Aircraft Engine Deterioration Forecasting With RNN Data Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods struggle to predict and address rapid aircraft engine deterioration caused by unknown combinations of factors, leading to unscheduled maintenance and operational disruptions.

Innovation Solution

A machine learning-based system using a recurrent neural network (RNN) algorithm that incorporates fused data sets including aircraft sensor data, GPS data, weather data, and environmental conditions to forecast engine deterioration, allowing for adjustments in maintenance schedules and route optimization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional maintenance scheduling based on expected part life cycles is used, then maintenance planning is straightforward, but rapid deterioration from unknown factors causes unscheduled maintenance and operational disruptions

Engineering Contradiction:
Improvemaintenance schedule reliabilityVSAvoidtime on wing
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of engine deterioration by continuously monitoring operating parameters and comparing them against historical data and deterioration models. This allows the system to predict potential failures before they occur, enabling proactive maintenance scheduling that prevents unscheduled maintenance events and maximizes time on wing.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements a feedback mechanism where actual engine performance data is continuously fed back into the deterioration model. This feedback loop allows the system to update predictions in real-time, adjust maintenance schedules dynamically, and improve the reliability of maintenance planning by accounting for actual engine behavior rather than relying solely on expected life cycles.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If comprehensive monitoring of all operating parameters is implemented to detect unknown deterioration causes, then prediction accuracy improves, but system complexity and data processing requirements increase

Engineering Contradiction:
Improvedeterioration detection precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts only the most relevant operating parameters and deterioration indicators from the comprehensive data set using feature selection techniques. By focusing on key parameters that have the strongest correlation with engine deterioration, the system maintains high detection precision while reducing the complexity of data processing and analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system introduces intermediary processing layers including data normalization, feature engineering, and predictive modeling that bridge the gap between raw operating parameters and deterioration predictions. These intermediaries simplify the relationship between complex input data and output predictions, making the system more manageable while preserving detection precision.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3712848B1System for forecasting aircraft engine deterioration using recurrent neural networks
Publication Date: 2023.12.27 RTX CORP
  • EP3712848B1 patent drawingFigure 1
  • EP3712848B1 patent drawingFigure 2
  • EP3712848B1 patent drawingFigure 3

AI summary

A method for forecasting aircraft engine deterioration includes creating a first fused data set (130) corresponding to a first actual aircraft engine (20). The first fused data set (130) includes at least one as manufactured parameter of the actual aircraft engine, expected operating parameters of the first actual aircraft engine, and actual operating parameters of the actual aircraft engine. The actual operating parameters of the actual aircraft engine include internal aircraft sensor data (110), and external flight tracking data (114). The method further includes predicting an expected engine deterioration of the first actual engine based on the expected operating parameters and the actual operating parameters of the first actual aircraft engine by applying the first fused data set to a forecasting model. The forecasting model is a recurrent neural network based algorithm, and the recurrent neural network based algorithm is trained via a plurality of second fused data sets corresponding to actual aircraft engines.