Wind turbine gears, operating at high speeds under complex environmental conditions, exhibit subtle early-stage fault signals that are easily masked, resulting in low accuracy with conventional diagnostic methods. To address this issue, this paper proposes a fault diagnosis method for wind turbine gears based on an improved sailfish optimizer (ISFO) algorithm optimising variational modal decomposition (VMD) and convolutional neural networks (CNN). Firstly, the ISFO algorithm is enhanced by incorporating initialisation via the Logistic chaotic map, optimisation principles from Lévy flight theory, and genetic algorithm techniques. This yields an ISFO algorithm based on hybrid strategies, effectively resolving the algorithm’s local optimum issue. Subsequently, using ISFO algorithm refines VMD parameter decomposition of signals, extracting fault feature information from the modal component with the highest correlation coefficient. A short-time Fourier transform (STFT) is then employed to construct a time-frequency map. Finally, the time-frequency map is input into an optimised CNN for fault diagnosis classification. Experimental comparisons and analyses demonstrate that the proposed method achieves high diagnostic accuracy on both public and self-test datasets, with an average accuracy rate of 98.67%, effectively addressing wind turbine gear fault diagnosis challenges.

The rotary air preheater plays a crucial role in recovering waste heat from the boiler, but its efficiency is significantly affected by air leakage, especially during deep peak-shaving operation, where rotor thermal deformation leads to prominent radial air leakage issues. To address this, a thermo-fluid-solid coupled computational model is proposed, which incorporates the rotor's “mushroom-shaped” thermal deformation characteristics to accurately simulate the leakage behavior induced by thermal deformation. The study primarily analyzes the impact of rotor thermal deformation on the sealing gap and leakage rate. Under boiler maximum continuous rating (BMCR) conditions, the model results show that hot-end leakage accounts for 78.75% of the total leakage. When the reserved clearance is increased to 25 mm, the leakage rate can reach up to 39.8 kg/s. For every 1% increase in leakage rate, an additional 2 102.9 tons of standard coal are consumed annually, and the model's prediction results are consistent with the actual data of the power plant. The study demonstrates that incorporating thermal deformation effects into the analysis of air leakage significantly improves the model's predictive accuracy for leakage distribution under different unit clearances. This research provides theoretical support for optimizing the sealing system design of the rotary air preheater and offers practical solutions for enhancing operational efficiency and reducing energy consumption.