Assembly Quality Scoring for High-Volume Weld Inspection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Welded assemblies of variable quality pose risks to downstream users, and high-volume production makes manual inspection difficult, especially in identifying imperfections and their causes.
Innovation Solution
An automated method and system that captures feature characteristics across multiple stages of the assembly process, including welding, using a computational engine to determine quality metrics and provide corrective recommendations, facilitating quick quality assessment and improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection is used to assess part quality, then inspection accuracy may be maintained, but productivity decreases and inspection becomes difficult in high-volume production
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated computational system that uses sensors, machine learning models, and data processing algorithms to assess part quality. This substitution enables high-volume inspection while maintaining or improving accuracy through consistent, data-driven evaluation of multiple quality parameters simultaneously.
Solution Approach 2:
The patent introduces a computational engine as an intermediary between the manufacturing process and quality assessment. This intermediary collects data from various sensors and process stages, processes it through machine learning models, and provides quality predictions, thereby enabling scalable inspection without direct human involvement in each inspection instance.
2Loss of information
If manual inspection is used to identify imperfections and their causes, then detailed analysis may be achieved, but the ability to spot less obvious imperfections decreases and inspection becomes difficult
Solution Approach 1:
The patent creates a multi-functional quality assessment system that simultaneously detects multiple types of imperfections (visual defects, dimensional variations, material properties) and analyzes their root causes by integrating data from various process stages. This universal approach enables comprehensive detection of both obvious and subtle imperfections that would be difficult for manual inspection to identify consistently.
Solution Approach 2:
The patent implements preliminary data collection and analysis during the manufacturing process itself, capturing quality-relevant information at multiple stages before final assembly. This preliminary action enables early detection of potential imperfections and their causes, allowing for preventive measures rather than reactive inspection after production.
3Reliability
If comprehensive quality assessment across multiple process stages is implemented, then quality confidence improves, but device complexity increases
Solution Approach 1:
The patent divides the quality assessment system into modular components: data collection modules at different process stages, a central computational engine for processing, and output modules for quality predictions. This segmentation allows comprehensive quality assessment while managing complexity through organized, independent modules that can be developed and maintained separately.
Solution Approach 2:
The patent implements feedback loops where quality predictions and analysis results are fed back to the manufacturing process in real-time. This feedback enables continuous improvement and validation of the quality assessment system, building quality confidence while the system learns and adapts, thereby managing complexity through iterative refinement rather than requiring perfect initial system design.
Data Source
AI summary
Systems and methods for part quality confidence are described. In some examples a part quality confidence system may receive inputs (e.g., via sensor measurements, operator input(s), etc.) related to one or more stages of a part assembly process. The inputs may be representative of certain feature characteristics of the part and/or one or more of the assembly stages. A computational engine of the system may determine one or more quality characteristics of the part based on the feature characteristics, and assign a quality metric to the part (and/or part assembly process) based on the quality characteristics. In some examples, a quality rating may be assigned to the part based on the quality metric, so as to provide an even simpler abstraction.