Prediction method and system for power transformer top layer oil temperature interval

Abstract

The invention discloses a prediction method and system for a power transformer top layer oil temperature interval. On the basis of a core limiting learning machine and a Bootstrap method, original training set data is obtained, and a sub training set is generated through the Bootstrap method; the sub training set is adopted for training a plurality of core limiting learning machine top layer oil temperature prediction models; the original training set is predicted on the basis of the core limiting learning models, and according to a prediction result, a training sample of the noise predicting core limiting learning machine is generated; the noise prediction core limiting learning machine is trained; the multiple core limiting learning machine top layer oil temperature prediction models are adopted for predicting a verification set, and the noise prediction core limiting learning machine is adopted for predicting the top layer oil temperature observation noise variance; according to the variance of the top layer oil temperature prediction result on the basis of the multiple core limiting learning, and the predicted observation noise variance, the top layer oil temperature prediction interval is obtained through calculation. According to the prediction method and system, the clear and reliable transformer top layer oil temperature prediction interval on the certain confidence level can be obtained.

Description

technical field [0001] The invention relates to a method and system for predicting the oil temperature range of the top layer of a power transformer. Background technique [0002] The safety and aging rate of the oil-paper insulation system of an oil-immersed power transformer are mainly affected by its internal temperature rise, and the top layer oil temperature is one of the important thermal variables describing the internal temperature rise state of the transformer. During the operation of the transformer load, it must be ensured that it does not exceed the limit value. According to the load curve of the transformer and the ambient temperature conditions, the top oil temperature can be accurately and reliably predicted in the future. On the one hand, it can make full use of its load capacity under the premise of ensuring the safety and reliability of the transformer. On the other hand, it can prevent the transformer from appearing. Overheating faults are significant. ...

AI Technical Summary

Problems solved by technology

[0003] At present, the prediction methods for the oil temperature on the top layer of the transformer are all point prediction methods, that is, the specific prediction value at a certain moment is given, and the overall error level is only used as the performance index of the prediction accuracy, without considering the uncertainty and prediction of the prediction model itself. Positive and negative characteristics of error

Images