Attention-Based Multiscale Temporal Fusion Network for Uncertain-Mode Fault Diagnosis in Multimode Processes
This addresses fault diagnosis for industrial systems with multiple operating modes, but it is incremental as it builds on existing methods like attention and normalization techniques.
The paper tackled fault diagnosis in multimode industrial processes by proposing an attention-based multiscale temporal fusion network, which achieved superior diagnostic performance on datasets like the Tennessee Eastman process while maintaining a small model size.
Fault diagnosis in multimode processes plays a critical role in ensuring the safe operation of industrial systems across multiple modes. It faces a great challenge yet to be addressed - that is, the significant distributional differences among monitoring data from multiple modes make it difficult for the models to extract shared feature representations related to system health conditions. In response to this problem, this paper introduces a novel method called attention-based multiscale temporal fusion network. The multiscale depthwise convolution and gated recurrent unit are employed to extract multiscale contextual local features and long-short-term features. Instance normalization is applied to suppress mode-specific information. Furthermore, a temporal attention mechanism is designed to focus on critical time points with higher cross-mode shared information, thereby enhancing the accuracy of fault diagnosis. The proposed model is applied to Tennessee Eastman process dataset and three-phase flow facility dataset. The experiments demonstrate that the proposed model achieves superior diagnostic performance and maintains a small model size. The source code will be available on GitHub at https://github.com/GuangqiangLi/AMTFNet.