Mechanical fault diagnosis method based on maximum reweighted kurtosis blind deconvolution

Abstract

The invention relates to a mechanical fault diagnosis method based on maximum reweighted kurtosis blind deconvolution, belongs to the technical field of wind turbine generator fault diagnosis, and provides a new blind deconvolution method, namely maximum reweighted kurtosis blind deconvolution. The reweighted kurtosis has good robustness to single or a small amount of strong impact interference in the fault signal, and priori knowledge of the fault impact sequence to be recovered is not needed. On the basis, the maximum reweighted kurtosis blind deconvolution method can effectively solve the problem that a classic kurtosis-based maximization method tends to recover a single dominant impact instead of a gear fault impact sequence, and meanwhile, compared with a common non-full'blind '(depending on fault characteristic frequency prior) method, the maximum reweighted kurtosis blind deconvolution method has higher applicability in the aspect of industrial equipment gear fault diagnosis. And application cases in wind turbine fault diagnosis prove the effectiveness of the provided method on gear fault diagnosis.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of wind turbines, and in particular relates to a mechanical fault diagnosis method based on blind deconvolution of maximum weighted kurtosis. Background technique [0002] The wind turbine is the main equipment of the wind farm, and the price accounts for 74-82% of the total investment of the wind farm. Due to the harsh operating environment, the equipment failure rate is high, and the maintenance cost is expensive. Therefore, the maintenance cost of the wind turbine has become the main operating cost of the wind farm. Reducing the maintenance cost of wind turbines is an important way to improve the economic benefits of wind farm operations. In order to effectively reduce the maintenance costs of wind turbines, wind power companies have introduced technologies such as condition monitoring, fault diagnosis and condition maintenance. [0003] In the fault diagnosis process, due to the influe...

Images