Jianfeng Zheng

To address the challenges of limited samples, class imbalance, and real-time requirements in surface defect detection for solar vacuum glass collector tubes, this study proposes an improved lightweight RT-DETR-based method. Specifically, DICM is introduced into the backbone to improve multi-directional and multi-scale feature extraction, HAFB is embedded in the neck to enhance the fusion of local details and global semantics, and transfer learning is adopted to alleviate data scarcity under small-sample conditions. Experiments on a self-built defect dataset of solar vacuum glass collector tubes show that the proposed method outperforms the original RT-DETR and several mainstream detectors in terms of Precision, Recall, mAP@0.5, and F1-score while maintaining favorable inference speed and model compactness. Under the same hardware conditions, the proposed model achieves an mAP@0.5 of 0.95, an inference speed of 83.21 FPS, and a model size of 82.36 MB. These results demonstrate the feasibility of the proposed method for real-time online defect detection in industrial scenarios.

The complex conditions of natural orchards, such as random distribution of fruits, serious shading, and highly variable illumination, make accurate and efficient citrus detection challenging, especially on low-cost hardware. To address these issues, this study proposes FPH-CDet, a lightweight citrus detection model based on YOLOv7-tiny that integrates Faster-PELAN, Partial Convolution (PConv), and Efficient Layer Attention Network-H (ELAN-H), together with an optimized detection head and Shape-IoU loss function, trained on a self-built citrus dataset. Experimental results showed that, compared with the baseline model, FPH-CDet increases precision, recall and FPS by 2.8%, 3.2% and 10.8% respectively, while reducing model size by 27.3%, effectively lowering computational complexity and storage requirements. To verify robustness and adaptability in unstructured scenarios, FPH-CDet was deployed on a low-cost Raspberry Pi and integrated into a UAV-based real-time citrus detection platform. In parallel, a PC-based web platform built with streamlit enables users to perform real-time citrus detection and counting on local images and videos directly through a browser. These results demonstrate that FPH-CDet and UAV-edge-web implementation provide a practical and scalable technical solution for intelligent citrus detection, offering important supports for the development of smart agriculture.

The issue of inadequate infrared recognition accuracy for substation equipment is addressed in this paper through the proposal of the IDSE-YOLO model, a high-precision infrared recognition model for substation equipment. The primary goal of this study is to improve recognition accuracy in complex backgrounds and low-resolution scenarios. It incorporates Dual Depthwise Convolution (DDConv) and Multi-scale Efficient Channel Attention (MECA) to enhance computational capabilities and feature extraction efficiency. Additionally, a multi-scale loss function is designed with optimised regression loss, enabling precise target identification. Experimental results, based on proprietary datasets, show that the enhanced model demonstrates substantial improvements in key performance metrics such as Precision (P), Recall (R), and Mean Average Precision (mAP), when compared to existing models. Notably, a comparison with the baseline YOLOv13 model reveals that the IDSE-YOLO model achieves an mAP of 95.3%, marking a 5.5% improvement, without a significant increase in computational load or parameter overhead. The model’s deployment on edge devices for on-site image recognition further demonstrates its efficacy and practicality. The findings validate the IDSE-YOLO model as a highly effective and viable solution for deploying infrared recognition systems for substation equipment on embedded devices, offering a significant boost in recognition accuracy.

In response to the problem of cooperative steering control between drivers and intelligent driving systems, a master–slave Game-Based human–machine cooperative steering control framework with adaptive weight fuzzy decision-making is constructed. Firstly, within this framework, a dynamic weight approach is established. This approach takes into account the driver’s state, traffic environment risks, and the vehicle’s global control deviation to adjust the driving weights between humans and machines. Secondly, the human–machine cooperative relationship with unconscious competition is characterized as a master–slave game interaction. The cooperative steering control under the master–slave game scenario is then transformed into an optimization problem of model predictive control. Through theoretical derivation, the optimal control strategies for both parties at equilibrium in the human–machine master–slave game are obtained. Coordination of the manipulation actions of the driver and the intelligent driving system is achieved by balancing the master–slave game. Finally, different types of drivers are simulated by varying the parameters of the driver models. The effectiveness of the proposed driving weight allocation scheme was validated on the constructed simulation test platform. The results indicate that the human–machine collaborative control strategy can effectively mitigate conflicts between humans and machines. By giving due consideration to the driver’s operational intentions, this strategy reduces the driver’s workload. Under high-risk scenarios, while ensuring driving safety and providing the driver with a satisfactory experience, this strategy significantly enhances the stability of vehicle motion.

Accurate estimation of photovoltaic (PV) power generation is of great significance to the operation and optimization of the power grid. However, due to the rapid movement of clouds in a short period of time, the changes in PV power are intermittent and fluctuating. Nowadays, sky images have been widely used for PV power estimation, which can effectively extract overall or local cloud information. However, Sun halos are often mistaken for being part of clouds and lead to incorrect cloud coverage calculations. To solve this problem, this paper proposes a method to calculate the local cloud occlusion index based on an improved two-dimensional Gaussian function. In addition, a new parameter, Sun block luminance, is introduced to quantify the lighting conditions in the solar area. On the other hand, this paper constructs a novel hybrid model, which introduces asymmetric convolution and SE attention module to enhance the extraction ability of sky image features. The test results show that, under sunny and cloudy conditions, the RMSE, MAE and R 2 values of the proposed model are 0.562, 0.462 and 0.989 on sunny days, 3.119, 2.248 and 0.774 on cloudy days, respectively, proving that the proposed model is superior to benchmark models.

