SVM multi-class expansion strategy based on BP neural network is used for transformer fault diagnosis, which has higher classification accuracy than traditional multi-class support vector machine. However, this method needs to train the initial weight threshold to diagnose transformer faults, and its coding calculation process is complicated. This paper presents an SVM transformer fault diagnosis method based on Improved BP neural network and multi parameter optimization. On the basis of improved BP neural network, the SVM algorithm is further optimized based on multi parameters of k-fold cross validation (CV) and artificial bee colony algorithm. Finally, it provides technical support for the inspection of transformer equipment.

K-fold cross validation, Improve BP neural network, Artificial bee colony algorithm, Penalty factor parameter, Transformer Fault Diagnosis.