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

Reinforcement Learning-Based Adaptive Adjustment Method for Dual Laser Path Defects

A technology of adaptive adjustment and reinforcement learning, applied in biological neural network models, manufacturing auxiliary devices, processing data acquisition/processing, etc., can solve problems such as the method of adaptive adjustment of dynamic path defects that has not been proposed

Active Publication Date: 2022-05-10
DALIAN UNIV OF TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] "Research and Implementation of Printing Path Planning Algorithm in Additive Manufacturing" uses the method of traveling salesman problem for static path planning, and does not propose a dynamic adaptive adjustment method for path defects

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
  • Reinforcement Learning-Based Adaptive Adjustment Method for Dual Laser Path Defects
  • Reinforcement Learning-Based Adaptive Adjustment Method for Dual Laser Path Defects
  • Reinforcement Learning-Based Adaptive Adjustment Method for Dual Laser Path Defects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific implementation manners of the present invention will be further described below in conjunction with the accompanying drawings and technical solutions.

[0030] The concrete implementation flowchart of the present invention is as figure 1 shown.

[0031] Step1: Algorithm application process

[0032] (1) First of all, during the printing process, the camera above the printer continuously collects the printed image and analyzes it. If a defect is found, the image of the frame where the defect occurs is transmitted.

[0033] (2) The program receives the image containing defects, analyzes the image, integrates the defective part and the unprinted part into a new graphic, uses the path defect completion algorithm to re-plan the path, and transfers the new path file to Return to the robot to continue printing.

[0034] (3) This process is repeated for each layer of printing to complete the final print.

[0035] Step2: path defect completion

[0036] (1) Set t...

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 present invention designs a dual laser path defect adaptive adjustment method based on reinforcement learning. Based on the reinforcement learning algorithm Policy Gradients algorithm, the printing process image is fed back to the program through the camera, and the defect and unprinted part are re-planned. Minimize print head lifts, turns, and empty jump paths. The invention uses ultrasonic micro-forging and online monitoring to realize online detection of defects, and re-plans the cooperative path for the remaining paths of the dual lasers according to the detected defect area and the original path, which can greatly improve the quality of printing and manufacturing, and improve the qualified rate of parts.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and additive manufacturing, and relates to an adaptive adjustment method for dual laser path defects based on reinforcement learning. Background technique [0002] With the development of the manufacturing industry and its intelligence, the combination of various fields of the manufacturing industry and computer intelligence technology has been better developed. Among them, the development prospect of the additive manufacturing industry is also broader. Applying additive manufacturing technology to some industries such as aerospace manufacturing, medical development, and dental manufacturing technology can effectively improve production efficiency and manufacturing accuracy. The process of additive manufacturing is to manufacture the model parts in a short time through the steps of modeling, slice layering, path planning and additive manufacturing printing accumulation of the designed model....

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): B29C64/393B33Y50/02G06N3/04
CPCB29C64/393G06N3/04B33Y50/02
Inventor 刘林升王祎范永刚崔紫微
Owner DALIAN 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