Thermo-Structural Machine Learning Framework for Malicious Sample Detection and Validation in Polymer Composite Materials

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 14 | 04 | Page :
By

Mahesh T. Dhande,

Nilesh V. Ingale,

Pankaj Deshmukh,

Ritesh S. Fegade,

Ashwini L. Patil,

Bhausaheb Varpe,

Vithoba Tale,

Rupendra Nehete,

  1. Assistant Professor, Department of Artificial Intelligence and Data Science Engineering, Matoshri College of Engineering & Research Centre, Nashik, Maharashtra, India
  2. Associate Professor, Department of Computer Science & Engineering (AIML), KCE Society’s College of Engineering and Management, Jalgaon, Maharashtra, India
  3. Assistant Professor, Department of Artificial Intelligence and Data Science Engineering, MET, BKC, Nashik, Maharashtra, India
  4. Associate Professor, Department of Mechanical Engineering, Parvatibai Genba Moze College of Engineering, Pune, Maharashtra, India
  5. Assistant Professor, Department of Information Technology Engineering, PVGCOE & SSDIOM, Nashik, Maharashtra, India
  6. Assistant Professor, Department of Mechanical Engineering, Amrutvahini College of Engineering, Sangamner, Maharashtra, India
  7. Associate Professor, Department of Mechanical Engineering, Rajarshi Shahu College of Engineering, Tathawade, Pune, Maharashtra, India
  8. Professor, Department of Mechanical Engineering, Indira College of Engineering & Management, Pune, Maharashtra, India

Abstract

The increased use of polymer composites in aerospace, automotive, biomedical and industrial applications has increased the urgency of developing dependable methods to detect malicious samples with counterfeited resins, unauthorized additives, recycled components, hidden flaws, or purposefully degraded physical properties. Most current machine learning techniques have focused either on isolated spectral analysis or detecting flaws in materials; as such, they are unable to perform joint verification of both chemical authenticity and structural integrity, provide credible explanations or identify all relevant material physics. PolyMal-GuardNet is a sequential analytical method that incorporates the Raman-FTIR Counterfeit Signature Disentanglement Network (CSDN) which dissects signatures from genuine polymers, additives, degradations, contaminants, etc., followed by the Spectro-Thermal Malicious Inclusion Localization Network (STMLN), utilizing hyperspectral and thermal imaging data to pinpoint exact locations of suspicious areas. Evidence collected from STMLN will be evaluated via Cure-Filler-Porosity Physics Graph Consistency Model, analyzed via Counterfactual Polymer Malice Attribution Network and ultimately authenticated via Bayesian Inter-Laboratory Polymer Trust Calibration Model to determine trusted cross laboratory decision making. The developed PolyMal-GuardNet Framework provides an enhanced approach to identifying malicious samples, reduces false positives, enhances explanation capability and increases robustness of validation and represents a complete intelligence-based solution for assuring the quality of secure polymer composites and for forensic authentication of materials.

Keywords: Polymer Composite Materials, Malicious Sample Detection, Physics-Guided Machine Learning, Hyperspectral Material Analysis, Raman-FTIR Spectroscopy, Assessments.

How to cite this article: Mahesh T. Dhande, Nilesh V. Ingale, Pankaj Deshmukh, Ritesh S. Fegade, Ashwini L. Patil, Bhausaheb Varpe, Vithoba Tale, Rupendra Nehete. Thermo-Structural Machine Learning Framework for Malicious Sample Detection and Validation in Polymer Composite Materials. Journal of Polymer & Composites. 2026; 14(04):-.
How to cite this URL: Mahesh T. Dhande, Nilesh V. Ingale, Pankaj Deshmukh, Ritesh S. Fegade, Ashwini L. Patil, Bhausaheb Varpe, Vithoba Tale, Rupendra Nehete. Thermo-Structural Machine Learning Framework for Malicious Sample Detection and Validation in Polymer Composite Materials. Journal of Polymer & Composites. 2026; 14(04):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=253567

