Optimal Sensor Locations for Polymer Injection Molding Process

Abstract:

Article Preview

The subject discussed in this article concerns the determination of optimal sensor (pressure & temperature) configurations for polymer injection moulds. A sensor configuration is considered optimal when it is able to predict the product quality (dimension, warpage, etc.) with a good accuracy (from experimental data provided by these sensors). Initially, plastic engineers integrated sensors in moulds to acquire knowledge about their processes and to have better understanding of physical phenomenon. This article presents a numerical methodology to identify optimal combinations of sensors. The methodology is firstly based on polymer injection molding simulation to collect virtual sensor data. In a second step, virtual sensor data are analyzed by modern data-driven modeling techniques to identify optimal sensor configurations.

Info:

Periodical:

Key Engineering Materials (Volumes 611-612)

Edited by:

Jari Larkiola

Pages:

1724-1733

Citation:

D. Garcia et al., "Optimal Sensor Locations for Polymer Injection Molding Process", Key Engineering Materials, Vols. 611-612, pp. 1724-1733, 2014

Online since:

May 2014

Export:

Price:

$38.00

[1] M. Basseville, A. Benveniste, G. Moustakides, A. Rougée, Optimal Sensor Location For Detecting Changes in Dynamical Behavior, IEEE TRANSACTIONS ON AUTOMATIC CONTROL, VOL. AC32 NO12 December (1987).

DOI: https://doi.org/10.1109/tac.1987.1104501

[2] D. Gay, M. Boullé, Construction de descripteurs à partir du coclustering pour la classification supervisee de series temporelles, EGC 2013 Revue des Nouvelles Technologies de l'Information vol. RNTI-E-24, pp.353-364.

[3] W.J. Staszewski, K. Worden, Overview of optimal sensor location methods for damage detection, Proc. SPIE 4326 Smart Structures and Materials 2001: Modeling, Signal Processing, and Control in Smart Structures, 179 August 21, (2001).

DOI: https://doi.org/10.1117/12.436472

[4] H. Deng, G. Runger, Feature Selection via Regularized Trees, information on http: /arxiv. org/abs/1201. 1587v3.

[5] H. Deng, G. Runger, Feature Gene selection with guided regularized random forest, information on http: /arxiv. org/abs/1209. 6425.