CHEMICAL-TECHNOLOGICAL PRECONDITIONS FOR DIGITAL TWIN IMPLEMENTATION IN POLYMER PROCESSING: A DOCUMENTED TECHNOLOGY BASELINE FROM BULGARIAN PLASTICS
DOI:
https://doi.org/10.59957/jctm.v61.i6.2026.16Keywords:
polymer processing, digital twin, extrusion and injection moulding, process monitoring, recycled polymersAbstract
Digital Twin technology is increasingly proposed for polymer processing, yet the chemical-technological conditions that make a twin useful, and the equipment baseline required to build one, are rarely examined together against documented industrial evidence. This paper establishes why polymer processing is a favourable domain for Digital Twin implementation and then tests how far the necessary preconditions are met in a national producing sector. The argument proceeds from polymer physics. Because melt viscosity is strongly shear- and temperature-dependent, and because thermal history governs crystallization, shrinkage and residual stress, a fixed set of machine settings does not reproduce a fixed process state when polymer grade, recycled fraction, moisture content or additive level varies. A twin is valuable in this domain precisely because the state variables that determine part quality cannot be measured directly in production. Against this background, a technology inventory was compiled for a census of 29 Bulgarian plastics manufacturers (NACE 22.2x), of which 20 firms have documented process-level evidence. Extrusion is documented at 13 of the 20 firms, injection moulding at 5 and internal recycling at 4, with thermoforming, coating and blow moulding at 1 - 2 firms each; 7 of the 20 firms disclose named equipment. Sensor-level process instrumentation is documented at no firm, and no firm provides evidence of an ERP, MES or SCADA system, or of a Digital Twin. On the classification applied here, no firm falls in the confirmed Digital Twin category and three fall in the Digital-Twin-ready category. The binding constraint in this sector is therefore not modelling capability but the absence
of the in-process measurements – melt temperature, melt pressure, cavity pressure and screw torque - from which any twin state estimate must be constructed. Firms processing recycled feedstock have the strongest technological case for instrumenting first.
References
T. Ageyeva, S. Horváth, J. G. Kovács, In-mold sensors for injection molding: on the way to Industry 4.0, Sensors, 19, 16, 2019, 3551.
C. Abeykoon, Sensing technologies for process monitoring in polymer extrusion: a comprehensive review on past, present and future aspects, Measurement: Sensors, 22, 2022, 100381.
R. D. Párizs, D. Török, T. Ageyeva, J. G. Kovács, Machine learning in injection molding: an Industry 4.0 method of quality prediction, Sensors, 22, 7, 2022, 2704.
S. Saeidi Aminabadi, P. Tabatabai, A. Steiner, D. P. Gruber, W. Friesenbichler, C. Habersohn, G. Berger-Weber, Industry 4.0 in-line AI quality control of plastic injection molded parts, Polymers, 14, 17, 2022, 3551.
H. Kagermann, W. Wahlster, J. Helbig (Eds.), Recommendations for Implementing the Strategic Initiative INDUSTRIE 4.0: Final Report of the Industrie 4.0 Working Group, Acatech, 2013.
H. Lasi, P. Fettke, H.-G. Kemper, T. Feld, M. Hoffmann, Industry 4.0, Bus. Inf. Syst. Eng., 6, 4, 2014, 239-242.
W. Kritzinger, M. Karner, G. Traar, J. Henjes, W. Sihn, Digital Twin in manufacturing: a categorical literature review and classification, IFAC-PapersOnLine, 51, 11, 2018, 1016-1022.
H. Vangheluwe, R. Paredis, From digital twins to the twinning paradigm (what every software engineer should know), in: Companion Proc. 34th ACM Int. Conf. on the Foundations of Software Engineering, ACM, 2026.
Q. Qi, F. Tao, T. Hu, N. Anwer, A. Liu, Y. Wei, L. Wang, A. Y. C. Nee, Enabling technologies and tools for digital twin, J. Manuf. Syst., 58, 2021, 3-21.
E. Bovo, M. Sorgato, G. Lucchetta, Digital twins for the rapid startup of manufacturing processes: a case study in PVC tube extrusion, Int. J. Adv. Manuf. Technol., 127, 2023, 5517-5529.
J. I. Hernández-Vega, L. A. Reynoso-Guajardo, M. C. Gallardo-Morales, M. E. Macías-Arias, A. Hernández, N. de la Cruz, J. E. Soto-Soto, C. Hernández-Santos, Plastic injection molding process analysis: data integration and modeling for improved production efficiency, Appl. Sci., 14, 22, 2024, 10279.
S. Nasiri, M. R. Khosravani, T. Reinicke, J. Ovtcharova, Digital twin modeling for smart injection molding, J. Manuf. Mater. Process., 8, 3, 2024, 102.
R. Chancharoen et al., Digital twin-enabled extrusion control for high-fidelity printing of polymers, Polymers, 17, 16, 2025, 2215.