References

  1. Zhong X, Zhou X, Zhou X. Minimising sample preparation damage for beam sensitive polymer matrix composite materials (paint). Microsc Microanal. 2023. doi:10.1093/micmic/ozad067.203.
  2. Kumar V, Alam M. Multifunctional polymer composite materials. Polymers. 2025. doi:10.3390/polym17121636.
  3. Hou B, Zhang K, Zuo X, et al. PIoT malicious traffic detection method based on GAN sample enhancement. Secur Commun Netw. 2022. doi:10.1155/2022/9223412.
  4. Gribkova O, Nekrasov A. Spectro electrochemistry of electroactive polymer composite materials. Polymers. 2022. doi:10.3390/polym14153201.
  5. Alam M, Kumar V. Multifunctional polymer composite materials. 2nd ed. Polymers. 2025. doi:10.3390/polym17212847.
  6. Wu X, Wang P, Song Y, et al. Few-shot learning for malicious traffic detection with sample relevance guided attention. Electronics. 2025. doi:10.3390/electronics14234717.
  7. Ilyas R, Sapuan S, Bayraktar E. Bio and synthetic based polymer composite materials. Polymers. 2022. doi:10.3390/polym14183778.
  8. Wu S, Wang W, Ding Z. Detecting malicious DoH traffic: leveraging small sample analysis and adversarial networks for detection. J Inf Secur Appl. 2024. doi:10.1016/j.jisa.2024.103827.
  9. Xie J, Li S, Yun X, et al. Sample analysis and multi-label classification for malicious sample datasets. Comput Netw. 2025. doi:10.1016/j.comnet.2024.110999.
  10. Kumar BM S, Keerthana P, Ravi G, et al. Bio polymer based food packaging using composite materials. Mater Today Proc. 2022. doi:10.1016/j.matpr.2022.04.434.
  11. Liu Y, Wang Z, Pang S, et al. Distributed malicious traffic detection. Electronics. 2024. doi:10.3390/electronics13234720.
  12. Isametova M, Nussipali R, Martyushev N, et al. Mathematical modeling of the reliability of polymer composite materials. Mathematics. 2022. doi:10.3390/math10213978.
  13. Matuš M, Šajgalík M, Holubják J, et al. Modelling and simulation of a compact sample of composite materials. Transp Res Procedia. 2023. doi:10.1016/j.trpro.2023.11.203.
  14. Wang Z, Liu L, Zhang Y, et al. A review of graphene-based materials/polymer composite aerogels. Polymers. 2023. doi:10.3390/polym15081888.
  15. Habib M, Lantgios I, Hornbostel K. A review of ceramic, polymer and composite piezoelectric materials. J Phys D Appl Phys. 2022. doi:10.1088/1361-6463/ac8687.
  16. Petrila L, Grădinaru V, Bucatariu F, et al. Polymer/enzyme composite materials—versatile catalysts with multiple applications. Chemistry. 2022. doi:10.3390/chemistry4040087.
  17. Das S, Kumar A. PP and LDPE polymer composite materials blend: a review. Mater Today Proc. 2023. doi:10.1016/j.matpr.2021.03.695.
  18. Zlobina I, Bekrenev N, Krylov V, et al. Heating of additively manufactured polymer composite materials under ultrasonic exposure. Russ Phys J. 2025. doi:10.1007/s11182-025-03416-0.
  19. Ibrahim A, DelloStritto M, Acharya S, et al. Understanding interlayer adhesion in lamellar polymer composite materials via computation. ACS Polym Au. 2026. doi:10.1021/acspolymersau.5c00134.
  20. Lai H, Zhou C, Liu Z. Study on ecological mini-aggregations based on polymer composite materials. Sustainability. 2024. doi:10.3390/su16083431.
  21. Bouranta A, Tudose I, Georgescu L, et al. 3D printed metal oxide-polymer composite materials for antifouling applications. Nanomaterials. 2022. doi:10.3390/nano12060917.
  22. Adam G, Sharker S, Ryu J. Emerging biomedical applications of carbon dot and polymer composite materials. Appl Sci. 2022. doi:10.3390/app122010565.
  23. Fontes A, Shadmehri F. Data-driven failure prediction of fiber-reinforced polymer composite materials. Eng Appl Artif Intell. 2023. doi:10.1016/j.engappai.2023.105834.
  24. Ramakrishnan T, Mohan Gift M, Chitradevi S, et al. Study of numerous resins used in polymer matrix composite materials. Adv Mater Sci Eng. 2022. doi:10.1155/2022/1088926.
