Estimation of Process Parameters Using QFD and Neural Networks in Injection Molding

The injection molding process is able to produce high precision manufactures as a single process with fast speed. However, the prices of both the mold and the molding machine are expensive, and the single process is very complex and difficult to compose of the exact relationship between the process setting conditions and the product quality. Therefore, the quality of a molded product often depends on a skillful engineer’s operations in the design of both parts and molds. In this paper, the relationship between the process conditions and the defectiveness is built for better manufactures under settings of the appropriate parameters, and so it can reduce the setup time in the injection molding process. Quality Function Deployment (QFD) provides severe defectiveness factors along with the related process parameters. Also, neural networks estimate the relationship between defective factors and process setting parameters, and lead to reduce the defectiveness of molded parts. 1) Keyword: injection molding, QFD, neural networks, defective factors, process parameters