Disease is one of the primary threats to maize growth. Currently, maize disease detection is mainly conducted in laboratories, making it difficult to promptly respond to diseases. To enable detection in the field, a lightweight model is required. Therefore, this paper proposes a lightweight model, YOLOv8-GO, optimized from the YOLOv8 (You Only Look Once version 8) model. The Global Attention Mechanism was introduced before the SPPF (Spatial Pyramid Pooling Fast) layer to enhance the model’s feature extraction capabilities without significantly increasing computational complexity. Additionally, Omni-dimensional Dynamic Convolution was employed to optimize the model’s basic convolutional structure, bottleneck structure, and C2f (Faster Implementation of CSP (Cross Stage Partial) Bottleneck with two convolutions) module, improving feature fusion quality and reducing computational complexity. Compared to the base model, YOLOv8-GO achieved improvements across all metrics, with mAP@50 increasing to 88.4%, a 2% gain. The computational complexity was 9.1 GFLOPs, and the model could run up to 275.1 FPS. YOLOv8-GO maintains a lightweight design while accurately detecting maize disease targets, making it suitable for application in resource-constrained environments.

In different light intensities, photovoltaic (PV) arrays with multi-peak characteristics encounter numerous challenges in maximum power point tracking (MPPT) control, such as low computational efficiency, slow convergence speed, and susceptibility to local optima. To address these issues, this study proposes an improved quantum particle swarm optimization (QPSO) algorithm that combines the advanced features of the Whale Optimization Algorithm (WOA) with the concept of Lévy flight, thereby forming a novel mechanism. The convergence of this algorithm, together with the particle swarm optimization (PSO) and quantum particle swarm optimization (QPSO) algorithms, was simulated and evaluated using 10 single-peak and multi-peak test functions, and then applied to a simulation model of PV array partial shading. The results show that, compared with the traditional PSO method, the tracking accuracy of this algorithm is improved by 2.80% and the convergence speed is increased by 57.14%. Under both static and sudden shading conditions, this algorithm can effectively enhance the tracking ability of the maximum power point of the PV array and achieve stable maximum power output. The average tracking accuracy of this algorithm reaches 99.71% and the average tracking speed is 0.06 s in simulation, showing an obvious advantage over both the PSO and QPSO algorithms. This simulation-based validation confirms the algorithm’s effectiveness, though hardware validation remains for future work. These results fully demonstrate the unique advantages and innovation of this algorithm in dealing with complex optimization problems, laying a solid foundation for improving the efficiency and reliability of PV systems and providing strong support for related research in this field.