DEVELOPMENT OF AN ARTIFICIAL INTELLIGENCE PLANNER FRAMEWORK FOR BESPOKE PRECAST CONCRETE PRODUCTION

Precast concrete industry is highly involved in construction projects through the supply of bespoke products. It delivers many advantages to the construction industry in terms of saving time, cost, and reducing congestion on construction sites. However, precast manufacturers are facing a substantial problem of long customer lead-time for bespoke concrete products. Most of time and effort is spent on a long production process consisting of product design, production planning, and shop floor manufacturing. Also, variations in the process due to many uncertainties, many parties and human involvements extend buffers of the customer lead-time. Lean construction concepts that are adapted for the unique production system of construction work recognize the above problem as waste and directly aim to eliminate them. Complying with the concepts, the authors have proposed an automatic planning system called artificial intelligence planner (AIP). The AIP retrieves product data from design process for the automatic planning process. In order to develop requirements and specifications of the AIP, this paper concisely describes precast design and production planning processes from a case study of a precast company. Artificial intelligence and flow-shop scheduling techniques that provide development background are reviewed. Also the components of the AIP are described. The AIP is expected to reduce the customer lead-time, assist precast manufacturers to manage changes in product requirements and/or delivery dates; therefore, the construction industry will share the benefits.

[1]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[2]  Tarek Hegazy,et al.  Neural networks as tools in construction , 1991 .

[3]  Tarek Hegazy,et al.  DBID: Analogy‐Based DSS for Bidding in Construction , 1993 .

[4]  Miroslaw J. Skibniewski,et al.  Estimating construction productivity: neural-network-based approach , 1994 .

[5]  Wallace J. Hopp,et al.  Factory physics : foundations of manufacturing management , 1996 .

[6]  Hojjat Adeli,et al.  Regularization neural network for construction cost estimation , 1998 .

[7]  Lauri Koskela,et al.  Management of production in construction: A theoretical view , 1999 .

[8]  Carlos T. Formoso,et al.  Method for Waste Control in the Building Industry , 1999 .

[9]  Gregory A. Howell,et al.  WHAT IS LEAN CONSTRUCTION - 1999 , 1999 .

[10]  Lucio Soibelman,et al.  Generating Construction Knowledge with Knowledge Discovery in Databases , 2000 .

[11]  Chi Ming Tam,et al.  Comparative study of artificial neural networks and multiple regression analysis for predicting hoisting times of tower cranes , 2001 .

[12]  Sou-Sen Leu,et al.  Ga-based resource-constrained flow-shop scheduling model for mixed precast production , 2002 .

[13]  Glenn Ballard,et al.  An application of lean concepts and techniques to precast concrete fabrication , 2002 .

[14]  Weng Tat Chan,et al.  Production Scheduling for Precast Plants using a Flow Shop Sequencing Model , 2002 .

[15]  Nico Vandaele,et al.  Advanced Resource Planning , 2003 .