Research on Multi-source Information Fusion Fault Diagnosis Technology for Power Transformers
This paper studies the problem of single source of fault diagnosis data of traditional power transformer,and aims to propose an innovative fault diagnosis method.By introducing multi-source information fusion technology,improve the accuracy and reliability of power transformer fault diagnosis.In this study,the method based on Deep Belief Network(DBN)is combined with DS evidence theory.First,DBN features are used to extract and classify multiple sensor data of power transformers.Secondly,the classification results are integrated through DS evidence theory to obtain the final fault diagnosis results.Finally,compared with the traditional method,the power transformer fault diagnosis method based on multi-source information fusion greatly improves the fault diagnosis accuracy,and shows good results in various types of fault diagnosis.
power transformermulti source information fusionfault diagnosis technology
NETL
NSTL
万方数据
