K-Fold Functional Tolerance Assessment for Gas Turbine Parts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for assessing the quality of manufactured gas turbine engine components, such as integrally bladed rotors, rely solely on geometric tolerances, which often misidentify functionally tolerant parts as unacceptable, leading to inefficiencies in the evaluation process.
Innovation Solution
A dual branch assessment method combining physical testing and machine learning, utilizing K-fold validation, to evaluate components based on functional tolerances by generating data at multiple locations, comparing it to training data, and determining functional dimensions using machine learning models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If geometric tolerance inspection is used to assess component quality, then manufacturing precision can be verified, but functionally tolerant parts are misidentified as unacceptable
Solution Approach 1:
The patent transforms the assessment from checking geometric dimensions against nominal tolerances to evaluating functional performance by simulating operational conditions (thermal expansion, centrifugal forces, gas flow). This parameter change allows parts that meet functional requirements but fall outside nominal geometric tolerances to be correctly identified as acceptable.
Solution Approach 2:
The patent replaces manual geometric inspection with an automated computer-based simulation system that models physical behavior under operating conditions. This substitution enables more accurate functional assessment by calculating thermal growth, centrifugal distortion, and aerodynamic effects rather than relying solely on dimensional measurements.
2Reliability
If manual inspection of dimensions is performed, then component quality can be assessed, but evaluation speed is reduced
Solution Approach 1:
The patent replaces slow manual inspection processes with automated computer-based simulation and machine learning algorithms. The system automatically generates test data, performs K-fold validation, and produces assessment results, dramatically increasing evaluation speed while maintaining or improving accuracy through consistent application of functional criteria.
Solution Approach 2:
The patent creates virtual copies of the component through digital modeling and simulation, allowing multiple assessments and iterations without physically handling the part. This digital copying enables rapid evaluation by testing virtual models under various operating conditions rather than performing repeated physical measurements.
3Reliability
If K-fold validation with machine learning is implemented, then functional tolerance assessment accuracy is improved, but device complexity increases
Solution Approach 1:
The patent divides the assessment system into distinct modular components: data generation module, machine learning training module, K-fold validation module, and assessment output module. Each module performs a specific function and can be independently developed, tested, and maintained, reducing overall system complexity despite the advanced capabilities.
Solution Approach 2:
The patent introduces a computer system as an intermediary between the physical component and the assessment decision. This intermediary handles the complex machine learning algorithms, K-fold validation processes, and simulation calculations, isolating the complexity from the user interface and allowing operators to interact with a simplified assessment workflow.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of assessing the quality of a manufactured component includes the steps of manufacturing a component (22) and generating data (24) at each of a plurality of locations through the component (22). The generated data (24) is passed to a machine learning branch (35). The generated data is compared to training data at each of the plurality of locations and across a plurality of folds using K-fold validation to determine whether the component is of a functionally tolerant dimension at each of the plurality of locations. The training data at each of the plurality of folds at each of the plurality of locations is from a common part. A system (20) is also disclosed.