A. Alvarado-Iniesta*1, D.J. Valles-Rosales2, J.L. García-Alcaraz1, A. Maldonado-Macias1
1 Departamento de Ingeniería Industrial y Manufactura Universidad Autónoma de Ciudad Juárez Ciudad Juárez, Chihuahua, México. *alejandro.alvarado@uacj.mx.
2 Department of Industrial Engineering New Mexico State University Las Cruces, NM, USA.
ABSTRACT
Injection molding is classified as one of the most flexible and economical manufacturing processes with high volume of plastic molded parts. Causes of variations in the process are related to the vast number of factors acting during a regular production run, which directly impacts the quality of final products. A common quality trouble in finished products is the presence of warpage. Thus, this study aimed to design a system based on recurrent neural networks to predict warpage defects in products manufactured through injection molding. Five process parameters are employed for being considered to be critical and have a great impact on the warpage of plastic components. This study used the finite element analysis software Moldflow to simulate the injection molding process to collect data in order to train and test the recurrent neural network. Recurrent neural networks were used to understand the dynamics of the process and due to their memorization ability, warpage values might be predicted accurately. Results show the designed network works well in prediction tasks, overcoming those predictions generated by feedforward neural networks.
]]> Keywords: Artificial neural network, recurrent neural network, plastic injection molding, warpage prediction.
RESUMEN
La inyección de plásticos se considera como uno de los procesos de manufactura más flexibles y económicos con un gran volumen de producción de piezas de plástico. Las causas de variación durante la inyección de plásticos se relacionan con el amplio número de factores que intervienen durante un ciclo de producción regular, tales variaciones impactan la calidad del producto final. Un problema común de calidad en productos terminados es la presencia de deformaciones. Así, este estudio tuvo como objetivo diseñar un sistema basado en redes neuronales recurrentes para predecir defectos de deformación en productos fabricados por medio de inyección de plásticos. Se emplean cinco parámetros del proceso por ser considerados críticos y que tienen un gran impacto en la deformación de componentes plásticos. El presente estudio hizo uso del software de análisis finito llamado Moldflow para simular el proceso de inyección de plásticos para recolectar datos con el fin de entrenar y probar la red neuronal recurrente. Redes neuronales recurrentes fueron utilizadas para entender la dinámica del proceso y debido a su capacidad de memorización, los valores de deformación pudieron ser predichos con exactitud. Los resultados muestran que la red diseñada funciona bien en términos de predicción, superando aquellas predicciones generadas por redes de propagación hacia adelante.
DESCARGAR ARTÍCULO EN FORMATO PDF
References
[1] D.V. Rosato and D.V. Rosato, "Injection Molding Handbook 2nd ed.", Chapman & Hall, 1995. [ Links ]
]]>[2] J. He and H. Huang, "Predicting processing parameters for water-assisted injection molding based on inverse GA-LMBP neural network," In Society of Plastics Engineers annual Technical Conference, Cincinnati, OH, 2007. [ Links ]
[3] S. Liao and W. Hsieh, "Shrinkage and warpage prediction of injection-molded thin-wall parts using artificial neural networks," Polym. Eng. Sci., Vol. 44, No. 11, pp. 2029-2040, Nov. 2004. [ Links ]
[4] W. Chen et al., "A neural network-based approach for dynamic quality prediction in a plastic injection molding process," Expert Syst. Appl., Vol. 35, No. 3, pp. 843-849, Oct. 2008. [ Links ]
[5] H. Lau et al., "A new method for monitoring and tuning plastic injection molding machines," Control Intell. Syst., Vol. 36, No. 2, pp. 129-136, Mar. 2008. [ Links ]
[6] E. Li et al., "A Genetic Neural Fuzzy System and its application in quality prediction in the injection process," Chem. Eng. Commun., Vol. 191, No. 3, pp. 335-355, Mar. 2004. [ Links ]
]]>[7] B. Reddy et al., "Application of Soft Computing for the Prediction of Warpage of Plastic Injection Molded Parts," JESTEC, Vol. 2, No. 1, pp. 56-62, 2009. [ Links ]
[8] H. Shi et al., "Optimization of injection molding process parameters using integrated artificial neural network model and expected improvement function method," Int. J. Adv. Manuf. Technol., Vol. 48, No. 9-12, pp. 955-962, 2009. [ Links ]
[9] F. Yin et al., "Backpropagation neural network modeling for warpage prediction and optimization of plastic products during injection molding," Mater. Des., Vol. 32, No. 4, pp. 1844-1850, Apr. 2011. [ Links ]
[10] W. Goh et al., "Application of a recurrent neural network to prediction of drug dissolution profiles," Neural Comput. Appl., Vol. 10, No. 4, pp. 311-317, 2002. [ Links ]
[11] G. Quek et al., "A novel recurrent neural network based prediction system for trading," In International Joint Conference on Neural Networks, Vancouver, Canada, 2006. [ Links ]
]]>[12] V. Kvasnicka et al., "Application of recurrent neural networks in Chemistry: Prediction and classification of 13C NMR Chemical shifts in a series of monosubstituted Benzenes," J. Chem. Inf. Comput. Sci., Vol. 32, No. 6, pp. 742-747, Nov. 1992. [ Links ]
[13] X. Cai et al., "Time series prediction with recurrent neural networks using a hybrid PSO-EA algorithm," IEEE, Vol. 2, pp. 1647-1652, Jul. 2004. [ Links ]
[14] C. Lu and C. Tsai, "Adaptive Predictive Control with Recurrent Neural Network for industrial processes: an application to temperature control of a variable-frequency oil-cooling machine," IEEE Transactions on Industrial Electronics, Vol. 55, No. 3, pp. 1366-1375, Mar. 2008. [ Links ]
[15] N. Costa and B. Ribeiro, "A Neural Prediction model for monitoring and fault diagnosis of a plastic injection molding process", 1999. [ Links ]
[16] C. Lu et al., "Predictive Control Based on Recurrent Neural Network and Application to Plastic Injection Molding Processes," In The 33rd Annual Conference of the IEEE Industrial Electronics Society, Taipei, Taiwan, 2007. [ Links ]
]]>[17] M.C. Huang and C.C. Tai, "The effective factors in the warpage problem of an injection molded part with a thin shell feature," J. Mater. Process. Technol., Vol. 110, No. 1, pp. 1-9, Mar. 2001. [ Links ]
[18] T. Erzurumlu and B. Ozcelik, "Minimization of warpage and sink index in injection-molded thermoplastic parts using Taguchi optimization method," Mater. Des., Vol. 27, No. 10, pp. 853-861, 2006. [ Links ]
[19] B. Ozcelik and I. Sonta, "Warpage and structural analysis of thin shell plastic in the plastic injection molding," Mater. Des., Vol. 30, No. 2, pp. 367-375, 2009. [ Links ]
[20] Y.M. Deng et al., "A hybrid of mode-pursuing sampling method and genetic algorithm for minimization of injection molding warpage," Mater. Des., Vol. 31, No. 4, pp. 2118-2123, Apr. 2010. [ Links ]
[21] B. Farshi et al., "Optimization of injection molding process parameters using sequential simplex algorithm," Mater. Des., Vol. 32, No. 1, pp. 414-423, Jan. 2011. [ Links ]
]]>[22] D. Mandic and J. Chambers, "Fundamentals In Recurrent Neural Networks for Prediction: Learning algorithms, architectures and stability", Wiley, 2001. [ Links ]
[23] D. Pham and L. Xing, "Neural Networks for Identification, Prediction and Control", Springer, 1995. [ Links ]
]]>