Engine-Specific Health Models Using Flight Data Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Developing accurate engine-specific models for gas turbine engines is time-consuming and often not optimized for extreme flight conditions, as they are typically fine-tuned through extensive testing rather than being adaptable to real-world operational environments.
Innovation Solution
A method and system for self-generating engine-specific models using a generic physics-based model, which involves identifying engine components, capturing observed parameters during training missions, and training an engine-specific model using AI and machine learning to predict component parameters during operational missions, allowing for real-time monitoring and maintenance actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If detailed engine-specific models are developed through extensive component rig testing, altitude testing, and full engine testing, then manufacturing precision and reliability are improved, but development time and productivity deteriorate
Solution Approach 1:
The system performs preliminary model development using generic engine models before actual flight testing. The generic models are pre-configured with expected engine component parameters and performance characteristics, allowing the system to be ready for data collection and model refinement before the engine is actually deployed to extreme flight conditions.
Solution Approach 2:
The engine-specific model automatically tunes and refines itself using flight data collected during actual operations. The system self-adjusts model parameters by comparing expected parameters from the generic model with actual sensor data from the engine, continuously improving accuracy without requiring external intervention or extensive manual testing.
2Reliability
If extensive component rig testing and full engine testing are conducted, then model accuracy for extreme conditions is improved, but loss of time and development duration worsen
Solution Approach 1:
Instead of conducting exhaustive testing across the entire flight envelope, the system uses partial action by collecting data only during actual flight operations when the engine is operated. The model is refined using the specific flight conditions that occur, rather than attempting to pre-test all possible extreme conditions.
Solution Approach 2:
The system changes the approach from static pre-determined model parameters to dynamic parameters that are continuously adjusted based on actual flight data. The model transitions from fixed generic parameters to adaptive parameters that reflect real engine behavior under varying flight conditions.
3Productivity
If generic models are used without customization, then productivity and ease of manufacture are improved, but adaptability to specific flight conditions and measurement precision deteriorate
Solution Approach 1:
The system transforms the static generic model into a dynamic model that automatically adapts to specific flight conditions. The model parameters are not fixed but are continuously adjusted based on actual sensor data from the engine during flight, allowing the same generic model structure to serve multiple engine types and flight conditions.
Solution Approach 2:
The system implements feedback loops where actual engine sensor data is continuously compared with model predictions. The discrepancies between expected and actual parameters feed back into the model, automatically tuning and refining it to better match the specific engine's behavior under various flight conditions.
Data Source
AI summary
A method for self-generating an engine-specific model in an engine health monitoring system is provided. The method comprises generating a generic engine model including a generic physics-based model for each of a plurality of engine components in the specific engine; capturing a plurality of observed engine component parameters for each of the plurality of engine components and a plurality of observed environmental parameters during one or more pre-planned training missions; and training an engine-specific model using the plurality of observed engine component parameters and the plurality of environmental parameters captured during the one or more pre-planned training missions, wherein the engine-specific model includes an engine-specific physics-based model for each of the plurality of engine components in the specific engine. Each engine-specific physics-based model for an engine component is configured for use in predicting one or more engine component parameters using a second plurality of observed environmental parameters captured during an operational mission.