Machines, Volume 12, Issue 6 (June 2024) – 29 articles

Flexsplines in harmonic gear reducers are usually characterized by a large number of teeth, small modulus, and poor stiffness, which makes them difficult to measure using conventional gear measuring centers. In order to efficiently evaluate the quality of flexsplines in harmonic gear reducers, a rapid measurement method for flexspline pitch using offset point laser sensors (PLS) is proposed. This paper investigates the principle of measuring the tooth flank of the flexspline under the offset of the PLS, establishes a model for collecting and analyzing gear surface data, builds an experimental system, calibrates the six pose parameters of the sensor using the geometric features of the flexspline’s outer circular surface, and completes the reconstruction of the left and right gear surfaces of the flexspline based on the measured data. In the experiment, the gear surface obtained by the proposed method is largely consistent with that measured by the video imaging method, and the repeatability of both single pitch deviation and cumulative pitch deviation is within ±3 µm. Full article

Time-series forecasting is crucial in the efficient operation and decision-making processes of various industrial systems. Accurately predicting future trends is essential for optimizing resources, production scheduling, and overall system performance. This comprehensive review examines time-series forecasting models and their applications across diverse industries. We discuss the fundamental principles, strengths, and weaknesses of traditional statistical methods such as Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ES), which are widely used due to their simplicity and interpretability. However, these models often struggle with the complex, non-linear, and high-dimensional data commonly found in industrial systems. To address these challenges, we explore Machine Learning techniques, including Support Vector Machine (SVM) and Artificial Neural Network (ANN). These models offer more flexibility and adaptability, often outperforming traditional statistical methods. Furthermore, we investigate the potential of hybrid models, which combine the strengths of different methods to achieve improved prediction performance. These hybrid models result in more accurate and robust forecasts. Finally, we discuss the potential of newly developed generative models such as Generative Adversarial Network (GAN) for time-series forecasting. This review emphasizes the importance of carefully selecting the appropriate model based on specific industry requirements, data characteristics, and forecasting objectives. Full article

Ultrasonic elliptical vibration-assisted cutting (UEVC) has been successfully applied in the precision and ultra-precision machining of hard and brittle materials due to its advantages of a low cutting force and minimal tool wear. This study developed a novel double-excitation ultrasonic elliptic vibration-assisted cutting (D-UEVC) device by coupling ultrasonic vibrations in orthogonal dual paths. A two-degree-of-freedom vibration system of the D-UEVC was modeled, form which the elliptical trajectory of the end under different phase angle φ values was derived. The initial dimensions of the D-UEVC device were obtained through theoretical calculations. Subsequently, with the aid of finite element analysis methods, structural dynamic analysis of the device was conducted to obtain the elliptical vibration trajectory under different phase differences of the excitation source. In order to verify the cutting trajectory and cutting performance of the D-UEVC device, a prototype of the device was developed, and a series of vibration performance tests as well as the Inconel 718 cutting experiment were conducted. The experimental results illustrated that the D-UEVC device can achieve the elliptical vibration trajectory at the tool tip with a resonant frequency of 36.5 KHz. The adjustable elliptical vibration trajectories covered a range of ±4 μm in the axial and radial directions. Compared with the surface roughness Ra = 0.36 μm under the conventional cutting, the surface roughness of Inconel 718 under D-UEVC was Ra = 0.215 μm. Thus, the surface quality can be significant improved by utilizing the D-UEVC device. Full article

