Research on SCARA Robot Fault Diagnosis Based on Hilbert-Huang Transform and Decision Tree

Abstract

Aiming at the current situation that industrial equipment failures are difficult to detect and diagnose with low efficiency, this paper takes Selective Compliance Assembly Robot Arm (SCARA) robots as the research object and proposes a method for extracting SCARA robot features based on Hilbert-Huang Transform (HHT). First, the original vibration signal is separated by the empirical mode decomposition (EMD) algorithm, and the intrinsic mode function (IMF) is obtained. Then the envelope of IMF is obtained through Hilbert transform and the spectrum energy of each envelope is calculated. Finally, the representative envelope spectrum energy is selected and combined into the feature vector of the signal, and the decision tree (DT) is used for classification prediction. The conclusion shows that the method proposed in this paper can accurately and effectively identify the state of SCARA robots and can be better applied to fault diagnosis.