Gas Turbine Recontouring Using Section-Wise ML Machining Offsets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The recontouring process for gas turbine engine components is currently iterative and time-consuming, requiring manual intervention due to significant part-to-part variation and uncertainties in the recontouring system, making automation unsuccessful.
Innovation Solution
A system utilizing machine-learned models, such as deep neural networks, to determine machine offsets for each section of the component, allowing for real-time adjustment of the material removal tool path, thereby automating the recontouring process and reducing cycle time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual inspection and iterative machining is used to determine machine offset, then the recontouring process can handle part-to-part variation and system uncertainties, but the process becomes time-consuming and cannot be automated
Solution Approach 1:
The system performs preliminary scanning of the component to capture its actual geometry and condition before machining begins. This advance information is used to pre-calculate the machine offset values, eliminating the need for iterative trial-and-error machining and significantly reducing cycle time while maintaining precision
Solution Approach 2:
The patent replaces manual inspection and mechanical measurement methods with automated optical scanning and computer-based calculation systems. This substitution enables rapid data acquisition and processing, allowing the system to determine machine offsets automatically without manual intervention, thus reducing time loss while achieving high manufacturing precision
2Manufacturing precision
If manual intervention is used to determine machine offset, then the process can account for significant part-to-part variation and geometrical shape complexities, but the extent of automation is reduced
Solution Approach 1:
The system enables the recontouring process to be self-sufficient by automatically scanning the component, calculating the appropriate machine offset values based on the scanned data and stored reference geometry, and adjusting the machining operations without requiring manual measurement or intervention. This self-service capability maintains high automation levels while ensuring accurate handling of part variations and geometrical complexities
3Manufacturing precision
If iterative inspection and machining is performed, then the desired specifications can be achieved, but the productivity is reduced due to repeated cycles
Solution Approach 1:
The system performs all necessary measurements and calculations before machining begins. By scanning the component and pre-determining the machine offset values in advance, the system eliminates the need for repeated inspection-machining cycles, thereby maintaining specification compliance while significantly improving productivity through a single-pass machining operation
Data Source
AI summary
Systems and methods that include and/or leverage a cluster of machine-learned models to recontour components of gas turbine engines are provided. In one exemplary aspect, the systems and methods leverage a cluster of machine-learned models to predict repair machining offsets for certain sections of the component that can be used to adjust or set a material removal tool path.