Computational Intelligence Approaches for Improving Serviceability of Material Handling Systems

The level of the serviceability of material handling systems can be measured by the effectiveness of completing each service request in terms of time and cost, and the speed of auto-recovery from any unexpected disturbance to the process of completing a service. In this paper, computational intelligence approaches based on ant colony system and genetic algorithm are investigated to perform auto-recovery for the supervisory control of a complex automated material handling facility (AMHF) in a dynamic environment. In addition, Dijkstra´s algorithm, is also introduced to evaluate the proposed computational intelligence approaches with positive results. The strengths and weaknesses of each algorithm are analyzed to determine the suitable applications of each algorithm. A single data representation of the actual AMHF database provided the comparison basis for evaluation of proposed approaches. The test results demonstrated the viability of using computational intelligence approaches to achieve optimal solutions within an acceptable computing time, and therefore can be successfully applied to improve the serviceability of AMHF.