A New Time Series Data Imaging Scheme for Mechanical Fault Diagnosis

Fault diagnosis based on vibration signals is widely used in various industrial production processes to prevent catastrophic accidents and ensure timely repairs. However, traditional fault diagnosis methods provide limited accuracy due to their inability to visually represent fault characteristics and heavy reliance on expert involvement. In this study, we propose a time series image generation scheme that incorporates a convolutional neural network (CNN) to perform data-driven analysis and open-set classification on fault data to represent faults intuitively and diagnose them more accurately. In this study, based on the basic G image, we proposed two series of extended coding methods, gray-transform (G-TF) and transform-gray (TF-G) to convert the 1-D time series signal into a grayscale image from different perspectives for figurative expression, so as to adapt to different fault diagnosis scenarios. Then, a CNN is designed to maximize recognition accuracy based on faster calculation. To demonstrate the effectiveness of the proposed method, three types of faults are tested in this study, i.e., faults with motor bearings, self-priming centrifugal pumps, and hydraulic pumps. The experimental results demonstrate that, when the most suitable method is employed, the proposed approach achieves better recognition performance in diagnosing these three types of faults. The proposed method provides a new solution for future fault diagnosis tasks.