existing studies mainly consider the economic scheduling of a single IES, dynamic [...] Read more.

The coordinated control of networked integrated energy systems (IESs) is complicated by the different response speeds of the electrical, gas, and thermal subsystems and by information exchange over directed communication graphs. Existing studies mainly consider the economic scheduling of a single IES, dynamic modeling of individual systems, or cooperative control of systems with two time scales, and therefore, they do not provide a unified supervisory framework for coordinating three energy domains with an explicit performance bound. This paper investigates whether a common leader-following framework can coordinate the principal variables of the three energy domains while limiting both regulation errors and control effort. Each IES is treated as an agent, the three energy domains are represented by separate reduced dynamic blocks sharing a common directed communication topology, and a distributed state feedback controller is developed using relative information, Riccati-based gain design, and complete Lyapunov analysis. Simulations of a network of four IESs show that the longest settling times in the electrical and gas domains are approximately 0.05 s and 5.41 s, respectively, whereas the thermal disagreement decreases by 96.5% over 300 s; the accumulated cost remains below its calculated upper bound in the nominal case and in all three time-scale settings, while a separate numerical communication reconfiguration case illustrates bounded responses during communication link removal and reconnection. These results demonstrate that the proposed framework can simultaneously coordinate variables with substantially different response speeds while accounting for regulation accuracy and control effort under the stated reduced model and fixed graph assumptions. The communication reconfiguration case provides a numerical illustration and does not constitute a general stability guarantee for arbitrary topology switching. Full article

(This article belongs to the Special Issue Distributed Control, Coordination and Optimization of Multi-Agent Systems)

► Show Figures

Figure 1

26 pages, 2430 KB

Open AccessArticle

A Lightweight Enhanced MobileNetV3 Method for Bearing Fault Diagnosis Integrating Vibration Signals and Multi-Sensor Features

by Tianwen Guo, Yi Lu, Xiaoguang Wu and Xingyue Cui

Machines 2026, 14(9), 978; https://doi.org/10.3390/machines14090978 - 28 Aug 2026

Abstract

Rolling bearings are vital for the reliable operation of mechanical systems. However, accurately and efficiently identifying faults under complex working conditions remains a significant challenge. This paper proposes a lightweight and high-precision diagnostic framework specifically designed for industrial edge computing. Specifically, a multi-sensor [...] Read more.

Rolling bearings are vital for the reliable operation of mechanical systems. However, accurately and efficiently identifying faults under complex working conditions remains a significant challenge. This paper proposes a lightweight and high-precision diagnostic framework specifically designed for industrial edge computing. Specifically, a multi-sensor data fusion method, termed GADFMap, is introduced. First, the Wavelet Packet Decomposition (WPD) is applied to extract three sub-band signals with the highest kurtosis values, which are then weighted and combined to generate a new signal. Subsequently, the resulting signals are encoded using Gramian Angular Difference Field (GADF) to effectively integrate the multi-sensor data. Moreover, an improved lightweight diagnostic network, Enhanced MobileNetV3, is developed by augmenting MobileNetV3-Small with Efficient Channel Attention (ECA) modules. This improvement reduces model parameters and computational complexity, while strengthening the model’s focus on salient features. Experimental validation demonstrates that by using the GADFMap and the Enhanced MobileNetV3 model, the proposed method achieves higher diagnostic accuracy with fewer parameters and lower computational complexity compared with mainstream models. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

Journal Description

Machines

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI