Vehicle Minor Fault Diagnosis Based on Multi-Residual Neural Networks and ER Rule

Micro fault diagnosis of vehicle powertrain systems can significantly bring safety and economic benefits in preventing major accidents and extending equipment lifespan. However, under variable operating conditions, effectively capturing and diagnosing fault-related weak current fluctuation or high-frequency noise features, presents substantial technical challenges. Regarding this issues, this paper proposes a fault diagnosis model based on multi-residual neural networks (multi-ResNets) and Evidential Reasoning Rule (ER Rule). While the multi-ResNets are employed to extract subtle fault features and diagnostic reasoning, the ER Rule dynamically estimate diagnostic condition and conduct fault diagnosis through a sub-model real time credibility assessment mechanism. The experimental results indicate that compared traditional machine learning algorithms, the proposed multi-ResNets-ER Rule based model achieves higher diagnostic accuracy and result reliability for minor faults under variable operating conditions.