Online monitoring and fault diagnosis system for wind turbine generator set bearing

Abstract

An online monitoring and fault diagnosis system for a wind turbine generator set bearing includes: a first step, template library creation: creating a wind turbine generator set bearing vibration template library offline; a second step, data acquisition: synchronously acquiring vibration acceleration signals of the bearing in four directions in a wind turbine generator set online monitoring platform, and allowing a data acquisition interface to complete configuration of a data acquisition card; a third step, signal initial fusion, wherein during a signal acquisition process, a sensor is affected by noise and the sensor itself, the acquired signals are preprocessed, so that the acquired signals can retain the fault information to the greatest extent; a fourth step, feature value extraction:using the EMD algorithm to decompose the fused vibration signal into different frequency bands; and a fifth step, fault monitoring: using the BP neural network and the Euclidean distance to calculatethe similarity between a fault feature vector and a vibration template, sending the results of the two methods as the D-S evidence theory as the evidence body for decision making and fault warning.

Description

technical field [0001] The invention relates to a wind power generating device, in particular to an online monitoring and fault diagnosis system for a wind power generating set bearing. Background technique [0002] The wind power bearing is the core component of the wind turbine, and its design life is required to be greater than 20 years. Once it fails, it will lead to the failure of the wind turbine and cause huge economic losses. In order to timely discover the potential fault factors of the bearing during operation and ensure the efficient and stable operation of the wind turbine, it is of great significance to implement online monitoring and fault diagnosis at the same time. [0003] At present, the running state monitoring of existing wind turbines generally uses the lower computer to collect signals, and then uploads them to the remote upper computer for analysis and processing. When an abnormality is found, an alarm signal is sent. There is an obvious lag in the dia...

AI Technical Summary

Problems solved by technology

[0006] Due to the complexity of the mechanical structure, there are various reasons for the failure of mechanical equipment, and the symptoms associated with the failure are becoming more and more complex. A single analysis and processing of data often leads to false alarms, false alarms, etc., while the existing technology There is a lack of online and timely alarm function, and when an abnormality is found, an alarm signal cannot be sent, and the diagnosis process has obvious hysteresis. Therefore, the present invention provides an online monitoring and fault diagnosis system for wind turbine bearings. The system uses information Fusion technology, which performs various analysis and processing on the measurement signals of multiple sensors, such as correlation, combination and estimation, so as to improve the accuracy of state recognition and realize the comprehensive evaluation of the state information to be measured

Images