Compressor Operability Prediction From Blade Damage Using AI
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computational fluid dynamic (CFD) techniques for predicting compressor operability in gas turbine engines are time-consuming, labor-intensive, and not sufficiently accurate, leading to potential unnecessary condemnation of components and increased costs due to inaccurate damage assessments and complex repair requirements.
Innovation Solution
A computer-implemented method using machine learning algorithms, specifically artificial neural networks, is employed to determine compressor operability by training the algorithms with data quantifying damage to compressor blades and operating parameters, allowing for rapid and more accurate assessments of compressor damage and operability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If computational fluid dynamic (CFD) techniques are used to model the effect of damage on compressor operability, then the prediction accuracy may be improved, but the time consumption and labor intensity increase significantly
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models using CFD simulation data before actual damage assessment is needed. The trained models can then rapidly predict compressor operability without requiring real-time CFD computations, thus achieving both accuracy and speed requirements
Solution Approach 2:
The patent creates simplified copies of the complex CFD models by training machine learning algorithms on CFD-generated data. These ML models serve as lightweight approximations that replicate the predictive capabilities of full CFD simulations but execute much faster
2Productivity
If machine learning algorithms are used to determine compressor operability, then the assessment speed is improved, but the training data requirements and computational preparation increase
Solution Approach 1:
The patent performs preliminary action by generating and curating training datasets in advance using CFD simulations and historical data. This preparation phase creates the necessary training material that enables rapid assessments later without requiring extensive data collection during actual operations
3Ease of manufacture
If accurate predictions of blade damage impact are made quickly, then component condemnation can be minimized and costs reduced, but the complexity of ensuring prediction accuracy increases
Solution Approach 1:
The patent merges multiple approaches by combining machine learning algorithms with traditional engineering judgment and validation procedures. This integration allows the system to leverage the speed of ML while maintaining accuracy through established engineering principles, reducing unnecessary condemnations without overly complicating the process
Data Source
AI summary
A computer-implemented method comprising: controlling input of data quantifying damage received by a compressor of a gas turbine engine into a first machine learning algorithm; receiving data quantifying a first operating parameter of the compressor as an output of the first machine learning algorithm; and determining operability of the compressor by comparing the received data quantifying the first operating parameter of the compressor with a threshold.