  25. Khandaker T, Ibrahim A, Al-Rashed W, et al. Sustainable wastewater treatment using novel zeolite-polymer (ZePol) composite materials. Nanoscale Adv. 2025. doi:10.1039/d5na00996k.
  26. Cózar I, Otero F, Maimí P, et al. A three-dimensional plastic-damage model for polymer composite materials. Compos Part A Appl Sci Manuf. 2022. doi:10.1016/j.compositesa.2022.107198.
  27. Leung C, Wu K, Liu M, et al. Advancing eddy current detection probes with magnetoelectric composite materials: enhancing crack detection in conductive materials. J Magn Magn Mater. 2024. doi:10.1016/j.jmmm.2024.171816.
  28. Alazab A, Khraisat A, Alazab M, et al. Detection of obfuscated malicious JavaScript code. Future Internet. 2022. doi:10.3390/fi14080217.
  29. Faizan S, Bakhtawara, Zaid F. Detection and removal of Congo red via aniline-based polymer and polymer composite. Polym Bull. 2023. doi:10.1007/s00289-022-04432-7.
  30. Ge Y, Gao Y, Li X, et al. EMTD-SSC: an enhanced malicious traffic detection model using transfer learning under small sample conditions in IoT. IEEE Internet Things J. 2024. doi:10.1109/JIOT.2024.3413580.
  31. Fegade R, Tale V, Shete G, Kanase S, Mate D, Komble S. Performance evaluation of indirect solar dryer assisted with forced convection for dehydration of sliced tomato at variable solar radiations. Int J Ambient Energy. 2026;47(1). doi:10.1080/01430750.2026.2695412.
  32. Fegade R, et al. Comprehensive review of composite materials: classification, manufacturing methods, mechanical behavior, failure modes, and emerging applications. J Polym Compos. 2026;14(1):923-939.
  33. Fegade R, et al. Development and mechanical characterization of hybrid natural fiber-reinforced polymer matrix composites for structural applications. J Polym Compos. 2026;14(1):1181-1189.
  34. Fegade R, et al. Design and mathematical quantification of a compressed-air vehicle. J Polym Compos. 2026;14(1):1026-1035.
  35. Fegade R, et al. Design and computational analysis of hybrid carbon fiber-enhanced metal matrix composite spur gears. J Polym Compos. 2026;14(1):158-172.
  36. Fegade R, et al. A systematic review of advanced composite materials for high-performance spur gear applications. J Polym Compos. 2026;14(1):209-220.
  37. Fegade R, Tated R, Nehete R. Numerical investigation of pull-in control of rectangular AA1050 rolling ingot through design of convex mould during direct chill casting process. Eng Res Express. 2024;6(1):1-15.
  38. Fegade R, Tated R, Nehete R. Experimental and numerical investigation of effect of melter temperature and casting speed on pull-in (concavity) of AA1050 ingot during direct chill casting. J Inst Eng India Ser C. 2024;105:69-79.
  39. Fegade R, Tated R, Nehete R. Numerical analysis to investigate the effect of solidification parameters on the pull-in effect of continuous casting. In: Applications of Computation in Mechanical Engineering. 2022. p. 313-325.
  40. Fegade R, Tated R, Nehete R, Parle DG. Finite element analysis of direct chill casting using concept of element birth and death. Int J Recent Technol Eng. 2019;8(4):2967-2975.
  41. Fegade R, Tated R, Nehete R. Improving the aluminium rolling ingot recovery using TQM technique. Int J Innov Technol Explor Eng. 2019;8(12):282-289.
  42. Fegade R, Tated R, Nehete R. Critical review on pull-in of aluminium in continuous casting. Int J Sci Technol Res. 2019;8(11):1950-1959.
  43. Dhande MT, et al. Design of an efficient malware prediction model using auto encoded & attention-based recurrent graph relationship analysis. Int Res J Multidiscip Technovation. 2025;7(1):71-87. doi:10.54392/irjmt2515.
  44. Dhande MT, Verma S, Rathod NJ. Empirical review and comparative analysis of machine learning models in malware detection. Int J Intell Syst Appl Eng. 2024;12(3):4599-4615. doi:10.17762/ijisae.v12i3.8437.

 

Ahead of Print Subscription Original Research
Volume 14
04
Received 23/07/2026
Accepted 13/08/2026
Published 29/08/2026
Publication Time 37 Days

Login

My IP

PlumX Metrics