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

Robot failure prediction device and system, and robot failure prediction method

A fault prediction and robotics technology, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problems of poor real-time accuracy, large processing capacity, and high computing costs

Active Publication Date: 2021-06-25
HITACHI LTD
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in the method disclosed in Patent Document 1, it is necessary to set a camera for each robot to acquire images of the robot during operation, and to perform analysis operations on each acquired video, etc.
Therefore, there are problems such as large processing capacity, high computing cost, and poor real-time performance and accuracy.

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 failure prediction device and system, and robot failure prediction method
  • Robot failure prediction device and system, and robot failure prediction method
  • Robot failure prediction device and system, and robot failure prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0039] First, the robot failure prediction system of the present invention will be described.

[0040] figure 1 It is a block diagram showing the structure of the robot failure prediction system of the present invention. Such as figure 1 As shown, the robot failure prediction system includes a robot 1, a control cabinet 10, a current measuring mechanism 20, an analog-to-digital converter 50, a teaching pendant TP, a robot failure prediction device 30, and a failure prediction result output device (not shown). The teach pendant TP records the teaching program used to make the robot perform prescribed actions; the control cabinet 10 controls the robot 1 to complete each prescribed action based on the teaching program; the current measuring mechanism 20 measures the current information when the robot moves; the analog-to-digital conversion The device 50 converts the analog signal information of the total current measured by the current measuring mechanism 20 into digital signal...

Embodiment approach 2

[0079] Hereinafter, a robot failure prediction device and a robot failure prediction method according to a second embodiment of the present invention will be described.

[0080] In this embodiment, the structure of the robot failure prediction device is the same as that in the first embodiment. The difference is that the failure prediction device in this embodiment performs failure prediction based on the time rationality of the robot's actions. The following description will focus on the above differences, and descriptions that are the same as or similar to Embodiment 1 will be omitted.

[0081] Figure 10 A flowchart showing failure prediction performed by the prediction unit according to the second embodiment. Such as Figure 10As shown in , in step S811 , the prediction unit 39 associates the individual current, individual time, rotation angle of each joint axis, and speed parameter according to the action progress. In step S812, the prediction unit 39 obtains the time...

Embodiment approach

[0084] In the above-mentioned first embodiment, the predicting part performs fault analysis based on the comparison between the individual current and the historical current value under the normal operation of the robot, or the comparison between the individual current and the individual current under the normal operation of the robot based on the teaching program. predict. In the second embodiment, the prediction unit performs failure prediction based on individual time and speed parameters based on the teaching program. But not limited thereto, fault prediction can also be performed based on individual current and speed parameters based on the teaching program, based on the rationality of the current, or based on the individual time and the rotation angle of each joint axis based on the teaching program, based on the rationality of time for fault prediction.

[0085] In addition, in the above-mentioned embodiment, the robot failure prediction device may also include a failu...

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 robot failure prediction device and system, and a robot failure prediction method. The robot failure prediction device comprises a current data collection part, a mode recognition part, an individual current extraction part, an individual time extraction part, a teaching program acquisition part, a motion control part, an axis determination part, a speed parameter extraction part and a prediction part. The current data collection part collects total current for driving a robot at certain time intervals. The mode recognition part performs pattern recognition on the collected total current. The individual current extraction part extracts individual current from the total current after mode recognition. The individual time extraction part extracts individual time from the total current after mode recognition. The teaching program acquisition part acquires a teaching program for making the robot perform a predetermined action. The motion control part obtains action information of the robot on the basis of the teaching program. The axis determination part acquires a rotation angle of each joint axis of the robot on the basis of the action information. The speed parameter extraction part acquires a speed parameter of the robot on the basis of the action information. The prediction part performs failure prediction and failure location of the robot on the basis of the individual current, the individual time, the rotation angle of each joint axis, and the speed parameter.

Description

technical field [0001] The invention relates to a robot failure prediction device and system, and a robot failure prediction method. Background technique [0002] With the continuous development of science and technology, a large number of industrial robots are introduced at the production site, which can meet the needs of rapid / mass processing and production, not only saving labor costs, but also greatly improving production efficiency. However, existing robots also fail during work, especially the robots used on the production line. When a robot stops due to a fault, other robots in series with it on the production line may also be forced to stop. , resulting in the stop of the entire production line, resulting in huge losses. Therefore, for the robot system, in order to detect the possible failure of the robot early and report the failure in time, it is a very important technology to diagnose and predict the failure of the robot. [0003] As a fault diagnosis and predic...

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): B25J19/00B25J9/22
CPCB25J19/0095B25J9/0081
Inventor 姚开鹏邹立明杨旭
Owner HITACHI LTD