0
Research Papers

Comprehensive Online Control Strategies for Plastic Injection Molding Process

[+] Author and Article Information
Jaho Seo

Korea Institute of Machinery and Materials,
156 Gajungbukno,
Yuseong-gu, Daejeon 305-343,
Republic of Korea
e-mail: seojaho@kimm.re.kr

Amir Khajepour

Department of Mechanical
and Mechatronics Engineering,
University of Waterloo,
200 University Avenue West,
Waterloo, ON N2L 3G1, Canada
e-mail: akhajepour@uwaterloo.ca

Jan P. Huissoon

Department of Mechanical
and Mechatronics Engineering,
University of Waterloo,
200 University Avenue West,
Waterloo, ON N2L 3G1, Canada
e-mail: jph@mecheng1.uwaterloo.ca

Contributed by the Manufacturing Engineering Division of ASME for publication in the JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING. Manuscript received July 28, 2013; final manuscript received April 16, 2014; published online May 21, 2014. Assoc. Editor: Robert Landers.

J. Manuf. Sci. Eng 136(4), 041009 (May 21, 2014) (10 pages) Paper No: MANU-13-1293; doi: 10.1115/1.4027491 History: Received July 28, 2013; Revised April 16, 2014

This study proposes an effective thermal control for plastic injection molding (polymer: Santoprene 8211-45 with density of 790 kg/m3, injection pressure: 1400 psi (9,652,660 Pa)) in a laminated die. For this purpose, a comprehensive control strategy is provided to cover various themes. First, a new method for determining the optimal sensor locations as a prerequisite step for modeling and controller design is introduced. Second, system identification through offline and online training with finite element analysis and neural network techniques are used to develop an accurate model by incorporating uncertain dynamics of the laminated die. Third, an additive feedforward control by adding direct adaptive inverse control to self-adaptive PID is developed for temperature control of cavity wall (cavity size: 52.9 × 32.07 × 16.03 mm). A verification of designed controller's performance demonstrates that the proposed strategy provides accurate online temperature tracking and faster response under thermal dynamics with various cycle-times in the injection mold process.

Copyright © 2014 by ASME
Your Session has timed out. Please sign back in to continue.

