Aircraft Engine Health Monitoring With Wear-Corrected Alarm Validation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for monitoring the health of aircraft engines require significant expert intervention and manual analysis following alarm triggers, leading to high processing time and costs, including false alarms, which increases the demand on experts and reduces efficiency.

Innovation Solution

A system that includes an anomaly detection unit and an engine operating condition tracking unit to analyze engine parameters, raise alarms based on threshold overruns, and weight the probability of engine degradation by determining wear rates, thereby reducing false alarms and automating decision-making for maintenance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual expert analysis is used to confirm alarms, then false alarms can be identified, but processing time and costs increase significantly

Engineering Contradiction:
Improveanomaly detection accuracyVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary wear rate calculation and probability weighting before expert analysis. By pre-computing the wear rate from engine operating conditions and weighting the anomaly probability accordingly, the system prepares decision-support information in advance, reducing the time experts need to spend on confirmation while maintaining detection accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system enables automated self-assessment of alarm validity through the wear rate mechanism. Instead of requiring expert intervention for every alarm, the system automatically evaluates whether an alarm is likely valid by comparing it against the calculated wear rate, allowing only ambiguous cases to be escalated to experts.

Inventive Principle:
Principle #25Self-service

2Reliability

If manual expert analysis is used to confirm alarms, then false alarms can be identified, but monitoring costs increase

Engineering Contradiction:
Improveanomaly detection accuracyVSAvoidmonitoring cost
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary filtering of alarms using automated wear rate comparison before expert review. By pre-evaluating alarms against the calculated wear rate and only presenting ambiguous cases to experts, the system significantly reduces expert workload and associated costs while maintaining high detection accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements automated self-filtering of false alarms through the wear rate mechanism. The system independently evaluates alarm validity by comparing monitored parameters against wear-based expectations, eliminating the need for expensive expert analysis of clearly valid or clearly invalid alarms.

Inventive Principle:
Principle #25Self-service

3Reliability

If threshold-based anomaly detection is used, then real anomalies are detected, but false alarms increase

Engineering Contradiction:
Improveanomaly detection capabilityVSAvoidfalse alarm rate
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The system transforms the static threshold approach into a dynamic evaluation by introducing wear rate as a variable parameter. Instead of using fixed thresholds, the system adjusts the expected parameter ranges based on the calculated wear rate, allowing the detection criteria to adapt to the engine's actual condition and reducing false alarms caused by normal wear variations.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements feedback by continuously monitoring engine operating conditions and updating the wear rate calculation. This feedback loop allows the system to learn from actual engine behavior and adjust its anomaly detection thresholds dynamically, reducing false alarms while maintaining sensitivity to real degradation.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3619408B1System and method for monitoring a turbomachine with anomaly detection corrected by a wear factor
Publication Date: 2021.01.27 SAFRAN AIRCRAFT ENGINES SAS
  • EP3619408B1 patent drawingFigure 1~3
  • EP3619408B1 patent drawingFigure 4

AI summary

The invention relates to a system (1) for monitoring the state of health of a monitored aircraft engine (2). The system comprises an anomaly detection unit (3) which analyses engine operating parameters and raises an alarm (Al) if a result of the analysis of one of the engine operating parameters crosses a threshold, the alarm being associated with a probability of a given type of engine damage occurring. The system (1) further comprises an engine operating conditions monitoring unit (4) which determines a state of wear of the engine, and an alarm corroboration unit (5) which weights the said probability of occurrence by the determined state of wear. The invention finds an application in the preventive maintenance of turbomachines.