Skip to main content

Automated Diagnosis for Helicopter Engines and Rotating parts

Final Report Summary - ADHER (Automated Diagnosis for Helicopter Engines and Rotating parts)

The main aim of the ADHER project was to enable 'fleet scale' health monitoring for helicopters, with robust failure diagnosis and possibly prognosis, relying on multi-sensor monitoring and automated analysis of sensor recorded data. The aim was to reduce false alarm rates and maintenance costs and to increase operational aircraft availability, enabling efficient scheduling of preventive maintenance.

Aircraft availability, in-flight reliability and low cost maintenance are major concerns for helicopter operators. Health usage monitoring system (HUMS) implementing sensor-based monitoring is an enabling technology seeking to provide a condition-based maintenance (CBM) relying on automated diagnosis / prognosis of the health of aircraft components. One challenge for HUMS is to implement automated low cost CBM systems as an alternative to periodic physical inspections. Existing HUMS technologies tend to generate high rates of false alarms due to the use of fixed alarm thresholds. Automated analysis of fleet operating data on engine and rotating parts recorded by on-board sensors is a major scientific direction to reach adaptive, reliable, and low cost HUMS systems.

The main scientific and technological objectives of project ADHER are:
1. to obtain a better understanding of the physical behaviour of ODM, vibration and acoustics sensing through new theoretical models and through a series of test bench experiments on helicopter gearboxes, especially in terms of 'ageing effects' and of 'progressive emergence of failures' for rotating parts;
2. to define innovative auto-adaptive algorithms enabling data-driven automatic learning to analyse empirical time evolutions of sensor data and to generate anticipative health diagnosis, taking account of vehicle context variables, as well as, to test these algorithms on helicopter fleet vibration data;
3. to evaluate the feasibility of automated health monitoring of helicopter fleets.

The project work breakdown structure included three sub-projects (SPs) divided into work packages (WPs):
- SP1 was concerned with project management and dissemination towards potential end-users (WP1.1) project scope specification (WP1.2) and results assessment (WP1.3).
- SP2 addressed experimental data acquisition and physical modelling of three key categories of measurements known to have discriminating capabilities to monitor the health of helicopter rotating parts: oil debris (WP2.1) vibrations (WP2.2) and acoustic emissions (WP2.3). The main goal of SP2 is to reduce fault non detection rate.
- SP3 focused on innovative multi-sensor diagnosis software tools and explores the diagnosis potential of self-learning algorithms. SP3 addresses helicopter fleet sensor data base (WP3.1) self-learning tools for vibration based diagnosis / prognosis (WP3.2) multi-sensor data fusion for diagnosis (WP3.3) automatic elimination of defective sensor data (WP3.4) and evaluation of the developed prototype tools (WP3.5). The main goal of SP3 was to reduce false alarm rate.

The main project outputs were:
- end-user needs / requirements and specifications for failure diagnosis and maintenance of helicopter gear boxes;
- extensive test results and data from laboratory gearboxes;
- advanced signal processing techniques applied to vibration and AE recordings;
- identification of diagnosis parameters extracted from data processing and performance assessment of these parameters;
- comparison of diagnosis indications from ODM, vibrations and AE;
- identification of contextual parameters (oil temperature, speed, load) effect on recordings;
- analysis and explanation of ODM behaviour;
- data from tribological analysis of gear contact mesh conditions in laboratory gear tests;
- modelling and analysis of gear mesh distress indicators from gear tests;
- comparisons of tribological analysis data and distress indicators with condition monitoring signal analysis;
- large base of vibration data recorded during flights of several helicopters in a period spanning over several years; recordings include data from healthy and faulty situations;
- methods to analyse large quantities of multi-sensor vibration data and to diagnose healthy / faulty situations; the methods use several techniques for data mining, automatic elimination of degraded recordings, data structuring, data aggregation, modelling of flight contextual variables, self learning based on healthy situations and diagnosis;
- software tool prototypes to implement the processing techniques and the diagnosis method;
- performance assessment of the developed methods and supporting tools;
- assessment of potential operational benefits of the project results and feasibility analysis of the industrialisation of the developed methods and software tools in the context of helicopter maintenance;
- preliminary plan for using and disseminating the project knowledge.

The project's results were disseminated through various activities, namely its website (please see online), papers and press releases and contacts with potential end users.

Related documents