Xiaoyan Wu

With the increase of service time, the rotation period of rotating machinery may become irregular, and the Ensemble Empirical Mode Decomposition (EEMD)can effectively reflect its periodic state. In order to accurately evaluate the working state of the Rotate Vector (RV) reducer, the torque transfer formula of the RV reducer is first derived to theoretically prove periodicity of torque transfer in normal operation. Then, EEMD is able to effectively reflect the characteristics of data periodicity. A fault diagnosis model based on EEMD-MPA-KELM was proposed, and a bearing experimental dataset from Xi‘an Jiaotong University was used to verify the performance of the model. In view of the characteristics of the industrial robot RV reducer fault was not obvious and the sample data is few, spectrum diagram was used to diagnose the fault from the RV reducer measured data. The EEMD decomposition was performed on the data measured by the RV reducer test platform to obtain several Intrinsic Mode Functions (IMF). After the overall average checking and optimization of each IMF, several groups of eigenvalues were obtained. The eigenvalues were input into the Kernel Extreme Learning Machine (KELM) optimized by the Marine Predators Algorithm (MPA), and the fault diagnosis model was established. Finally, compared with other models, the prediction results showed that the proposed model can judge the working state of RV reducer more effectively.