Robotic manipulators are critical for industrial automation, boosting productivity, quality, and safety in various production applications. Key factors like the payload, speed, accuracy, and reach define robot performance. Optimizing these factors is crucial for future robot applications across diverse fields. While 6-Degrees-of-Freedom (DoF)-articulated robots are popular due to their diverse applications, this research proposes a novel 5-DoF robot design for industrial automation, featuring a combination of three prismatic and two revolute (2R) joints, and analyzes its workspace. The proposed techno-economically efficient design offers control over the robot manipulator to achieve any reachable position and orientation within its workspace, replacing traditional 6-DoF robots. The kinematic model integrates both parallel and serial manipulator principles, combining a Cartesian mechanism with rotational mechanisms. Simulations demonstrate the end effector’s flexibility for tasks like welding, additive manufacturing, and material inspections, achieving the desired position and orientation. The research encompasses the design of linear and rotational actuators, kinematic modeling, Human–Machine Interface (HMI) development, and welding application integration. The developed robot demonstrates a superior performance and user-friendliness in welding. The experimental work validates the design’s optimized joint trajectories, efficient power usage, singularity avoidance, easy access in application areas, and reduced costs due to fewer actuators. Full article

In order to solve the problem of large eddy current losses and high temperature rises caused by a large number of permanent magnets, a new type of combined-magnetic-pole permanent magnet motor is proposed in this paper. The sinusoidally distributed subdomain model of a non-uniform-air-gap rotor was established using the Laplace equation, and the analytical expression of eddy current losses in the rotor in a uniform air gap and non-uniform air gap was derived. The effect of the rotor’s eccentricity on eddy current losses was obtained. According to the characteristics of the distributed winding of the non-uniform-air-gap combined-pole permanent magnet motor, an equivalent treatment was performed to obtain the equivalent thermal conductivity value; to establish an equivalent thermal network model of the motor; determine the temperature of each component of the motor; and verify the correctness of the thermal network model through magnetothermal bidirectional coupling. Finally, an experimental platform was set up to carry out temperature rise experiments on the two prototypes. The experimental results show that a non-uniform-air-gap rotor structure can effectively reduce a rotor’s eddy current losses and motor temperature rise, as well as verify the accuracy of the analytical model’s calculation results. Full article

A nonlinear passive observer (NPO) for estimating the time-varying velocity vector of a multi-axis high-precision motion control stage is presented. The proposed nonlinear estimation strategy is developed based on a Lyapunov stability analysis, which proves that the NPO is stable. Three test cases are used to investigate the performance of the proposed observer. Experimental results are given to demonstrate the performance of the proposed NPO in accurately estimating time-varying velocity during alignment, reciprocating motion, and multi-axis motion in high-precision motion control applications. Full article

Existing vehicle-road models used for road tracking do not take into account the side slip angle, which leads to a reduction in road tracking accuracy in scenarios where the vehicle is at a large side slip angle, such as an emergency lane change. Consequently, this study presents a path-tracking control technique based on the T-S fuzzy model of heading angle vehicle autonomy. In this paper, based on the yaw angle-based vehicle tracking model, a heading angle-based tracking model considering the side slip angle is constructed. Second, since the vehicle speed varies with time, this paper selects the membership function of the vehicle speed to establish the T-S fuzzy model of autonomous vehicle based on the yaw angle and heading angle, respectively, and ensures the robustness and stability over the whole parameter space by the linear parameter variation robust $H_{\infty }$ controller. Then, cost functions based on the yaw angle and heading angle augmented error systems are created separately to optimize the system’s overall performance. Ultimately, simulation and experimentation confirm that the algorithm for control, which is based on the fuzzy model of the heading angle vehicle, has superior autonomous trajectory performance. Full article

A car seat’s function is to support, protect, and make passengers and drivers feel comfortable during a trip. A more uniform pressure distribution and a larger contact area usually provide less discomfort. Consequently, the seat pan’s material and geometry play an essential role in the design process. A shaped pad was opportunely designed and realized, starting from the pressure distributions between the buttocks and the seat pan; pressure data were acquired during an initial experiment involving 41 people, representing a wide range of percentiles. The shaped pad was compared with a standard one by building a special seat with an interchangeable internal pad and testing the standard and the new seat; the second experiment involved 52 people that tested both seats. The tests were conducted to assess comfort (33 subjects were asked to be seated for 1 min each) and discomfort (19 subjects were asked to be seated for 15 min each); during the tests, pressure distribution and contact area data were gathered. The results showed that, for both tests, about 80% of the participants, among which 100% of the female sample, preferred the shaped seat pan pad. Even if the material was exactly the same, the shaped pad seemed to be softer, more comfortable, and more suited to the body’s shape than the standard one. The design methodology was demonstrated to be very useful for granting a more uniform pressure distribution and a wider contact area, i.e., higher comfort and less discomfort. Full article

