Weld Quality Prediction Using In-Process Sensor Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for determining weld quality involve destructive testing, which is costly and results in significant financial losses due to the destruction of parts, especially in high-volume production environments.
Innovation Solution
A system and method using machine learning and data analytics to predict weld quality by processing weld parameter data from various sensors during the welding process, allowing for real-time evaluation and potential elimination of destructive testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If destructive testing is used to determine weld quality, then measurement precision is improved, but loss of substance worsens due to destruction of tested parts
Solution Approach 1:
The patent replaces mechanical destructive testing systems with an optical/electrical sensing and machine learning system. Sensors capture weld parameter data (electrical, mechanical, thermal) during the welding process, and machine learning models analyze this data to predict weld quality without physically destroying the test pieces.
Solution Approach 2:
The patent introduces sensors and machine learning algorithms as intermediaries between the welding process and quality assessment. These intermediaries capture and analyze weld parameter data to predict weld quality, eliminating the need for direct destructive testing of the welded joints.
2Reliability
If destructive testing is performed on all welded pieces, then reliability is improved, but productivity worsens due to loss of production parts
Solution Approach 1:
The patent replaces physical destructive testing with a virtual assessment system using sensors and machine learning. This substitution allows real-time quality prediction without removing parts from production, maintaining both reliability and productivity.
Solution Approach 2:
The patent performs quality assessment during or immediately after the welding process by analyzing weld parameter data captured in real-time. This preliminary action eliminates the need for subsequent destructive testing of production parts, as quality is determined before parts leave the production line.
3Measurement precision
If sample rate is increased to improve weld quality assessment, then measurement precision is improved, but loss of time worsens due to more destructive tests
Solution Approach 1:
The patent enables continuous quality monitoring by capturing and analyzing weld parameter data for every weld in real-time during production. This continuous assessment replaces periodic destructive testing, providing precise quality evaluation for all parts without interrupting production flow or consuming additional time.
Data Source
AI summary
System and methods for using analytics and algorithms to predict weld quality are provided and include a computer having a processor and memory configured to receive weld parameter data generated during a welding process by a welder to join at least two parts with a weld, input the received weld parameter data to a data analytics model to generate at least one predicted weld quality parameter, compare the predicted weld quality parameter with a weld quality parameter threshold, and generate output indicating at least one of: the at least one predicted weld quality parameter and a result of the comparison between the at least one predicted weld quality parameter and the weld quality parameter threshold