Clean air switch equipment fault diagnosis method and system

By adopting the CNN-LSTM-Attention model for multimodal feature fusion and lightweight deployment in clean air switchgear, the problems of insufficient monitoring accuracy and poor adaptability in existing technologies are solved, and efficient fault diagnosis and real-time prediction are achieved.

CN120595097APending Publication Date: 2025-09-05XI AN JIAOTONG UNIV +2
View PDF 13 Cites 4 Cited by

Patent Information

Application Number
CN202510869586.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-26
Publication Date
2025-09-05

AI Technical Summary

Technical Problem

The existing technology in clean air switchgear insulation fault diagnosis has problems such as insufficient monitoring accuracy of a single sensor, weak modeling ability of traditional machine learning models for time series data and spatial correlation, and poor model adaptability due to feature drift.

Method used

The CNN-LSTM-Attention model is used for multimodal feature fusion, combining gas concentration signals, partial discharge signals, and environmental parameters. A bidirectional long short-term memory network is used to capture long-term temporal dependencies, a convolutional neural network is used to extract spatial correlations, and multi-head self-attention is used to focus on key fault features. Simultaneously, model pruning and quantization are performed to achieve lightweight deployment, and an incremental learning mechanism is introduced.

Benefits of technology

It improves the fault detection rate and the timeliness of diagnosis and prediction, solves the problem that traditional methods cannot capture the multi-dimensional characteristics of complex faults, realizes the real-time and adaptability of the model, and reduces maintenance costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120595097A_ABST
    Figure CN120595097A_ABST
Patent Text Reader

Abstract

The invention discloses a clean air switch equipment fault diagnosis method and system, and the method comprises the steps: firstly collecting a gas concentration signal, a partial discharge signal and environment parameters of clean air switch equipment, carrying out the preprocessing, feature extraction and feature fusion, and outputting a multi-modal feature vector; inputting the multi-modal feature vector into a pre-constructed CNN-LSTM-Attention model, and carrying out classification processing on the multi-modal feature vector to obtain a fault type and a fault severity degree of the clean air switch equipment; according to the pre-constructed CNN-LSTM-Attention model, a bidirectional long-short-term memory network is adopted to capture time sequence long-term dependence, a convolutional neural network is used to extract spatial correlation, and key fault features are focused through multi-head self-attention. According to the method, the technical problems that the monitoring precision of a single sensor is insufficient and the modeling capability of a traditional machine learning model on time series data and spatial correlation is weak are effectively solved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Insulating gas state detection system for GIS (gas insulated switchgear) equipment

    CN105911106A

  • NDIR gas sensor system and temperature and humidity compensation method thereof

    CN110006837A

  • CNN-LSTM fan fault prediction method and CNN-LSTM fan fault prediction system based on attention mechanism

    CN112633317A

  • High-dimensional anomaly detection preprocessing method based on mutual information and feature grouping strategy

    CN113419883A

  • Temperature and humidity compensation method and device for gas sensor

    CN114461621A

Cited By

  • Switch cabinet fault diagnosis method based on discharge gas O3 detection

    CN121027764A

  • Multi-agent-based gas insulated switchgear fault diagnosis method and system

    CN121144766A

  • Fault diagnosis method and system applied to impressed current cathodic protection system

    CN121350829A

  • A fault diagnosis method and system applied to impressed current cathodic protection system

    CN121350829B