Machine Vision Re-Measurement Using Stored Calibration Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional coordinate measuring machines are slow and fail to detect all deviations in objects, particularly in complex geometries like holes, and existing machine vision systems are limited in re-measuring or re-evaluating objects for quality control, especially in high-volume production where defective parts may not be identified until they cause safety issues.
Innovation Solution
A machine vision system that records and stores measurement images and calibration data, allowing for re-measurement of objects without physical re-probing, using a calibrated camera system with multiple cameras and a data system connected to a database for batch processing and self-calibration, enabling the detection of defects in previously measured objects and improving quality control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional coordinate measuring machines are used, then measurement accuracy is maintained, but measurement speed is slow and productivity is reduced
Solution Approach 1:
The patent replaces the mechanical probing system with an optical machine vision system using cameras and image processing. This substitution eliminates the slow mechanical contact measurement process while maintaining measurement accuracy through calibrated optical fields, thereby significantly improving measurement speed and productivity.
Solution Approach 2:
The patent creates digital copies of measurement data and calibration information that can be stored and reused. Instead of performing repeated physical measurements, the system uses stored image data and calibration records to enable rapid re-measurement and re-evaluation of objects, dramatically increasing productivity without sacrificing precision.
2Measurement precision
If mechanical probing is used to measure holes, then specific points are measured accurately, but deviations in defective sections are not detected
Solution Approach 1:
The patent implements a multi-functional measurement system that can perform both precise point measurements and comprehensive defect detection using the same optical infrastructure. The machine vision system captures complete object geometry and surface conditions, enabling simultaneous execution of dimensional measurement and quality inspection functions.
Solution Approach 2:
The patent transitions from one-dimensional point probing to multi-dimensional optical imaging. By capturing two-dimensional images from multiple cameras and processing them to reconstruct three-dimensional geometry, the system obtains comprehensive spatial information that reveals defects, irregularities, and deviations invisible to traditional point-based mechanical probing.
3Reliability
If machine vision systems are used for quality control, then detection capability is improved, but the ability to re-measure objects for further analysis is limited
Solution Approach 1:
The patent performs preliminary capture and storage of complete measurement data, calibration information, and image records during the initial measurement process. This preliminary action enables subsequent re-measurement, re-evaluation, and further analysis without requiring physical re-handling of objects, thereby providing adaptability for multiple inspection purposes while maintaining high detection capability.
4Reliability
If extensive physical inspections are conducted, then product quality is ensured, but cost and time consumption increase
Solution Approach 1:
The patent creates comprehensive digital copies of product geometry and surface characteristics through optical measurement. These digital models enable virtual inspection, re-evaluation, and analysis without requiring repeated physical handling or extensive manual inspection, thereby ensuring product quality while dramatically reducing inspection time and associated costs.
Data Source
AI summary
A method and a system for the quality control of objects after they have been supplied. After manufacturing, the object is checked by means of a measuring machine vision system. The measurement results of the machine vision system are recorded in a data system together with the corresponding calibration data. When the calibration data is known, new measurements can be conducted later from the recorded images at a time when the actual object has already been supplied and possibly placed in an end product.