Aircraft Engine Exhaust Gas Temperature Margin Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The random oscillations in the exhaust gas temperature residual margin time signal of an aircraft engine, caused by servicing operations and measurement conditions, complicate accurate prediction of engine failure.
Innovation Solution
A method that smooths the time signal to eliminate artificial increases, identifies decreasing pieces representing engine wear, constructs a continuous curve by concatenating these pieces, and uses prediction models such as autoregressive or linear models with dynamic filters to forecast engine failure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the time signal of exhaust gas temperature residual margin is monitored directly, then the engine state can be tracked, but the random oscillations caused by servicing operations complicate the analysis and reduce prediction accuracy
Solution Approach 1:
The patent segments the time signal into multiple curves, each representing a period between two consecutive servicing operations. By dividing the continuous monitoring data into discrete segments that exclude servicing periods, the method isolates the natural wear trend from artificial fluctuations, thereby improving prediction accuracy while simplifying analysis of each segment individually
Solution Approach 2:
The patent extracts and removes the portions of the time signal that correspond to servicing operations. By identifying and excluding these artificial increase periods from the analysis, the method isolates only the natural wear-related decreasing trends, eliminating the complicating oscillations and enabling more accurate failure prediction
2Reliability
If servicing operations are performed frequently to maintain engine performance, then the temperature residual margin is restored, but artificial increases in the margin occur that complicate failure prediction
Solution Approach 1:
The patent applies preliminary action by predicting the timing of future servicing operations based on historical patterns and engine usage. By anticipating when servicing will occur, the method can proactively exclude these periods from the wear analysis before they contaminate the data, thereby preserving the integrity of the wear trend information while still benefiting from regular maintenance
Solution Approach 2:
The patent converts the harmful effect of servicing-induced oscillations into a beneficial analytical framework. By recognizing that servicing operations create predictable patterns of artificial margin increases, the method uses these patterns as markers to define segment boundaries, thereby transforming the noise into useful structural information for organizing the wear analysis
Data Source
AI summary
A method and a system for monitoring an aircraft engine (2), including: acquisition and processing part (11) configured to collect a time signal of the exhaust gas temperature residual margin of the aircraft engine (2), acquisition and processing part (11) configured to smooth the time signal thus forming a first curve representing the temperature residual margin, acquisition and processing part (11) configured to identify decreasing pieces in the first curve, acquisition and processing part (11) configured to construct a second curve by concatenation of the decreasing pieces, the second curve being continuous while being restricted to the decreasing pieces of the first curve, acquisition and processing part (11) configured to construct a prediction model from the second curve to determine at least one failure forecast indicator.