Search Results (569)

We present a novel approach to performing fitness approximation in genetic algorithms (GAs) using machine learning (ML) models, focusing on dynamic adaptation to the evolutionary state. We compare different methods for (1) switching between actual and approximate fitness, (2) sampling the population, and (3) weighting the samples. Experimental findings demonstrate significant improvement in evolutionary runtimes, with fitness scores that are either identical or slightly lower than those of the fully run GA—depending on the ratio of approximate-to-actual-fitness computation. Although we focus on evolutionary agents in Gymnasium (game) simulators—where fitness computation is costly—our approach is generic and can be easily applied to many different domains. Full article

In order to address the issue of poor fuel efficiency in hydraulic bulldozers during operation, this paper proposes a speed–load control strategy aimed at minimizing the overall fuel consumption rate of the machine. First, input–output models of the engine, hydraulic torque converter and the entire vehicle were established. Then, based on the bulldozer’s output power and fuel consumption rate, a performance metric for the overall fuel consumption rate was proposed to reflect the machine’s working efficiency. The characteristics of the overall fuel consumption rate were analyzed under different load, speed, and gear conditions. Next, a work point optimization control strategy was proposed for the whole machine energy-saving mode and constant power mode, aiming to minimize the overall fuel consumption rate while using the load, speed, and gear as control variables. To verify the feasibility of the work point optimization control strategy, simulations were conducted for both the energy-saving and constant power modes. The simulation results showed that in the whole machine energy-saving mode, this control strategy resulted in the lowest fuel consumption compared to constant speed control strategies at 1500, 1700, and 2000 rpm, with significant reductions in most cases. In the constant power mode, a comparison between four optimal operating points and the whole machine energy-saving mode revealed that while the former had slightly higher fuel consumption, it ensured a stable power output. Finally, experimental testing demonstrated that the proposed control strategy reduced the overall fuel consumption rate by 12.5% compared to the constant speed mode, verifying the effectiveness of the strategy. The study concludes that the energy-saving control strategy, through the coordinated switching between the two modes in complex operating conditions, not only ensures a stable power output for the bulldozer but also significantly improves fuel efficiency, providing an important reference for optimizing the efficiency of transmission systems in construction machines. Full article

A directional valve is a core component of the electro-hydraulic shakers in fatigue testing machines, controlling the cylinder or motor that drives the piston for reciprocating linear or rotary motion. In this article, a high-speed rotating directional valve with a symmetrical flow channel layout is designed to optimize the force on the valve core of the directional valve. A comparative analysis is conducted on the flow capacity of valve ports with different shapes. A steady-state hydrodynamic mathematical model is established for the valve core, the theoretical analysis results of which are verified through a Computational Fluid Dynamics (CFD) simulation of the fluid domain inside the directional valve. A prototype of the rotatory directional valve is designed and manufactured, and an experimental platform is built to measure the hydraulic force acting on the valve core to verify the performance of the valve. The displacement curves at different commutation frequencies are also obtained. The experimental results show that the symmetrical flow channel layout can significantly optimize the hydraulic force during the movement of the valve core. Under a pressure of 1 MPa, the hydraulic cylinder driven by the prototype can achieve a sinusoidal curve output with a maximum frequency of 60 Hz and an amplitude of 2.5 mm. The innovation of this design lies in the creation of a directional valve with a symmetric flow channel layout. The feasibility of the design is verified through modeling, simulation, and experimentation, and it significantly optimizes the hydraulic forces acting on the spool. It provides us with the possibility to further improve the switching frequency of hydraulic valves and has important value in engineering applications. Full article

This article presents an analysis of the behavior of an asymmetric machine subjected to dynamic switching at different load levels. The authors herein present theoretical and practical results regarding the drive of a 2 HP asymmetric three-phase induction motor, allowing for conclusions to be drawn concerning its operation in such a configuration using capacitive dynamic switching. Previous research has demonstrated that the efficiency of single-phase powered asymmetric motors is only viable when the applied load matches the rated load of the motor. Given that this mode of operation is shown to hold practical infeasibilities for asymmetric three-phase motors, the proposal of a solution is put forward that involves varying the capacitance according to demand. This approach results in a significant improvement in efficiency regardless of whether the motor is running on a full or reduced load. Full article

