1.

1 Distributed Aircraft Maintenance Environment (DAME)

Contributors: Martyn Fletcher, Tom Jackson, Jim Austin (University of York)

1.1.1 Use case summary

The Distributed Aircraft Maintenance Environment (DAME) [Austin] provides a
Grid-based, collaborative and interactive workbench of remote services and tools
for use by human experts. It currently supports remote analysis of vibration and
performance data by various geographically dispersed users: local engineers and
remote experts. The diagnosis environment is built around a workflow system,
and an extensive set of data analysis tools and services, which can provide
automated diagnosis for known conditions. Where automated diagnosis is not
possible DAME provides remote experts with a collaborative and interactive
diagnosis and analysis environment.

1.1.2 Customers
The customers for the operational system are the primary actors: Maintenance
Engineers, Maintenance Analysts and Domain Experts who use the system to
assist in the analysis and diagnosis of engine conditions. The system is made up
of applications performing the analysis (and requiring possible transport) of very
large data sets on the order of terabytes from remote locations.
The DAME tools and services, which are used to provide diagnosis and
prognosis of engine conditions, are the “network customers” and these include:
 Signal processing tools and services – to detect known conditions.
 Search tools and services – to allow the searching of historical fleet
archives and current data archives for similar data amounting to terabytes
of data.
 Case based reasoning tools and services – to provide advice based on
symptoms and cases.

1.1.3 Scenarios
Figure 1 shows the actors and interactions with the system, which is shown as
the cloud in the centre.
The diagnostic process includes the following actors:
 Maintenance Engineers (located at airports): carry out engine diagnosis
and maintenance activities.
 Remote Maintenance Analysts (located at the data centre): provide
technical advice, coordinate analysis and brokerage and use the DAME
tools and services interactively.
  Remote Domain Experts (located at the engine manufacturer’s site): act
as a repository of knowledge, provide expert diagnostic advice on
unidentified anomalies and use the DAME tools and services interactively.
The role of the DAME administrator shown in figure 1 is to manage the systems
facilities and plays no active part in the diagnostic process. The Maintenance,
Repair & Overhaul (MRO) facility is an internal company facility providing
maintenance, repair & overhaul of engines off the aircraft, this is only used when
an engine has to be removed from the aircraft when, for example, a planned
major overhaul is required.
Engine
Manufacturer
Airline / Maintenance Contractor
(RR)
(at Airport)

Information / request for advice

Domain Expert (DE)

- engine expert
Dowload Investigate using tools
Engine
Data

Remote / Distributed Provide

Perform
Diagnosis
Minor Repair Tools and Services / Prognosis
Upload / Advice
Perform
Engine
Inspections Ground Data
Local Support Update Engine Records
Diagnosis System
Distributed Aircraft
DAME
Maintenance Environment (DAME)
Diagnosis
and other systems

Request advice
Maintenance from MA
Engineer (ME)
Information / request
Investigate using for advice
Update Engine tools
Record
Provide
Remove engine and Diagnosis
dispatch for major overhaul / Prognosis
/ Advice
Request advice
Return overhauled from DE
engine to service Update Engine
Record Modify
System Configuration
Information Update Engine
Records

Maintenance Analyst (MA)

- maintenance expert

Data Center
(DS&S)
Engine Maintenance
Repair and Overhaul DAME Administrator
(MRO) Facility Data Center
(RR / Contractor) (DS&S)

Figure 1 DAME, actors and interactions

The interactions between the various users can be complex, particularly in
situations where additional tests are requested by the remote experts in order to
confirm a diagnosis.
The Maintenance Engineer (ME) uses the automated features of DAME in
carrying out diagnosis and minor engine maintenance in preparation for turn
round of the aircraft. The ME will receive diagnosis information automatically
from DAME and, if necessary, may request assistance from the Maintenance
Analyst via the DAME infrastructure for particular conditions.
The Maintenance Analyst (MA) uses DAME tools and services interactively to
determine the course of action and will inform the ME of the decision. If the MA
desires he can refer the condition to the Domain Expert for further advice.
The Domain Expert (DE) uses DAME tools and services interactively to
determine the course of action and will provide advice and informed decisions to
the MA and ME.
An overview of the typical diagnostic scenario including escalation to the remote
experts (Maintenance Analyst and possibly Domain Expert) is described below.
1. An aircraft lands and data from on-wing system (QUICK see [Nairac]) is
automatically downloaded to the associated local Ground Support System
(GSS).
2. QUICK and its GSS indicate whether any abnormality (this is a detected
condition for which there is a known cause) or novelty (this is a detected
deviation from normality for which there is currently no known cause) has
been detected.
3. DAME executes an automatic workflow to determine its diagnosis. This is
a standard pre-programmed diagnostic sequence.
4. Depending on the result of the QUICK and DAME automatic diagnoses
there are three outcomes:
a. Everything is normal – the engine is ready for the next flight.
b. A condition, which has a known cause, has been detected. This
can be resolved by immediate maintenance action or planned for
future maintenance action, as appropriate.
c. A condition, which currently does not have a clear cause, has been
detected or there is some ambiguity about the cause. This case is
referred to the remote experts (a Maintenance Analyst and possible
a Domain Expert) for consideration.

