Yaroslavl, Yaroslavl, Russian Federation
Yaroslavl, Yaroslavl, Russian Federation
Yaroslavl, Yaroslavl, Russian Federation
Yaroslavl, Yaroslavl, Russian Federation
VAK Russia 5.2.3
The article provides a comprehensive analysis of global technological, market, and institutional trends in the development of digital inverse engineering of polymer materials, with a particular focus on applications in additive manufacturing. It is demonstrated that traditional empirical approaches to polymer development increasingly fail to meet modern industrial requirements, which are characterized by growing product complexity, shortened innovation cycles, and the need for rapid delivery of materials with precisely defined properties. The concept of inverse engineering is examined as an alternative paradigm, where material development starts from target performance characteristics, and the selection of structure and composition is carried out using computational modeling and artificial intelligence methods. The study reviews key technological drivers of digital materials science, including machine learning techniques, generative models, graph neural networks, and natural language processing for the formalization of engineering requirements. Special attention is given to platform-based solutions that implement a closed digital loop “request — model — material” and their integration with CAD/CAE, PLM, ELN systems, and robotic laboratories. The economic rationale for adopting digital inverse engineering is analyzed, highlighting reduced R&D costs, accelerated commercialization of new materials, and the democratization of access to advanced materials design capabilities for small and medium-sized enterprises. The paper identifies major barriers to market development, including data scarcity, limited interpretability of AI models, and discrepancies between laboratory-scale predictions and industrial-scale performance. Perspective directions are outlined, such as autonomous R&D loops, extension of inverse design approaches to composite and functional materials, and the integration of sustainability and regulatory constraints into digital platforms. The results of the study can support strategic decision-making in the development of digital materials design platforms and in assessing the long-term growth potential of the industry.
digital inverse engineering; industrial digital transformation; polymer materials market; additive manufacturing; innovation economics; artificial intelligence in industry; platform-based business models; research and development (R&D); high-tech markets
1. Voevodina, E. I. Oblasti primeneniya tehnologiy iskusstvennogo intellekta v biznese / E. I. Voevodina, V. A. Kvasha, A. D. Burykin // Myagkie izmereniya i vychisleniya. – 2022. – T. 61, № 12. – S. 75–83. DOI: https://doi.org/10.36871/2618-9976.2022.12.006; EDN: https://elibrary.ru/FDTDBE
2. Voevodina, E. I. Sovremennye sistemy podderzhki prinyatiya resheniy i problemy ispol'zovaniya v nih neyronnyh setey / E. I. Voevodina, Yu. M. Gulyaeva, D. E. Varahtin [i dr.] // Ekonomika i upravlenie: problemy, resheniya. – 2023. – T. 2, № 2(134). – S. 69–74. DOI: https://doi.org/10.36871/ek.up.p.r.2023.02.02.008; EDN: https://elibrary.ru/WTRBXL
3. Kichatov, K. G. Primenenie cifrovyh instrumentov dlya sozdaniya polimerov s zadannymi svoystvami / K. G. Kichatov, T. R. Prosochkina, R. F. Hamadaliev [i dr.] // Bashkirskiy himicheskiy zhurnal. – 2023. – T. 30, № 2. – S. 56–59. – DOI:https://doi.org/10.17122/bcj-2023-2-56-59. EDN: https://elibrary.ru/RPZCOY
4. Kudryavcev, I. V. Issledovanie tehnologii posloynogo sinteza pri sozdanii izdeliy iz termoplastichnyh polimerov s zadannymi svoystvami / I. V. Kudryavcev, K. D. Kuznecova, D. S. Kotov // Opticheskie tehnologii, materialy i sistemy («Optoteh 2022») : sbornik dokladov konferencii, Moskva, 05–10 dekabrya 2022 goda. – Moskva : MIREA – Rossiyskiy tehnologicheskiy universitet, 2022. – S. 321–324. EDN: https://elibrary.ru/LGRAQQ
5. Ob'em mirovogo rynka polimerov k 2030 godu [Elektronnyy resurs]. – URL: https://www.icrowdru.com/2024/08/27/ob'em-mirovogo-rynka-polimerov-k-2030-god/ (data obrascheniya: 24.11.2025).
6. SIBUR. Ob'em proizvodstva polimerov v Rossii [Elektronnyy resurs]. – URL: https://www.sibur.ru/ru/ (data obrascheniya: 20.10.2025).
7. Audus, D. J. Polymer informatics: Opportunities and challenges / D. J. Audus, J. J. de Pablo // ACS Macro Letters. – 2017. – Vol. 6, No. 10. – P. 1078–1082. DOI: https://doi.org/10.1021/acsmacrolett.7b00228
8. Butler, K. T. Machine learning for molecular and materials science / K. T. Butler, D. W. Davies, H. Cartwright [et al.] // Nature. – 2018. – Vol. 559. – P. 547–555. DOI: https://doi.org/10.1038/s41586-018-0337-2; EDN: https://elibrary.ru/YIGQRV
9. Citrine Informatics. AI-driven materials design and inverse design platforms [Elektronnyy resurs]. – URL: https://citrine.io/resources/ (data obrascheniya: 26.11.2025).
10. Copolymer informatics with multi-task deep neural networks [Elektronnyy resurs]. – URL: https://www.researchgate.net/publication/350456853 (data obrascheniya: 25.11.2025).
11. Court, C. J. Auto-generated materials discovery pipelines using text mining / C. J. Court, J. M. Cole // Advanced Materials. – 2018. – Vol. 30, No. 20. – Art. 1704944.