References

Bishenden, W., and Bhola, R., 1999, “Die Temperature Control,” Transaction of the 20th International Die Casting Congress and Exposition, North American Die Casting Association, pp. 161–164.
Gorbach, P., and Shutts, B., 2002, “The Use of Temperature Control Units in Die Casting Dies,” Die Cast. Eng., 46, pp. 50–55.
Dubay, R., Pramujati, B., and Hernandez, J., 2005, “Cavity Temperature Control in Injection Molding,” 2005 IEEE International Conference on Mechatronics and Automation, pp. 911–916.
Yang, T., Chen, X., and Hu, H., 2007, “A Fuzzy PID Thermal Control System for Die Casting Processes,” 22nd IEEE International Symposium on Intelligent Control, Singapore, pp. 389–394.
Yang, T., Hu, H., Chen, X., Chu, Y., and Cheng, P., 2007, “Thermal Analysis of Casting Dies With Local Temperature Controller,” Int. J. Adv. Manuf. Technol., 33, pp. 277–284. [CrossRef]
Vetter, R., Maijer, D., Huzmezan, M., and Meade, D., 2004, “Control of a Die Casting Simulation Using an Industrial Adaptive Model-Based Predictive Controller,” Proceedings of the Symposium Sponsored by the Extraction and Processing Division of the Minerals, Metals and Materials Society, pp. 235–246.
Dubay, R., 2002, “Self-Optimizing MPC of Melt Temperature in Injection Moulding,” ISA Trans., 41(1), pp. 81–94. [CrossRef] [PubMed]
Tsai, C., and Lu, C., 1998, “Multivariable Self-Tuning Temperature Control for Plastic Injection Molding Process,” IEEE Trans. Ind. Appl., 34(2), pp. 310–318. [CrossRef]
Lu, C., and Tsai, C., 2001, “Adaptive Decoupling Predictive Temperature Control for an Extrusion Barrel in a Plastic Injection Molding Process,” IEEE Trans. Ind. Electron., 48(5), pp. 968–975. [CrossRef]
Demetriou, M., 2005, “Robust Sensor Location Optimization in Distributed Parameter Systems Using Functional Observers,” Proceedings of the 44th IEEE Conference on Decision and Control and European Control Conference, Seville, Spain, pp. 7187–7192.
Dour, G., Dargusch, M., and Davidson, C., 2006, “Recommendations and Guidelines for the Performance of Accurate Heat Transfer Measurements in Rapid Forming Processes,” Int. J. Heat Mass Transfer, 49, pp. 1773–1789. [CrossRef]
Hamasaiid, A., Dour, G., Dargusch, M., Loulou, T., Davidson, C., and Savage, G., 2008, “Heat-Transfer Coefficient and In-Cavity Pressure at the Casting-Die Interface During High-Pressure Die Casting of the Magnesium Alloy AZ91D,” Metall. Mater. Trans. A, 39, pp. 853–864. [CrossRef]
Udwadia, F., 1994, “Methodology for Optimum Sensor Locations for Parameter Identification in Dynamic Systems,” J. Eng. Mech., 120, pp. 368–390. [CrossRef]
Seo, J., Khajepour, A., and Huissoon, J., 2011, “Optimal Sensor Location in Laminated Die System,” ASME J. Dyn. Syst. Meas. Control, 134(2), p. 021013. [CrossRef]
Zheng, C., and Bennett, G., 2002, Applied Contaminant Transport Modeling, Wiley-Interscience, New York, pp. 343–348.
McLoone, S., and Irwin, G., 1997, “Fast Parallel Off-Line Training of Multilayer Perceptrons,” IEEE Trans. Neural Netw., 8, pp. 646–653. [CrossRef] [PubMed]
Haykin, S., 1999, Neural Networks: A Comprehensive Foundation, Prentice-Hall, Pearson Education, Englewood Cliffs, NJ, pp. 754–811.
Lin, T., Horne, B., Tino, P., and Giles, C., 1996, “Learning Long-Term Dependencies in NARX Recurrent Neural Networks,” IEEE Trans. Neural Netw., 7(6), pp. 1329–1351. [CrossRef] [PubMed]
Gao, Y., and Er, M., 2005, “NARMAX Time Series Model Prediction: Feedforward and Recurrent Fuzzy Neural Network Approaches,” Fuzzy Sets Syst., 150(2), pp. 331–350. [CrossRef]
Diaconescu, E., 2008, “The Use of NARX Neural Networks to Predict Chaotic Time Series,” WSEAS Trans. Comput. Res., 3(3), pp. 182–191.
Hu, H., Chen, F., Chen, X., Chu, Y., and Cheng, P., 2004, “Effect of Cooling Water Flow Rates on Local Temperatures and Heat Transfer of Casting Dies,” J. Mater. Process. Technol., 148, pp. 439–451. [CrossRef]
Seo, J., Khajepour, A., and Huissoon, J., 2011, “Identification of Die Thermal Dynamics Using Neural Networks,” ASME J. Dyn. Syst. Meas. Control, 133(6), p. 061008. [CrossRef]
Gao, F., Patterson, W., and Kamal, M., 1993, “Dynamics and Control of Surface and Mold Temperature in Injection Molding,” Int. Polym. Process., 8, pp. 147–157. [CrossRef]
He, X., and Asada, H., 1993, “A New Method for Identifying Orders of Input–Output Models for Nonlinear Dynamic Systems,” Proceedings of the American Control Conference, pp. 2520–2523.
Seo, J., Khajepour, A., and Huissoon, J., 2014, “Thermal Management in Laminated Die System,” Int. J. Control, Autom. Syst. (to be published). [CrossRef]
Sha, D., and Bajic, V., 1999, “On-Line Adaptive Learning Rate BP Algorithm for Multi-Layer Feed-Forward Neural Networks,” J. Appl. Comput. Sci, 7(2), pp. 67–82.
Karray, F., and De Silva, C., 2004, Soft Computing and Intelligent Systems Design, Addison-Wesley, Reading, MA, pp. 299–335.
Dias, F., Antunes, A., and Mota, A., 2005, “Additive Internal Model Control: A New Control Strategy,” Int. Trans. Comput. Sci. Eng., 25, pp. 1–12.
Wang, J., Zhang, C., and Jiang, Y., 2008, “Adaptive PID Control With BP Neural Network Self-Tuning in Exhaust Temperature of Micro Gas Turbine,” 3rd IEEE Conference on Industrial Electronics and Applications, pp. 532–537.
Jiang, J., Wen, S., Zhou, Z., and He, H., 2008, “Fuzzy Barrel Temperature PID Controller Based on Neural Network,” CISP ‘08 Proceedings of the 2008 Congress on Image and Signal Processing, 1, pp. 90–94.
Guo, B., Liu, H., Luo, Z., and Wang, F., 2009, “Adaptive PID Controller Based on BP Neural Network,” International Joint Conference on Artificial Intelligence, pp. 148–150.
Seo, J., Khajepour, A., and Huissoon, J., 2011, “Thermal Dynamic Modeling and Control of Injection Moulding Process,” Autonomous Intell. Syst., 6752, pp. 102–111. [CrossRef]

