Wind turbine generator system state prediction method for carrying out similarity search on basis of history data

Abstract

The invention provides a wind turbine generation system state prediction method for carrying out similarity search on basis of history data, and relates to the technical field of wind turbine generation system state monitoring. The method comprises the following steps of: carrying out fan attribute selection and dimensionality reduction after preprocessing history data; carrying out clustering analysis on the dimensionality reduced data through an improved K-mean clustering algorithm; and carrying out history data similarity query to predict a fan operation state. According to the wind turbine generation system state prediction method for carrying out similarity search on basis of history data, a database can be established through history operation data of the wind turbine generator system, and the operation data can be compared with the history data of the fan and similar fans in real time so as to assess the state of the wind turbine generator system.

Description

technical field [0001] The invention relates to the technical field of wind turbine state monitoring, in particular to a wind turbine state prediction method based on similar search in historical data. Background technique [0002] At present, the research in the field of condition monitoring and fault diagnosis of wind turbines is in its infancy. Among the existing research results, the research on the whole machine focuses on the state evaluation and fault prediction, and the research on the key components of the wind turbine focuses on fault diagnosis. In wind turbine state assessment, it is mainly the residual analysis. The monitoring data of SCADA (Supervisory Control And Data Acquisition, that is, data acquisition and monitoring control system) is used as the input of the prediction model, and the prediction model such as artificial neural network or support vector machine is established. Obtain the predicted value, and then combine the actual monitoring value with the...

AI Technical Summary

Problems solved by technology

The main problem in this patent is that wind turbines work in harsh natural environments for a long time, and are affected by factors such as normal and extreme extreme temperatures, solar radiation, rainfall, snow, salt fog, sand and dust, and terrain contours. There are certain fluctuations in the operating state of the wind turbine, and the generated health state model may not be able to reflect all changes in the healthy state of the wind turbine, which has limitations

Moreover, due to changes in natural conditions, the safety baseline of the wind turbine should also change with the seasons and temperature. A simple fixed baseline cannot well indicate whether the operation status of the wind turbine is safe.

Images