Harmonic reducer in-situ fault diagnosis for industrial robots based on deep learning

The harmonic reducer is an essential kinetic transmission component in the industrial robots.It is easy to be fatigued and resulted in physical malfunction after a long period of operation.Therefore,an accurate in-situ fault diagnosis for the harmonic reducers in an industrial robot is especially important.This paper proposes a fault diagnosis method based on deep learning for the harmonic reducer of industrial robots via consecutive time-domain vibration signals.Considering the sampling signals from industrial robots are long,narrow,and channel-independent,this method combined a 1-dimensional convolutional neural network with matrix kernels(1-D MCNN)adaptive model.By adjusting the size of the convolution kernels,it can concentrate on the contextual feature extraction of consecutive time-domain data while retaining the ability to process the multi-channel fusion data.The proposed method is examined on a physical industrial robot platform,which has achieved a prediction accuracy of99%.Its performance is appeared to be superior in comparison to the traditional 2-dimensional CNN,deep sparse automatic encoding network(DSAE),multilayer perceptual network(MLP),and support vector machine(SVM).

A Comprehensive Evaluation Method for Kinematic Accuracy of Space Manipulator Based on Analytic Hierarchy Process

The kinematic accuracy of space manipulator determines whether the spacecraft performs normally or not. Problems pertaining to structural deformation have received increased attention in recent times. In the space manipulator systems, flexible arms and joints can induce drastic dynamic instabilities. In applications such as the space station, kinematic error due to structural deformation can jointly affect the performance characteristics. And it is crucial for accuracy control of space manipulator to establish a precision index. Here we analyze the dynamics characteristic of flexible space manipulator considering the hysteresis of harmonic reducer based on method of nonconstraint boundary modal. For the sake of describing the output accuracy, we integrate the method of analytic hierarchy process(AHP) to establish a comprehensive evaluation index. A numerical simulation is performed to analyze the nonlinear dynamic characteristics of space manipulator with harmonic reducer. With the analysis of accuracy assessment, the relation among the hysteresis angle, rigidity and output accuracy is revealed. Considering the elastic modulus of flexible space manipulator and the hysteresis angle of harmonic reducer, we conduct an evaluation of output characteristics of flexible space manipulator with the proposed comprehensive evaluation index. The accuracy evaluation of output characteristics based on the proposed comprehensive evaluation index is implemented in the initial stage of space manipulator's design, which can not only solve the problems existing in the design but also save cost savings for ground tests. The results can be used in designing and optimizing future space manipulators, which may provide valuable references for design and thermal control of the space manipulator.