Title :
Conventional Methods and AI models for Solving an Industrial an Industrial Problem
Author :
Bustillo, Andrés ; Sedano, Javier ; Villar, José Ramón ; Curiel, Leticia ; Corchad, Emilio
Author_Institution :
Dept. of Civil Eng., Burgos Univ., Burgos
Abstract :
This study presents a research that identifies and applies unsupervised connectionist models in conjunction with modelling systems, in order todetermine optimal conditions to perform laser milling of metallic components. This industrial problem is defined by a data set relayed through sensors situated on a laser milling centre that is a machine-tool used to manufacture high value micro-molds and micro-dies. The results of the study and the application of the connectionist architectures allow the identification, in a second phase, of a model for the milling machine process based on low-order models such as Black Box, which are capable of approximating the optimal form of the model. Finally, it is shown that the most appropriate model to control these industrial tasks is the Box-Jenkins algorithm, which calculates the function of a linear system from its input and output samples.
Keywords :
artificial intelligence; dies (machine tools); laser beam machining; linear systems; milling; moulding; problem solving; Box-Jenkins algorithm; artificial intelligence models; high value micro-molds; industrial problem solving; laser milling centre; linear system; low-order models; machine-tool; metallic components; micro-dies; milling machine process; modelling systems; unsupervised connectionist models; Artificial intelligence; Hebbian theory; Laser modes; Manufacturing industries; Metalworking machines; Milling; Optical control; Optical materials; Principal component analysis; Vectors;
Conference_Titel :
Computer Modeling and Simulation, 2008. EMS '08. Second UKSIM European Symposium on
Conference_Location :
Liverpool
Print_ISBN :
978-0-7695-3325-4
Electronic_ISBN :
978-0-7695-3325-4
DOI :
10.1109/EMS.2008.106