Objective
Time spent by airline maintenance operators to solve engine failures and the related costs (flight delays or cancellations) are a major concern to SNECMA which manufacture engines for civilian aircraft such as BOEING 737s and Airbus A340s. The use of an intelligent diagnostic software contributes to improving customer support and reduces the cost of ownership by improving troubleshooting accuracy and reducing aeroplane downtime. Our goal is to improve the development of troubleshooting systems by extracting decision knowledge from cases through Case Based Reasoning and Data Mining. New problems are solved by searching for similar problem solving experiences and by adapting the solutions that worked in the past.
THE EXPERIMENT
The experiment is to improve the development of Case Based Reasoning (CBR) and Data Mining (DM) software by improving the quality of the technical information that is fed into the system. Classical maintenance databases do not contain information that can be directly used by a CBR & DM system or it is in a form that is hardly usable (ex: free text). The goal of the PIE is to collect structured information about engine failures (i.e. cases) that is of a high quality. The case quality will be monitored through a steering committee of specialists and will be ensured by collecting quality information at the source. We will thus set-up the application at a customer's site (an airline). The major steps of the experiment are the following :
- definition of the case engineering methodology
- definition of an organisation to collect failure cases and to monitor their quality
- setting up of a pilot application at a customer's site for joint testing,
- measuring the resulting improvements & disseminating the results
The CBR software is developed by our subcontractor Acknosoft, an SME that is specialised in building decision support software from case history.
EXPECTED IMPACT AND EXPERIENCE
It is expected that the completion of the PIE will improve the process by which we develop quality decision support systems by obtaining better case descriptions and setting up an organisation to monitor their quality. The experience gained in the aircraft industry will contribute to raise the case quality culture and will enable a large scale deployment of CBR & DM technologies in other industries as well.
Fields of science
- natural sciencescomputer and information sciencessoftware
- natural sciencescomputer and information sciencesdatabases
- humanitieshistory and archaeologyhistory
- engineering and technologymechanical engineeringvehicle engineeringaerospace engineeringaircraft
- natural sciencescomputer and information sciencesdata sciencedata mining
Call for proposal
Data not availableFunding Scheme
ACM - Preparatory, accompanying and support measuresCoordinator
75724 Paris
France