Machine Learning-Based Process Control for Injection Molding of Recycled Polypropylene

Krantz, Joshua; Licata, Juliana; Raju, Muntaqim Ahmed; Gao, Peng; Ma, Ruizhe; Masato, Davide

doi:10.3390/polym17070940

Machine Learning-Based Process Control for Injection Molding of Recycled Polypropylene

Journal Article · Sun Mar 30 00:00:00 EDT 2025 · Polymers

DOI:https://doi.org/10.3390/polym17070940· OSTI ID:2545121

Krantz, Joshua; Licata, Juliana; Raju, Muntaqim Ahmed; Gao, Peng; ;

The increased interest in artificial intelligence in manufacturing has driven the adoption of machine learning to optimize processes and improve efficiency. A key challenge in injection molding is the variability of recycled materials, which affects part quality and processing stability. This study presents a novel closed-loop process control approach for injection molding, leveraging machine learning to adaptively predict processing inputs and quality outcomes. The methodology was tested on five blends of recycled polypropylene (rPP), using artificial neural networks (ANNs), linear regression, and polynomial regression to model the relationships between material properties and process parameters. The dataset was split 80/20 into training and testing sets. The ANN model was implemented using TensorFlow and Keras, with six hidden layers of 32 neurons per layer, ReLU activation, and an Adam optimizer. Empirical tuning and early stopping were used to optimize performance and prevent overfitting. Predictions were evaluated based on mean absolute error (MAE), mean squared error (MSE), and percentage error. The results showed that yield stress, ultimate elongation, and part weight were accurately predicted within a 5% error for linear and polynomial regression models and within a 10% error for the ANN. However, modulus predictions were less reliable, with errors of ~11% for ANN and linear regression and ~40% for polynomial regression, reflecting the inherent variability of this property in rPP blends. Predictions of processing inputs had errors ranging from 3% to 25%, depending on the model and response variable. No single modeling approach was consistently superior across all responses, highlighting the complexity of the relationship between material properties, process parameters, and quality metrics. Overall, the work demonstrates that closed-loop process control, powered by machine learning, can effectively predict key quality parameters in injection molding of recycled materials. The proposed approach can improve process stability and material utilization, facilitating increased adoption of sustainable materials.

View Journal Article

Sponsoring Organization:: USDOE

Grant/Contract Number:: EE0007897

OSTI ID:: 2545121

Journal Information:: Polymers, Journal Name: Polymers Journal Issue: 7 Vol. 17; ISSN POLYCK; ISSN 2073-4360

Publisher:: MDPI AGCopyright Statement

Country of Publication:: Switzerland

Language:: English

References (24)