Cloud image segmentation is a technique that divides images captured by meteorological satellites or ground-based observations into different regions or categories. By extracting the distribution, shape, and dynamic features of clouds, it provides precise data support for the meteorological and environmental fields, significantly influencing photovoltaic (PV) power generation forecasting, astronomical telescope observatory site selection, and weather forecasting. A ground-based cloud image segmentation model based on an improved U-Net is proposed, which adopts an overall encoder–decoder structure. In the encoder phase, this paper constructs a dilated convolution–atrous spatial pyramid pooling (ASPP)–dilated convolution structure to enhance early cloud feature extraction. Dilated convolution is a novel type of convolution that expands the receptive field by inserting holes into standard convolution, thereby capturing a larger range of contextual information. ASPP maintains high resolution while paying attention to both local details and global structures of the image. In the decoder stage, the bicubic interpolation method is used for up-sampling to restore the feature map resolution and improve the clarity of the segmented image. The bicubic interpolation method refers to the use of cubic polynomial functions to interpolate the pixel values of the input image. In addition, this paper designs a novel skip connection layer structure between the encoder and decoder, composed of a depthwise separable path (DS path) and an improved channel spatial attention module (Im-CSAM) connected in sequence. The DS path combines depthwise separable convolutions and residual structures to facilitate information exchange between high-level and low-level features. The Im-CSAM is a modular attention mechanism that focuses on important cloud features in spatial and channel dimensions to enhance segmentation accuracy. Experiments show that compared to the traditional U-Net, the accuracy, precision, and MIoU of this model improved by 2.2%, 4.1%, and 5.0%, respectively, in the SWINySEG dataset, and by 3.2%, 3.6%, and 5.8%, respectively, in the TCDD dataset, proving that the improved method has a better generalization ability and segmentation performance.

To minimize the occurrence of traffic accidents, such as vehicle rear-end collisions, while enhancing vehicle following, stability, economy, and ride comfort, a hierarchical adaptive cruise control strategy for vehicles is proposed. The upper-level controller computes the desired vehicle output acceleration based on model predictive control and switches between speed and spacing control in accordance with driving conditions. The brake/throttle opening switching model, brake control inverse model, and throttle opening inverse model in the lower-level controller of ACC are designed to obtain the desired throttle opening and braking pressure of the vehicle, thereby achieving control of the vehicle. A joint simulation platform was established using PreScan, CarSim and Matlab/Simulink. Finally, simulations for three typical working conditions were conducted in Simulink to verify the performance of the adaptive cruise control strategy. The results indicate that, in both the constant-speed cruise and vehicle-following cruise conditions, the vehicle can rapidly and stably follow the set initial speed and consistently maintain a safe distance from the preceding vehicle. Under the emergency braking condition, the vehicle can promptly respond with deceleration, ensuring driving safety. The proposed control strategy can accurately and safely track the target vehicle in diverse driving conditions and can concurrently fulfill the requirements of economy and comfort during vehicle travel.

The state of health (SOH) prediction of lithium-ion batteries is a pivotal function within the battery management system (BMS), and achieving accurate SOH predictions is crucial for ensuring system safety and prolonging battery lifespan. To enhance prediction performance, this paper introduces an SOH prediction model based on an improved sparrow algorithm and support vector regression (ISSA-SVR). The model uses nonlinear weight reduction (NWDM) to enhance the search capability of the Sparrow algorithm and combines a mixed mutation strategy to reduce the risk of local optimal traps. Then, by analyzing the characteristics of different voltage ranges, the charging time from 3.8 V to 4.1 V, the discharge time of the battery, and the number of cycles are selected as the feature set of the model. The model’s prediction capabilities are validated across various working environments and training sample sizes, and its performance is benchmarked against other algorithms. Experimental findings indicate that the proposed model not only confines SOH prediction errors to within 1.5% but also demonstrates robust adaptability and widespread applicability.

To address the common issues of accuracy and stability in trajectory tracking tasks for autonomous vehicles, this study proposes an innovative composite control strategy that skillfully integrates lateral and longitudinal dynamic control. For lateral control, model predictive control (MPC) theory is introduced to compute the front wheel steering angle that ensures optimal trajectory following. On the longitudinal control level, the vehicle’s acceleration and deceleration logic are finely tuned to ensure precise adherence to the preset speed trajectory. More importantly, by deeply integrating these two control methods, the comprehensive coordination of the vehicle’s lateral and longitudinal movements is achieved. To validate the effectiveness of the proposed control strategy, simulations were conducted using the CarSim and MATLAB/Simulink platforms. The analysis of the simulation results confirms that the proposed method effectively improves speed tracking stability and significantly enhances path tracking accuracy and overall driving stability.