DAME: A Distributed Diagnostics Environment for Maintenance Professor Jim Austin/Dr Tom Jackson...

DAME: A Distributed Diagnostics Environment for Maintenance

Professor Jim Austin/Dr Tom Jackson

University of York

Distributed Aircraft Maintenance Environment - DAMERR Grid Forum Meeting, September 12th

Demonstrator Status

• Mid Term Demonstrator just completed– Grid Portal providing access to DAME Diagnostic Grid

Services– Broad range of applications ported to Grid services, including

RR engine models, commercial CBR tools, data mining technologies, and databases;

– Built on Globus Toolkit 3 OGSA/OGSI model (DAME was an early adopter of GT3)

– Fully deployed on White Rose Grid– Populated with data to support ‘Bird Strike’ diagnosis


Portal Environment

The DAME portal provides hosting environment for all the diagnostic activity and data analysis, and also:

– Manages issues of distributed diagnosis team and virtual organisations

– Manages DAME automatic workflows and manual interaction with the diagnosis toolkit

– Manages issues of security and user roles, based on GT3 security and certification (X509)


DAME Architectural Overview

QUOTE

Data-Mining

Signal

Processing

Case BasedReasoning

NovelData

Ra

wE

ngin

eD

ata

VibrationShaft Speed

Fuel Flow

Ser

vice

Dat

a

Par

tsD

ata

Grid Services ManagementModelling/Simulation

Ope

ratio

nal

Dat

a

The Grid

...

AURA-G

DAMEGrid Portal


WRG Distribution

Leeds

Grid Middleware Services

Sheffield

Modeling & Decision Support

DAME WRGSign-on Portal

SDMDatabase

CBRAnalysis-GEngineModel-G

GT3 ServiceCBR advisor

GT3 ServiceBD25 Enginemodel wrappedas Grid Service

XTO-G

GT3 ServiceXTO plug-ins via a GridService

DataVisualiser

GT3 ServiceJchart Viewer forviewing XTO output

Workflow

Browser basedworkflow tool.Compliant withResource Broker

Resource BrokerGT2 ServiceSchedule workflowtasks on WRGresource

Oxford

Engine Data Store

Engine DataDatabase

York

Data Mining Services

AURA-GAURA-GDatabase

DataStore-GGT3 ServiceSimulates arrival &storage of QUOTEdata

Zmod Viewer

GT3 ServiceBrowser based dataviewer for zmod files

GT3 ServiceZmod datasearch facility

Collaboration tools

GT3 ServiceToolset for multiusercollaboration

WRGGT3/2

WRGGT3/2

WRGGT3/2

WRGGT3/2

DAME workbench

SecurityGT3 SecurityServiceProxy-Management

DAME GUI

GT3 ServiceBrowser based GUIto DAME services


Fundamental work flow

• Three major stages to DAME:• Take vibration data from all engines in flight

– Detect• events on that engine that look unusual

– Search• for similar events on other engines that are known about or not

known about

– Reason• Using historical data that is associated with past similar events


Tools

• Detect:– Uses a QUOTE on wing statistical classifier system –

Oxford University

• Search:– Uses AURA pattern matching methods to search large

vibration data sets - York

• Reason:– Uses CBR tools based on existing technology– Uses Engine model– Uses signal processing system


Event detection

• Uses the Quote systemDeveloped by Oxford University.

• Uses various methods to detect possible

events on the engine.

• On wing system, highlighting where an incident may be.


Zmod data


Data Mining Services

• The AURA correlation matrix technology is used for rapid pattern matching– Rapid data mining is pivotal to DAME diagnosis process

• Provides capability for massively parallel search on vast datasets of ZMOD vibration data;

• Built on mature AURA technology, but now deployed as a Grid service.


The AURA system

Data

Dat

a A

dapt

orS

tore

Se

arc

h

Inp

ut

pa

tte

rn

Candidate Engine(Back check)

Indexer

Output pattern

AURASearchEngine

Results

binary

Store & Search

Store &

Search

Indexes or Data

Result

Store

AURA Search Process


Data Mining Services, cont

• Interactive front end developed for AURA search engine– Allows direct search on raw vibration features;

• AURA-G is a two-tier architecture.– First tier hosts a generic

AURA service– Second tier containing application

specific code

• Clients interact directly with thesecond tier, allowing applicationdevelopers to abstract away fromthe pattern matching domain.


Case Based Reasoning

CBR service is provided via a Grid service interface to a commercial CBR package(Orenge, by Empolis);

A Service Factory supports the creation of multiple CBR instances

– Permits many CBR processes to be executed in parallel from a single service access point

CBR provides decision support for fault ranking and workflow advice;

Knowledge Model

Case Indexer

Indexed casebase

Fault and Maintenance

Data

CBR Process Managers

CBR Broker

Instance of

CBR SERVICE

Instance of

CBR SERVICE

Instance of

CBR SERVICE

Instance of

CBR SERVICE

Instance of

CBR SERVICE

Indexed casebase

Indexed casebase

CBR Service Factory


Engine Model Service

RR thermo-dynamic engine performance simulation deployed as a Grid service, through interactive JAVA application.

