Fault diagnosis system and fault diagnosis method based on massive data technology

Abstract

The invention discloses a fault diagnosis system and a fault diagnosis method based on a massive data technology. The fault diagnosis system comprises a data acquiring module, a data pre-processing and exchanging module, a data analysis and diagnosis module and an intelligent control module, wherein the data pre-processing and exchanging module is connected with the data acquiring module; the data analysis and diagnosis module is connected with the data pre-processing and exchanging module in a bidirectional manner; and the intelligent control module is connected with the data pre-processing and exchanging module. Acquired state data are pre-processed through the data pre-processing and exchanging module, noise interferences are eliminated, and acquired state data can be conveniently analyzed well; and the state data are analyzed through the data analysis and diagnosis module by using the massive data technology, all the state data are analyzed to obtain specific and comprehensive diagnosis information, the fault diagnosis speed is increased, and the fault detection accuracy is improved. By the fault diagnosis system and the fault diagnosis method, faults of a wind driven generator can be detected and controlled, and the labor cost is greatly reduced.

Description

technical field [0001] The invention relates to the field of fault diagnosis of wind power generation equipment, in particular to a fault diagnosis system and a diagnosis method based on big data technology. Background technique [0002] my country is rich in wind resources, and wind power has developed rapidly in recent years. Since wind turbines are installed at an altitude of tens of meters, and the site environment of the wind farm is harsh, the abnormal operation or failure of the wind turbine generator set cannot be detected and dealt with effectively in time, which may cause serious damage to the wind turbine and cause the wind turbine to be shut down for maintenance. It not only affects the working time of the wind turbine, but also increases the maintenance cost, causing the wind farm to suffer huge losses. Therefore, it is particularly important to be able to detect the abnormal operation and failure of the fan in time. [0003] According to the current actual op...

AI Technical Summary

Problems solved by technology

A wind farm is equipped with dozens or even hundreds of wind turbines. Vibration sensors are installed on the main vulnerable parts of each wind turbine, which will generate hundreds of vibration signals. If ordinary data processing methods are used, then It is impossible to process such a large number of data sources in a short period of time, and it is impossible to realize the synchronization of data monitoring, fault diagnosis and prediction

In the existing data processing flow, first perform fast Fourier transformation (FFT) on the obtained vibration signal, then compress the original data, select the frequency band data that may have faulty vibration waveforms, and use the least data to represent the original signal to achieve The purpose of saving the physical space for storing these signals, however, this method is only based on the frequency band data of some vibration waveforms, ignoring the vibration waveforms of other frequency bands, failing to give comprehensive analysis and diagnosis results, and reducing the detection accuracy of faults

Images