Induced network-based transfer learning in injection molding for process modelling and optimization with artificial neural networks

The necessity of an abundance of training data commonly hinders the broad use of machine learning in the plastics processing industry. Induced network-based transfer learning is used to reduce the necessary amount of injection molding process data for the training of an artificial neural network in order to conduct a data-driven machine parameter optimization for injection molding processes. As base learners, source models for the injection molding process of 59 different parts are fitted to process data. A different process for another part is chosen as the target process on which transfer learning is applied. The models learn the relationship between 6 machine setting parameters and the part weight as quality parameter. The considered machine parameters are the injection flow rate, holding pressure time, holding pressure, cooling time, melt temperature, and cavity wall temperature. For the right source domain, only 4 sample points of the new process need to be generated to train a model of the injection molding process with a degree of determination R2 of 0.9 or and higher. Significant differences in the transferability of the source models can be seen between different part geometries: The source models of injection molding processes for similar parts to the part of the target process achieve the best results. The transfer learning technique has the potential to raise the relevance of AI methods for process optimization in the plastics processing industry significantly.

[1]  DuchiJohn,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011 .

[2]  G. Schuh,et al.  Integrative Produktionstechnik für Hochlohnländer , 2011 .

[3]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[4]  N. Rudolph,et al.  3 – Generalized Newtonian Fluid (GNF) Models , 2015 .

[5]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[6]  Lutz Prechelt,et al.  Early Stopping - But When? , 2012, Neural Networks: Tricks of the Trade.

[7]  Qian Li,et al.  Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method , 2007 .

[8]  Ullrich Köthe,et al.  Analyzing Inverse Problems with Invertible Neural Networks , 2018, ICLR.

[9]  Wenjun Zhang,et al.  A Method to Measure The Resilience of Algorithm for Operation Management , 2016 .

[10]  Kuo-Ming Tsai,et al.  An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm , 2014, Journal of Intelligent Manufacturing.

[11]  F. Trovalusci,et al.  Neural network approach to quality monitoring of injection molding of photoluminescent polymers , 2019, Applied Physics A.

[12]  Maurice Pillet,et al.  Quality prediction in injection molding , 2017, 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA).

[13]  Jorge Luis García Alcaraz,et al.  Optimization of injection molding process parameters by a hybrid of artificial neural network and artificial bee colony algorithm , 2013 .

[14]  Liang Ma,et al.  Multiobjective optimization of injection molding process parameters based on Opt LHD, EBFNN, and MOPSO , 2015, The International Journal of Advanced Manufacturing Technology.

[15]  Furong Gao,et al.  Injection molding product weight: Online prediction and control based on a nonlinear principal component regression model , 2006 .

[16]  Meiabadi Mohammad Saleh,et al.  Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm , 2013 .

[17]  Kwangyeol Ryu,et al.  Real-time parameter optimization based on neural network for smart injection molding , 2018 .

[18]  Kuo-Ming Tsai,et al.  Comparison of injection molding process windows for plastic lens established by artificial neural network and response surface methodology , 2015 .

[19]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[20]  Fanhuai Shi,et al.  Optimisation of Plastic Injection Moulding Process with Soft Computing , 2003 .

[21]  Qiang Yang,et al.  Transfer learning for collaborative filtering via a rating-matrix generative model , 2009, ICML '09.

[22]  Geoff Giordano.  Don't Shut It Down: Holiday shutdowns have long been the norm, but automation is helping manufacturers keep their shops open as workers enjoy time with their families , 2019 .

[23]  Arie Ben-David,et al.  Control of properties in injection molding by neural networks , 2001 .

[24]  N. Subramanian,et al.  Comparison of artificial neural network and multiple linear regression in the optimization of formulation parameters of leuprolide acetate loaded liposomes. , 2005, Journal of pharmacy & pharmaceutical sciences : a publication of the Canadian Society for Pharmaceutical Sciences, Societe canadienne des sciences pharmaceutiques.

[25]  Thomas G. Dietterich,et al.  To transfer or not to transfer , 2005, NIPS 2005.

[26]  Prasad Krishna,et al.  Prediction and Optimization of Dimensional Shrinkage Variations in Injection Molded Parts Using Forward and Reverse Mapping of Artificial Neural Networks , 2012 .

[27]  Bin Li,et al.  Online Transfer Learning , 2014, Artif. Intell..

[28]  Mohammadreza Sedighi,et al.  Optimisation of gate location based on weld line in plastic injection moulding using computer-aided engineering, artificial neural network, and genetic algorithm , 2017 .

[29]  Yoshua Bengio,et al.  Deep Learning of Representations for Unsupervised and Transfer Learning , 2011, ICML Unsupervised and Transfer Learning.

[30]  Rolf Isermann,et al.  Identifikation dynamischer Systeme , 1988 .

[31]  Prasad K. Yarlagadda,et al.  Prediction of processing parameters for injection moulding by using a hybrid neural network , 2001 .

[32]  Oscar Castillo,et al.  A state of the art review of intelligent scheduling , 2018, Artificial Intelligence Review.

[33]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[34]  Stefan Wrobel,et al.  A review of machine learning for the optimization of production processes , 2019, The International Journal of Advanced Manufacturing Technology.

[35]  Jürgen Schmidhuber,et al.  Transfer learning for Latin and Chinese characters with Deep Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[36]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[37]  Tobias Meisen,et al.  Transfer-Learning: Bridging the Gap between Real and Simulation Data for Machine Learning in Injection Molding , 2018 .

[38]  Geoff Giordano.  Buying Power: As Industry 4.0 continues to influence the plastics industry, manufacturers must consider connectivity and other factors when purchasing equipment , 2019 .

[39]  C. Osborne,et al.  RADYNVERSION: Learning to Invert a Solar Flare Atmosphere with Invertible Neural Networks , 2019, The Astrophysical Journal.

[40]  R Spina,et al.  OPTIMIZATION OF INJECTION MOLDED PARTS BY USING ANN-PSO APPROACH , 2006 .

[41]  Wen-Chin Chen,et al.  An integrated parameter optimization system for MISO plastic injection molding , 2009 .

[42]  C. A. van Luttervelt,et al.  Toward a resilient manufacturing system , 2011 .

[43]  Sung-Hoon Ahn,et al.  Smart Machining Process Using Machine Learning: A Review and Perspective on Machining Industry , 2018, International Journal of Precision Engineering and Manufacturing-Green Technology.

[44]  C. Jebaraj,et al.  Injection molding process optimization of a bi-aspheric lens using hybrid artificial neural networks (ANNs) and particle swarm optimization (PSO) , 2019, Measurement.

[45]  Vittaldas V. Prabhu,et al.  A Review of Current Machine Learning Techniques Used in Manufacturing Diagnosis , 2017, APMS.

[46]  Taghi M. Khoshgoftaar,et al.  A survey of transfer learning , 2016, Journal of Big Data.