14 March 2022 in IEEE Sensors Journal
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.
1 September 2021 in IEEE Transactions on Instrumentation and Measurement
Fault diagnosis has a direct impact on the economic benefits of the modern rotating machinery industry. The input of current fault diagnosis methods is mostly the original vibration signal or the time-frequency graph (TFG) obtained by short-time Fourier transform. Both of these inputs use many data points, which reduce the real-time performance of the fault diagnosis model. Therefore, a novel fault diagnosis model is proposed to achieve high accuracy when the input data points are few. First, the two inputs of the model are the frequency-domain signal (FDS) and TFG obtained by processing the original signal with fast Fourier transform and continuous wavelet transform. Then, convolution (Conv) and deformable atrous Conv are used to extract the FDS and TFG features, respectively. These features are then fused by squeezing-and-excitation aggregation. Finally, the outputs of three different dimensions are obtained. Experimental results show that the proposed feature extraction and fusion module can increase the generality of the diagnostic model, and the proposed model has a better effect on three outputs compared to state-of-the-art methods.