An intelligent condition monitoring system for wind turbines based on multiple templates

Abstract

The invention relates to a multi-template-based wind turbine generator intelligent state monitoring system. The system comprises a system configuration module, a data quality detection module, an intelligent diagnosis module, a trend analysis module, a cluster benchmarking module, an early warning module and an early warning information statistics module. According to the multi-template-based windturbine generator intelligent state monitoring system, the application range is wide, data transmission is timely and reliable, omni-directional monitoring can be carried out on the health state of awind turbine generator, intelligent diagnosis can be realized under variable rotating speed working conditions, and statistics and analysis are more comprehensive and more practical.

Description

technical field [0001] The application relates to an intelligent condition monitoring system for wind turbines based on multiple templates, which is applicable to the technical field of wind turbine monitoring. Background technique [0002] Wind power can convert wind energy into electrical energy, and is the main means for human beings to utilize wind energy, a clean energy source. At present, the proportion of wind power in the field of electric energy is increasing year by year. According to the "Statistical Briefing on China's Wind Power Lifting Capacity in 2018", as of the end of 2018, the cumulative installed capacity of wind turbines in my country was about 210 million kilowatts, and the installed capacity of wind turbines maintained a steady growth trend. In the wind power generation system, the wind turbine is the core equipment and plays an important role in converting wind energy into electrical energy. At present, wind turbines are mainly divided into three typ...

AI Technical Summary

Problems solved by technology

However, building a machine learning model requires a large number of fault samples of wind turbines, and it is difficult to obtain fault samples in practice, which hinders the application of machine learning in practice.

Expert systems usually require a large amount of expert knowledge to build a wind turbine fault diagnosis expert system, but it is difficult to obtain a large amount of expert knowledge, and it is difficult to accurately describe the fault phenomenon of wind turbines

In addition, the expert system is too costly in subsequent updates and is not easy to maintain

It can be seen that the existing intelligent diagnosis methods for wind turbines have relatively large deficiencies, and it is difficult to implement them in practical applications.

Images