A Channel Attention-Based Method for Micro-Motor Armature Surface Defect Detection

With the development of modernization, micro-motors are widely used in industry. The quality of its core armature components directly affects the performance of micro-motors. Detection methods rely on manual visual inspection, with the problems of fluctuating accuracy and low detection efficiency. A high-precision, high-efficiency detection system is proposed to address these issues. Deep learning techniques are applied to handle complex patterns. The detection model consists of feature-extraction module, feature-fusion module and classifier module. The feature-fusion module improves the ability to detect artifacts, which are easily misclassified. Multi-dimensional feature fusion is performed using the BiFPN structure, and an attention mechanism is adopted for feature screening. In this module, we propose a novel channel attention mechanism to be more suitable for the feature-fusion module than other existing models. Experimental results indicate that the proposed method has the highest accuracy for micro-motor armature defect detection and significantly improves the accuracy of detection for confusable artifacts. The proposed inspection system can perfectly achieve the detection of surface defects of micro-motor armatures.