Real-Time Diagnosis of Abrupt and Incipient Faults in IMU Using a Lightweight CNN-Transformer Hybrid Model
Jia Song, Zhipeng Chen, Wenling Li
Abstract
The fault diagnosis is crucial for improving the reliability and safety of industrial sensors. Diagnosing faults in inertial measurement units (IMUs) is particularly challenging due to the complex nature of abrupt and incipient faults, which require the accurate and rapid diagnosis. This article presents a hybrid model that combines convolutional neural networks (CNNs) and Transformer encoder architectures. The CNN component effectively extracts local fault features, while the Transformer encoder captures long-range dependencies in time-series data, enabling the precise and rapid IMU fault diagnosis. To meet the autonomous and real-time operational demands of IMU fault diagnosis, the knowledge distillation is applied to develop a lightweight version of the model. This optimization facilitates efficient deployment on resource-limited hardware, maintaining the original model’s accuracy and rapid processing speed. The effectiveness of the proposed approach is validated through comprehensive comparisons with other models, demonstrating the superior diagnostic accuracy, low fault diagnosis delay, and suitability for real-time applications.