Weld Quality Prediction Using Surface Topology and Process Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current weld quality analysis methods rely heavily on post-weld visual and volumetric inspections, which are subjective and time-consuming, and fail to effectively detect subsurface defects without extensive equipment and processes.
Innovation Solution
The system employs machine learning algorithms to analyze pre-weld and post-weld surface topology data and welding process parameters to identify weld characteristics, predict defects, and classify welds as conforming or non-conforming, potentially reducing or eliminating the need for post-weld inspections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If post-weld visual and volumetric inspections are used to detect weld discontinuities, then weld quality can be assessed, but the process becomes time-consuming and subjective
Solution Approach 1:
The system performs preliminary weld quality assessment during the welding process itself by continuously monitoring welding parameters (current, voltage, speed, gas flow) and comparing them against predefined quality criteria. This real-time monitoring enables early detection of potential defects without waiting for post-weld inspections, thereby reducing inspection time while maintaining reliability through immediate feedback and alert mechanisms.
2Difficulty of detecting and measuring
If traditional inspection methods are used to detect subsurface discontinuities, then defects can be identified, but extensive equipment and complex processes are required
Solution Approach 1:
The system uses welding parameters (current, voltage, speed, gas flow rate) as intermediary indicators to infer subsurface discontinuities. By monitoring these measurable parameters during welding and comparing them against established patterns and thresholds, the system can predict subsurface defects without requiring complex volumetric inspection equipment like ultrasonic or radiographic testing apparatus, thereby reducing device complexity while maintaining detection capability.
3Measurement precision
If visual inspection methods are used to identify weld discontinuities, then surface defects can be detected, but the process is subjective and lacks consistency
Solution Approach 1:
The system implements automated feedback mechanisms that continuously monitor welding parameters and provide real-time comparisons against predefined quality standards and historical data. This objective feedback system eliminates human subjectivity by using algorithmic analysis of current, voltage, speed, and gas flow parameters to consistently identify potential discontinuities, ensuring uniform application of quality criteria across all welds without relying on individual inspector judgment.
4Reliability
If comprehensive post-weld inspections are performed to ensure weld quality, then defect detection improves, but productivity decreases due to extended inspection time
Solution Approach 1:
The system enables continuous weld quality monitoring throughout the welding process without interrupting production flow. By performing real-time analysis of welding parameters and providing immediate feedback, the system maintains uninterrupted welding operations while ensuring quality control, thereby preserving productivity without sacrificing defect detection reliability through seamless integration of monitoring into the continuous welding process.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Systems and methods are provided herein useful to analyzing weld quality. In some embodiments, the systems and methods identify or predict weld characteristics such as surface discontinuities and/or subsurface discontinuities based on surface topology data and/or welding process parameters. The systems and methods described herein leverage machine learning algorithms to identify relationships between historic weld characteristics and historic pre-weld surface topology, historic post-weld surface topology, and/or historic welding process parameters. Thus, the systems and methods described herein may identify weld characteristics for a weld based on the relationships and the pre-weld surface topology, post-weld surface topology, and/or welding process parameters for the weld. Further, the systems and methods described herein may also identify weld as conforming or not conforming to one or more weld standards based on the relationships and the pre-weld surface topology, post-weld surface topology, and/or welding process parameters for the weld.