EDM Hole Characterization Using Key-Point Rule Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current software tools for analyzing EDM fast hole drilling processes are limited in their ability to handle large datasets, lack automated inspection capabilities, and struggle to detect non-conformances such as blocked or tapered holes, leading to inefficient and skill-dependent manual analysis, which can impact the quality of gas turbine engine components.
Innovation Solution
A method and system that automatically determine key points from depth, tool velocity, and process current data using programmed gates, applying rules to characterize hole characteristics like blocked or tapered holes, enabling automated inspection and process adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of plots is performed by process engineers, then expertise-based insights can be obtained, but the analysis is extremely time consuming and dependent on user skills
Solution Approach 1:
The system enables self-service automated analysis of machining plots through AI/ML models that independently evaluate depth data, tool velocity data, and process current data to detect non-conformances and generate insights without requiring manual expert intervention
Solution Approach 2:
The patent replaces the mechanical manual analysis process with an automated computational system using AI/ML algorithms that process machining data plots, substituting human expert labor with intelligent software automation to reduce analysis time while maintaining or improving accuracy
2Device complexity
If only a few plots are visualized at a time in current software tools, then the software remains simple, but the analysis becomes extremely time consuming and cannot handle large amounts of data
Solution Approach 1:
The system segments the analysis process into distinct AI/ML models that handle different aspects of plot analysis separately (depth analysis, velocity analysis, current analysis), allowing each model to specialize in specific patterns while collectively processing large datasets efficiently
Solution Approach 2:
The patent changes the fundamental parameter of data processing capacity by implementing AI/ML models that can handle and visualize multiple plots simultaneously, transforming the system from processing a few plots at a time to processing large volumes of machining data efficiently
3Manufacturing precision
If existing inspection methods are used, then basic hole depth can be measured, but non-conformances such as blocked holes, tapered holes, and back wall impingement are difficult to detect
Solution Approach 1:
The system implements feedback mechanisms where AI/ML models continuously analyze machining plots during the drilling process, providing real-time feedback about potential non-conformances such as blocked holes, tapered holes, and back wall impingement, allowing for immediate detection and corrective action
Solution Approach 2:
The patent applies preliminary action by using AI/ML models to predict and detect potential non-conformances before they become critical defects, analyzing patterns in the machining data that indicate upcoming issues with hole quality
4Reliability
If process engineers react to non-conformances after they occur, then existing inspection methods can identify problems, but preventive measures cannot be implemented
Solution Approach 1:
The system uses feedback from AI/ML analysis of machining plots to enable preventive action by detecting early signs of process drift or instability, allowing process engineers to adjust parameters before non-conformances occur, transforming reactive inspection into proactive process control
Solution Approach 2:
The patent implements preliminary action through AI/ML models that predict potential non-conformances before they manifest as actual defects, allowing preventive measures to be taken in advance by analyzing trends in the machining data
Data Source
AI summary
A method for determining one or more characteristics of a hole includes obtaining depth data, tool velocity data, process current data, and a plurality of gates. The method further includes determining a plurality of first, second, and third key points. The plurality of first, second, and third key points together form a plurality of key points. The method further includes obtaining a plurality of rules. Each rule includes one of: a relationship between a respective key point and a value associated with the respective key point; and a relationship between two or more respective key points. The method further includes determining the one or more characteristics of the hole based on the plurality of rules and the plurality of key points.