Optimization of injection molding process parameters by a hybrid of artificial neural network and artificial bee colony algorithm

This paper presents a hybrid of artificial neural networks and artificial bee colony algorithm to optimize the process parameters in injection molding with the aim of minimize warpage of plastic products. A feedforward neural network is employed to obtain a mathematical relationship between the proc...

Descripción completa

Detalles Bibliográficos
Autores: Alejandro Alvarado Iniesta, Jorge L. García Alcaraz, Manuel Iván Rodríguez Borbón
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2013
País:México
Institución:Universidad Autónoma de Ciudad Juárez
Repositorio:Redalyc-UACJ
OAI Identifier:oai:redalyc.org:43029146004
Acceso en línea:https://www.redalyc.org/articulo.oa?id=43029146004
Access Level:acceso abierto
Palabra clave:Ingeniería
injection molding
finite element simulation
artificial neural networks
Artificial bee colony algorithm
optimization of process parameters
Descripción
Sumario:This paper presents a hybrid of artificial neural networks and artificial bee colony algorithm to optimize the process parameters in injection molding with the aim of minimize warpage of plastic products. A feedforward neural network is employed to obtain a mathematical relationship between the process parameters and the optimization goal. Artificial bee colony algorithm is used to find the optimal set of process parameters values that would result in the optimal solution. An experimental case is presented by coupling Moldflow simulations along with the intelligent schemes in order to validate the proposed approach. Melt temperature, mold temperature, packing pressure, packing time, and cooling time are considered as the design variables. Results revealed the proposed approach can efficiently support engineers to determine the optimal process parameters and achieve competitive advantages in terms of quality and costs.