1.1.4 Involved resources

In the deployment of DAME, GridFTP may be used in the download of raw data.
The most intensive computing application is the use of the engine simulations –
the number of simulations will depend eventually on the demands of the Domain
Experts using the system.
All activities will all take place under control of the workflow system, which
orchestrates the DAME services and tools and transfers data between them.

1.1.5 Functional requirements

Remote experts may want to consider and review the current data, search and
review historical data in detail and run various tools including simulations and
signal processing tools in order to evaluate a particular situation. Each aircraft
flight can produce up to 1 Gigabyte of data per engine, which, when scaled to the
fleet level, represents a collection rate of the order of terabytes of data per year.
The storage of this data also requires vast data repositories that may be
distributed across many geographic and operational boundaries. DAME provides
a diagnostic infrastructure to allow enhanced condition monitoring and diagnosis
using geographically dispersed data, services and experts.
The significant requirements on the infrastructure are:
 The diagnostic processes require collaboration between Maintenance
Engineers, Maintenance Analysts and Domain Experts from different
organisations: airline, support contractors and engine manufacturer.
These individuals are geographically dispersed and need to deploy a
range of different engineering and computational tools to analyse the
problem.
 To allow appropriate access by users to the data from the engine under
consideration.
 To allow appropriate access by users to the terabytes of historical data
from the engine under consideration and other similar engines.
 The ability to search the vast stores of historical vibration and performance
data. Advanced pattern matching and data mining methods are used to
search for matches to novel features detected in the vibration data. These
services are able to operate on the large volumes of data and must be
able to return the results in a time that meets operational demands.
 Provide signal processing and engine simulation tools using data from the
engine or historical data.
 The diagnostic process must be completed in a timely and dependable
manner commensurate with the turn round times of the aircraft.
The DAME system is advisory so the data and results transfer must be reliable
and have integrity to be effective for the business case.

1.1.6 Security considerations

Elements of the raw data and data transferred between tools and services has
confidentiality requirements which must be protected during transfer.

1.1.7 Performance considerations

Significant network scenarios are:
a. Download of raw engine data from the aircraft to the ground – this starts
the automatic workflow for the DAME diagnosis for the Maintenance
Engineer.
b. The movement of raw data to its store on the ground, for various reasons
there are two options in early deployments:
a. Deployments where all data is moved to one centralised store.
Potentially, tens of terabytes of data per day from a worldwide
operation would eventually need to be transported over networks to
the central store and data management centre. Here the raw data
(high bandwidth) is effectively taken to the tools and services with
results (low bandwidth) being passed to the workflow system and
then on to the geographically dispersed users.
b. Deployments where a distributed store (at the airports) would be
used. Larger airport data stores would, potentially, need to store
 around 1Tb per day, if all aircraft landing produced data, however
the transfer would only take place over the local networks within the
airport. Tools and services would be locally resident at the airport.
Here the tools and services are taken to the raw data with results
being passed back to a centralised workflow system and then to the
geographically dispersed users.
All diagnoses and escalation through all experts must take place within the turn
round time of the aircraft, this includes all executed workflow including all service
execution and data transit times have to take place within the turn round time of
the aircraft.

1.1.8 Use case situation analysis

The system has been developed with industrial customers (Rolls-Royce plc and
Data Systems and Solutions LLC) and a proof of concept demonstrator
produced. Industrial deployment with is now in progress as part of the
BROADEN (Business Resource Optimisation for Aftermarket and Design on
Engineering Networks) project, this is a UK Department of Trade and Industry
(DTI) Inter Enterprise Computing Technology Call Project.

1.1.9 Acknowledgements
This work was undertaken as part of the DAME project, with grateful assistance
from Rolls-Royce plc, Data Systems & Solutions LLC and Cybula Ltd and the
teams at the Universities of York, Leeds, Sheffield and Oxford. This research
was supported by the UK Engineering and Physical Sciences Research Council
(Grant GR/R67668/01) and through contributions from Rolls-Royce plc, and Data
Systems and Solutions LLC.

1.1.10 References
[Austin] Austin, Jackson, et al, Chapter 5, Predictive Maintenance: Distributed
Aircraft Engine Diagnostics, in The Grid: 2nd Edition, edited by Ian Foster and
Carl Kesselman. MKP/Elsevier , Oct 2003.

[Nairac] Nairac A, Townsend N, Carr R, King S, Cowley P, Tarassenko L. A

system for the analysis of jet engine vibration data. Integrated Computer-Aided
Engineering, 53-65, 1999.