Timely prediction of bearing faults is essential for minimizing unexpected machine downtime and improving industrial equipment’s operational dependability. The Q transform was utilized for preprocessing the sixty-four vibration signals that correspond to the four bearing conditions. Additionally, statistical features, also known as attributes, are extracted from the Histogram of Oriented Gradients (HOG). To assess these features, the Explainable AI (XAI) technique employed the SHAP (Shapely Additive Explanations) method. The effectiveness of the GRU, LSTM, and SVM models in the first stage was evaluated using training and tenfold cross-validation. The SSA optimization algorithm (SSA) was employed in a subsequent phase to optimize the hyperparameters of the algorithms. The findings of the research are rigorously analyzed and assessed in four specific areas: the default configuration of the model, the inclusion of selected features using XAI, the optimization of hyperparameters, and a hybrid technique that combines SSA and XAI-based feature selection. The GRU model has superior performance compared to the other models, achieving an impressive accuracy of 98.2%. This is particularly evident when using SSA and XAI-informed features. The subsequent model is the LSTM, which has an impressive accuracy rate of 96.4%. During tenfold cross-validation, the Support Vector Machine (SVM) achieves a noticeably reduced maximum accuracy of 84.82%, even though the hybrid optimization technique shows improvement. The results of this study usually show that the most effective model for fault prediction is the GRU model, configured with the attributes chosen by XAI, followed by LSTM and SVM. Full article

Cable-driven parallel robots (CDPRs) offer significant advantages, such as the lightweight design, large workspace, and easy reconfiguration, making them essential for various spatial applications and extreme environments. However, despite their benefits, CDPRs face challenges, notably the uncertainty in terms of the post-reconstruction parameters, complicating cable coordination and impeding mechanism parameter identification. This is especially notable in CDPRs with redundant constraints, leading to cable relaxation or breakage. To tackle this challenge, this paper introduces a novel approach using reinforcement learning to drive redundant constrained cable-driven robots with uncertain parameters. Kinematic and dynamic models are established and applied in simulations and practical experiments, creating a conducive training environment for reinforcement learning. With trained agents, the mechanism is driven across 100 randomly selected parameters, resulting in a distinct directional distribution of the trajectories. Notably, the rope tension corresponding to 98% of the trajectory points is within the specified tension range. Experiments are carried out on a physical cable-driven device utilizing trained intelligent agents. The results indicate that the rope tension remained within the specified range throughout the driving process, with the end platform successfully maneuvered in close proximity to the designated target point. The consistency between the simulation and experimental results validates the efficacy of reinforcement learning in driving unknown parameters in redundant constraint-driven robots. Furthermore, the method’s applicability extends to mechanisms with diverse configurations of redundant constraints, broadening its scope. Therefore, reinforcement learning emerges as a potent tool for acquiring motion data in cable-driven mechanisms with unknown parameters and redundant constraints, effectively aiding in the reconstruction process of such mechanisms. Full article

The lack of real-world data on Connected and Autonomous Vehicles (CAVs) has prompted researchers to rely on simulations to assess their societal impacts. However, few studies address the operational and technological challenges of integrating CAVs into existing transport systems. This paper introduces a new CAV driving model featuring a constant time gap longitudinal control algorithm that accounts for sensor errors and platoon formations of varying sizes. Additionally, it develops a high-level route-based decision-making algorithm for CAV path choice. These algorithms were tested in a calibrated motorway corridor simulation, examining different market penetration rates, platoon sizes, and sensor error scenarios. Traffic conflicts were used as a primary safety performance indicator. The findings indicate that CAV sensors are generally adequate, but optimal platoon sizes vary with market penetration rates. To further explore factors influencing traffic conflicts, a hierarchical Bayesian negative binomial regression model was used. This model revealed that in addition to unobserved heterogeneity and spatial autocorrelation, the standard deviation of speeds between lanes and the CAV market penetration rate significantly affect conflict occurrences. These results corroborate the simulation outcomes, enhancing our understanding of CAV deployment impacts on traffic safety. Full article

