Unlock instant, AI-driven research and patent intelligence for your innovation.

Vision-based industrial robot failure detection method and system

An industrial robot, fault detection technology, applied in manipulators, manufacturing tools, program control manipulators, etc., can solve the problems of wrong judgment, high cost, inconsistent communication interface and protocol, etc., to achieve low cost, low acquisition difficulty, anti-interference ability strong effect

Active Publication Date: 2020-08-14
武汉鸿海源科技发展有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1) It is necessary to use special equipment to collect industrial robot data, which has a high cost;
[0006] 2) The communication interfaces and protocols of different types of industrial robots are inconsistent, so the robot data collector is not universal;
[0007] 3) When the industrial robot is disturbed by the signal, the robot state data collected by the data collector may be inconsistent with the real state of the robot, resulting in wrong judgments

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vision-based industrial robot failure detection method and system
  • Vision-based industrial robot failure detection method and system
  • Vision-based industrial robot failure detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] A vision-based industrial robot fault detection method, comprising the following steps:

[0074] S1: Obtain the operation video under the normal operation of the industrial robot, and calculate the longest

[0075] A public hash subsequence, the longest public hash subsequence includes a plurality of hash values, the longest public hash subsequence is used to represent the periodic action pattern of the industrial robot, and S2 is executed;

[0076] S2: collect the working image of the industrial robot in real time, separate the industrial robot image in the working image, form a second working image, calculate the hash value of the second working image, record it as h1, and execute S3;

[0077] S3: Match the hash value h1 with the longest public hash subsequence in order of close approximation. If the match is successful, execute S2. If the match fails, an abnormal action is detected, and the industrial robot is controlled to stop in an emergency.

[0078] First, by c...

Embodiment 2

[0107] A vision-based fault detection system for industrial robots, comprising,

[0108] Such as Figure 7 As shown, the image acquisition device is used to collect the operation video of the industrial robot under normal work, and is also used to collect the working image of the industrial robot in real time; in this embodiment, the image acquisition device adopts a high-definition industrial camera.

[0109] The fault detection device is used to receive the operation video of the industrial robot under normal operation collected by the image acquisition device and calculate the longest public hash subsequence according to the operation video. The longest public hash subsequence contains multiple hash values, and the longest public hash subsequence The sequence is used to represent the periodic action pattern of the industrial robot; it is also used to separate the industrial robot image in the working image according to the real-time industrial robot working image collected ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a vision-based industrial robot failure detection method and system. The vision-based industrial robot failure detection method comprises the following steps: S1, an operation video of an industrial robot under normal work is obtained, the longest public Hash subsequence is calculated according to the operation video, the longest public Hash subsequence comprises a pluralityof Hash values and is used for representing the periodic action pattern of the industrial robot, and S2 is executed; S2, a working image of the industrial robot is collected in real time, the industrial robot is separated, a second operation image is formed, a Hash value of the second operation image is calculated and denoted as h1, and S3 is executed; and S3, the Hash value h1 and the longest public Hash subsequence are subjected to order extreme approximation match, if matching is successful, S2 is executed, if matching is failed, abnormal actions are detected, and the industrial robot is controlled to stop emergently. Failure detection is conducted on the industrial robot in the mode of collecting the operation images, the cost is low, the collecting difficulty is small, and the capacity of resisting disturbance is high.

Description

technical field [0001] The invention relates to the fields of intelligent manufacturing and robots, in particular to a vision-based industrial robot fault detection method and system. Background technique [0002] Industrial robot is a complex system composed of automation, machinery, embedded, hydraulic, electrical and other hardware and its control software. It can replace workers in some dangerous and complicated repetitive labor. Industrial robots have been widely used in the manufacturing industry due to their high precision and no need for rest. However, with the extensive application of industrial robots, incidents of industrial robots hurting people happen from time to time. The main causes of industrial robot safety accidents are human factors and the failure of the robot itself. Among them, the safety accidents caused by the robot's own misoperation accounted for more than half of the proportion. Human factors can be controlled through enhanced management and t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): B25J19/00B25J9/16
CPCB25J19/0095B25J9/1697B25J9/1661
Inventor 陈灯彭煜祺魏巍张彦铎吴云韬周华兵刘玮段功豪于宝成卢涛鞠剑平唐剑影徐文霞彭丽杨艺晨王逸文
Owner 武汉鸿海源科技发展有限公司