Innovative production planning system for bespoke precast concrete products

摘要

Bespoke precast concrete products are increasingly becoming major components of construction projects. This is mainly because offsite prefabrication and production offer a unique opportunity for innovation and cost savings for construction projects. The workload in the precast industry is a complex combination of uniquely and identically designed products, which have various delivery dates. The production process from design to manufacturing contains uncertainties due to many factors such as: multi-disciplinary design, progress on construction site, and requirement of costly purpose-built moulds. In this context, this research is aimed to improve the efficiency of the process by addressing the production planning because it has a significant impact to the success of the business. An innovative planning system and its prototype called 'Artificial Intelligence Planner' (AIP) is being developed. The manufacturing process model is mathematically formulated according to current practices, characteristics and scheduling logics. Two artificial intelligent techniques: Genetic Algorithm (GA) and Neural Network (NN) have been implemented in AIP to enhance data analyses and decision supports for production planning. GA is used in the optimization to search for optimal schedules and NN based estimation is applied to estimate the processing time required for any individual unique product design. The outcomes of the research include shortened customer lead-time, optimum factory's resource utilization, and in-house repository of production knowledge.