Neural-Fuzzy Approach to Optimize Process Parameters for Injection Molding Machine

Injection molding technology should assure a high level of quality control of the molded parts in an automated way. Inherent complexities of the process make mathematical modeling difficult, hindering the control quality demands of conventional methods. Neural Network adaptive data based technology has been successfully applied in industrial applications since these rely on highly nonlinear modeling systems and are able to provide enough rich data for high control models the required process relationships. The focus of this paper is a Neural-Fuzzy approach for optimizing injection molding parameters settings. The approach consists of design of experiments (DOE) and Neural-Fuzzy systems.