塑膠射出成型是一項高度非線性之製程，有許多因素會對產品品質造成影響，其中因環境變化如溫度、濕度等因素或者材料生產批次不同而有分子量差異或新舊料混合比例不同等因素，造成不穩定的材料熔融性質，使材料射出成型工件的品質變異，例如重量變異。因此維持射出品質的穩定一直都是射出成型領域重要的研究課題，若能利用自適應調控系統讓機器具有適當的判斷能力來自行調整射出參數，使射出品質維持一致性並解決品質不穩定的問題。
本文定義產品重量為產品品質指標，由相關實驗以及文獻發現射出過程中熔膠壓力與溫度對產品重量有直接的影響，藉由此關係掌握每一模次之壓力曲線與溫度穩定便能掌握產品品質穩定。本文建立了一套智慧調控系統並結合類神經網路，在模具內安裝熔膠溫度感測器以及機台射嘴端安裝壓力感測器，即時量測熔膠溫度以及射嘴端熔膠壓力，並即時計算黏度因子、壓力峰值以及壓力峰值時間點。擷取射出過程相關資訊後，利用智慧調控系統分析並回授修改保壓切換位置以及射出速度等參數，使其在長時間生產狀況下，仍能保持產品品質之一致性。
本研究除了實現系統發展外，也經由實驗驗證了本研究所開發的智慧調控系統的可行性，在使用智慧調控系統自適應控制的狀況下，能有效調整每一模次適當之保壓切換位置以及射出速度，穩定每一模次之產品穩定性，且產品品質表現優於無使用系統之狀況，產品重量變異量降至0.14%，使生產之產品品質更加穩定一致，達到機台智慧化之要求。

We developed and implemented a control system for injection molding. The purpose of this control system is to maintain the consistency of product weight by stabilizing the pressure curve. The characteristics of the pressure curve in this paper are restricted to the viscosity index, the peak pressure, and the timing of the peak pressure.
First, we performed ordinary experiments and found that the V-P switchover position and the injection speed were correlated with product weight and the pressure curve characteristics.
We added smartness to our control system through a neural network. In order to adjust the process parameters such as injection speed and V-P switchover position for the next cycle, we accumulated measurements of the viscosity index, the peak pressure, the timing of the peak pressure, and the melt temperature from earlier cycles.
The variation of part weight decreased from 0.25% to 0.14% under the system control. The potential uses of our control system include (1) the maintenance of stable product weight and (2) the reduction of transient behavior and abnormal operation due to material properties change.

[1] W.-W. Wu and C.-C. Huang, "Study of Influence of Injection-Molding Conditions on Shear Effect and Finished Surface Quality of Plastic Parts," Master Thesis, Department of Mold and Die Engineering, National Kaohsiung University of Applied Sciences, 2012.
[2] J. Wang, "PVT properties of polymers for injection molding," in Some Critical Issues for Injection Molding: IntechOpen, 2012.
[3] J. Wang and Q. Mao, "A novel process control methodology based on the PVT behavior of polymer for injection molding," Advances in Polymer Technology, vol. 32, no. S1, pp. E474-E485, 2013.
[4] R. E. Nunn, "Adaptive process control for injection molding," ed: Google Patents, 1989.
[5] A. Agrawal, I. Pandelidis, and M. Pecht, "Injection‐molding process control—A review," Polymer Engineering & Science, vol. 27, no. 18, pp. 1345-1357, 1987.
[6] M. Song, Z. Liu, M. Wang, T. Yu, and D. Zhao, "Research on effects of injection process parameters on the molding process for ultra-thin wall plastic parts," Journal of Materials Processing Technology, vol. 187, pp. 668-671, 2007.
[7] Y. Yang and F. Gao, "Adaptive control of the filling velocity of thermoplastics injection molding," Control Engineering Practice, vol. 8, no. 11, pp. 1285-1296, 2000.
[8] C. Collins, "Monitoring cavity pressure perfects injection molding," Assembly Automation, vol. 19, no. 3, pp. 197-202, 1999.
[9] M.-S. Huang, "Cavity pressure based grey prediction of the filling-to-packing switchover point for injection molding," Journal of materials processing technology, vol. 183, no. 2-3, pp. 419-424, 2007.
