[Home] [Project Overview] [Members] [Latest] [Press News] [Presentations] [Papers] [Links]

 

Home

Project Overview

Management

Latest

Press News

Presentations

Papers

Links

Project Overview

DAME will develop a generic test bed for Distributed diagnostics that will be built upon grid-enabled technologies and web services.  The generic framework will be deployed in a proof of concept demonstrator in the context of maintenance applications for civil aerospace engines. The project will draw together a number of advanced core technologies, within an integrated web services system:


AURA Advanced Uncertain reasoning architecture for Pattern Matching (York)
QUOTE neural network based techniques for real-time monitoring applications (Oxford)
CBR- Case based Reasoning systems for intelligent decision support (Sheffield)
Web services Architecture based on Globus open architecture protocols (Leeds)

DAME will address a number of problems associated with the design and implementation of On-line decision support systems.  The most significant of these are access to remote resources (experts, computing, knowledge bases etc), communications between key personnel and actors in the system, control of information flow and data quality, and the integration of data from diverse global sources within a strategic decision support system.
The new web services model for information brokerage on the Internet offers an inherently pragmatic framework within which to address these issues.  DAME will exploit emerging open standard web service architectures over a GRID network to demonstrate how the data management aspects of maintenance support systems can be handled within a unified knowledge broker model.

The The project builds on a key metropolitan grid infrastructure, the White Rose Computational Grid (WRCG), currently under construction between the partner institutions Leeds, Sheffield and York at a cost of 2.8M. The essential theme of this project is real-time intelligent feature extraction, intelligent data mining and decision support techniques, where expertise and software tools are distributed across the Grid. The enormity of the databases and the need for distributed access to the data make this a particularly challenging problem for the Grid.

Summary: Aims

The project has the following aims:

  To develop a Distributed Diagnostic Grid Test-bed.

  To demonstrate the benefits of the Grid test-bed on a realistic Rolls-Royce Aircraft Engine Maintenance scenario.

  To design and build a system architecture for distributed diagnostic support that takes advantage of the Grid middleware, focusing particularly on the management of the data within the Grid.

  To study, and increase understanding of, the performance issues associated with data grids (e.g. data replication).

  To design a distributed data store for unstructured, non-indexed data

  To develop Grid-enabled fault identification and diagnostic methods

Home

Send mail to tom.jackson@cs.york.ac.uk with questions or comments about this web site.
Last modified: September 11, 2003