Genetic Algorithms and Grouping Problems
Genetic Algorithms and Grouping Problems
Knowledge-based injection mold design automation
Knowledge-based injection mold design automation
Evolving product form designs using parametric shape grammars integrated with genetic programming
Artificial Intelligence for Engineering Design, Analysis and Manufacturing
Runner sizing in multiple cavity injection mould by non-dominated sorting genetic algorithm
Engineering with Computers
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Evolutionary Optimization of Plastic Injection Mould Cooling System Layout Design
ISDEA '10 Proceedings of the 2010 International Conference on Intelligent System Design and Engineering Application - Volume 01
| Hi-index | 0.00 |
Family Mould Cavity Runner Layout Design (FMCRLD) is the most demanding and critical task in the early Conceptual Mould Layout Design (CMLD) phase. Traditional experience-dependent manual FCMRLD workflow causes long design lead time, non-optimum designs and human errors. However, no previous research can support FMCRLD automation and optimisation. The nature of FMCRLD is non-repetitive and generative. The complexity of FMCRLD optimisation involves solving a complex two-level combinatorial layout design optimisation problem. Inspired by the theory of evolutionary design in nature ''Survival of the Fittest'' and the biological genotype-phenotype mapping process of the generation of form in living systems, this research first proposes an innovative evolutionary FMCRLD approach using Genetic Algorithms (GA) and Mould Layout Design Grammars (MLDG) that can automate and optimise such generative and complex FMCRLD with its explorative and generative design process embodied in a stochastic evolutionary search. Based on this approach, an Intelligent Conceptual Mould Layout Design System (ICMLDS) prototype has been developed. The ICMLDS is a powerful intelligent design system as well as an interactive design-training system that can encourage and accelerate mould designers' design alternative exploration, exploitation and optimisation for better design in less time. This research innovates the traditional manual FMCRLD workflow to eliminate costly human errors and boost the less-experienced mould designer's ability and productivity in performing FCMRLD during the CMLD phase.