Wind turbine generating set fault diagnosis method based on bispectral entropy

Abstract

The invention relates to a wind turbine generating set fault diagnosis method based on bispectral entropy. The method includes the steps: collecting vibration signals of a wind turbine generating set in a normal running state, a minor faulty state, a medium faulty state and a severe faulty state; calculating fault characteristic bands of all the vibration signals; establishing a fault deviation degree detection model; collecting vibration signals of a to-be-detected wind turbine generating set, carrying out fault characteristic band calculation on the to-be-detected vibration signals, obtained fault characteristics are input to the fault deviation degree detection model, calculating the fault deviation degree between the faulty state and the above four faulty states, and finally obtaining the minimal deviation degree which is the faulty state of the wind turbine generating set. The fault characteristics of non-stationary signals can be effectively extracted, fault diagnosis for the wind turbine generating set can be carried out, and the fault diagnosis precision can be improved. The method can be widely applied to fault diagnosis for wind turbine generating set equipment.

Description

technical field [0001] The invention relates to a device fault diagnosis method, in particular to a bispectral entropy-based fault diagnosis method for wind power generators. Background technique [0002] Since the operation of large-scale rotating electromechanical equipment such as wind turbines is in a non-stationary and nonlinear state, changes in non-fault factors such as operating conditions and loads during operation will cause changes in signal energy. The usual energy-based vibration level and power The development and changes of the spectrum do not necessarily correspond to the development and changes of the fault state; on the other hand, the random changes in wind force and wind direction cause the speed of the wind turbine drive system to change at all times, and it has become very difficult to analyze its characteristic frequency. Therefore, the traditional The feature extraction method based on energy change and the feature extraction method of finding the fau...

AI Technical Summary

Problems solved by technology

[0002] Since the operation of large-scale rotating electromechanical equipment such as wind turbines is in a non-stationary and nonlinear state, changes in non-fault factors such as operating conditions and loads during operation will cause changes in signal energy. The usual energy-based vibration level and power The development and changes of the spectrum do not necessarily correspond to the development and changes of the fault state; on the other hand, the random changes in wind force and wind direction cause the speed of the wind turbine drive system to change at all times, and it has become very difficult to analyze its characteristic frequency. Therefore, the traditional The feature extraction method based on energy change and the feature extraction method of finding the fault characteristic frequency are difficult to effectively extract the characteristics of the wind turbine drive system's operational stability degradation, and cannot effectively diagnose system faults

Images