Semi-Automatic X-Ray Inspection for Turbomachine Blade Welding Defects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current quality control systems for industrial parts, particularly in the aeronautical field, face challenges in fully automating the detection of complex welding defects due to the uniqueness of each blade weld, requiring operator intervention and complex, costly integration of partial automation techniques.
Innovation Solution
A quality control system that integrates an annotation module for image marking, a learning module for algorithm development, and a penalty module for defect detection, allowing semi-automatic assistance to operators, with minimal changes to existing systems and reduced training needs, using X-ray images and metadata to enhance defect detection efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If full automation by algorithms is implemented, then productivity is improved, but reliability deteriorates due to inability to handle complex unique welding defects
Solution Approach 1:
The patent introduces an intermediary system that bridges full automation and manual inspection. The algorithmic module processes images and generates preliminary defect detections, which are then reviewed and validated by human operators. This intermediary approach allows the system to benefit from both automated speed and human reliability in complex decision-making.
2Productivity
If partial algorithmic automation is integrated into existing quality control systems, then productivity is improved, but device complexity increases due to system integration requirements
Solution Approach 1:
The patent segments the quality control system into distinct functional modules: an existing inspection unit, a separate algorithmic module, and a database component. Each module operates independently with well-defined interfaces, allowing the algorithmic automation to be integrated without fundamentally redesigning the entire system. This modular approach reduces integration complexity while maintaining productivity benefits.
3Ease of operation
If existing quality control systems are revised to integrate automation, then ease of operation is improved, but loss of time increases due to operator training and certification requirements
Solution Approach 1:
The algorithmic module operates autonomously to perform preliminary defect detection and analysis, reducing the need for operators to perform complex manual inspection tasks. The system self-manages the automated processing workflow, requiring minimal operator intervention beyond reviewing algorithmic results. This reduces both the training time needed and the time operators spend on routine inspection activities.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides a fast, reliable, and efficient method for detecting welding defects in turbomachine blades with high accuracy, reducing operator inspection time and simplifying integration, while maintaining system integrity and compliance with international standards.
Implementation Method 1
acquiring images of the part to be inspected... by X-rays
Data Source
Figure 1
AI summary
The present invention relates to a quality control system (1) for manufactured parts. The system (1) comprises an acquisition device (2) for providing images (90) of the manufactured parts, a database (3), and an inspection unit (4) including an interface (41) for viewing the images (90), into which are integrated annotation (5), learning (6), and penalty (7) modules, so as to allow semi-automatic defect detection. The invention also relates to a method for quality control of manufactured parts using said system (1).