This paper presents a minimally invasive surgical robot system for endoluminal gastrointestinal endoscopy through natural orifices. In minimally invasive gastrointestinal endoscopic surgery (MIGES), surgical instruments need to pass through narrow endoscopic channels to perform highly flexible tasks, imposing strict constraints on the size of the surgical robot while requiring it to possess a certain gripping force and flexibility. Therefore, we propose a novel minimally invasive robot system with advantages such as compact size and high precision. The system consists of an endoscope, two compact flexible continuum mechanical arms with diameters of 3.4 mm and 2.4 mm, respectively, and their driving systems, totaling nine degrees of freedom. The robot’s driving system employs bidirectional ball-screw-driven motion of two ropes simultaneously, converting the choice of opening and closing of the instrument’s end into linear motion, facilitating easier and more precise control of displacement when in position closed-loop control. By means of coordinated operation of the terminal surgical tools, tasks such as grasping and peeling can be accomplished. This paper provides a detailed analysis and introduction of the system. Experimental results validate the robot’s ability to grasp objects of 3 N and test the system’s accuracy and payload by completing basic operations, such as grasping and peeling, thereby preliminarily verifying the flexibility and coordination of the robot’s operation in a master–slave configuration. Full article

Strut-based or open lattice materials are a category of advanced materials used in medical and aerospace applications due to their properties, such as high strength-to-weight ratio and energy absorption capability. The most prominent method for the fabrication of lattice materials is the Laser-based Powder Bed Fusion (L-PBF) additive manufacturing (AM) process, due to its ability to produce parts of complex geometries. The current work presents an efficient meso-scale finite element (FE) modeling methodology of the L-PBF process demonstrated in the fabrication of body-centered cubic (BCC) lattice materials. The modeling efficiency is gained through an adaptive mesh refinement technique, which results in accurate and efficient prediction of the temperature field during the process evolution. To examine the efficiency of the modeling method, the computational time is compared with that of a conventional FE simulation, based on the element and birth technique. The temperature history difference between the two approaches is minor but the adaptive mesh modeling requires only a small portion of the simulation time of the conventional model. In addition, the computational results present a good correlation with the available experimental measurements for various process parameters validating the presented efficient method. Full article

Because of the difficulty in fault detection for and diagnosing the adjustment hydraulic servomotor, this paper uses feature extraction technology to extract the time domain and frequency domain features of the pressure signal of the adjustment hydraulic servomotor and splice the features of multiple pressure signals through the Multi-source Information Fusion (MSIF) method. The comprehensive expression of device status information is obtained. After that, this paper proposes a fault detection Algorithm GA-SVDD-neg, which uses Genetic Algorithm (GA) to optimize Support Vector Data Description with negative examples (SVDD-neg). Through joint optimization with the Mutual Information (MI) feature selection algorithm, the features that are most sensitive to the state deterioration of the adjustment hydraulic servomotor are selected. Experiments show that the MI algorithm has a better performance than other feature dimensionality reduction algorithms in the field of the abnormal detection of adjustment hydraulic servomotors, and the GA-SVDD-neg algorithm has a stronger robustness and generality than other anomaly detection algorithms. In addition, to make full use of the advantages of deep learning in automatic feature extraction and classification, this paper realizes the fault diagnosis of the adjustment hydraulic servomotor based on 1D Convolutional Neural Network (1DCNN). The experimental results show that this algorithm has the same superior performance as the traditional algorithm in feature extraction and can accurately diagnose the known faults of the adjustment hydraulic servomotor. This research is of great significance for the intelligent transformation of adjustment hydraulic servomotors and can also provide a reference for the fault warning and diagnosis of the Electro-Hydraulic (EH) system of the same type of steam turbine. Full article

