The Fault Prediction of Converting Station Based on Big Data Technology and Machine Learning
In response to the shortcomings of current substation fault data processing,a machine learning based substation fault predic-tion method is proposed.Firstly,various data are collected during the normal operation and fault occurrence of the substation,and the dataset is divided into a training set,a validation set,and a testing set according to a certain proportion.Afterwards,appropriate features are selected for extraction,and distributed machine learning algorithms are used for model training and prediction.Finally,the feasibility of the proposed method is verified by analyzing the data generated from two actual substations.The experimental results show that the proposed method can effectively improve the accuracy and efficiency of fault prediction,and can help the power system achieve intelli-gent management and optimized operation.
国家科技期刊平台
NSTL
万方数据
