Research Article
Transformer Fault Diagnosis Based on BP Neural Network by Improved Apriori Algorithm
@INPROCEEDINGS{10.1007/978-3-030-62483-5_27, author={Chang Guoxiang and Gao Qiaoli and Gao Xinming and Cheng Junting}, title={Transformer Fault Diagnosis Based on BP Neural Network by Improved Apriori Algorithm}, proceedings={Green Energy and Networking. 7th EAI International Conference, GreeNets 2020, Harbin, China, June 27-28, 2020, Proceedings}, proceedings_a={GREENETS}, year={2020}, month={11}, keywords={Apriori algorithm BP neural network Transformer Fault diagnosis}, doi={10.1007/978-3-030-62483-5_27} }- Chang Guoxiang
Gao Qiaoli
Gao Xinming
Cheng Junting
Year: 2020
Transformer Fault Diagnosis Based on BP Neural Network by Improved Apriori Algorithm
GREENETS
Springer
DOI: 10.1007/978-3-030-62483-5_27
Abstract
With the continuous expansion of power system, it is increasing that the fault rate of transformer equipment in power system. Through the fault diagnosis technology, it can be found that the transformer fault in advance, the accident rate is can taken to reduce by measures in time, so the high accuracy of transformer fault diagnosis is required. In this paper, the BP neural network based on the optimized Apriori algorithm which is used to diagnose the transformer fault. It is found that the Apriori algorithm reveals association rules by mining the high frequency term of feature data. The data is directly analyzed and infered to achieve the purpose of simplifying data association by rough set algorithm. Apriori algorithm combines the rough set is used to accurately mine the confidence of association rules, which is used as the weight of BP neural network link, it is simplifying the complexity of data training. Through the simulation experiment, this new method is compared with the traditional BP neural network method, it has the advantages of high accuracy and fast speed of fault diagnosis, and has certain practical value.
