Hydroelectric generating set operation data trend early warning method

Abstract

The invention discloses a hydroelectric generating set operation data trend early warning method. The method comprises the following steps of S1, regularly collecting hydroelectric generating set operation data; s2, preprocessing the hydroelectric generating set working condition data set to obtain a training data set; s3, training the LSTM to obtain a currently optimized LSTM; s4, performing trend prediction on the working condition of the hydroelectric generating set by adopting the currently optimized LSTM to obtain a prediction result; s5, setting a multi-stage early warning value when thehydroelectric generating set runs, judging whether a prediction result reaches the early warning value or not, if yes, giving early warning time, displaying the prediction result and the early warning time at the front end of the power station monitoring system, and ending an early warning process, and if not, displaying the prediction result at the front end of the power station monitoring system, and ending the early warning process; according to the method, the problems of low reliability of single-factor prediction, lack of combination of multiple influence factors, unobvious advantages of time series data and low high-efficiency real-time efficiency of an existing prediction method are solved.

Description

technical field [0001] The invention relates to the field of fault diagnosis of hydroelectric units, in particular to a method for early warning of the trend of hydroelectric unit operation data. Background technique [0002] The amount of information and data that needs to be monitored and analyzed, such as the production equipment systems of hydropower plants, complex associations, and the operating status of each equipment, is very large. For the equipment failure that has occurred, it can be monitored through the monitoring system. However, in order to prevent problems before they happen and ensure safe operation, the operation and maintenance personnel on duty and professional engineers use their own experience and feelings to check the abnormal data one by one to monitor the status of the equipment. Even if experienced professionals rely on excellent personal ability to analyze parameters, there must be problems such as limited monitoring range, limited monitoring tim...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a hydroelectric unit operation data trend early warning method to solve the problems of the support vector machine-based power distribution equipment temperature monitoring data prediction method: the reliability of single-factor prediction is low, and the lack of multi-influence The combination of factors, the inconspicuous advantages of time series data, and the problems of high efficiency and low real-time efficiency

Images