Ball bearings are one of the most critical components of rotating machines. They ensure shaft support and friction reduction, thus their malfunctioning directly affects the machine’s performance. As a consequence, it is necessary to monitor the health conditions of such a component to avoid major degradations which could permanently damage the entire machine. In this context, HMS (Health Monitoring Systems) and PHM (Prognosis and Health Monitoring) methodologies propose a wide range of algorithms for bearing diagnosis and prognosis. The present article proposes an end-to-end PHM approach for ball bearing RUL (Remaining Useful Life) estimation. The proposed methodology is composed of three main steps: HI (Health Indicator) construction, bearing diagnosis and RUL estimation. The HI is obtained by processing non-stationary vibration data with the MODWPT (Maximum Overlap Discrete Wavelet Packet Transform). After that, a degradation profile is defined and coupled with crack initiation and crack propagation fatigue models. Lastly, a MB-HMM (Hidden Markov Model) is trained to capture the bearing degradation dynamics. This latter model is used to estimate the current degradation state as well as the RUL. The obtained results show good RUL prediction capabilities. In particular, the fatigue models allowed a reduction of the ML (Machine Learning) model size, improving the algorithms training phase. Full article

During long-duration dynamic loads, such as wind loads or seismic effects, the internal temperature and pressure of a damping cylinder escalate rapidly, which induce shifts in the mechanical attributes of viscous fluid dampers (VFDs). This study investigated the mechanical performance of VFD considering the coupling effects of temperature and pressure under long-duration loads. First, we analyzed the mechanical and energy-dissipation performances of the dampers based on the dynamic mechanical tests considering different loading frequencies, displacement amplitude, and loading cycles. The experimental results indicated that both temperature and pressure influenced the output of the dampers, and in the sealed environment of the damper pip, temperature and pressure exerted mutual influence. Furthermore, the relationship between the damping coefficient and temperature–pressure coupling effects was obtained. Subsequently, an improved mathematical model for the mechanical performance of a gap-type VFD was proposed by considering the macroscopic energy balance of the entire fluid within the damper. Finally, the accuracy of the mathematical model for VFD under long-duration dynamic loads was validated by comparing the computational results with the experimental data. Full article

This paper provides a novel application of a multi-criterion decision-making (MCDM) method to the multi-objective optimization problem of designing a two-stage helical gearbox. This study’s goal is to identify the ideal primary design elements that increase gearbox efficiency while reducing the gearbox cross-section area. In this work, three primary design parameters were selected for investigation: the gear ratio of the first stage and the coefficients of wheel face width (CWFW) of the first and second stages. The multi-objective optimization problem was further split into two phases: phase 1 solved the single-objective optimization problem of minimizing the gap between the variable levels, and phase 2 solved the multi-objective optimization issue of identifying the ideal key design factors. Moreover, the multi-objective optimization problem was handled by the SAW method as an MCDM approach, and the weight criteria were computed using the entropy approach. This study’s significant characteristics are as follows: First, a multi-objective optimization problem was successfully solved using the MCDM approach (SAW technique) for the first time. Second, the power losses in idle motion were investigated in this work in order to determine the efficiency of a two-stage helical gearbox. From this study’s findings, the ideal values for three major design parameters can be determined for the design of a two-stage helical gearbox. Full article

Dexterous manipulation of unknown objects performed by robots equipped with mechanical hands represents a critical challenge. The difficulties arise from the absence of a precise model of the manipulated objects, unpredictable environments, and limited sensing capabilities of the mechanical hands compared to human hands. This paper introduces a data-driven approach that provides a learning-based planner for dexterous manipulation employing an Adaptive Neuro-Fuzzy Inference System (ANFIS) fed by data obtained from an analytical manipulation planner. ANFIS captures the complex relationships between inputs and optimal manipulation parameters. Moreover, during a training phase, it is able to fine-tune itself on the basis of its experiences. The proposed planner enables a robot to interact with objects of various shapes, sizes, and material properties while providing an adaptive solution for increasing robotic dexterity. The planner is validated in a real-world environment, applying an Allegro anthropomorphic robotic hand. A link to a video of the experiment is provided in the paper. Full article