[10] M. Kamiguchi and N. Neko, "Method and apparatus for monitoring injection pressure," ed: Google Patents, 1994.
[11] S. Orzechowski, A. Paris, and C. J. Dobbin, "A process monitoring and control system for injection molding using nozzle-based pressure and temperature sensors," in TECHNICAL PAPERS OF THE ANNUAL TECHNICAL CONFERENCE-SOCIETY OF PLASTICS ENGINEERS INCORPORATED, 1998, vol. 1: SOCIETY OF PLASTICS ENGINEERS INC, pp. 424-430.
[12] S. Kruppa and G. P. Holzinger, "IN SITU CHARACTERIZATION OF POLYMER MELT AND MOLDED PART QUALITY," presented at the KraussMaffei Technologies GmbH, Munich, Germany.
[13] R. Schiffers, S. Kruppa, and S. Moser, "The Right Changeover Point for Each Shot," Kunststoffe international, vol. 104, no. 11, pp. 26-30, 2014.
[14] T.-H. Wang, "Design of an Adaptive Gain-Scheduling Fuzzy-PID Controller in Pressure Control of a Servo Hydraulic System," Master Thesis, National Cheng Kung University, 2015.
[15] C.-Y. Lin, "Adaptive Process Control of V-P Transition of Injection Molding Process," Master Thesis, National Cheng Kung University, 2017.
[16] C.-J. Chen, "Development of a Servo Hydraulic System with a Self-tuning Fuzzy PID Controller," Master Thesis, National Cheng Kung University, 2017.
[17] Y.-S. Chen, "Adaptive Process Control of the Changeover Point for Injection Molding Process," Master Thesis, Department of Mechanical Engineering, National Cheng Kung University, 2018.
[18] C. Bader and L. Greco, "Process for determining the changeover point when producing plastic injection mouldings and die-castings," ed: Google Patents, 1997.
[19] C.-H. Chung and J.-W. J. Cheng, "Evaluation of Effectiveness ofMeltfront Virtual Sensing for the Filling-to-Packing Switching of InjectionMolding," Master Thesis, Department of Mechanical Engineering, National Chung Cheng University, 2007.
[20] D. O. Kazmer, S. Velusamy, S. Westerdale, S. Johnston, and R. X. Gao, "A comparison of seven filling to packing switchover methods for injection molding," Polymer Engineering & Science, vol. 50, no. 10, pp. 2031-2043, 2010.
[21] M. Watany, M. A. Eltantawie, and S. A. Abouel-Seoud, "Application of an adaptive neuro fuzzy inference system for low speed planetary gearbox vibration control," Journal of Low Frequency Noise, Vibration and Active Control, vol. 34, no. 3, pp. 323-341, 2015.
[22] M. Kosaka and H. Shibata, "Automatic initialization of adaptive control using previously measured input and output data," Journal of low frequency noise, vibration and active control, vol. 23, no. 3, pp. 189-198, 2004.
[23] H. Lau, A. Ning, K. Pun, and K. Chin, "Neural networks for the dimensional control of molded parts based on a reverse process model," Journal of Materials Processing Technology, vol. 117, no. 1-2, pp. 89-96, 2001.
[24] X. Liao, H. Xie, Y. Zhou, and W. Xia, "Adaptive adjustment of plastic injection processes based on neural network," Journal of Materials Processing Technology, vol. 187, pp. 676-679, 2007.
[25] W.-C. Chen, P.-H. Tai, M.-W. Wang, W.-J. Deng, and C.-T. Chen, "A neural network-based approach for dynamic quality prediction in a plastic injection molding process," Expert systems with Applications, vol. 35, no. 3, pp. 843-849, 2008.
[26] 王鎮杰, "最新PVT量測設備在塑膠材料之檢測應用," presented at the 2015 國際CAE模具成型技術研討會, 台北, 2015.
[27] A. L. Maas, A. Y. Hannun, and A. Y. Ng, "Rectifier nonlinearities improve neural network acoustic models," in Proc. icml, 2013, vol. 30, no. 1, p. 3.