Details of Grant 

EPSRC Reference:	GR/K84257/01
Title:	ON-LINE NEURAL NET FAULT DIAGNOSIS FOR DIESEL ENGINES
Principal Investigator:	Sharkey, Dr A
Other Investigators:	Sharkey, Professor N Saunders, Mr R Fleming, Professor PJ Kadirkamanathan, Professor V
Researcher Co-Investigators:
Project Partners:	Lloyd's Register Pre Nexus Migration Rolls-Royce Plc
Department:	Computer Science
Organisation:	University of Sheffield
Scheme:	Standard Research (Pre-FEC)
Starts:	01 March 1997	Ends:	30 June 2000	Value (£):	182,497
EPSRC Research Topic Classifications:	New & Emerging Comp. Paradigms
EPSRC Industrial Sector Classifications:	Aerospace, Defence and Marine Financial Services
Related Grants:
Panel History:
Summary on Grant Application Form
The main aims of the proposed research are (i) to establish a set of general practical principles for improving the accuracy and reliability of neural computing techniques; and (ii) to establish the viability of a reliable online neural net fault prediction and diagnosis system for internal combustion (diesel) engines.A variety of faults would be physically induced in a real diesel engine through systematic modifications of that engine. Data corresponding to each fault would be collected, using in-cylinder pressure, acoustic vibration, and noise emission as the main fault indicators. Samples of this data would be used to train neural nets to identify different engine faults. The reliability of any neural net solution would be increased by combining neural nets to form ensembles in which the combined performance was better than the nets considered individually. This situation can be achieved when the nets in an ensemble exhibit a degree of diversity whereby their errors are uncorrelated. Research would focus on the comparative analysis and development of techniques for the creation of diverse nets, on methods for combining ensembles of nets, and on the most effective way to distribute the task to sets of specialist fault detectors.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.shef.ac.uk