When launching a heavy-duty vehicle, torque and position control during automatic clutch engagement is critical, and the driver’s intention to launch and changes in the vehicle’s launching resistance make clutch control more complex. This paper analyses the automatic engagement process of automated mechanical transmission (AMT) clutches and proposes an optimal control of the clutch torque for launching heavy-duty vehicles. Firstly, a fuzzy neural network (FNN)-based vehicle launching states recognition (LSR) system is designed for distinguishing the driver’s launching intention and the vehicle’s launching equivalent moment of resistance. Secondly, jerk, friction work, and launching reserve power are taken as the performance indexes for clutch torque optimization, the weight coefficients of each performance index are adjusted according to the LSR results, and the optimal clutch torque is solved by using the minimum value principle based on the shooting method. Finally, simulations and tests are conducted to validate the strategy of optimizing clutch torque, and the impact of torque optimization on the position change during the engagement process is analyzed. The results indicate that under different driver’s intentions, vehicle masses, and road gradient conditions, the jerk, friction work, and slipping time of heavy vehicles during the launching process are improved by applying the optimization strategy. Full article

As one of the most important components in rotating machinery, if bearings fail, serious disasters may occur. Therefore, the remaining useful life (RUL) prediction of bearings is of great significance. Health indicator (HI) construction and early fault detection play a crucial role in data-driven RUL prediction. Unfortunately, most existing HI construction methods require prior knowledge and preset trends, making it difficult to reflect the actual degradation trend of bearings. And the existing early fault detection methods rely on massive historical data, yet manual annotation is time-consuming and laborious. To address the above issues, a novel deep convolutional auto-encoder (CAE) based on envelope spectral feature extraction is developed in this work. A sliding value window is defined in the envelope spectrum to obtain initial health indicators, which are used as preliminary labels for model training. Subsequently, CAE is trained by minimizing the composite loss function. The proposed construction method can reflect the actual degradation trend of bearings. Afterwards, the autoencoder is pre-trained through contrast learning (CL) to improve its discriminative ability. The model that has undergone offline pre-training is more sensitive to early faults. Finally, the HI construction method is combined with the early fault detection method to obtain a comprehensive network for online health assessment and fault detection, thus laying a solid foundation for subsequent RUL prediction. The superiority of the proposed method has been verified through experiments. Full article

In electric or hybrid vehicles’ propulsion systems, Permanent Magnet-Assisted Synchronous Reluctance Machines represent a viable alternative to Permanent Magnet Synchronous Machines. Based on previous research work, the present paper proposes, designs, and optimizes two ferrite PMaSynRM topologies, analyzed against a reference machine (also PMaSynRM) with improved torque ripple content, based on similar specifications and dimensional constraints. Considering the trend of increasing the DC voltage level in electric and hybrid vehicles, the optimal topology is included in an analysis of the DC voltage level impact on the design and performances of PMSynRM. Full article

In welding tasks, the repeated positioning precision of robots can generally reach the micron level, but the data of each axis during each operation may vary. There may even be out-of-control situations where the robot does not run according to the set welding trajectory, which may cause the robot and equipment to collide and be damaged. Therefore, a real-time judgment method for the welding robot trajectory is proposed. Firstly, multiple sets of axis data are obtained by running the welding robot, and the phase of the data is aligned by using a proposed algorithm, and then the Kendall correlation coefficient is used to identify and remove weak axis data. Secondly, the mean of multiple sets of axis data with strong correlation is calculated as the standard trajectory, and the trajectory threshold of the robot is set using the μ ± nσ method based on the trajectory deviation judgment sensitivity. Finally, the absolute difference between the real-time axis trajectory and the standard trajectory is used to determine the deviation of the running trajectory. When the deviation reaches the threshold, a forewarning starts. When the deviation exceeds the threshold + σ, the robot is stopped. Take the six-axis welding robot as an example, by collecting the axis data of the robot running multiple times under the same conditions, it is proved that the proposed method can accurately warn the deviation of the running trajectory. The research results have important practical value for the prevention of welding robot accidents in industrial production. Full article