This paper presents a hybrid control strategy for the LLC resonant converter in X-ray machines, addressing the limitations of voltage gain range under Pulse Frequency Modulation (PFM) and dynamic response under Phase Shift Modulation (PSM). The strategy employs an improved fruit fly optimization algorithm (IFOA) to optimize PI control and integrate Hybrid Phase-Shifted and Frequency-Modulated control. It dynamically adjusts the switching frequency and phase shift angle to maintain output stability and efficiency, ensuring optimal operation under rated conditions. A Matlab-based system simulation model confirmed the stability and accuracy of the IFOA in controlling the converter. Subsequent prototype testing validated the strategy’s effectiveness in reducing conduction losses, enhancing overall efficiency, and demonstrating practical feasibility and superiority. Full article

Achieving increased fault tolerance in an electric motor requires decisions to be made about the type and specifications of the motor machine and its appropriate design. Depending on the type of motor, there are generally three ways to achieve an increased resistance of the drive system to tolerate resulting faults. The simplest way is to select the right motor and design it appropriately. Switched reluctance motors (SRMs) have a high tolerance for internal faults (in the motor windings). Failure tolerance can be improved by using parallel paths. The SRM 24/16 solution has been proposed, which allows for operation with four parallel paths. In this paper, a mathematical model designed to analyse the problem under consideration is provided. Based on numerical calculations, the influence of typical faults (open and partial short circuit in one of the paths) on the electromagnetic torque generated as well as its ripple and (source and phase) currents were determined. The higher harmonics of the source current (diagnostic signal) were determined. Laboratory tests were performed to verify the various configurations for the symmetric and emergency operating states. The feasibility of SRM correct operation monitoring was determined from an FFT analysis of the source current. Full article

Radiomics provides a structured approach to support clinical decision-making through key steps; however, users often face difficulties when switching between various software platforms to complete the workflow. To streamline this process, matRadiomics integrates the entire radiomics workflow within a single platform. This study extends matRadiomics to preclinical settings and validates it through a case study focused on early malformation differentiation in a zebrafish model. The proposed plugin incorporates Pyradiomics and streamlines feature extraction, selection, and classification using machine learning models (linear discriminant analysis—LDA; k-nearest neighbors—KNNs; and support vector machines—SVMs) with k-fold cross-validation for model validation. Classifier performances are evaluated using area under the ROC curve (AUC) and accuracy. The case study indicated the criticality of the long time required to extract features from preclinical images, generally of higher resolution than clinical images. To address this, a feature analysis was conducted to optimize settings, reducing extraction time while maintaining similarity to the original features. As a result, SVM exhibited the best performance for early malformation differentiation in zebrafish (AUC = 0.723; accuracy of 0.72). This case study underscores the plugin’s versatility and effectiveness in early biological outcome prediction, emphasizing its applicability across biomedical research fields. Full article

The high-performance vector control technology of permanent magnet synchronous machines (PMSMs) relies on high-precision rotor position. The Hall-effect sensor has the advantages of low cost, simple installation, and strong anti-interference ability. However, it can only provide six discrete rotor angles in an electrical cycle, which makes high-precision vector control of PMSMs difficult. Hence, to obtain the necessary rotor position of PMSMs, a rotor position fitting method combining the Hall signal and machine flux information is proposed. Firstly, the rotor position signal output by the Hall-effect sensors is used to calibrate and update the stator flux obtained under pure integration. Then, based on the corrected stator flux and its relationship with current and angle, the rotor position and speed are obtained. Experimental verification shows that the rotor position observer combining Hall signal and flux information can reduce the initial value bias and integral drift caused by traditional average speed method hysteresis and pure integration method calculation of flux and can quickly and accurately track and estimate the rotor position, achieving high-performance vector control of PMSMs. Full article

