Intelligent Fault Diagnosis Method of Power Transformer Based on SSA-CNN
The stable operation of power transformers is crucial for the safety of the power system.Fault diagnosis of power transformers is a necessary step in their operation and maintenance process.Dissolved Gas Analysis(DGA)in oil is one of the most effective methods to determine the type of fault in power transformers.With dissolved gas analysis in oil as the core,a smart diagnosis method for power transformer faults based on Sparrow Search Algorithm to Convolutional Neural Network(SSA-CNN)optimization is proposed.Due to the current mainstream approach of manually selecting hy-perparameters in convolutional neural networks(CNN)models,which can lead to inaccurate diagnostic results,this paper introduces the Sparrow Search Algorithm(SSA)to achieve hyperparameter optimization in convolutional neural networks.The experimental test results show that compared with traditional artificial intelligence methods,the convolutional neural network optimized by the sparrow search algorithm has higher accuracy in power transformer fault diagnosis and higher optimization efficiency.
power transformerfault diagnosisCNNSSAhyperparameter search optimization
万方数据
维普
