Engine Blade Thermal Acoustic Inspection for Defect Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated inspection systems for engine blades using thermal acoustic imaging are inefficient due to the need for manual analysis of scan data, which is tedious, time-consuming, and prone to errors, especially when dealing with non-crack-like indications such as foreign material, non-uniform paint, and noise.
Innovation Solution
An automated system that uses thermal acoustic imaging (TAI) to generate scans, applies an indication detection module to identify potential defects, and employs a ranking system to prioritize defects based on attributes and likelihood, using machine learning techniques to distinguish between actual defects and non-defects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated inspection systems are used to inspect engine blades, then inspection speed is improved, but the accuracy and reliability of defect detection deteriorates due to manual analysis requirements
Solution Approach 1:
The inspection system performs self-service by automatically analyzing TAI scan data through automated workflows that detect indications, evaluate confidence levels, and prioritize defects without requiring manual analyst intervention for each inspection case
Solution Approach 2:
The patent replaces manual mechanical analysis with automated computational systems that process thermal acoustic imaging data through algorithms, machine learning models, and automated workflows to detect and prioritize defects
2Reliability
If manual analysis of scan data is performed, then defect detection accuracy is improved, but inspection time and workload increase significantly
Solution Approach 1:
The system performs preliminary automated analysis to detect and prioritize defects before manual review is needed, pre-processing the scan data to identify potential indications and rank them by confidence level and severity
Solution Approach 2:
The automated inspection system performs self-service by independently analyzing TAI scan data, detecting indications, evaluating confidence levels, and prioritizing defects without requiring manual analyst intervention for each inspection case
3Productivity
If automated workflows are used to analyze TAI scan data, then inspection efficiency is improved, but the ability to handle complex non-crack-like indications deteriorates
Solution Approach 1:
The patent replaces manual mechanical analysis with automated computational systems that process thermal acoustic imaging data through algorithms, machine learning models, and automated workflows to detect and prioritize defects
Solution Approach 2:
The system changes the approach by analyzing multiple parameters including confidence levels, indication types, and spatial characteristics to differentiate between crack-like and non-crack-like indications, enabling automated handling of complex cases
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 efficiently ranks potential defects by considering various factors, reducing the need for manual inspection and improving the accuracy and speed of defect detection in engine blades.
Implementation Method 1
generating a thermal acoustic imaging (TAI) scan of a component using an infrared camera
Data Source
AI summary
A thermal acoustic imaging (TAI) inspection system scans a component using an infrared camera to capture a plurality of image frames of friction heat emitting from a possible defect in the component. The TAI inspection system generates a TAI scan that is provided to an indication analysis system having modules to determine whether one or more indications exist for the possible defects within the TAI scan. Each indication has attributes, including a matching score. The respective indication and its attributes are provided to a ranking system. The ranking system determines a priority score for the component or part of the component having the one or more indications based on the attributes. The priority score is used to rank the component or part of the component for further inspection operations.