A review of current developments in process and quality control for injection molding Chen, Zhongbao; Turng, Lih-Sheng Advances in Polymer Technology, Vol. 24, Issue 3 https://doi.org/10.1002/adv.20046	journal	January 2005
Development of Artificial Neural Network System to Recommend Process Conditions of Injection Molding for Various Geometries Lee, Chihun; Na, Juwon; Park, Kyongho Advanced Intelligent Systems, Vol. 2, Issue 10 https://doi.org/10.1002/aisy.202000037	journal	July 2020
Influence of V/P switchover point, injection speed, and holding pressure on quality consistency of injection‐molded parts Huang, Ming‐Shyan; Nian, Shih‐Chih; Lin, Guan‐Ting Journal of Applied Polymer Science, Vol. 138, Issue 41 https://doi.org/10.1002/app.51223	journal	June 2021
Optimization of injection‐molding process for mechanical properties of polypropylene components via a generalized regression neural network Shie, Jie‐Ren Polymers for Advanced Technologies, Vol. 19, Issue 1 https://doi.org/10.1002/pat.976	journal	August 2007
Injection molding product weight: Online prediction and control based on a nonlinear principal component regression model Yang, Yi; Gao, Furong Polymer Engineering & Science, Vol. 46, Issue 4 https://doi.org/10.1002/pen.20522	journal	February 2006
In‐mold rheology and automated process control for injection molding of recycled polypropylene Krantz, Joshua; Nieduzak, Zarek; Licata, Juliana Polymer Engineering & Science, Vol. 64, Issue 9 https://doi.org/10.1002/pen.26836	journal	June 2024
A Review of Current Machine Learning Techniques Used in Manufacturing Diagnosis Ademujimi, Toyosi Toriola; Brundage, Michael P.; Prabhu, Vittaldas V. Advances in Production Management Systems. The Path to Intelligent, Collaborative and Sustainable Manufacturing https://doi.org/10.1007/978-3-319-66923-6_48	book	January 2017
Influence of molding conditions on the shrinkage and roundness of injection molded parts Kurt, Mustafa; Kaynak, Yusuf; Kamber, Omer S. The International Journal of Advanced Manufacturing Technology, Vol. 46, Issue 5-8 https://doi.org/10.1007/s00170-009-2149-x	journal	June 2009
Optimization of injection molding process parameters to improve the mechanical performance of polymer product against impact Xu, Yingjie; Zhang, QingWen; Zhang, Weihong The International Journal of Advanced Manufacturing Technology, Vol. 76, Issue 9-12 https://doi.org/10.1007/s00170-014-6434-y	journal	October 2014
A statistical quality monitoring method for plastic injection molding using machine built-in sensors Zhang, Yun; Mao, Ting; Huang, Zhigao The International Journal of Advanced Manufacturing Technology, Vol. 85, Issue 9-12 https://doi.org/10.1007/s00170-015-8013-2	journal	November 2015
Mainstreaming Green Product Innovation: Why and How Companies Integrate Environmental Sustainability Dangelico, Rosa Maria; Pujari, Devashish Journal of Business Ethics, Vol. 95, Issue 3 https://doi.org/10.1007/s10551-010-0434-0	journal	February 2010
Control of properties in injection molding by neural networks Kenig, S.; Ben-David, A.; Omer, M. Engineering Applications of Artificial Intelligence, Vol. 14, Issue 6 https://doi.org/10.1016/S0952-1976(02)00006-4	journal	December 2001
Comparison of design of experiment methods for modeling injection molding experiments using artificial neural networks Heinisch, Julian; Lockner, Yannik; Hopmann, Christian Journal of Manufacturing Processes, Vol. 61 https://doi.org/10.1016/j.jmapro.2020.11.011	journal	January 2021
Transfer learning with artificial neural networks between injection molding processes and different polymer materials Lockner, Yannik; Hopmann, Christian; Zhao, Weibo Journal of Manufacturing Processes, Vol. 73 https://doi.org/10.1016/j.jmapro.2021.11.014	journal	January 2022
Back Propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding Yin, Fei; Mao, Huajie; Hua, Lin Materials & Design, Vol. 32, Issue 4 https://doi.org/10.1016/j.matdes.2010.12.022	journal	April 2011
Prediction of the Mechanical Properties of PE/PP Blends Using Artificial Neural Networks Yousef, Basem F.; Mourad, Abdel-Hamid I.; Hilal-Alnaqbi, Ali Procedia Engineering, Vol. 10 https://doi.org/10.1016/j.proeng.2011.04.452	journal	January 2011
Applied Statistics and Probability for Engineers Alexander, Melvin T. Technometrics, Vol. 37, Issue 4 https://doi.org/10.1080/00401706.1995.10484379	journal	November 1995
An Empirical Study of the Impact of Hyperparameter Tuning and Model Optimization on the Performance Properties of Deep Neural Networks Liao, Lizhi; Li, Heng; Shang, Weiyi ACM Transactions on Software Engineering and Methodology, Vol. 31, Issue 3 https://doi.org/10.1145/3506695	journal	April 2022
Optimizing mechanical properties of injection-molded long fiber-reinforced polypropylene Youssef, Al Herz; Madhuranthakam, Chandra Mouli R.; Elkamel, Ali Journal of Thermoplastic Composite Materials, Vol. 28, Issue 6 https://doi.org/10.1177/0892705714533371	journal	April 2014
Plastic Part Design for Injection Molding Malloy, Robert A. https://doi.org/10.3139/9783446433748.fm	book	January 2010
Effects of Input Parameter Range on the Accuracy of Artificial Neural Network Prediction for the Injection Molding Process Lee, Junhan; Yang, Dongcheol; Yoon, Kyunghwan Polymers, Vol. 14, Issue 9 https://doi.org/10.3390/polym14091724	journal	April 2022
Industry 4.0 In-Line AI Quality Control of Plastic Injection Molded Parts Aminabadi, Saeid Saeidi; Tabatabai, Paul; Steiner, Alexander Polymers, Vol. 14, Issue 17 https://doi.org/10.3390/polym14173551	journal	August 2022
In-Mold Sensors for Injection Molding: On the Way to Industry 4.0 Ageyeva, Tatyana; Horváth, Szabolcs; Kovács, József Gábor Sensors, Vol. 19, Issue 16 https://doi.org/10.3390/s19163551	journal	August 2019
Machine Learning in Injection Molding: An Industry 4.0 Method of Quality Prediction Párizs, Richárd Dominik; Török, Dániel; Ageyeva, Tatyana Sensors, Vol. 22, Issue 7 https://doi.org/10.3390/s22072704	journal	April 2022

Similar Records

Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models

Journal Article · Thu Jul 15 00:00:00 EDT 2021 · Cement and Concrete Research · OSTI ID:23206271

Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

Journal Article · Wed Jan 19 19:00:00 EST 2022 · Applied Optics · OSTI ID:1841043

Machine Learning-Based Process Control for Injection Molding of Recycled Polypropylene

Citation Formats

References (24)

Similar Records

Related Subjects