Abstrak

The maintenance scheduling problem has been previously tackled
by various traditional optimization techniques. Lots of research has been done on strategies finding optimal maintenance schedules. Much less attention is turned to optimizing malfunction machine repair plan.

In this paper, we propose a new method for machine repair planning using hybrid genetic algorithm including tabu-search, as well as continuous assessment and prediction of time performance of technicians. A Genetic Algorithm based optimization procedure is used to search for the most time-effective maintenance planning, considering urgency of repair orders, distribution of works and performance of technicians. Performance of technicians are generated using a simple machine learning algorithm.