Abstract
Conventional permanent magnet synchronous motor (PMSM) fault diagnosis methods rely on one-dimensional (1-D) time-series signals. These approaches face challenges such as complex signal processing, difficulty in extracting fault features, and limited noise immunity. To address these issues, a novel approach method is proposed. Its core process includes wavelet packet decomposition (WPD), distributed recurrence plot (DRP) generation, and image transformation. This approach enables feature representation of the original signal across multiple frequency bands, and the shortcomings of traditional recurrence plots in terms of feature redundancy and long-sequence representation are overcome. On this basis, a lightweight multi-frequency-scale fault diagnosis model is developed, consisting of a multi-frequency-scale convolutional neural network (CNN), a convolutional block attention module (CBAM), and a global average pooling (GAP) layer. Experimental results demonstrate that the proposed method achieves high diagnostic accuracy and strong noise immunity. Under identical hardware and dataset conditions, the inference time of the proposed method is only 12.35% as long as that of traditional recurrence plot-based CNN and 50.03% as long as that of asymmetric recurrence plot-based CNN.