Provides simulation of different flight operational conditions and requirements, e.g. Idle, Take-off, Climb

The Factory Service can generate a group of engine simulation instances for different client requirements.

Both Transport Level and Message Level Security are implemented to protect the secure sensitive engine model and user data.


Signal Processing Services

• Grid based deployment of the vibration analysis algorithms.

• Provides:– Opportunity for finer grain analysis;– More powerful algorithms;– Testing environment for

development of newalgorithms;


Workflow Engine

• Workflow Engine providesmanagement of manual andautomated workflows.

• Also handles certificationand role management

Browser

Portal

WorkflowManager

RoleDatabase

MyProxyServer

XTO CBR

Broker

Aura-G

EventGenerator

WorkflowCredential

EngineData Store

EngineModel

SDM toXTO


Brokering and SLA’s

• Brokerage system is used for job allocation on available Grid resource

• Due to commercial application domain, broker should also demonstrate capability to manage QoS issues, and specifically Service Level Agreements (SLA’s)


Brokering and SLA’s, cont

• Use an SLA negotiation meta-service to negotiate SLAs

• Use a monitoring service – policing mechanism

• Integrate with GGF Grid Economic Architecture


Dependability Issues

• Contribute to the GRID community dependability and security studies, where possible.

• Provide dependability and security analysis to support the ultimate deployment of DAME as a working engine diagnosis environment.

• If possible, provide a basis (identify good practices) for dependability and security analysis for the deployment of DAME as a working diagnosis environment for other domains e.g. medical.

• Dependability analysis has meant need for business process analysis, asset identification, risk identification.


Dependability Issues, cont

UploadEngineData

Information / request for advice

MaintenanceEngineer (ME)

Domain Expert (DE)- engine expert

DAMEDiagnosis

PerformMinor Repair

Investigate using tools

ProvideDiagnosis

/ Prognosis/ Advice

Remove engine anddispatch for major overhaul

Return overhauledengine to service

Request advicefrom MA

Update EngineRecord

GroundSupportSystem

DowloadEngineData

LocalDiagnosis

Distributed AircraftMaintenance Environment (DAME)

- Miscellaneous Providers.

Engine Data Center (EDC) - DS&S

Service Data Manager (SDM) including Workscope Generator- RR

Maintenance Analyst (MA)- maintenance expert

Investigate usingtoolsUpdate Engine

RecordProvide

Diagnosis/ Prognosis

/ Advice

Airline / Maintenance Contractor(at Airport)

Engine MaintenanceRepair and Overhaul

(MRO) Facility(RR / Contractor)

Remote / DistributedTools and Services

EngineManufacturer

(RR)

Data Center(DS&S)

Request advicefrom DE

Update EngineRecords

Information / requestfor advice

Update Engine Records

PerformInspections


GT3 Experiences

• Transition from web services to OGSA grid services reasonably straight forward;

• However, poor documentation and technical support in early GT3 releases;

• Fairly substantial changes in OGSA/OGSI spec between releases (e.g. registry definitions);

Demonstrator DetailDr. Tom Jackson


Demonstrator Detail

• Portal provides role based access to diagnostic data and tools

Maintenance Engineer Maintenance Analyst


Automatic Workflow

• Arrival of QUOTE data with ‘Novelty’ initiates an automatic workflow in DAME

• Attempt to match current fault conditions with historic data for initial diagnosis

• Four stages to automatic workflow– Assessment of data with ground based feature analysis

service (XTO)– Aura-G pattern match ‘find one similar’– Search of Service Data Manager for fault records– Ranking of recovered data into fault hypothesis list

• Diagnosis available to ME and to MA


Maintenance Analyst

• Work list of escalated engines• Can work on multiple engines simultaneously


Toolset available

• MA has access to following toolset:

– CBR Analysis

– Feature Detection Algorithms

– Engine Model Service

– Data search and visualisation

• MA aided by CBR decisionsupport service (work flowadvice)


Toolbench, cont

• Portal


Future Work

• Development of work-flow manager in the portal, for flexible workflow configuration;

• Further analysis of dependability properties, including detailed studies on timeliness properties and security issues;

• Larger scale database deployment, and possible OGSA-DAI development;

• Further development of Grid monitoring services as basis for SLA and brokering;

• Continued development of data mining capability;• Enhanced data visualisation and processing

capability.


Thanks…

The development team:

Further info: http://www.cs.york.ac.uk/dame

Jeff Allan Bojian Liang

Richard Bagshaw Sarfraz Nadeem

Vernon Bailey Max Ong

Rob Davis Andy Pasley

Martyn Fletcher Xiaoxu Ren

Iain Gourlay Duncan Russell

Georges Honore Martin Thompson

John Hodrien Simukai Utete

Mark Jessop Julian Young

Date post:	25-Dec-2015
Category:	Documents
Upload:	april-watkins
View:	219 times
Download:	0 times

DAME: A Distributed Diagnostics Environment for Maintenance Professor Jim Austin/Dr Tom Jackson...

Documents