Gas Turbine Compressor Operability from Blade Damage Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting the impact of compressor blade damage on gas turbine engine operability are inaccurate and time-consuming, leading to unnecessary component condemnation and increased costs due to the complexity of repairing bladed disks.
Innovation Solution
A computer-implemented method using machine learning algorithms to determine compressor operability by quantifying damage to compressor blades and comparing operating parameters with thresholds, allowing for rapid and accurate assessments.
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 analysis can be performed, but the process is time consuming and labour intensive taking days of an expert's time
Solution Approach 1:
The patent creates a simplified computational model that copies the essential physics of compressor flow and damage effects without requiring full CFD complexity. This reduced-order model captures the key relationships between blade damage and compressor performance while enabling rapid calculation, reducing analysis time from days to minutes while maintaining sufficient accuracy for operability assessment
Solution Approach 2:
The patent transforms the complex CFD problem into a parameter-based computational model that uses simplified equations and empirical relationships. By changing the mathematical representation from full Navier-Stokes solutions to algebraic relationships between damage parameters and performance metrics, the system achieves rapid results suitable for real-time decision-making
2Measurement precision
If computational fluid dynamic (CFD) techniques are used to model the effect of damage on compressor operability, then the analysis can be performed, but it is labour intensive requiring days of an expert's time
Solution Approach 1:
The patent creates a simplified computational model that copies the essential physics of compressor flow and damage effects without requiring full CFD complexity. This reduced-order model captures the key relationships between blade damage and compressor performance while enabling rapid calculation, reducing analysis time from days to minutes while maintaining sufficient accuracy for operability assessment
Solution Approach 2:
The patent replaces the complex mechanical process of manual CFD setup, grid generation, solution, and analysis with an automated computational algorithm. The system substitutes expert human labor with a computer-executable model that automatically processes damage data and predicts operability impacts, significantly reducing both time and expertise requirements
3Productivity
If current prediction methods are used, then component assessment can be performed, but the predictions are inaccurate leading to unnecessary component condemnation and significant cost penalties
Solution Approach 1:
The patent incorporates feedback mechanisms where the computational model is trained and validated against actual compressor performance data and inspection results. This feedback loop allows the system to continuously improve its predictions by learning from real-world outcomes, reducing false condemnations while maintaining rapid assessment capabilities for production decision-making
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method comprising: controlling input of data quantifying damage received by one or more components of a gas turbine engine into a first machine learning algorithm; receiving data quantifying a first operating parameter of the gas turbine engine as an output of the first machine learning algorithm; and determining operability of the gas turbine engine by comparing the received data quantifying the first operating parameter of the gas turbine engine with a threshold.