Check patentability & draft patents in minutes with Patsnap Eureka AI!

Robot fault diagnosis method and device and apparatus

A technology of fault diagnosis and robotics, applied to instruments, computer components, calculations, etc., can solve the problems of real-time diagnosis and low accuracy, and achieve the effect of improving speed and accuracy

Pending Publication Date: 2019-08-09
GUANGDONG UNIV OF TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a robot fault diagnosis method, device, equipment and computer-readable storage medium to solve the problem of low real-time and low accuracy of diagnosis in traditional robot fault diagnosis schemes

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
  • Robot fault diagnosis method and device and apparatus
  • Robot fault diagnosis method and device and apparatus
  • Robot fault diagnosis method and device and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] The following is an introduction to Embodiment 1 of a robot fault diagnosis method provided by the present application, see figure 1 , embodiment one includes:

[0045] Step S101: collect the running data of the robot as the original feature set;

[0046] Specifically, the operation data of the above robot may include: command position, feedback position, command speed, feedback speed, command acceleration, feedback acceleration, command torque, feedback torque, error and so on. In a practical application scenario, the operating data of the robot can be collected at an appropriate frequency to obtain the above-mentioned original feature set, and specifically, the operating data in a single or multiple action execution cycles can be collected. When the above-mentioned robot lacks a corresponding collector or sensor, the above-mentioned data collection process can be realized by reading the feedback signal of the motor encoder of the robot. It is worth mentioning that, ...

Embodiment 2

[0056] Specifically, see figure 2 , embodiment two includes:

[0057] Step S201: collect the feedback signal of the motor encoder in the robot as the original feature set;

[0058] Specifically, the feedback signal of the motor encoder within a single action execution cycle can be collected, and the feedback signal includes any one or more of the following: command position signal, feedback position signal, command speed signal, feedback speed signal, command acceleration signal, Feedback acceleration signal, command torque signal, feedback torque signal, error signal. It is worth mentioning that during the collection process, the feedback signals of each axis of the robot can be collected separately to obtain the original feature set of each axis.

[0059] Specifically, in this embodiment, it can be assumed that the original feature set of condition C is:

[0060] {q m,c,j ,m=1,2,...,M c ;c=1,2,...,C;j=1,2,...,J} (1)

[0061] where q m,c,j is the jth eigenvalue of the...

Embodiment approach

[0088] As a specific implementation manner, the fault diagnosis module 304 includes:

[0089]A clustering unit: used to determine the outlier and the operation state corresponding to the outlier according to the clustering result;

[0090] Fault analysis unit: used to determine the fault type of the robot according to the outlier point and the running state.

[0091] The robot fault diagnosis device of this embodiment is used to implement the aforementioned robot fault diagnosis method, so the specific implementation in this device can be seen in the embodiment part of the robot fault diagnosis method above, for example, the original feature set determination module 301, sensitive feature The set determination module 302, the clustering module 303, and the fault diagnosis module 304 are respectively used to implement steps S101, S102, S103, and S104 in the above robot fault diagnosis method. Therefore, for the specific implementation manners thereof, reference may be made to ...

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 discloses a robot fault diagnosis method which is characterized by being able to collect the operation data of a robot as an original feature set; and screening a sensitive feature set from the original feature set, determining the feature weight of a sensitive feature in the sensitive feature set, clustering the sensitive feature set by using a clustering method based on an inversecovariance matrix according to the feature weight, and finally determining a fault diagnosis result of the robot according to a clustering result. Therefore, according to the method, the clustering isrealized by utilizing the clustering method based on the inverse covariance matrix, and according to the clustering method, the fault diagnosis can be carried out by discovering different performances of the robot in the same operation state, and the diagnosis reliability is improved. In addition, the method considers the difference of the sensitivity degrees of all sensitive features in fault diagnosis, the corresponding feature weights are distributed for all the sensitive weights, and the diagnosis accuracy is improved. The invention further provides a robot fault diagnosis device, an apparatus and a computer readable storage medium which have the effects corresponding to those of the above method.

Description

technical field [0001] The present application relates to the field of fault diagnosis, in particular to a robot fault diagnosis method, device, equipment and computer-readable storage medium. Background technique [0002] A robot is a semi-autonomous or fully autonomous machine that integrates modern manufacturing technology, new material technology and information control technology, and is a representative product of intelligent manufacturing. [0003] At this stage, the integration and complexity of robot systems are getting higher and higher. The operation process parameter setting and operation and maintenance management and control of most robot operations are only performed on-site by skilled workers, and it is no longer sufficient to rely solely on experience and process knowledge for operation and maintenance. Due to the current demand for complex systems, there are widespread problems such as blind scheduled inspections and scheduled repairs that lead to increased...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/2113G06F18/23
Inventor 潘屹豪肖红周玉彬符基高万意彬
Owner GUANGDONG UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com