建構一混合模式應用於塑膠射出成型產品方案排序

由於近年來溫室效應及能源資源短缺逐漸受到重視，加上全球產業環境快速的變化以及產品生命週期不斷的縮短之下，塑膠射出成型產品變化非常頻繁，企業必須不斷推出新產品來符合目前以及未來即將形成的消費市場，來獲取利潤與競爭地位。因此，本研究運用倒傳遞類神經網路解決塑膠射出成型產業之新產品成本、含碳量及回收率/再利用率預測問題，研究中先運用皮爾遜績差相關(Pearson Product-Moment Correlation)又稱Pearson相關係數找出原始資料變數之關聯性並決定類神經網路最佳預測之模型，精確預測塑膠射出成型產業的產品成本、含碳量及回收值，期望適時提供企業正確迅速的資訊。此外，為了瞭解新產品方案之績效評估，因此，本研究運用視覺化決策模型(Spherical Decision Model )又稱決策球模型(Decision Ball Models)發展新產品的績效評估模式。透過上述之分析，希望可以協助企業評選出兼具環保考量與經濟價值的產品。

關鍵字

塑膠射出成型； Pearson相關係數；倒傳遞類神經網路；視覺化決策模型

並列摘要

In recent years, the energy resources shortage and the effect of greenhouse is paid attention gradually. Injection plastic products are subjects to frequent variability due to the environment is fast changed, and the products life cycle is constantly short for the global industry. The enterprises must provide the new products to fulfill the present and future consumer market constantly, to obtain profits and competitiveness. For this reason, the study focuses on the neural network to solve the problem concerned with cost, carbon content and recycling estimation for new products for the plastic injection molding industry. First, the study the Pearson Product-Moment Correlation was used to solve the problem concerned with to find the relatedness of Original variable data in order find the optimum forecast model of neural network. The utilization of optimum forecast model of neural network was aimed at precise estimation of production cost, carbon content and recycling / reuse for plastic injection molding, expected to timely provide quickly correct information for the business. Second, in order to understand the new product's performance evaluation program, this study focuses on the Decision Ball Models to develop the performance evaluation model for the new product. With the analysis provided above, We expect to help enterprises to select the appropriate product which can fulfill the green environmental protection and economic benefits simultaneously.

並列關鍵字

Plastic injection molding ； Pearson Product-Moment Correlation ； Back-Propagation Neural Network (BPNN) ； Decision Ball Models

參考文獻

[8] H. Abe and S. Tusmoto, Analyzing Behavior of objective Rule Evaluation Indices Based on Pearson Product-Moment correlation coefficient, Ph.D. Thesis, Shimane University , Izumo Shimane, 2008, pp. 84-89.

[9] S. M. Al-Salem, Lettieri, P. Baeyens, “Recycling and recovery routes of plastics solid waste (PSW): A review,”Waste Management, vol. 29, 2009, pp. 2625-2643.

[10] Z. Ayag and R. G. Ozdemir, “A hybrid approach to concept selection through fuzzy analytic network process,” Computers and Industrial Engineering, vol 56, no.1, 2009, pp. 368-379.

[11] S. M. Brenner, “Practical R&D Project Prioritization,” Research Technology Management , vol. 137, no. 5, 1994 , pp. 38.

[12] B. Jürgen, “Neural networks for cost estimation：Simulations and Pilot application,” International Journal of Production Research, vol. 38, no. 6, 2000 pp. 1231-1254.

國際替代計量

建構一混合模式應用於塑膠射出成型產品方案排序

未授權

主題瀏覽