Compressed air ranks among the most expensive forms of energy. In recent decades, increased efforts have been made to enhance the overall energy efficiency of pneumatic actuator systems and develop reliable fault detection methods for preventing energy losses. However, most of the methods developed so far require additional sensors, resulting in extra costs, and/or are not applicable during machine operation, which leads to their limited use in the industry. This article introduces a cycle time-based method for detecting faults in pneumatic actuators through the use of proximity switches, enabling cost-effective monitoring in real time without the necessity of further sensors. A systematic analysis is conducted, expanding the current state of knowledge by detailing the influence of all potential leakage points on the movement times of a pneumatic drive and taking into account the different velocity control strategies (meter-out and meter-in) and operating points expressed via the pneumatic frequency ratio. Previously unassessed specifics of internal leakage, including the impact of pressure profiles and differences between differential cylinders and cylinder with equal piston areas, are also presented. The applicability of the proposed method and its detection limits in an industrial environment are examined using pneumatic assembly machines. Full article

Due to accidents, upper limb movement disorders have become increasingly common. Training can help restore muscle strength and rebuild neurological function. However, the existing single mode has limitations in adapting to the training needs of different rehabilitation stages. Therefore, this paper conducts research on active–passive training control strategies for an upper limb rehabilitation robot. It establishes an upper limb kinematic model based on the Lagrange method and builds a man–machine integration dynamics model for upper limb rehabilitation in MATLAB (R2016a)/Simulink. A design active controller, passive controller, and switching controller based on PI and feedforward compensation strategies are proposed to improve training control accuracy. The output moment of the system during active training is planned to ensure the safety and stability of the training process. By utilizing neural networks to train sample data during rehabilitation training, the fuzzy rules and membership functions in fuzzy intention recognition algorithm are optimized to improve the accuracy of intention recognition during training. By adopting the independently developed experimental platform for the upper limb rehabilitation robot, active–passive training, intention recognition, and training mode switching are achieved. The results show that the active and passive training processes are smooth, the training intention recognition is accurate, and the switching between active and passive training modes is steady. This verifies the feasibility and effectiveness of the established mathematical model in upper limb rehabilitation training. Full article

The population is often opposed to wind turbines being erected near their homes, mainly because the machines are noisy, especially at night. In an effort to establish a compromise between the needs of the people and the fulfilment of energy demands, wind turbines have the ability to switch between day and night operation by reducing the rotation speed during the night, resulting in a loss of generated power. The present study investigates simple models for noise emission, propagation, and prediction, with the objective of proposing a control system configuration that continuously adjusts the rotational speed as much as necessary until it matches sound level regulations while minimising power losses. Thus, several approaches are implemented and tested with a very large reference wind turbine. The simulation results of a reference wind turbine show that the approaches provide significant improvements in sound reduction as well as in power conversion. Full article

Since the beginning of the 21st century, infrared Nd:YVO₄ pulsed lasers have been widely applied, especially in some actual industrial processes. In the working process of a laser-aided etching device, the “match-head” effect must be effectively controlled by suppressing the first giant pulse for a solid-state Q-switched laser. In the process of optimizing the infrared Nd:YVO₄ pulsed laser by adjusting the slope parameters of the radio frequency (RF) modulation to suppress the first giant pulse, it has been found that an abnormal horizontally polarized emission with a very short time appears before the formal vertically polarized emission when the gate signal is artificially started. Actually, abnormal horizontally polarized emissions will bring some unexpected machining traces during the production process and even greater dangers. The experimental results show that with the increase in the slope duration of an RF signal, the existence time of abnormal output horizontally polarized light will be shortened, and the horizontal giant pulse and vertical giant pulse are well suppressed. When the slope duration is greater than 0.18 ms, both horizontal and vertical giant pulses will disappear. The horizontally polarized light can be thoroughly suppressed when the slope duration is greater than 13.7 ms. Compared with the method of adding a polarizer to eliminate abnormal output horizontally polarized light, this method does not add elements in the laser, ensuring that the laser volume is relatively small, and does not affect the quality of the normal output laser. The research conclusion is thought to be of great practical significance, especially for processing transparent materials. Full article

