Fault diagnosis of rolling bearings using an Improved Multi-Scale Convolutional Neural Network with Feature Attention mechanism

Machine learning techniques have been successfully applied for the intelligent fault diagnosis of rolling bearings in recent years. This study has developed an Improved Multi-Scale Convolutional Neural Network integrated with a Feature Attention mechanism (IMS-FACNN) model to address poor performance traditional CNN-based models under unsteady and complex working environments. The proposed IMS-FACNN good extrapolation because novel IMS coarse grained procedure training interference introduced feature attention mechanism, which improves model’s generalization ability. better than existing methods all examined scenarios including diagnosing bearing real wind turbine. results show that reliability superiority faults bearings.