To address the challenges posed by complex backgrounds and the low occurrence in photovoltaic cell images captured by industrial sensors, we propose a novel defect detection method: MRA-YOLOv8. First, a multi-branch coordinate attention network (MBCANet) is introduced into the backbone. The coordinate attention network (CANet) is incorporated to mitigate the noise impact of background information on the detection task, and multiple branches are employed to enhance the model’s feature extraction capability. Second, we integrate a multi-path feature extraction module, ResBlock, into the neck. This module provides finer-grained multi-scale features, improving feature extraction from complex backgrounds and enhancing the model’s robustness. Finally, we implement alpha-minimum point distance-based IoU (AMPDIoU) to the head. This loss function enhances the accuracy and robustness of small object detection by integrating minimum point distance-based IoU (MPDIoU) and Alpha-IoU methods. The results demonstrate that MRA-YOLOv8 outperforms other mainstream methods in detection performance. On the photovoltaic electroluminescence anomaly detection (PVEL-AD) dataset, the proposed method achieves a mAP₅₀ of 91.7%, representing an improvement of 3.1% over YOLOv8 and 16.1% over detection transformer (DETR). On the SPDI dataset, our method achieves a mAP₅₀ of 69.3%, showing a 2.1% improvement over YOLOv8 and a 6.6% improvement over DETR. The proposed MRA-YOLOv8 also exhibits great deployment potential. It can be effectively integrated with drone-based inspection systems, allowing for efficient and accurate PV plant inspections. Moreover, to tackle the issue of data imbalance, we propose generating synthetic defect data via generative adversarial networks (GANs), which can supplement the limited defect samples and improve the model’s generalization ability.

Image classification and segmentation are important tasks in computer vision. ResNet and U-Net are representative networks for image classification and image segmentation, respectively. Although many scholars used to fuse these two networks, most integration focuses on image segmentation with U-Net, overlooking the capabilities of ResNet for image classification. In this paper, we propose a novel U-ResNet structure by combining U-Net’s convolution–deconvolution structure (UBlock) with ResNet’s residual structure (ResBlock) in a parallel manner. This novel parallel structure achieves rapid convergence and high accuracy in image classification and segmentation while also efficiently alleviating the vanishing gradient problem. Specifically, in the UBlock, the pixel-level features of both high- and low-resolution images are extracted and processed. In the ResBlock, a Selected Upsampling (SU) module was introduced to enhance performance on low-resolution datasets, and an improved Efficient Upsampling Convolutional Block (EUCB*) with a Channel Shuffle mechanism was added before the output of the ResBlock to enhance network convergence. Features from both the ResBlock and UBlock were merged for better decision making. This architecture outperformed the state-of-the-art (SOTA) models in both image classification and segmentation tasks on open-source and private datasets. Functions of individual modules were further verified via ablation studies. The superiority of the proposed U-ResNet displays strong feasibility and potential for advanced cross-paradigm tasks in computer vision.

Optimal path planning algorithms offer substantial benefits in high-density storage (HDS) systems in modern smart manufacturing. However, traditional algorithms may encounter significant optimization challenges due to intricate architectural configurations and traffic constraints of the HDS system. This paper addresses these issues by introducing a two-step novel path planning method: (1) the mesh-tree grid map topological representation and the (2) Lattice-Hopping (LH) algorithm. The proposed method first converts the layout of an HDS system into a mesh-tree grid hierarchical structure by capturing and simplifying the spatial and geometrical information as well as the traffic constraints of the HDS system. Then, the LH algorithm is proposed to find optimal shipping path by leveraging the global connectivity of main tracks (main track priority) and the ‘jumping’ mechanism of sub-tracks. The main track priority and the ‘jumping’ mechanism work together to save computational complexity and enhance the feasibility and optimality of the proposed method. Numerical and case studies are performed to demonstrate the superiorities of our method to properly modified benchmark algorithms. Algorithm scalability, robustness, and operational feasibility for industrial production in modern smart manufacturing are also displayed and emphasized.