Ensuring the stability of power systems is essential to promote energy sustainability. The integrated operation of these systems is critical in sustaining modern societies and economies, responding to the increasing demand for electricity and curbing environmental consequences. This study focuses on the optimization of energy system stability through the coordination of power system stabilizers (PSSs) and power oscillation dampers (PODs) in a single-machine infinite bus energy grid configuration that has flexible AC alternating current transmission system (FACTS) devices. Intelligent control strategies using PSS and POD techniques are suggested to increase power system stability and generate supplementary control signals for both the generator excitation system and FACTS device switching control. An intelligent optimal modal control framework equipped with deep learning methods is introduced to control the generator excitation system and thyristor-controlled series capacitor (TCSC). By optimally choosing the weighting matrix Q and implementing close-loop pole shifting, an optimal modal control approach is formulated. To harness its adaptive potential in fine-tuning controller parameters, an auxiliary deep learning-based optimization algorithm with actor–critic architecture is implemented. This comprehensive technique provides a promising path to effectively reduce electromechanical oscillations, thereby enhancing voltage regulation and transient stability in power systems. Full article

This study introduces an integrated computational environment that leverages Brain–Computer Interface (BCI) technology to enhance information access for individuals with severe disabilities. Traditional assistive technologies often rely on physical interactions, which can be challenging for this demographic. Our innovation focuses on creating new assistive technologies that use novel Human–Computer interfaces to provide a more intuitive and accessible experience. The proposed system offers four key applications to users controlled by four thoughts: an email client, a web browser, an e-learning tool, and both command-line and graphical user interfaces for managing computer resources. The BCI framework translates ElectroEncephaloGraphy (EEG) signals into commands or events using advanced signal processing and machine learning techniques. These identified commands are then processed by an integrative strategy that triggers the appropriate actions and provides real-time feedback on the screen. Our study shows that our framework achieved an 82% average classification accuracy using four distinct thoughts of 62 subjects and a 95% recognition rate for P300 signals from two users, highlighting its effectiveness in translating brain signals into actionable commands. Unlike most existing prototypes that rely on visual stimulation, our system is controlled by thought, inducing brain activity to manage the system’s Application Programming Interfaces (APIs). It switches to P300 mode for a virtual keyboard and text input. The proposed BCI system significantly improves the ability of individuals with severe disabilities to interact with various applications and manage computer resources. Our approach demonstrates superior performance in terms of classification accuracy and signal recognition compared to existing methods. Full article

The incompleteness of the existing knowledge graphs in the railway domain creates information gaps, impacting their quality and effectiveness in the operation and maintenance of high-speed railway turnout switch machines. To address this, we propose a multi-layer model (KBGC) that combines KG-BERT, graph attention network (GAT), and Convolutional Embedding Network (ConvE) for knowledge graph completion in railway maintenance. KG-BERT fine-tunes a pre-trained BERT model to extract deep semantic features from entities and relationships, converting them into graph structures. GAT captures key structural relationships between nodes using an attention mechanism, producing enriched semantic and structural embeddings. Finally, ConvE reshapes and convolves these embeddings to learn complex entity interactions, enabling accurate link prediction. Extensive experiments on the HRTOM dataset, containing triplet data from high-speed railway turnout switch machines, demonstrate the model’s effectiveness, achieving an MRR of 50.8% and a Hits@10 of 60.7%. These findings show that the KBGC model significantly improves knowledge graph completion, aiding railway maintenance personnel in decision making and preventive maintenance, and providing new tools for railway maintenance applications. Full article