12. European Commission. Digital Product Passport under the Ecodesign Regulation [Elektronnyy resurs]. – URL: https://environment.ec.europa.eu/topics/circular-economy/digital-product-passport_en (data obrascheniya: 26.11.2025).
13. Gibson, I. Additive Manufacturing Technologies / I. Gibson, D. Rosen, B. Stucker. – Springer, 2021. – 498 p. DOI: https://doi.org/10.1007/978-3-030-56127-7
14. Gilmer, J. Neural message passing for quantum chemistry / J. Gilmer, S. S. Schoenholz, P. F. Riley [et al.] // Proceedings of ICML. – 2017. – P. 1263–1272.
15. Häse, F. Next-generation experimentation with self-driving laboratories / F. Häse, L. M. Roch, A. Aspuru-Guzik // Trends in Chemistry. – 2019. – Vol. 1, No. 3. – P. 282–291. DOI: https://doi.org/10.1016/j.trechm.2019.02.007
16. Jain, A. The Materials Project: A materials genome approach to accelerating materials innovation / A. Jain, S. P. Ong, G. Hautier [et al.] // APL Materials. – 2013. – Vol. 1, No. 1. – Art. 011002. DOI: https://doi.org/10.1063/1.4812323
17. Kearnes, S. Molecular graph convolutions: moving beyond fingerprints / S. Kearnes, K. McCloskey, M. Berndl [et al.] // Journal of Computer-Aided Molecular Design. – 2016. – Vol. 30. – P. 595–608. DOI: https://doi.org/10.1007/s10822-016-9938-8; EDN: https://elibrary.ru/WKOUDW
18. Kim, C. Polymer informatics: Current status and critical next steps / C. Kim, T. J. Webb, J. J. de Pablo // Materials Science and Engineering R. – 2021. – Vol. 147. – Art. 100627.
19. Kuenneth, C. PolyBERT: a chemical language model for polymer property prediction / C. Kuenneth, G. Ramakrishnan, M. Häse [et al.] // Nature Communications. – 2023. – Vol. 14. – Art. 4098. DOI: https://doi.org/10.1038/s41467-023-39809-3; EDN: https://elibrary.ru/BSEGUD
20. Materials Genome Initiative [Elektronnyy resurs]. – URL: https://www.mgi.gov (data obrascheniya: 26.11.2025).
21. McKinsey & Company. The future of materials informatics and R&D digitalization [Elektronnyy resurs]. – URL: https://www.mckinsey.com/industries/chemicals/our-insights (data obrascheniya: 27.11.2025).
22. McKinsey & Company. The state of the chemicals industry: Time for bold action and innovation [Elektronnyy resurs]. – URL: https://www.mckinsey.com/industries/chemicals/our-insights/the-state-of-the-chemicals-industry-time-for-bold-action-and-innovation (data obrascheniya: 27.11.2025).
23. Ngo, T. D. Additive manufacturing (3D printing): A review of materials, methods, applications / T. D. Ngo, A. Kashani, G. Imbalzano [et al.] // Composites Part B. – 2018. – Vol. 143. – P. 172–196. DOI: https://doi.org/10.1016/j.compositesb.2018.02.012; EDN: https://elibrary.ru/YEXMXZ
24. OECD. Advanced materials for sustainability and industrial competitiveness [Elektronnyy resurs]. – URL: https://www.oecd.org/innovation/advanced-materials/ (data obrascheniya: 27.11.2025).
25. Olson, G. B. Designing a new material world // Science. – 2000. – Vol. 288, No. 5468. – P. 993–998. DOI: https://doi.org/10.1126/science.288.5468.993; EDN: https://elibrary.ru/DHMIZJ
26. polyOne Data Set: 100 million hypothetical polymers including 29 properties [Elektronnyy resurs]. – URL: https://zenodo.org/records/7766806 (data obrascheniya: 25.11.2025).
27. Precedence research. Polymers Market Strengthen industrial application with bio-based materials, lightweight thermoplastics, and Asia-Pacific scale [Elektronnyy resurs]. – URL: https://www.precedenceresearch.com/polymers-market (data obrascheniya: 27.11.2025).
28. Rajan, K. Materials informatics: The materials “gene” and big data // Annual Review of Materials Research. – 2015. – Vol. 45. – P. 153–169. DOI: https://doi.org/10.1146/annurev-matsci-070214-021132; EDN: https://elibrary.ru/XPRLCL
29. Schmidt, J. Recent advances and applications of machine learning in solid-state materials science / J. Schmidt, M. R. G. Marques, S. Botti, M. A. L. Marques // npj Computational Materials. – 2019. – Vol. 5. – Art. 83. DOI: https://doi.org/10.1038/s41524-019-0221-0; EDN: https://elibrary.ru/HLYIMU
30. Schwaller, P. Molecular transformer: A model for uncertainty-calibrated chemical reaction prediction / P. Schwaller, T. Laino, T. Gaudin [et al.] // ACS Central Science. – 2019. – Vol. 5, No. 9. – P. 1572–1583. DOI: https://doi.org/10.1021/acscentsci.9b00576; EDN: https://elibrary.ru/JHDODZ
31. Training data set for the property predictors [Elektronnyy resurs]. – URL: https://www.nature.com/articles/s41467-023-39868-6/tables/1 (data obrascheniya: 25.11.2025).
32. Tshitoyan, V. Unsupervised word embeddings capture latent knowledge from materials science literature / V. Tshitoyan, J. Dagdelen, L. Weston [et al.] // Nature. – 2019. – Vol. 571. – P. 95–98. DOI: https://doi.org/10.1038/s41586-019-1335-8
