Multi-feature fusion single-phase earth fault type identification method based on deep learning

Abstract

The invention discloses a multi-feature fusion single-phase earth fault type identification method based on deep learning. The method mainly comprises the following steps: 1) obtaining fault recording data collected by a field fault recording device; 2) carrying out fault recording data preprocessing, and carrying out HHT-based time-frequency decomposition on the preprocessed fault recording data to obtain corresponding time-frequency information features; 3) constructing the time-frequency information characteristics of the fault recording data obtained in the step 2) into a primary data set; 4) establishing and training a basic learner Resnet18, and extracting complex nonlinear features in the data set; 5) establishing and training a basic learner LSTM, and extracting time sequence correlation features in the data set; and (6) splicing and fusing the complex nonlinear features and the time sequence correlation features learned and extracted in the steps (4) and (5), constructing a secondary data set, and identifying a specific single-phase earth fault type in combination with a decision tree model. The method has the advantages of good accuracy, robust performance and good universality. The method is suitable for identification of various single-phase earth fault types including intermittent arc light earth faults and high-resistance earth faults, and identification results can provide reliable basis for subsequent formulation of targeted fault processing measures.

Description

technical field [0001] The invention relates to the field of intelligent distribution network, in particular to a multi-feature fusion single-phase grounding fault type identification method based on deep learning. [0002] technical background [0003] Safety, reliability, high quality and economy are the basic requirements for the operation of the power system. However, single-phase-to-ground faults occur frequently in my country's medium and low voltage distribution network systems, which have a certain impact on the reliable operation of the power system. Since the fault is weak when a single-phase-to-ground fault occurs, the feature discrimination between different fault types is low, and it is difficult to accurately identify the fault type. [0004] The existing research results have achieved certain results in single-phase-to-ground fault detection, but most of them only select part of the characteristics of the distribution network, that is, the unique attributes of...

AI Technical Summary

Problems solved by technology

However, single-phase ground faults occur frequently in the medium and low voltage distribution network systems in my country, which has a certain impact on the reliable operation of the power system.

Since the fault is weak when a single-phase ground fault occurs, the characteristic discrimination between different fault types is low, and it is difficult to accurately identify the fault type

[0004] The existing research results have achieved certain results in single-phase ground fault detection, but most of them only select some characteristics of the distribution network, that is, the unique attributes of a certain type of fault for analysis, resulting in insufficient description of fault information. It can only be identified for a specific fault type, and the single-phase ground fault type is not comprehensively classified. The generality of the algorithm is not enough, which is not conducive to the dispatcher to formulate targeted fault handling measures

Images