Power grid fault diagnosis method based on multi-data fusion

Abstract

The invention discloses a power grid fault diagnosis method based on multi-data fusion. The method comprises steps: as for suspicious fault elements in an outage region, fault features are quantized from two angles of the electric quantity and the protective switch quantity respectively, according to electric quantity quantization indexes, features presented by the electric quantity before and after the fault are quantized according to Hilbert-Huang transform, and two indexes of an energy variation degree and an amplitude variation degree are defined, and according to protective switch quantity quantization indexes, a directed bipartite graph model for elements is built, and Bayesian suspected degree indexes are calculated and obtained; and a D-S evidence theory method is adopted to fuse elements, as evidences in a diagnosis frame, in the outage region to obtain an element fault degree, and the diagnosis function is realized. The fault diagnosis accuracy and the quickness can be improved.

Description

technical field [0001] The invention relates to the technical field of power network fault diagnosis, in particular to an online fault diagnosis method of a power network, in particular to a power network fault diagnosis method based on multi-data fusion. Background technique [0002] Fault diagnosis technology is to quickly and accurately identify the fault area and the nature of the fault by analyzing the alarm information indiscriminately received by the dispatching system after the fault occurs. Provide auxiliary decision-making to reduce the adverse impact on system operation caused by failures. As a hot issue in the power field, fault diagnosis technology has achieved many research results. However, with the interconnection of power grids, the structure and operation mechanism of the power grid are becoming more and more complicated, and the uncertainty of alarm information and protection action behavior, many fault diagnosis technologies are also Shows disadvantages ...

AI Technical Summary

Problems solved by technology

As a hot issue in the power field, fault diagnosis technology has achieved many research results. However, with the interconnection of power grids, the structure and operation mechanism of the power grid are becoming more and more complicated, and the uncertainty of alarm information and protection action behavior, many fault diagnosis technologies are also Demonstrated disadvantages, incompetent

[0003] After the system fails, the alarm information has uncertainty such as omission / false alarm, which brings difficulties to the application of the fault diagnosis system, and is also one of the main difficulties in the realization of the grid fault diagnosis system.

Images