基于多维度信息融合的实用型变压器故障诊断专家系统

针对由于变压器结构复杂而导致其故障诊断的快速准确判断越来越依赖于大量信息的融合处理的情况,建立了基于多维度信息融合的实用型电力变压器故障诊断专家系统。首先分析多维度信息融合模型结构,给出基于因子分析计算各维度信息融合权重的方法,再构建基于多维度信息融合的专家系统,分析该专家系统的诊断流程,对多维度信息的识别、选择和判断进行了研究,最后结合110 k V变压器案例进行验证。结果表明,该专家系统逻辑简单、诊断精度高、诊断快速,可嵌入智能终端装置,为现场工作人员提供智能专家诊断。

Practical Expert System for Transformer Fault Diagnosis Based on Multi-Dimensional Information Fusion Technology

Due to the complex structure of the power transformer, the fault diagnosis is more and more dependent on the fusion of a large amount of information. Therefore, a practical expert system for power transformer fault diagnosis based on multi-dimensional information fusion technology is proposed in this paper. First, the structure of the multi-dimensional information fusion model is analyzed, and then the method of factor analysis is proposed to calculate the information fusion weights. Based on the fusion technology, the practical expert system for transformer fault diagnosis is built, which is finally verified by an example of 110 kV main transformer. Moreover, the recognition, selection and excavation of the multidimensional data are analyzed. With the advantage of simple logic, high reliability, and fast diagnosis, the proposed expert system can be embedded in intelligent terminals to provide intelligent expert diagnosis for the staff on-site.