Active power distribution network fault diagnosis method and system based on local abnormal factor detection

Abstract

The invention belongs to the field of power distribution network fault diagnosis, and particularly relates to an active power distribution network fault diagnosis method and an active power distribution network fault diagnosis system based on local abnormal factor detection. The diagnosis method comprises the following steps: acquiring operating electrical parameters of the active power distribution network in real time and preprocessing the operating electrical parameters to obtain one-dimensional fault characteristic quantity column matrixes based on time sequences; fusing the plurality of one-dimensional fault characteristic quantity column matrixes of different fault types in space to form a multi-fault characteristic quantity monitoring matrix of the same time sequence, and fusing themulti-dimensional fault characteristic quantity monitoring matrixes based on the plurality of time sequences to form a high-dimensional fault characteristic quantity monitoring matrix; carrying out dimension reduction processing on the high-dimensional fault characteristic quantity monitoring matrix, and solving the first two characteristic roots of the matrix after dimension reduction and the corresponding orthogonal characteristic vectors; and performing density-based local abnormal factor detection on a column matrix formed by the two orthogonal characteristic vectors to obtain an abnormalphysical node, and carrying out network topology of the power distribution network to obtain a fault section corresponding to the abnormal physical node, and thus the diagnosis fault result is obtained.

Description

technical field [0001] The invention belongs to the field of distribution network fault diagnosis, and in particular relates to a fault diagnosis method and system for an active distribution network based on detection of local abnormal factors. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] As the penetration rate of distributed power generation in distribution network becomes higher and higher, the reliability of distribution network operation becomes more and more important. If the active distribution network fails and the line fault cannot be diagnosed in time, it will not only affect the normal life of residents, but may also lead to the failure of the entire system, paralysis and huge losses of personnel and production. Therefore, it is of great practical significance to accurately diagnose faults in active distribution networks. ...

AI Technical Summary

Problems solved by technology

These methods have their advantages and disadvantages. Among them, the fault diagnosis method based on uncertainty knowledge can realize the fault diagnosis under the condition of missing information, but it is not suitable for large-scale active distribution network; the fault diagnosis based on waveform similarity directly uses all The time series of signals is extracted to measure the similarity of waveforms, but its principle needs to be further verified; the fault diagnosis method based on the logical relationship of system direction components transforms the fault diagnosis problem into a mathematical optimization and planning problem, but does not make full use of fault information

The inventors found that the existing fault diagnosis methods have certain limitations, such as difficulty in convergence, large amount of calculation, and failure to take into account the problem of distributed power when dealing with the influx of massive fault information, and are not suitable for large-scale applications. Active distribution network, which affects the accuracy of active distribution network fault diagnosis

Images