Fault Diagnosis of Harmonic Drives Based on an SDP-ConvNeXt Joint Methodology

Abstract

Harmonic Drives (HDs) are key components of industrial robots, and damages or failures of the HDs can lead to robot paralysis or even cause operational accidents. To prevent this from happening, it is of great importance to design proper algorithms for fault diagnosis of the HDs, especially in real HD manufacturing lines. In this paper, a fault diagnosis method was proposed to convert multiple vibration signals into symmetrized dot pattern (SDP) images, and to use a ConvNeXt model with Transformer training procedures to classify fault features of the HDs under various fault states and working conditions. The method was experimentally validated on three datasets with a diagnostic accuracy of up to 98.5% and 95.3% under constant and variable conditions, respectively, both higher over those using either state-of-the-art convolutional neural networks or Transformers. This was the first time where the SDP and the ConvNeXt were unitedly used to give superior visibility, interpretability, accuracy and efficiency for HD fault diagnosis, indicating good feasibility of using the ConvNeXt as a backbone for this task.