电力变压器多源信息融合故障诊断技术研究

Research on Multi-source Information Fusion Fault Diagnosis Technology for Power Transformers

文章深入研究传统电力变压器故障诊断数据来源单一、诊断结果准确性不足的问题,提出一种创新的故障诊断方法。通过引入多源信息融合技术,提高电力变压器故障诊断的准确性和可靠性。在本研究中,采用以深度信念网络(Deep Belief Network,DBN)为基础,与DS证据理论相结合的方法。首先,利用DBN特征提取和分类电力变压器的多个传感器数据。其次,通过DS证据理论融合分类结果,从而得到最终的故障诊断结果。最后,与传统方法相比,基于多源信息融合的电力变压器故障诊断方法大幅提升了故障诊断准确率,并且在多种类型的故障诊断中表现出良好的效果。

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.