| KBS-IMPROVE | This project is closed |
| Improving Maintenance Scheduling Through Knowledge Based Simulation |
|
Context Maintenance of production equipment is rapidly becoming the largest indirect cost for manufacturers. This contrasts with falling direct costs through greater automation and reduced work-in-progress. A key element of the maintenance process is the scheduling of maintenance tasks. If performed effectively these reduce the loss of throughput caused my machine failure and reduces the need for buffer stocks. Maintenance scheduling is a very complex task that relies on the judgement of the supervisor. A means of improving the performance of supervisors in this task would reduce manufacturing costs and improve throughput. Aims To develop a means of determining the scheduling strategies used by maintenance supervisors Find a way to predict the effect of alternative decision making strategies on key performance measures of a manufacturing system. Improve maintenance scheduling by comparing alternative decision making strategies. Method The research will use a combination of simulation and artificial intelligence systems to represent the maintenance supervisors decision making strategies. A detailed model of a particular Ford facility will be developed. The response of maintenance supervisors to typical maintenance scenarios will be recorded, used as inputs to simulations, and the consequences used to train neural nets and rule-based expert systems. Benefits An improvement in the decision making strategy of maintenance supervisors will lead to increased throughput, reduced maintenance costs and buffer stock. It will be possible to create maintenance strategies prior to the commissioning of new plant, so that optimum maintenance activities can be implemented from start-up. Participants Warwick Business School Aston University Ford Motor Company Lanner Group |
|
|
|
|
|
|
|
|