Facilities Layout in Uncertainty Demand and Environmental Requirements by Machine Learning Approach
Abstract
Facility layout optimization plays a crucial role in manufacturing efficiency and environmental impact. However, traditional approaches often struggle when dealing with uncertain demand patterns and stringent environmental regulations. This paper proposes a novel framework for facilities layout design that integrates machine learning (ML) with traditional optimization techniques. The framework accounts for demand uncertainty and environmental considerations, leading to a more robust and sustainable facility layout. The methodology employs a two-stage approach: 1) demand forecasting with a chosen ML algorithm and 2) layout optimization using a genetic algorithm with objective functions incorporating environmental factors alongside traditional metrics like material handling cost and flow time. The paper presents a numerical case study to illustrate the effectiveness of the proposed framework. The results demonstrate that the ML-driven approach generates layouts that are both adaptable to demand fluctuations and minimize environmental footprint compared to traditional methods. Finally, the paper discusses limitations and future research directions in this emerging field.