In this study, to improve the efficiency of the pipetting workstation and reduce the impact of the pipetting device on the stability performance of the workstation, a novel fully automatic pipetting method is proposed. Based on this method, a lightweight, multifunctional, and quantitative twelve-channel pipetting device was designed. This device can achieve simultaneous quantitative liquid absorption for twelve channels and sequential interval liquid discharge for each channel. Initially, the overall functional requirements were determined, and with the aim of a lightweight design, the total weight of the device was controlled to be within 580 g through a reasonable structural design, material selection, and choice of driving source. The device’s overall dimensions are 170 mm × 70 mm × 180 mm (length × width × height), with a micropipetting volume ranging between 1.3 $\mathsf{\mu }$L and 1.4 $\mathsf{\mu }$L. Subsequently, factors affecting liquid suction stability were experimentally analyzed, and appropriate pipetting parameters were selected. The stability performance of this pipetting method during prolonged operation was investigated. Finally, the twelve-channel pipetting device was validated through experiments, demonstrating results that meet the national standards for the stability of a pipetting device. In summary, the device designed in this study exhibits novel design features, low cost, and modularity, thus demonstrating promising potential for applications in high-speed micro-volume pipetting. Full article

This study aims to analyze the load-bearing characteristics of non-pneumatic tires with composite spokes using experimental and finite element simulation methods and to establish a mechanical analysis model based on the Timoshenko beam theory. Subsequently, experiments were conducted on carbon fiber-reinforced plastics and rubbers to establish the corresponding constitutive model. A finite element model of the non-pneumatic tires with composite spokes was also developed. The main structural and material parameters were selected, and their correlation with the vertical stiffness of the non-pneumatic tires with composite spokes was studied using response surface methodology. The stiffness characteristics of the composite spokes were simplified, and a load-bearing characteristic analysis model was established. The results indicated that among the parameters of the reinforcement plate structure and rubber, the constitutive parameter C₁₀ of the rubber in the spokes had the greatest impact, with a comprehensive influence value of 319.83 N/mm. Under a load of 5000 N, the load-bearing characteristic analysis model results were consistent with those of the finite element simulation, with a maximum relative error of 7.49%. The proposed load-bearing characteristic analysis model can assist in the rapid design and performance prediction of non-pneumatic tires with composite spokes. Full article

Non-neural machine learning (ML) and deep learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three datasets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously, and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM, and Transformers) are compared on multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure. Full article

The effectiveness of a wind turbine elastic support in reducing vibrations significantly impacts the unit’s lifespan. During the structural design process, it is necessary to consider the influence of structural design parameters on multiple performance indicators. While neural networks can fit the relationships between design parameters on multiple performance indicators, traditional modeling methods often isolate multiple tasks, hindering the learning on correlations between tasks and reducing efficiency. Moreover, acquiring training data through physical experiments is expensive and yields limited data, insufficient for effective model training. To address these challenges, this research introduces a data generation method using a digital twin model, simulating physical conditions to generate data at a lower cost. Building on this, a Multi-gate Mixture-of-Experts multi-task prediction model with Long Short-Term Memory (MMoE-LSTM) module is developed. LSTM enhances the model’s ability to extract nonlinear features from data, improving learning. Additionally, a dynamic weighting strategy, based on coefficient of variation weighting and ridge regression, is employed to automate loss weight adjustments and address imbalances in multi-task learning. The proposed model, validated on datasets created using the digital twin model, achieved over 95% predictive accuracy for multiple tasks, demonstrating that this method is effective. Full article

