Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for predicting the overall performance of industrial robots based on feed-forward neural network

A feed-forward neural network and industrial robot technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as disturbance, time-consuming and labor-intensive, and useless work.

Active Publication Date: 2021-04-20
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, on the one hand, it will greatly increase the difficulty of executing the test experiment, which is time-consuming and labor-intensive; During the experimental testing process, a large amount of useless work is added, and most of the performance index data of core components are not of the same order of magnitude. The data analysis will be seriously disturbed, and the obvious influence law cannot be accurately analyzed in the end.

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
  • A method for predicting the overall performance of industrial robots based on feed-forward neural network
  • A method for predicting the overall performance of industrial robots based on feed-forward neural network
  • A method for predicting the overall performance of industrial robots based on feed-forward neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0054] Step 1: Construct the structure of the industrial robot machine performance impact model:

[0055] The input of the model architecture mainly considers the performance indicators of core components (servo motors, reducers) and the environmental impact parameters during operation, and the output mainly considers the motion performance of industrial robots. The specific implementation plan is as follows: figure 2 , theoretically analyze which performance of the core components (servo motor, reducer) and which environmental factors may affect the performance of the industrial robot during operation, and summarize it into the performance impact of the industrial robot from a broad perspective In the model framework, the input parameters determined in this embodiment are servo motor performance indicators (positive and negative speed difference rate, torque fluctuation coefficient, speed fluctuation coefficient, speed, torque, continuous stall torque, continuous stall curren...

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 belongs to the field of performance testing of industrial robots, and specifically discloses a method for estimating the performance of a complete industrial robot based on a feedforward neural network, which includes the following steps: S1 Constructing a model framework for the performance impact of an industrial robot and performing a performance test to Obtain the corresponding input parameters and output parameters, wherein the input parameters are the performance parameters of the core components of the industrial robot and the environmental impact parameters, and the output parameters are the performance parameters of the whole machine of the industrial robot; S2 normalizes the input parameters and output parameters, and Use the normalized data to train the neural network model to obtain the whole machine performance prediction network model; S3 substitutes the performance parameters and environmental impact parameters of the core components of the industrial robot to be tested into the whole machine performance prediction network model In order to obtain the performance parameters of the industrial robot. The invention can realize the prediction of the performance of the whole industrial robot, and has the advantages of wide applicability, accurate prediction and the like.

Description

technical field [0001] The invention belongs to the field of performance testing of industrial robots, and more particularly relates to a method for predicting the overall performance of industrial robots based on a feedforward neural network. Background technique [0002] In the field of industrial robot performance testing and evaluation technology, the research method of the influence law of the overall performance of industrial robots is usually based on the conventional control variable method to do a large number of test experiments, and obtain a certain amount of experimental test data for drawing analysis, so as to obtain the specified variables. Specifies the influence law of the performance index. For example, keep other variables constant, change the motor rigidity by adjusting the differential gain and proportional gain parameters of the industrial robot joints, and use the robot performance testing equipment to test the robot end accuracy performance, and obtain...

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 Patents(China)
IPC IPC(8): G06F30/27G06N3/08G06N3/04G01M99/00B25J19/00
CPCG06N3/084G01M99/005B25J19/0095G06N3/048
Inventor 叶伯生谢鹏张文彬陶婕妤帅思远谭朝饶阿龙
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products