Changhong Jiang

This paper presents a composite control strategy for gearless coal mill to improve the disturbance immunity under low-speed variable operating conditions. First, the gearless coal mill encounters power supply voltage fluctuations, mechanical failures, or ambient temperature changes during operation. These situations can cause the system to suffer from the problem of insufficient control accuracy of the rotational speed. Therefore, a non-singular fast terminal sliding mode control strategy is proposed to improve the speed response. Then, to address the problem of load perturbation caused by different coal quality, this paper designs the extended state observer. Feed-forward compensation of the perturbation is performed to improve the robustness. Finally, due to the parameter mismatch problem caused by heat in operations that take a long time, this paper proposes a sliding-mode-based deadbeat predictive current control. The strategy possesses the fast dynamic response of deadbeat predictive current control while retaining the strong robustness of sliding mode control. Lyapunov proved the stability of the proposed control strategy. The experimental results verified that the proposed control strategy had better control performance.

In intelligent electric vehicle (EV) driving technology, the high safety and accuracy of steering system is an important concern. This article presents a dual-motor steer-by-wire (DMSBW) system to improve reliability and safety of the steering system for intelligent EV. However, the parameter uncertainties, time-varying road disturbances, and severe failures of the steering motors in the dual-motor SBW system deteriorates the vehicle tracking performance. In order to solve the above problems, an adaptive fault-tolerant control method is presented integrated with variable-exponential fixed-time sliding-mode control (VEFTSMC) technology and neural network (NN) for the dual-motor SBW system, in which the neural network is used to approximate the system uncertainty term. First, for the dual-motor SBW system loss of effectiveness, an adaptive law is developed to estimate the unknown fault coefficient. Then, considering the unknown upper bound of the time-varying disturbances, the switching function containing the disturbance term is designed to improve the robustness. Furthermore, considering the transient response, a VEFTSMC is developed for the dual-motor SBW system, which has better convergence rate than conventional SMC. Experimental results are given to validate the effectiveness of the proposed control strategy. The verification results show that the proposed control strategy can improve the stability under the parameters disturbances and different types of actuator faults.

To tackle the challenges associated with lane changes in diverse driving environments, this study introduces an Improved Model Predictive Control (IMPC) approach that integrates vehicle state and driving context to execute maneuvers effectively. Initially, a simplified model is established, incorporating vehicle position, velocity, and driving conditions. Subsequently, a Sigmoid function is utilized to restrict vehicle movements, while Finite State Machine (FSM) decision-making selects appropriate maneuvers in real time according to changing driving conditions. In addition, a discrete Simplified Dual Neural Network (SDNN) is utilized to efficiently solve Quadratic Programming (QP) problems, overcoming the slow-solving issue of traditional MPC and ensuring rapid acquisition of longitudinal and lateral accelerations for lane changes, braking, and overtaking maneuvers. Finally, the results from hardware-in-the-loop (HIL) simulation validation indicate that IMPC can efficiently address collision avoidance with surrounding dynamic vehicles across three distinct driving scenarios.

To address the issues of high environmental complexity, insufficient model performance, and low computational efficiency in underwater image analysis, this paper proposes a lightweight underwater object detection algorithm named SGL-YOLO, which is based on an enhanced YOLOv8 framework. In the backbone network, we introduce a newly designed SCA-C2f module that replaces the original C2f module, thereby improving feature discrimination and representation capabilities. To solve the problem of insufficient feature fusion in the neck network, a global-local cross-layer aligned bidirectional feature pyramid network (GLCA-BiFPN) is constructed, which improves the detection performance of small objects while reducing the model parameters and computational cost. A lightweight shared convolutional detection head (LSCD) is introduced in the head to optimize the computational efficiency. Finally, the WIoU is adopted to replace the CIoU loss function, thereby improving the accuracy of bounding box regression. SGL-YOLO achieves outstanding results on the DUO dataset. Compared with YOLOv8, the model parameters are reduced by 45.2%, the model computational complexity is decreased by 27.2%, and the average detection accuracy is increased by 1.1%, achieving a good balance between detection accuracy and detection speed.

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.

Real-time object detection and pose estimation are critical in practical applications such as virtual reality, scene understanding, and robotics. In this paper, we propose a compact generalized non-local pose estimation network capable of directly predicting the projection of an object’s 3D bounding box vertices onto a 2D image, facilitating the estimation of the object’s 6D pose. The network is constructed using the YOLOv5 model, with the integration of an improved non-local module termed the Compact Generalized Non-local Block. This module enhances feature representation by learning the correlations between the positions of all elements across channels, effectively capturing subtle feature cues. The proposed network is end-to-end trainable, producing accurate pose predictions without the need for any post-processing operations. Extensive validation on the LineMod dataset shows that our approach achieves a final accuracy of 46.1% on the average 3D distance of model vertices (ADD) metric, outperforming existing methods by 6.9% and our baseline model by 1.8%, thus underscoring the efficacy of the proposed network.

Six-dimensional object pose estimation is a fundamental problem in the field of computer vision. Recently, category-level object pose estimation methods based on 3D-GC have made significant breakthroughs due to advancements in 3D-GC. However, current methods often fail to capture long-range dependencies, which are crucial for modeling complex and occluded object shapes. Additionally, discerning detailed differences between different objects is essential. Some existing methods utilize self-attention mechanisms or Transformer encoder–decoder structures to address the lack of long-range dependencies, but they only focus on first-order information of features, failing to explore more complex information and neglecting detailed differences between objects. In this paper, we propose SAPENet, which follows the 3D-GC architecture but replaces the 3D-GC in the encoder part with HS-layer to extract features and incorporates statistical attention to compute higher-order statistical information. Additionally, three sub-modules are designed for pose regression, point cloud reconstruction, and bounding box voting. The pose regression module also integrates statistical attention to leverage higher-order statistical information for modeling geometric relationships and aiding regression. Experiments demonstrate that our method achieves outstanding performance, attaining an mAP of 49.5 on the 5°2 cm metric, which is 3.4 higher than the baseline model. Our method achieves state-of-the-art (SOTA) performance on the REAL275 dataset.