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

A Method for Optimizing Robotic Welding Process Parameters Based on CBR and RBR

A technology for process parameter optimization and robotic welding, applied in welding equipment, welding accessories, manipulators, etc., can solve problems such as a large number of experiments, increase the time and cost of welding process formulation, and is not conducive to the intelligent decision-making of welding processes by welding robots.

Active Publication Date: 2020-04-17
SHANDONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since many rules in the rule base are derived from expert experience or welding practical manuals during the inference process, only an applicable range of welding process parameters can be inferred, and a large number of experiments are often required to further determine the optimal welding process parameter combination for a specific welding task.
However, selecting a reasonable combination of welding process parameters through welding experiments increases the time and cost of welding process formulation, which is not conducive to the intelligent decision-making of welding robots for welding processes.

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 Optimizing Robotic Welding Process Parameters Based on CBR and RBR
  • A Method for Optimizing Robotic Welding Process Parameters Based on CBR and RBR
  • A Method for Optimizing Robotic Welding Process Parameters Based on CBR and RBR

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] A method for optimizing robot welding process parameters based on CBR and RBR, including a welding process input module, a welding process expert system, and a welding process output module; figure 1 shown.

[0071] The welding process input module is used to convert the welding resource file and welding task file into an ontology language based on certain mapping rules, and then submit the welding information to the welding process expert system.

[0072]The welding process expert system is used to judge welding information and transfer corresponding welding processes; the welding process expert system includes a query engine, a reasoning engine, a knowledge base, and a welding process parameter optimization module, and the knowledge base includes a welding process case base and a welding process rule base, the query engine is used to judge whether the welding information belongs to a similar case in the welding process case base and imports the similar case into the ...

Embodiment 2

[0079] A kind of robot welding process parameter optimization method based on CBR and RBR as described in embodiment 1, its method is as described in embodiment 1, and concrete steps comprise:

[0080] (1) The welding process input module converts the welding resource file and welding task file into a reasonable format based on certain mapping rules and submits them to the welding process expert system;

[0081] (2) The query engine performs similar case query in the welding process case library. If a similar case is matched, the similar case is submitted to the welding process output module, and if there is no similar case, it enters the inference engine;

[0082] (3) The inference engine generates a suitable welding process after extracting the relevant rules in the welding process rule base; the welding speed, welding current, welding voltage, and shielding gas flow in the welding process obtained by the inference engine inference are suitable range values, which need Perfo...

Embodiment 3

[0087] A method for optimizing robot welding process parameters based on CBR and RBR as described in embodiment 1, its steps are as described in embodiment 2, further, in step (2), the query engine is composed of case-based reasoning (CBR ) mechanism, by analyzing and extracting the welding condition information in the welding task file, searching for similar cases in the welding process case library, and selecting the most matching welding process case according to the degree of similarity; specifically, when a new welding task appears, First, data preprocessing is performed on the welding condition information and represented by the problem feature vector X:

[0088] X=(x 1 ,x 2 ,x 3 ,x 4 ,x 5 ) (1)

[0089] where x 1 ,x 2 ,x 3 ,x 4 ,x 5 They are welding position, base metal material, base metal thickness, joint thickness and joint form;

[0090] The data preprocessing is to perform normalization processing on the base metal thickness and joint thickness whose dat...

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 relates to a robot welding technology parameter optimization method based on CBR and RBR, and belongs to the technical field of robot welding. The robot welding technology parameter optimization method involves a welding technology input module, a welding technology expert system and a welding technology output module. The welding technology input module receives welding tasks and welding resources and further submits the welding tasks and the welding resources to the welding technology expert system. A query engine in the welding technology expert system reuses historical welding cases, and it enters a reasoning engine for case-based reasoning on the basis of rules if no similar welding technology cases exist. A range value exists in the reasoned welding technology, particleswarm optimization in a welding technology parameter optimization module is adopted for multi-objective optimization of welding technology parameters, the optimal welding technology parameter combination is determined, an exact value is acquired for a welding robot to execute, and robot welding intelligence is realized. Production efficiency can be improved and the effect is remarkable.

Description

technical field [0001] The present invention relates to a robot welding process parameter optimization method based on CBR and RBR, in particular to a welding process reasoning based on case reasoning (Case-based Reasoning, CBR), rule-based reasoning (Rule-based Reasoning, RBR) and based on The combination of a neural network and a particle swarm optimization algorithm is suitable for a method for a welding robot to independently determine a welding process, and belongs to the field of robot welding technology. Background technique [0002] Traditional welding robots require experienced process designers to formulate welding processes for specific welding tasks before welding. The experience levels of designers are uneven, and due to the complexity of the welding process, many factors need to be considered during the welding process formulation process. Therefore, the process design efficiency is low. The welding expert system based on CBR and RBR can replace such a cumbers...

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): B23K9/02B23K9/095B23K9/32B25J9/16B25J11/00
Inventor 胡天亮李政誉张承瑞沈卫东
Owner SHANDONG UNIV
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