Assembly Unit Defect Prediction Using Inspection Image Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing optical inspection methods struggle to predict defects in assembly units efficiently, leading to potential defects in completed units and reduced yield on the assembly line.
Innovation Solution
A method that involves accessing inspection images of assembly units, detecting features, generating vectors in a multi-dimensional feature space, and grouping these vectors to predict defects and anomalies in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional optical inspection methods are used to detect defects in assembly units, then inspection coverage is achieved, but prediction capability for future defects is insufficient leading to reduced yield
Solution Approach 1:
The system performs preliminary defect prediction by analyzing inspection images and generating defect probability scores before assembly units complete production. This allows potential defects to be identified and addressed proactively, preventing defective units from progressing through the entire assembly line and improving overall yield while maintaining reliable defect detection
Solution Approach 2:
The system implements feedback mechanisms where defect predictions and inspection results are continuously fed back into the inspection model. This enables the system to learn from actual defect occurrences and improve its prediction accuracy over time, creating a closed-loop system that enhances both reliability and productivity by reducing false positives and negatives
2Measurement precision
If comprehensive feature detection is performed on all assembly units, then defect detection capability is improved, but processing time increases reducing real-time prediction capability
Solution Approach 1:
The system applies local quality by focusing detailed feature detection and analysis only on regions of interest or areas with higher defect probability. Rather than uniformly processing all features across all assembly units with equal depth, the system adapts its analysis intensity based on local characteristics, maintaining high detection accuracy where needed while reducing processing time in low-risk areas
Solution Approach 2:
The system performs partial feature detection by identifying and analyzing only the most critical features necessary for defect prediction. Instead of exhaustively detecting all possible features, it focuses on a subset of high-impact features that provide sufficient prediction accuracy, thereby reducing processing time while maintaining effective defect detection capability
Data Source
AI summary
One variation of a method for predicting manufacturing defects includes: accessing a first set of inspection images of a first set of assembly units recorded by an optical inspection station over a first period of time; generating a first set of vectors representing features extracted from the first set of inspection images; grouping neighboring vectors in a multi-dimensional feature space into a set of vector groups; accessing a second inspection image of a second assembly recorded by the optical inspection station at a second time succeeding the first period of time; detecting a second set of features in the second inspection image; generating a second vector representing the second set of features in the multi-dimensional feature space; and, in response to the second vector deviating from the set of vector groups by more than a threshold difference, flagging the second assembly unit.