SSGC
SSGC: Synergistic Similarity Graph Construction for Steel Plate Fault Diagnosis with Graph Attention Networks
Fault diagnosis in industrial production is vital as emerging technologies require innovative methods to identify subtle fault distinctions. Traditional machine learning approaches for steel plate fault classification inadequately exploit sample relationships, limiting accurate diagnosis. Here, we propose to use graph construction methods in conjunction with Graph Attention Networks (GAT) for steel plate fault classification. We introduce four techniques: k-Nearest Neighbors (k-NN), threshold-based cosine similarity, threshold-based Mahalanobis distance, and minimum spanning tree (MST), generating adjacency matrices representing sample connections. Additionally, we propose a novel graph construction algorithm, Synergistic Similarity Graph Construction (SSGC), to fuse these adjacency matrices, leveraging the strengths of each technique. We evaluate our techniques on the UCI Steel Plates Faults dataset, comparing them with traditional machine learning models. Our results demonstrate that the combination of GAT and SSGC leads to superior performance over the best traditional machine learning models, improving the accuracy, precision, recall, and Macro-F1 scores by approximately 4.8%, 4.6%, 4.6%, and 4.7%, respectively. In conclusion, we present a novel approach for steel plate fault classification by leveraging GAT and effective graph construction techniques. Our method expands Graph Neural Networks (GNNs) applicability to tabular datasets without explicit connections, enhancing fault classification performance in industrial production. This work paves the way for introducing GNNs into fault diagnosis across diverse domains. Our code and data are available at https://github.com/AnguoCYF/SSGC
If you wish to use this code, please kindly cite our work. The citation format for the paper will be provided soon. Thank you for your support!
Y. Chen, Z. Chen and H. U. Amin, "Synergistic Similarity Graph Construction (SSGC) for Steel Plate Fault Diagnosis with Graph Attention Networks," 2023 IEEE 6th International Conference on Knowledge Innovation and Invention (ICKII), Sapporo, Japan, 2023, pp. 655-660, doi: 10.1109/ICKII58656.2023.10332743. https://ieeexplore.ieee.org/document/10332743