Aircraft Engine Sensor Training for Fault-Tolerant AI Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aircraft engine control systems face challenges in identifying and accommodating sensor malfunctions, leading to potential system failures during flight missions, which can be costly and complex to mitigate with redundant sensors.
Innovation Solution
An AI model trained using data from multiple sensors senses different parameters, producing derived values to replace faulty sensor data, allowing the engine control unit to continue operating safely until maintenance, thereby reducing the need for redundant sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple redundant sensors are used to mitigate sensor failures, then system reliability is improved, but system complexity and cost increase
Solution Approach 1:
An AI model is introduced as an intermediary component that processes data from multiple sensors and generates derived parameter values. This mediator enables the system to accommodate sensor failures without requiring redundant sensors, as the AI model can infer missing or faulty sensor data from other available sensor inputs, thereby maintaining reliability while reducing system complexity
Solution Approach 2:
The AI model creates derived copies of sensor parameter values through mathematical relationships and machine learning algorithms. Instead of physically duplicating sensors, the system generates virtual copies of sensor data through AI-derived values, allowing the control system to continue operating with accurate parameter information even when physical sensors fail
2Reliability
If multiple redundant sensors are used to mitigate sensor failures, then system reliability is improved, but cost increases
Solution Approach 1:
The system creates virtual sensor copies through AI-derived parameter values, eliminating the need to purchase and install additional physical redundant sensors. The AI model generates accurate parameter estimates using existing sensor data and mathematical relationships, providing the same reliability function at lower cost
Solution Approach 2:
The control system uses its existing sensor network and AI processing capabilities to self-correct for sensor failures. Rather than requiring external redundant sensors, the system leverages its own available sensor data and AI algorithms to compensate for failures, reducing the need for additional hardware investments
3Duration of action of stationary object
If sensor failures occur, then system operation is disrupted, but with AI model the system can continue operating until maintenance
Solution Approach 1:
The AI model is pre-trained during ground operations using data from all functional sensors to learn the complex relationships between different engine parameters. This preliminary training enables the model to accurately predict and derive parameter values even when sensors fail during flight, allowing the system to maintain operation until the next maintenance opportunity without compromising reliability
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and method for controlling an aircraft engine is provided. The method includes a) producing first sensor data using a first sensor sensing a first parameter during operation of the aircraft engine on a flight mission; b) producing other sensor data using a plurality of second sensors sensing a plurality of other parameters, during operation of the aircraft engine; c) providing the first and other sensor data to a control unit during operation of the aircraft engine; d) storing the first and other sensor data during operation of the aircraft engine; e) using an artificial intelligence (AI) model that is trained using the stored first and other sensor data produced during operation of the aircraft engine, to produce one or more derived first parameter values; and f) selectively providing the one or more derived first parameter values to the control unit for use in controlling the aircraft engine.