Neural Networks as Tools in Construction

TLDR

The construction industry’s competitive, risk‑averse nature and heuristic problem‑solving needs have driven the adoption of AI tools, including expert systems, while recent neural‑network research offers powerful supplements to these conventional systems. This paper proposes neural networks as a promising management tool to enhance automation in construction, complementing existing expert systems. The authors describe basic neural‑network architectures, discuss their potential construction applications, develop a markup‑estimation model, and outline future integration with expert systems. The study finds that expert‑system performance in construction over the past decade remains far from ideal.

Abstract

The competitive and risk‐averse nature of the construction industry and its heuristic problem‐solving needs, among other reasons, have contributed to the development of nontraditional decision‐making tools. Research in artificial intelligence (AI), a branch of computer science, has provided more suitable tools to the construction industry. Expert systems have steadily been introduced for different applications in the industry. However, the performance of these systems during the last decade, is far from ideal. Neural networks research in AI has recently provided powerful systems that work as a supplement or a complement to such conventional expert systems. In this paper, neural networks are introduced as a promising management tool that can enhance current automation efforts in the construction industry, including expert systems applications. Basic neural network architectures are described, and their potential applications in construction engineering and management discussed. A neural network application is developed for optimum markup estimation. Future possibilities of integrating neural networks and expert systems as a basis for developing efficient intelligent systems are described.