Real-Time Fault Diagnosis: A Transformer-Based Approach

Fault diagnosis in process control and monitoring is crucial for ensuring safety and maintaining operational efficiency. Faults represent deviations from the normal trajectory of the system, indicating potential issues that require timely intervention. However, current fault diagnosis methods often encounter delays or low accuracy with many hyper parameters to tune, limiting their applicability and generalizability in real-world industrial settings, particularly in high-frequency data environments. To address these challenges, this paper proposes an online fault diagnosis strategy based on a modified transformer architecture, which is specifically tailored for time-series classification. By considering fault diagnosis as a classification problem, the proposed model provides real-time fault diagnosis in a highly parallelizable manner without introducing any systematic delays, which is crucial for maintaining seamless operation. This approach also mitigates real-world challenges such as missing data, asynchronous data flow, and delays. Leveraging deep-learning techniques, the proposed approach harnesses the in-herent parallelizability of attention-based models to enable rapid fault diagnosis without compromising accuracy. Furthermore, to increase the classification accuracy, a two-step training procedure is employed. To demonstrate the effectiveness of the proposed method, it is compared with other well-established fault diagnosis methods using the extended Tennessee Eastman Process Dataset. This research highlights the power of deep learning in enhancing fault diagnosis capabilities, paving the way for safer and more efficient industrial operations.