When a permanent magnet synchronous motor runs at low speed, the inverter will output discontinuous current and generate torque ripple; when the motor is runs at high speed, a large amount of stator harmonic current generates, which affects its speed following ability and torque stability. To ensure the fast and smooth switching of a permanent magnet synchronous motor in the full speed domain, this paper proposes the nonsingular terminal sliding mode control of PMSM speed control based on the improved exponential reaching law. Firstly, the improved exponential reaching law is composed of the state variables and power terms of the sliding mode surface functions. The reaching law function is designed in sections to balance the fast dynamic response of the system and chattering control. Secondly, an improved exponential reaching law based on the sliding mode control strategy of the PMSM speed loop is proposed. By designing the initial value of the integral term in the nonsingular terminal sliding mode surface function, the initial state of the system is located on the sliding mode surface. The integral sliding mode surface is used to reduce the system steady-state error, while the proposed sliding mode reaching law is used to increase the arrival speed and suppress system chattering, ultimately affecting modeling error problems, complex working conditions, and uncertainty factors. This paper proposes a sliding mode observer based on an improved exponential reaching law to compensate for the disturbances. Lyapunov stability theory can prove that this system can make the speed tracking error converge to zero in finite time. Hardware-in-the-loop experiments were used to validate the effectiveness of the proposed method.

In response to the problems of difficult identification of degradation stage start points and inadequate extraction of degradation features in the current rolling bearing remaining life prediction method, a rolling bearing remaining life prediction method based on multi-scale feature extraction and attention mechanism is proposed. Firstly, this paper takes the normalized bearing vibration signal as input and adopts a quadratic function as the RUL prediction label, avoiding identifying the degradation stage start point. Secondly, the spatial and temporal features of the bearing vibration signal are extracted using the dilated convolutional neural network and LSTM network, respectively, and the channel attention mechanism is used to assign weights to each degradation feature to effectively use multi-scale information. Finally, the mapping of bearing degradation features to remaining life labels is achieved through a fully connected layer for the RUL prediction of bearings. The proposed method is validated using the PHM 2012 Challenge bearing dataset, and the experimental results show that the predictive performance of the proposed method is superior to that of other RUL prediction methods.

In this paper, we present an active fault-tolerant, vehicle motion control, based on the multi-agent approach for a four-wheel independent steering system. This improves handling stability and active safety of the vehicle in the case of actuator faults. Firstly, an eight-degree-of-freedom four-input vehicle model is established by using the vector transformation method, which takes the four-wheel angle as the input and the yaw rate and the sideslip angle, obtained by the lateral force of a single wheel, as the outputs. Then, we established the topological structure of the four-wheel independent steering subsystems based on graph theory. Aiming at the known fault conditions, an adaptive sliding mode active fault-tolerant control based on the multi-agent four-wheel independent steering system is proposed, in which the unmodeled part of the system is estimated using adaptive methods. For unknown fault conditions, an active fault-tolerant control of the four-wheel independent steering system based on state observer is proposed. An extended state observer with sliding mode surface function as a state variable is designed to estimate actuator faults. Finally, it was demonstrated that the designed state observer and distributed active fault-tolerant control method reduced the impact of actuator failures on vehicle steering and improved the stability of the steering process based on the Lyapunov theory. The hardware in the loop experimental results validate the effectiveness of the proposed novel method.

Addressing the challenges and significant risks associated with diagnosing faults in wind turbine yaw systems, along with the typically low diagnostic accuracy, this study introduces a Long Short-Term Memory (LSTM) neural network augmented by a self-attention mechanism (SAM) as a novel fault diagnosis technique for wind turbine yaw systems. The method integrates the automatic weighting capability of the self-attention mechanism on input features with the advantage of LSTM in processing time series data, thereby effectively capturing key information and long-term dependencies in the operating data of the yawing system. This combination enhances the accuracy of fault feature extraction to more accurately identify various types of fault modes within the yawing system. Six types of feature parameters are extracted from the raw data collected by the SCADA (Supervisory Control And Data Acquisition) system of the wind turbine and are utilized as inputs for the diagnostic model. These parameters are then fed into the self-attention–LSTM neural network model to diagnose the health status of the yaw system, including yaw bearing damage, yaw gearbox failure, yaw motor failure, and sensor failure. The experimental results demonstrate that the accuracy of LSTM fault diagnosis, when enhanced with the self-attention mechanism, can reach 98.67% with an appropriate amount of training samples, verifying its significant advantages in terms of accuracy and stability of fault diagnosis. The proposed fault diagnosis method exhibits a better model fitting effect, strong generalization ability, and high accuracy compared to other methods, providing robust support for the reliable operation and maintenance of wind turbines.

A press-rotary triboelectric-electromagnetic hybrid energy harvesting device (PR-TEHD) is proposed to harvest micro-motion energy generated during manual press and rotation movements for IoT node powering and smart home control.

In this study, a tyre defect detection model is improved and optimized under the YOLOv5 framework, aiming at radial tyre defects with characteristics such as an elongated shape and various target sizes and defect types. The DySneakConv module is introduced to replace the first BotteneckCSP in the Backbone network. The deformation offset of the DySneakConv module is used to make the convolutional energy freely adapt to the structure to improve the recognition rate of tyre defects with elongated features; the AIFI module is introduced to replace the fourth BotteneckCSP, and the self-attention mechanism and the processing of large-scale features are used to improve the recognition rate of tyre defects with elongated features using the AIFI module. This latter module has a self-attention mechanism and the ability to handle large-scale features to solve the problems of diverse tyre defects and different sizes. Secondly, the CARAFE up-sampling operator is introduced to replace the up-sampling operator in the Neck network. The up-sampling kernel prediction module in the CARAFE operator is used to increase the receptive field and allow the feature reorganization module to capture more semantic information to overcome the information loss problem of the up-sampling operator. Finally, based on the improved YOLOv5 detection algorithm, the Channel-wise Knowledge Distillation algorithm lightens the model, reducing its computational requirements and size while ensuring detection accuracy. Experimental studies were conducted on a dataset containing four types of tyre defects. Experimental results for the training set show that the improved algorithm improves the mAP0.5 by 4.6 pp, reduces the model size by 25.6 MB, reduces the computational complexity of the model by 31.3 GFLOPs, and reduces the number of parameters by 12.7 × 10⁶ compared to the original YOLOv5m algorithm. Experimental results for the test set show that the improved algorithm improves the mAP0.5 by 2.6 pp compared to the original YOLOv5m algorithm. This suggests that the improved algorithm is more suitable for tyre defect detection than the original YOLOv5.