Automated Workpiece Inspection via Multi-Position Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual inspection methods for machine assembly components, such as gas turbine engines, are subjective, inconsistent, and inaccurate due to human bias and limitations in lighting conditions, leading to inefficiencies and potential defects being missed.
Innovation Solution
An automated inspection system utilizing imaging devices and processors to capture images of components from multiple positions and under different light settings, employing machine learning algorithms like artificial neural networks to generate and merge prediction images, thereby reducing the influence of lighting variations and human error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If manual inspection is performed by human operators, then the inspection process can be conducted with simple equipment, but the inspection accuracy and consistency deteriorate due to human bias and error
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated imaging system that uses cameras, lights, and image processing algorithms to detect defects. The system captures images from multiple positions and light settings, then uses computer vision to objectively identify defects, eliminating human subjectivity while maintaining operational simplicity through automation.
Solution Approach 2:
The system creates multiple copies of the work piece images from different positions and lighting conditions. By capturing and analyzing multiple image copies, the system ensures comprehensive defect detection while maintaining a non-contact, automated process that eliminates the need for complex manual inspection procedures.
2Productivity
If single position and lighting condition imaging is used, then the inspection process is faster and simpler, but the defect detection accuracy deteriorates due to lighting variations and specular reflection
Solution Approach 1:
The inspection process is segmented into multiple image capture steps, each taken from different positions and light settings. Instead of attempting to capture all defect information in a single image, the system divides the inspection into multiple targeted captures, then combines them through image processing to achieve comprehensive and accurate defect detection.
Solution Approach 2:
The system adds dimensional diversity by capturing images from multiple spatial positions and multiple lighting dimensions. This multi-dimensional approach allows the system to overcome limitations of single-view inspection, as defects visible under certain lighting angles or positions can be detected by capturing images from multiple perspectives and combining them through processing.
3Measurement precision
If multiple positions and light settings are used for imaging, then the defect detection accuracy improves, but the inspection time and system complexity increase
Solution Approach 1:
The system performs preliminary actions by capturing all necessary images from multiple positions and light settings before conducting the actual defect analysis. This preparatory image capture phase allows subsequent processing to work with pre-acquired data, reducing the time required during the critical detection phase and enabling efficient batch processing of multiple work pieces.
Solution Approach 2:
The system merges multiple images captured from different positions and light settings into a unified analysis. By combining information from multiple sources through image processing and fusion algorithms, the system achieves comprehensive defect detection while efficiently utilizing the captured data, reducing redundant inspections and optimizing the overall inspection time.
Data Source
AI summary
An inspection system includes one or more imaging devices and one or more processors. The imaging devices generate a first set of images of a work piece at a first position relative to the work piece and a second set of images of the work piece at a second position relative to the work piece. At least some of the images in the first and second sets are acquired using different light settings. The processors analyze the first set of images to generate a first prediction image associated with the first position, and analyze the second set of images to generate a second prediction image associated with the second position. The first and second prediction images include respective candidate regions. The processors merge the first and second prediction images to detect at least one predicted defect in the work piece depicted in at least one of the candidate regions.