Figures

Grahic Jump Location
Fig. 2

Monitored nodes of mold (side view (a) and top view (b))

Grahic Jump Location
Fig. 1

Laminated die with cavity and conformal cooling channel

Grahic Jump Location
Fig. 3

Input conditions of the FEA for clustering

Grahic Jump Location
Fig. 6

Training data using all flow rate ranges (0, 1, 3, 4, 5, 6, 8 gpm) and one cycle-time (91 s) at node Mo484

Grahic Jump Location
Fig. 7

Schematic of NARX model

Grahic Jump Location
Fig. 4

Four optimal sensor locations for thermocouple installation

Grahic Jump Location
Fig. 5

System identification procedure

Grahic Jump Location
Fig. 8

Training results with ARX, ARMAX, and NARX models at node 484 using training data in Fig. 6

Grahic Jump Location
Fig. 9

Offline training results (comparison between model (yN) and actual outputs (y))

Grahic Jump Location
Fig. 10

Offline training results (error between yN and y)

Grahic Jump Location
Fig. 11

Experimental setup: (a) installation of laminated die on molding machine, (b) laminated die with thermocouples, and (c) host PC with USB DAQ

Grahic Jump Location
Fig. 18

Linear relationship between an average of four Ta at four nodes and cavity wall temperature immediately after ejection

Grahic Jump Location
Fig. 15

Direct adaptive inverse control

Grahic Jump Location
Fig. 16

Additive feedforward control

Grahic Jump Location
Fig. 17

Final product of plastic injection molding

Grahic Jump Location
Fig. 19

Performance of direct adaptive inverse controller (InvOnly), conventional PID (ConPID), AFC with self-adaptive BP PID (InvBPPID), AFC with self-adaptive RBF PID (InvRBFPID), and AFC with conventional PID (InvConPID) for multisetpoints with various cycle-times

Grahic Jump Location
Fig. 20

Coolant flow rate (control variable) of direct adaptive inverse controller (InvOnly), conventional PID (ConPID), AFC with self-adaptive BP PID (InvBPPID), AFC with self-adaptive RBF PID (InvRBFPID), and AFC with conventional PID (InvConPID) for multisetpoints with various cycle-times

Grahic Jump Location
Fig. 12

Input conditions for experimental validation

Grahic Jump Location
Fig. 13

Experimental validation results (comparison between model (yN) and actual outputs (y))

Grahic Jump Location
Fig. 14

Experimental validation results (error between yN and y)

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In