Engine Blade TAI Inspection Ranking for Crack Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated inspection processes for engine blades using thermal acoustic imaging are prone to misinterpretation due to non-crack-like indications, leading to tedious, time-consuming, and imprecise manual analyses, which are error-prone and inefficient.
Innovation Solution
An automated system that utilizes thermal acoustic imaging (TAI) to generate scans, employs an indication detection module to identify potential defects, and a ranking system to prioritize defects based on attributes and likelihood, using machine learning and statistical methods to rank the severity and criticality of indications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated thermal acoustic imaging inspection is used to identify possible defects, then inspection coverage and data collection are improved, but the number of identified possible defects becomes very large requiring extensive manual analysis
Solution Approach 1:
The patent replaces manual mechanical inspection processes with automated image processing and machine learning algorithms. The system uses automated workflows to analyze thermal acoustic imaging data, identify possible defects, and rank them by likelihood, eliminating the need for tedious manual analysis of scan data while maintaining high inspection coverage.
Solution Approach 2:
The inspection system performs self-analysis through automated detection and ranking algorithms. The system automatically processes thermal acoustic imaging data, identifies indications, calculates likelihood scores, and prioritizes defects without requiring human intervention for the initial analysis phase, thereby reducing manual workload and analysis time.
2Reliability
If manual inspection is performed on identified possible defects, then defect verification can be achieved, but the process becomes tedious, time-consuming, and error-prone
Solution Approach 1:
The patent replaces manual defect verification with automated image processing and machine learning models. The system automatically analyzes thermal acoustic imaging data, identifies possible defects, and ranks them by likelihood of being actual defects. This automated approach maintains high verification accuracy while dramatically improving inspection efficiency and reducing human error.
Solution Approach 2:
The system implements automated feedback loops where detection results are continuously refined through ranking algorithms. The feedback mechanism prioritizes high-likelihood defects for verification while automatically filtering low-likelihood cases, creating an efficient verification process that maintains high accuracy without requiring manual review of all possible defects.
3Measurement precision
If all identified possible defects are analyzed manually, then comprehensive defect detection is achieved, but the workload and time required become excessive
Solution Approach 1:
The patent applies partial action by focusing manual or detailed analysis only on high-priority defects that exceed a certain likelihood threshold. The automated ranking system identifies and prioritizes the most probable defects, allowing the system to achieve comprehensive defect detection by thoroughly analyzing only the critical subset rather than all possible defects equally.
Solution Approach 2:
The system applies different levels of analysis quality to different defects based on their likelihood scores. High-likelihood defects receive detailed automated analysis and are flagged for priority verification, while low-likelihood defects are automatically filtered or given minimal attention. This local quality approach ensures comprehensive detection of critical defects while reducing overall analysis time.
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, reducing manual effort and improving accuracy by systematically identifying and prioritizing critical defects for re-inspection, thereby enhancing the integrity and reliability of engine blades.
Implementation Method 1
generating a thermal acoustic imaging (TAI) scan of a component using an infrared camera
Implementation Method 2
thermal acoustic imaging (TAI) scan
Data Source
Figure 1A
Figure 1B
Figure 2~3
AI summary
A thermal acoustic imaging (TAI) inspection system (400) scans a component (103) using an infrared camera (402) to capture a plurality of image frames of friction heat emitting from a possible defect in the component. The TAI inspection system (400) generates a TAI scan (414) that is provided to an indication analysis system (700) having modules to determine whether one or more indications exist for the possible defects within the TAI scan (414). Each indication has attributes, including a matching score. The respective indication and its attributes are provided to a ranking system (716). 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.