Wind driven generator gearbox fault diagnosis method and system

Abstract

The invention discloses a wind driven generator gearbox fault diagnosis method and system based on a stacked denoising auto-encoder, and belongs to the field of fault diagnosis. The method comprises the following steps: taking a signal obtained by preprocessing collected original vibration signals of a gearbox of a wind driven generator in different working states as training data; inputting the training data into a stacked denoising auto-encoder; meanwhile, introducing a quantum particle swarm optimization algorithm to optimize the structure and parameters; inputting the preprocessed test signal into a trained stacked denoising auto-encoder to extract high-dimensional fault features implied in the original vibration signal, and finally inputting the extracted fault features into a least square support vector machine to perform fault classification, thereby completing fault diagnosis of the gearbox. According to the method, the fault type can be effectively distinguished, a powerful basis is provided for finding out the fault position of the gearbox and maintaining, and stable and reliable operation of equipment is guaranteed.

Description

technical field [0001] The invention belongs to the field of fault diagnosis, and more specifically relates to a fault diagnosis method and system for a wind power generator gearbox based on a stacked denoising autoencoder. Background technique [0002] In recent years, wind power generation has made great progress, but compared with traditional power generation systems such as coal, natural gas, etc., due to the relatively high operation and maintenance costs, the maintenance strategy of wind power projects requires more initiative. Therefore, it is necessary to reduce the maintenance cost of wind turbines through condition monitoring, diagnosis, prediction and health management. Most of the gearbox failures are gear failures. At the same time, maintenance operations usually caused by gearbox failures are very complicated, and the disassembly, transportation and repair costs are also very high. Therefore, in order to ensure the normal operation of wind turbines, it is ver...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention proposes a wind turbine gearbox fault diagnosis method and system based on a stacked denoising autoencoder, thereby solving the technical problem that the existing diagnostic methods have unsatisfactory diagnostic results

Images