Structuring and Analysis of the Injection Molding Process for the Neural Network- using the Taguchi Method
| Autor: | Li Yeung-Chang, 李永昌 |
|---|---|
| Rok vydání: | 2002 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 90 The purpose of this thesis is to carry out the optimal injection molding process by using Polyether Ether Ketone (PEEK) which is the most advanced material in the plastic industry. PEEK has been widely used by the semiconductor industry due to its excellent anti-chemical and stabilized property. In this research, the Taguchi Quality Design Method, Back Propagation Neural Network and General Regression Neural Network are integrated and used in the injection molding process. The purpose is to improve the accuracy of injection molding and minimize the dimensional errors. In the meantime, the Taguchi Method is used to structure the test plan and on the other, the control factors of molding temperature, screw pitch, injection pressure, injection speed, screw RPM, the holding pressure, the holding time and the cooling time are used to analyze to what extent the processing parameters would work on the product quality in order to elevate the product quality with optimal processing parameters. In the meantime, the obvious factor affecting the injection quality will be used to structure the neural network prediction system on the one hand and on the other, to carry out micro adjustment with the processing parameters obtained from the Taguchi Method so as to accomplish much better quality. The test has indicated that the average dimension value of screw outer diameter produced by the optimal processing parameters is much closer to the target than the existing conditions. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|