A training method and a fault diagnosis method of a solid oxide fuel cell system multi-fault diagnosis model based on a graph neural network

By using a multi-fault diagnosis model based on graph neural networks, the importance between nodes is adaptively learned through multi-head graph attention layers and residual graph convolutional layers, and the correlation of multi-source data is explicitly expressed. This solves the feature mixing problem caused by multi-fault coupling in solid oxide fuel cell systems and achieves high-precision multi-fault decoupling diagnosis.

CN121637213BActive Publication Date: 2026-06-26HUAZHONG UNIV OF SCI & TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUAZHONG UNIV OF SCI & TECH
Filing Date
2025-11-04
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies are unable to effectively address the issues of feature mixing and low diagnostic accuracy caused by multiple fault coupling in solid oxide fuel cell systems, especially under high temperature and high airtight conditions, where fault characteristics are difficult to observe directly and traditional methods fail to fully explore the intrinsic correlation between multi-source data.

Method used

A multi-fault diagnosis model based on graph neural networks is adopted. By constructing a multi-head graph attention layer, a residual graph convolutional layer and a global pooling classification layer, the importance weights between nodes are adaptively learned to capture the spatiotemporal dependencies of multi-source time series data. The graph structure model is used to explicitly express the correlation between data. The binary cross-entropy loss function and attention mechanism are used to enhance the diagnostic capability.

Benefits of technology

This method enables decoupled diagnosis of multiple faults in solid oxide fuel cell systems, improving diagnostic accuracy and generalization ability. It can effectively distinguish concurrent fault characteristics and solve the problem of feature mixing in traditional methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121637213B_ABST
    Figure CN121637213B_ABST
Patent Text Reader

Abstract

The application discloses a kind of based on graph neural network's solid oxide fuel cell system multi-fault diagnosis model training method and fault diagnosis method, obtains the multi-source time series operation data of SOFC system under different operating conditions, obtains data set;Operating condition includes normal state, single fault state and compound fault state, and data set is labeled with operating condition label;Sample data in data set is preprocessed, node feature matrix and corresponding adjacency matrix are generated according to each sample data, and graph structure data set is formed;Graph neural network model including multi-head graph attention layer, residual graph convolution layer and global pooling classification layer in turn is constructed, then the graph structure data in graph structure data set is as input, corresponding operating condition is as output, graph neural network model is trained, i.e. the multi-fault diagnosis model trained is obtained, and can be used for the multi-fault decoupling diagnosis of SOFC system, improves diagnostic accuracy and practicality.
Need to check novelty before this filing date? Find Prior Art