Fault locating method and system based on multilayer evaluation model

Abstract

The invention discloses a fault locating method based on a multilayer evaluation model. The method comprises the steps of: firstly determining a to-be-detected fault type and a fault symptom for precisely and effectively reflecting the running status of a transformer, and determining the weight of each fault type by using an association rule and a set-pair analysis; then, building a DBN (Deep Belief Network) model to perform feature extraction and classification to multidimensional data of the fault; and at last, comprehensively assessing the existing diagnosis result by using the D-S evidencetheory, so as to enhance the support strength of the common target, weaken the influence of the divergence target, and greatly reduce the uncertainty of the diagnosis result. The method provided by the invention mainly aims at the quantity of state of the transformer to monitor and diagnose in time; the state evaluation of the transformer is regarded as a multi-attribute decision-making problem;a double-layer fault locating model under two indexes is built; the accuracy of the weight is improved by using the set-pair analysis and the association rule; the fault is recognized by using the D-Sevidence theory and the deep belief network; and, the accuracy of the fault recognition is improved.

Description

technical field [0001] The invention belongs to the field of transformer fault diagnosis, and in particular relates to a fault location method and system based on a multi-layer evaluation model. Background technique [0002] The safe operation of power equipment is the basis for the safe and stable operation of the power grid, especially as the key hub equipment of the power system, the health level and operation status of large power transformers are directly related to the safety and stability of power grid operation. During the operation of power transformers, they are affected by high current, high voltage and external environment, etc., and the internal structure and wiring of the transformer are likely to fail. According to the development process, they are divided into sudden faults and latent faults; according to the nature of faults , There are mainly thermal faults, electrical faults and mechanical faults, and mechanical faults are generally manifested in the form ...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to propose a fault location method and system based on a multi-layer evaluation model in view of the above-mentioned shortcomings of the existing single diagnosis algorithm and the subjectivity defect that the combined model relies on expert experience to determine the weight

Images