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.
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
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.
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.
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.
Smart Images

Figure CN121637213B_ABST