Based on the characteristics of the whale optimization algorithm (WOA) and perturbation observation (P&O) method, this paper proposes a novel hybrid approach called the improved chaotic whale optimization combined with perturb and observe (ICWOA-P&O) method for maximum power point tracking (MPPT) control to solve the challenge of low efficiency in photovoltaic (PV) power generation under local shadows. First, the ICWOA is used for a global search to quickly locate the position of the maximum power point (MPP). Then, the P&O method is used for a fine-grained local search to quickly track the position of the global maximum power point (GMPP) with low oscillation. To ensure accuracy, the tracking performance of the ICWOA-P&O method is comprehensively compared with the WOA-P&O, WOA, and PSO models under four conditions: uniform irradiance, static local shading, dynamic shading, and sudden changes in irradiance and temperature. The simulation results verify that under the above four conditions, the ICWOA-P&O method can track the MPP continuously and stably and greatly improves the convergence time and accuracy. Compared with the other three methods, the ICWOA-P&O method can effectively obtain the fastest tracking speed (less than 0.1 s), the highest tracking accuracy (more than 99.97%), the smallest relative error (less than 0.03%), and the smallest oscillation fluctuation. Finally, this study integrated the ICWOA-P&O algorithm into the designed MPPT controller hardware and established a practical PV experimental platform based on the ICWOA-P&O control algorithm for practical tests.

Rice blast caused by Magnaporthe oryzae is a major cause of yield reductions and quality deterioration in rice. Therefore, early detection of the disease is necessary for controlling the spread of rice blast. This study proposed a dual-channel feature fusion model (DCFM) to achieve effective identification of rice blast. The DCFM model extracted spectral features using successive projection algorithm (SPA), random frog (RFrog), and competitive adaptive reweighted sampling (CARS), and extracted spatial features from spectral images using MobileNetV2 combined with the convolutional block attention module (CBAM). Then, these features were fused using the feature fusion adaptive conditioning module in DCFM and input into the fully connected layer for disease identification. The results show that the model combining spectral and spatial features was superior to the classification models based on single features for rice blast detection, with OA and Kappa higher than 90% and 88%, respectively. The DCFM model based on SPA screening obtained the best results, with an OA of 96.72% and a Kappa of 95.97%. Overall, this study enables the early and accurate identification of rice blast, providing a rapid and reliable method for rice disease monitoring and management. It also offers a valuable reference for the detection of other crop diseases.