Industrial robot consistency detection system and method based on DTW distance

Abstract

The invention provides an industrial robot consistency detection method based on a DTW distance. The industrial robot consistency detection method comprises the following steps of: obtaining feedback currents of N robots during normal operation, and extracting single periodic sequence data Ti of the feedback currents of the N robots during normal operation respectively; obtaining a reference sequence T0 according to the single periodic sequence data Ti of the feedback currents of the N robots during normal operation; obtaining a to-be-detected sequence corresponding to the feedback currents of the robots during real-time operation; respectively calculating the similarity between the single periodic sequence data Ti of the feedback currents of the N robots during normal operation through a DTW algorithm to obtain a similarity range Ss; calculating the similarity St between the to-be-detected sequence and the reference sequence through the DTW algorithm; and detecting the consistency of the industrial robots according to the similarity St and the similarity range Ss. According to the industrial robot consistency detection method, the accuracy of consistency detection of the industrial robots can be improved. Correspondingly, the invention further provides an industrial robot consistency detection system based on the DTW distance.

Description

technical field [0001] The invention relates to the technical field of robots, in particular to a DTW distance-based consistency detection system and method for industrial robots. Background technique [0002] Time series are a common representation of data in most disciplines. A common task for time series processing is to compare the similarity of two series. Industrial robots generate a large amount of time series data every day. By comparing the similarity between the time series data to be detected and the benchmark time series data, the consistency of industrial robots can be detected and the health status of industrial robots can be judged. [0003] In the prior art, the Euclidean distance between the time series data to be detected and the benchmark time series data is generally calculated to judge the similarity between the two, and then detect the consistency of the industrial robot. However, the lengths of the time series data to be detected and the benchmark ti...

AI Technical Summary

Problems solved by technology

[0004] Based on this, in order to solve the problem that the prior art judges the similarity between the time series data to be detected and the reference time series data by calculating the Euclidean distance, which easily causes errors in the consistency detection of industrial robots, the present invention provides a method based on DTW distance The industrial robot consistency detection system and method, its specific technical scheme is as follows:

Images