M. P. Lambán et al., Overall equipment effectiveness as a strategic KPI in intelligent manufacturing: a case study in plastic injection moulding, J. Manuf. Mater. Process., 10, 5, 2026, 159.
R.-Y. Chang et al., Retrieving equivalent shear viscosity for molten polymers from 3-D nonisothermal capillary flow simulation, Polymers, 13, 23, 2021, 4094.
S. Cruz et al., In-cavity pressure measurements for failure diagnosis in the injection moulding process and correlation with numerical simulation, Int. J. Adv. Manuf. Technol., 126, 1, 2023, 291-300.
B. Rhee et al., Novel analysis methodology of cavity pressure profiles in injection-molding processes using interpretation of machine learning model, Polymers, 13, 19, 2021, 3297.
C.-T. Feng et al., Prediction of part shrinkage for injection molded crystalline polymer via cavity pressure and melt temperature monitoring, Appl. Sci., 13, 17, 2023, 9884.
Y.-H. Ting et al., Experimental study on the modified P-V-T model to improve shrinkage prediction for injection-molded semi-crystalline polymer, Polymers, 18, 3, 2026, 349.
C. Abeykoon et al., Machine learning enhanced grey box soft sensor for melt viscosity prediction in polymer extrusion processes, Sci. Rep., 15, 1, 2025, 5613.
G. Balasubramanian et al., Machine learned and explainable prediction of melt pressure and temperature for polypropylene extrusion, J. Intell. Manuf., 37, 6, 2026, 2381-2394.
N. Kim et al., Multi-objectives optimization of plastic injection molding process parameters based on numerical DNN-GA-MCS strategy, Polymers, 16, 16, 2024, 2247.
S. M. S. Mukras et al., Experiment-driven Gaussian process surrogate modeling and Bayesian optimization for multi-objective injection molding, Polymers, 18, 8, 2026, 902.
L. Schmidt et al., Polypropylene degradation on co-rotating twin-screw extruders, Polymers, 15, 9, 2023, 2181.
C. Lubongo, M. A. A. Bin Daej, P. Alexandridis, Recent developments in technology for sorting plastic for recycling: the emergence of artificial intelligence and the rise of the robots, Recycling, 9, 4, 2024, 59.
J. Krantz, J. Licata, M. A. Raju, P. Gao, R. Ma, D. Masato, Machine learning-based process control for injection molding of recycled polypropylene, Polymers, 17, 7, 2025, 940.
O. Kolade, M. Oyinlola, O. Ogunde, C. Ilo, O. Ajala, Digitally enabled business models for a circular plastic economy in Africa, Environ. Technol. Innov., 35, 2024, 103657.
J. Kua et al., Performance analysis of OPC UA for industrial interoperability towards Industry 4.0, IoT, 3, 4, 2022, 507-525.
M. Martinelli, M. Lippi, M. Picone, S. Mariani, Interaction patterns between artificial intelligence and digital twins in the industrial domain, Inf. Softw. Technol., 198, 2026, 108227.
M. F. Faqih, M. Darsin, Implementation of Internet of Things (IoT) in a plastic blow moulding machine and its performance measurement, J. Mech. Eng. Sci. Technol., 5, 2, 2021, 96-109.
V. Pandey et al., Data-driven digital twin framework for predictive maintenance of smart manufacturing systems, Machines, 13, 6, 2025, 481.
G. Samigulina, Z. Samigulina, D. Bekeshev, T. Samigulin, Digital twin-enabled intelligent HMI for real-time industrial automation systems, Sci. Rep., 16, 2026, 21999.
V. Fani, I. Bucci, M. Rossi, R. Bandinelli, Building operational resilience: a digital twin approach in mixed-model assembly line, J. Ind. Inf. Integr., 52, 2026, 101122.
M. P. Groover, Automation, Production Systems, and Computer-Integrated Manufacturing, 4th global ed., Pearson Education, 2015.
N. Banús, I. Boada, P. Xiberta, P. Toldrà, N. Bustins, Deep learning for the quality control of thermoforming food packages, Sci. Rep., 11, 2021, 21887.
S. Nahavandi, Industry 5.0 - a human-centric solution, Sustainability, 11, 16, 2019, 4371.
A. Adel, Future of Industry 5.0 in society: human-centric solutions, challenges and prospective research areas, J. Cloud Comput., 11, 2022, 40.
L. Liu, F. Guo, Z. Zou, V. G. Duffy, Application, development and future opportunities of collaborative robots (cobots) in manufacturing: a literature review, Int. J. Hum.-Comput. Interact., 40, 4, 2024, 915-932.
S. Peng et al., Energy consumption prediction of injection molding process based on rolling learning Informer model, Polymers, 16, 21, 2024, 3097.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Chemical Technology and Metallurgy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
