Optimized material management in construction using multi-layer perceptron

Abstract

Construction material represents a major component of the project cost. Therefore, it is essential to control material on construction job sites. Efficient material management system requires trade-offs and optimized balance among elements of material cost including purchase cost, storage cost, opportunity cost, ordering cost, and unavailability cost. Thus, there is a need to develop an automated method for optimizing the delivery and inventory of construction materials not only in the planning phase but also in the construction phase to account for introduced changes. In this research a novel genetic algorithm – multi-layer perceptron (GA-MLP) method is proposed to generate optimized material delivery schedule. Multi-layer perceptron (MLP) is utilized to improve genetic algorithm (GA) by generating memory to overcome local minima encountered in applying GA for optimization. This automated method supports contractors to buy construction materials with the least cost and without leading to material shortage or surplus. The proposed automated method has been validated through a numerical example. The obtained results demonstrate that GA-MLP outperform GA in optimizing construction material inventory.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 18 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.