The pursuit of sustainable and environmentally friendly transportation has led to the exploration of alternative fuel sources, among which hydrogen stands out prominently. This work delves into the potential of hydrogen fuel for internal combustion engines (ICEs), emphasizing its capacity to ensure the required performance levels while concurrently enhancing overall efficiency. The integration of a mild hybrid powertrain in a small size passenger car was considered for obtaining a twofold advantage: mitigating power loss due to low volumetric efficiency and increasing fuel economy. A comprehensive approach combining 0D/1D modeling simulations and experimental validations was employed on a gasoline-powered small size ICE, considering its conversion to hydrogen, and mild hybridization. Vehicle simulations were performed in AVL Cruise M and validated against experimental data. Various electric motors were scrutinized for a small size battery pack typical of mild hybrid vehicles. Furthermore, the paper assesses the potential range achievable with the hydrogen-powered hybrid vehicle and compares it with the range reported by the manufacturer for the original gasoline and pure electric version. In terms of global results, these modifications were found to successfully improve efficiency compared to baseline gasoline and hydrogen fueling. Additionally, performance gains were achieved, surpassing the capabilities of the original gasoline vehicle despite its intrinsic volumetric efficiency limitations when using hydrogen. Along with the conversion to hydrogen and thus zero-carbon tail-pipe emissions, incorporating a Start/Stop system, and the integration of mild hybrid technology with energy recuperation during braking, overall efficiency was enhanced by up to 30% during urban use. Furthermore, the hybridization implemented in the H₂ version allows an autonomy comparable to that of the electric vehicle but with evident shorter refilling times. Specific aspects of the 48 V battery management are also scrutinized. Full article

In view of the problem that the output thrust of the solenoid actuator is affected by various factors and is difficult to calculate in actual working conditions, this paper proposes a semi-analytical model constructed by magnetic field subdomain method with internal and external boundary conditions in a cylindrical coordinate system for calculation, and the general solution equations of magnetic vector potential for each subdomain are derived and solved by MATLAB. Taking a push–pull electromagnet as an example, the finite element simulation and experimental comparative analysis are carried out. The correctness and applicable conditions of the subdomain method are illustrated by comparing the gradient plot of magnetic vector potential, inductance curve and electromagnetic force. It is shown that the results calculated by the subdomain method are very close to the finite element method when the magnetic saturation problem is neglected. However, when the nonlinearity of core permeability is considered, the magnetic saturation gradually deepens with the increase in current, and the error of the subdomain method calculation results gradually increases. Through simulation and experimental verification at slight magnetic saturation, the output thrust after considering the core gravity, spring force and electromagnetic force, it is shown that this method has the advantage of computational flexibility compared with the finite element method, and it is easier to write special algorithms according to various working conditions to calculate the important parameters in engineering applications. Full article

Machine learning models have been used to precisely forecast emissions from diesel engines, specifically examining the impact of various fuel types (HVO10, HVO 30, HVO40, HVO50) on the accuracy of emission forecasts. The research has revealed that models with different numbers of perceptrons had greater initial error rates, which subsequently reached a stable state after further training. Additionally, the research has revealed that augmenting the proportion of Hydrogenated Vegetable Oil (HVO) resulted in the enhanced precision of emission predictions. The use of visual data representations, such as histograms and scatter plots, yielded significant insights into the model’s versatility across different fuel types. The discovery of these results is vital for enhancing engine performance and fulfilling environmental regulations. This study highlights the capacity of machine learning in monitoring the environment and controlling engines and proposes further investigation into enhancing models and making real-time predictive adjustments. The novelty of the research is based on the determination of the input interface (a sufficient amount of input parameters, including chemical as well as technical), which characterizes the different regimes of the diesel engine. The novelty of the methodology is based on the selection of a suitable ANN type and architecture, which allows us to predict the required parameters for a wide range of input intervals (different types of mixtures consisting of HVO and pure diesel, different loads, different RPMs, etc.). Full article