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

Fault prediction method and fault prediction device

A failure prediction and failure technology, applied in the direction of measuring devices, vibration testing, testing of mechanical components, etc., can solve time-consuming and labor-intensive problems

Pending Publication Date: 2021-10-01
SEIKO EPSON CORP
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in order to predict the failure of the reducer built in the joint of the robot, if the prediction method is used based on the iron powder concentration data of the grease of the reducer, it is necessary to disassemble the robot arm every time to confirm the reducer
Doing this kind of work is time-consuming and labor-intensive

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
  • Fault prediction method and fault prediction device
  • Fault prediction method and fault prediction device
  • Fault prediction method and fault prediction device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 approach

[0023] figure 1 It is a figure which shows the overall structure of the robot system of 1st Embodiment. figure 2 yes figure 1 A block diagram of the robotic system is shown. image 3 yes figure 1 The block diagram of the fault prediction device is shown. Figure 4 yes image 3 An example of the configuration example of the failure prediction model generation unit shown is a schematic diagram of a neural network. Figure 5 This is an example of a graph in which the vertical axis represents the operating speed of a specific motor when the robot arm is caused to perform a specific motion, and the horizontal axis represents time. Figure 6 This is an example of a graph in which the vertical axis represents the operating speed of a specific motor when the robot arm is caused to perform a specific motion, and the horizontal axis represents time. Figure 7 It is a graph in which the horizontal axis represents the frequency and the vertical axis represents the effective value o...

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

Provided are a fault prediction method and a fault prediction device, which can simply predict a fault of an element component having a mechanical arm. A fault prediction method is characterized in that a fault of an element component of a robot is predicted, the robot has a mechanical arm and a detection part, the robot arm is provided with the element component, and the detection part detects information related to vibration characteristics when the mechanical arm moves; in the fault prediction method, based on information related to the vibration characteristic, a fault prediction model used for predicting a fault of the element component is generated through machine learning, and the fault of the element component is predicted based on the generated estimated value of the fault prediction output by the generated fault prediction model.

Description

technical field [0001] The invention relates to a fault prediction method and a fault prediction device. Background technique [0002] In recent years, due to the increase in labor costs and the shortage of human resources in factories, various robots and peripheral equipment for the robots have accelerated the automation of manual operations. For example, the robot described in Patent Document 1 has a robot arm and a drive unit that drives the robot arm. In addition, the drive unit has a motor and a speed reducer. [0003] In this type of robot, elemental parts such as reducers sometimes break down as they are used. As means for predicting this failure, Patent Document 1 discloses a control system that uses machine learning to predict a failure of a reducer based on robot speed and iron powder concentration data of grease of the reducer. Thus, the control system is able to derive a recommended period for maintenance of the reducer. [0004] Patent Document 1: Japanese P...

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): B25J9/16
CPCB25J9/1674B25J9/1694G05B23/0283G05B2219/37351G05B2219/37435B25J9/161G05B2219/33296G05B2219/37388G05B2219/40549G05B2219/39529G05B2219/34048G05B2219/37209G05B2219/33025G01M13/028G05B23/024G01M7/02B25J9/163B25J13/003B25J13/085B25J13/088
Inventor 平出俊宪丁熠玫
Owner SEIKO EPSON CORP