Automated knowledge discovery in facility layout planning

Abstract

This paper proposes a novel methodology for facilities layout planning and optimization in which fitness evaluation of layout alternatives is done in an automated manner using an artificial neural network trained to user preferences. The intrinsically uncertain, unstructured, and often tacit nature of facilities layout design preferences and constraints necessitates the use of domain experts in the fitness evaluation of layout alternatives. However, unavailability of domain experts in a timely or economical fashion highlights the need for resorting to the use of automation in this important area. To test the key novel component of the proposed approach, a variety of artificial neural networks are trained on a large data set containing both qualitative and quantitative fitness of layout alternatives and subjective ranking by a domain expert utilizing the knowledge of the application domain. Simulation results strongly support the viability of the proposed concept. Such an automated approach to fitness evaluations of layout alternatives is expected to significantly improve the efficacy and efficiency of the facilities layout planning process. Furthermore, such an approach would spur the much sought for research in decision support and expert systems in layout planning.