Optimization of tensile strength in injection molded polyamide-6 pieces using neuronal network techniques and non-linear programming

The main objective of this research is the optimization of tensile stress of injection molded parts of polyamide-6 to establish process conditions that maximize tensile strength of parts in a real industrial process. The methodology consisted in development of assays based on I-optimal experimental...

Descripción completa

Detalles Bibliográficos
Autor: ROBERTO ZITZUMBO GUZMAN
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2018
País:México
Institución:Centro de Innovación Aplicada en Tecnologías Competitivas
Repositorio:Repositorio Institucional de CIATEC
Idioma:inglés
OAI Identifier:oai:ciatec.repositorioinstitucional.mx:1019/161
Acceso en línea:http://ciatec.repositorioinstitucional.mx/jspui/handle/1019/161
Access Level:acceso abierto
Palabra clave:info:eu-repo/classification/LEMD/Polímeros
info:eu-repo/classification/LEMD/Poliamida
info:eu-repo/classification/cti/7
info:eu-repo/classification/cti/33
info:eu-repo/classification/cti/3312
info:eu-repo/classification/cti/331210
Descripción
Sumario:The main objective of this research is the optimization of tensile stress of injection molded parts of polyamide-6 to establish process conditions that maximize tensile strength of parts in a real industrial process. The methodology consisted in development of assays based on I-optimal experimental design to get a data base. Four parameters were considered as inputs: injection holding pressure, injection packing time, % wt virgin material and % wt recycled material. Measurement of maximum tensile stress in parts was made according to ISO 527-1 standard. Three models were developed by the techniques Response Surface Methodology, Back Propagation Neural Network and Generalized Regression Neural Network to predict parts maximum tensile stress. Finally, the best model (with lowest forecasting error) was optimized by Trust Region Method Based on Interior Point Techniques for Nonlinear Programming to maximize tensile strength. This proposed methodology is capable for modeling the process with low error and for stablish process conditions to obtain the maximum tensile stress on molded parts. Keywords: Plastic Injection Molding; Tensile stress; Polyamid-6; Response Surface; Backpropagation Neural Network; Generalized Regression Neural Network; Nonlinear programming.