Aircraft Engine Health Monitoring With Wear-Corrected Alarm Validation
Find Innovative SolutionsGenerate 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
Engineering 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
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.
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.
2Reliability
If manual expert analysis is used to confirm alarms, then false alarms can be identified, but monitoring costs increase
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.
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.
3Reliability
If threshold-based anomaly detection is used, then real anomalies are detected, but false alarms increase
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.
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.
Data Source
Figure 1~3
Figure 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.