PAUT S-Scan Classification for Defect vs Diffuse Reflection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing phased array ultrasonic testing (PAUT) methods face challenges in accurately distinguishing between defective areas and diffuse reflection areas in S-scan images due to varying skill levels of testers and increased diffuse reflection signals, affecting defect detection accuracy.
Innovation Solution
A system and method that utilize pre-trained classification models to classify S-scan images from PAUT, involving an input unit, conversion unit, extraction unit, and classification unit to identify and distinguish between defective and diffuse reflection areas by analyzing signal characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If S-scan imaging is used in phased array ultrasonic testing, then two-dimensional cross-sectional views can be obtained, but diffuse reflection signals increase and defect detection accuracy varies depending on tester skill
Solution Approach 1:
A classification model is introduced as an intermediary between the S-scan image and the defect detection result. The model processes the image data and outputs classified regions, serving as a mediator that filters out diffuse reflection signals and identifies actual defective areas, thereby improving detection accuracy without requiring high tester skill levels
Solution Approach 2:
The manual inspection process dependent on tester skill is replaced with an automated classification model. The model uses machine learning algorithms to analyze S-scan images and distinguish between defective areas and diffuse reflection areas, substituting human judgment with an objective, skill-independent system
2Adaptability or versatility
If multiple probes are used to receive ultrasonic signals, then comprehensive coverage is achieved, but diffuse reflection signals increase
Solution Approach 1:
The classification model acts as an intermediary that processes data from multiple probes. It receives the composite S-scan image containing signals from all probes and systematically separates useful defect information from harmful diffuse reflection signals generated by the multi-probe configuration, allowing comprehensive coverage to be maintained while filtering noise
3Ease of operation
If manual inspection of S-scan images is performed, then flexibility is maintained, but detection accuracy varies depending on tester skill
Solution Approach 1:
The system enables self-service inspection where the classification model autonomously performs the analysis that previously required skilled human operators. The model automatically processes S-scan images, identifies defective areas, and provides consistent results without varying based on individual tester expertise, thereby maintaining operational simplicity while eliminating skill-dependent variability in accuracy
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
Enables rapid and accurate classification of defective and diffuse reflection areas, improving defect detection precision and reducing reliance on tester skill.
Implementation Method 1
Ultrasonic testing is a method of detecting discontinuity in a test specimen by transmitting ultrasonic waves into the test specimen and is a method of measuring a position, size, etc. of a defect by comparing the amount of energy reflected from the discontinuity within the test specimen, a travel time of the transmitted ultrasonic waves to pass through a test object and be reflected back from the discontinuity, and a difference in attenuation when the ultrasonic waves pass through the test specimen
Implementation Method 2
an S-scan refers to a sector scan generated when an ultrasonic beam is electronically swept through various angles using a phased array, and is typically represented as a sector scan image showing a two-dimensional cross-sectional view derived from a series of A-scans displayed in relation to time delay and refraction angle
Data Source
AI summary
The present disclosure relates to a system and method for area classification and a defect detection system using the same. The system includes an input unit configured to receive an S-scan image from phased array ultrasonic testing (PAUT) using at least one probe; a conversion unit configured to detect at least one defective candidate using a pre-trained first model and convert the S-scan image into an original image; an extraction unit configured to acquire column data of the defective candidate, select representative data, extract at least one peak by overlapping the representative data in an index direction, and extract signal characteristics; and a classification unit configured to input the signal characteristics into a pre-trained second model to classify each defective candidate as a defective area or a diffuse reflection area.