Rectifying circuit fault detection method based on one-dimensional double convolutional network self-attention mechanism

Through the dual-channel convolutional network model, the output sequence signal of the rectifier circuit is extracted and analyzed, which solves the problem of lack of effective fault detection methods in the existing technology, and accurately detects the faults of the rectifier circuit, and improves the stability of the power system.

CN119719988APending Publication Date: 2025-03-28GUILIN UNIV OF ELECTRONIC TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202411855276.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-17
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

There is a lack of effective rectifier circuit fault detection methods in the prior art, especially the detection of open circuit faults is difficult, which leads to unstable rectification circuit system and affects the normal operation of the load circuit.

Method used

The dual-channel convolutional network model is used to extract and analyze the output sequence signal samples of the circuit. Through the LSTM and ECA attention mechanism, a classifier is designed to integrate and classify the features to realize the detection of rectifier tube faults.

Benefits of technology

Effectively identify and detect fault samples in the rectifier circuit, improve the accuracy and efficiency of fault detection of rectifier circuits, help solve the problem of open circuit fault detection, and enhance the stability of the power system.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a rectification circuit fault detection method based on a one-dimensional double convolutional network self-attention mechanism. The method comprises the following steps: receiving time domain feature vector samples corresponding to a rated number of simulation sample data; a double convolutional network model is designed, and multi-directional feature extraction and classification are realized through LSTM and ECA attention feature mechanisms. The method and the system are suitable for rectification power supply fault detection tasks and have universality. On the basis, circuit fault detection is achieved, and the technical problem that in the prior art, a rectifying circuit fault detection method is lacked is solved.
Need to check novelty before this filing date? Find Prior Art