STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Polymer & Composites Original Research Special issue

Reinforcement Learning for Adaptive Sensing with Shape Memory Polymer-Based IoT Nodes

  1. Priyanka Vashisht Department of Computer Science and Engineering, Amity University
  2. Anvesha Katti Department of Computer Science and Engineering, Amity University
  3. Manna Sheela Rani Chetty Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Guntur
  4. Tarun Gehlot Department of Civil Engineering, College of Technology and Agriculture Engineering, Agriculture University Jodhpur
  5. N. Sreekanth Department of Electronics and Communication Engineering, G.Pullaiah College of Engineering and Technology, Kurnool
  6. Harish Reddy Gantla Department of Computer Science and Engineering, Vignan Institute of Technology and Science

Abstract

The rapid expansion of intelligent sensing in the Internet of Things (IoT) has revealed the pressing need for materials and algorithms capable of self-adaptation in volatile environments. Conventional polymer-based sensors and static control strategies often fail to capture nonlinear thermo-mechanical dynamics, leaving them unsuitable for unpredictable operating conditions. Although prior studies have improved polymer composites or introduced algorithmic optimization independently, few attempts have coupled the adaptability of smart materials with machine-driven learning. This gap leaves IoT systems vulnerable to drift, energy inefficiency, and poor scalability when deployed at large scale. In this work, we introduce a reinforcement learning–driven framework that directly integrates shape memory polymer (SMP) composites into IoT sensing nodes. The novelty lies in embedding an RL policy engine within the material–device interface, enabling the system to continuously recalibrate sensing, actuation, and energy expenditure in response to environmental fluctuations. Unlike static calibration or rule-based heuristics, the proposed approach co-evolves with the dynamic response of SMPs, creating a dual-adaptive sensing architecture. Experimental evaluation demonstrates marked improvements: sensing accuracy exceeded 95%, latency reduced to 0.18 s, and network lifetime extended by nearly 22% relative to federated and static baselines. Moreover, emergent behaviors such as autonomous frequency modulation of sensing cycles revealed the system’s ability to anticipate variations rather than merely react. By fusing polymer adaptability with reinforcement intelligence, this study establishes a pathway toward intelligent matter—self-optimizing sensing platforms capable of functioning reliably in uncertain, resource-constrained domains spanning healthcare monitoring, aerospace structures, and smart infrastructure.

Keywords

References (30)

  1. Khaldy MAA, Nabot A, al-Qerem A, Jebreen I, Darem AA, Alhashmi AA, et al. Adaptive conflict resolution for IoT transactions: A reinforcement learning-based hybrid validation protocol. Scientific Reports. 2025;15(1). doi:10.1038/s41598-025-09698-1
  2. Kim J, Kim S, Yun T, Kim JH, Son C, Lee Y, et al. Shape memory polymer surfaces with controllable roughness for multiscale switchable dry adhesion. Nature Communications. 2025;16(1). doi:10.1038/s41467-025-60220-7
  3. Rawat, Yashpal, and J. K. Purohit, “Smart Manufacturing with Advanced Polymer Composites: Enabling Industry 4.0 Readiness in Indian MSMEs,” J. Polymer Compos., vol. 13, no. 4, pp. 194–216, 2025. [Online]. Available: https://journals.stmjournals.com/article/article%3D2025/view%3D217163
  4. Zhou P, Kan M, Chen W, Wang Y, Cao B. An adaptive coverage method for dynamic wireless sensor network deployment using deep reinforcement learning. Scientific Reports. 2025;15(1). doi:10.1038/s41598-025-16031-3
  5. Tiwari, K. S. Kumar, S. Erat, T. Bhowmik, P. Neopolean, S. Verma, K. P. Yuvaraj, and R. Subbiah, "Development of Self-Healing Circuit Boards Using Shape Memory Polymer Composites," Journal of Polymer Composites, vol. 13, no. 5, Aug. 2025. [Online]. Available: https://journals.stmjournals.com/article/article%3D2025/view%3D222993
  6. Hassan M, Mohanty AK, Wang T, Dhakal HN, Misra M. Current status and future outlook of 4D printing of polymers and composites-A prospective. Composites Part C: Open Access. 2025;17:100602. doi:10.1016/j.jcomc.2025.100602
  7. A. Pasalwad et al., “Progress on Polymer-Based Materials and Composites for Humidity Sensor Applications: From Materials Aspects to Sensor Performances,” J. Mater. Chem. A, vol. 13, pp. 23248–23311, May 2025.
  8. Lu Y. A multimodal deep reinforcement learning approach for IoT-driven adaptive scheduling and robustness optimization in global logistics networks. Scientific Reports. 2025;15(1). doi:10.1038/s41598-025-10512-1
  9. Yadav A, Singh SK, Das S, Kumar S, Kumar A. Shape memory polymer and composites for space applications: A review. Polymer Composites. 2025;46(13):11647-11683. doi:10.1002/pc.29707
  10. Improving Polymer Composite Properties Through Reinforcement Learning Guided Prototyping: A Novel Approach for Material Engineering,” J. Polymer Compos., vol. 12, no. 4, pp. 208–218, 2024 — but available in a 2025 Special Issue of JOPC, and open-access
  11. Recent progress in shape memory polymer composites: driving methods, forming technologies and applications,” Materials & Polymer review, 2024. [Online]. (comprehensive SMP composites review for sensor/actuator design).
  12. Khan MN, Lee S, Shah M. Adaptive Scheduling in Cognitive IoT Sensors for Optimizing Network Performance Using Reinforcement Learning. Applied Sciences. 2025;15(10):5573. doi:10.3390/app15105573
  13. Boosting-Based Machine Learning Applications in Polymer Science,” Polymers (MDPI), vol. 17, no. 4, 2025 — overview of ML methods (including ensemble approaches) applied to polymer property prediction and manufacturing.
  14. Truong T, Kim J. A Wearable Strain Sensor Utilizing Shape Memory Polymer/Carbon Nanotube Composites Measuring Respiration Movements. Polymers. 2024;16(3):373. doi:10.3390/polym16030373
  15. Sikiru S, Busari YO, Olutoki JO, Mahat MM, Kolawole SY. Recent Advances in Polymer-Based Photocatalysts for Environmental Remediation and Energy Conversion: A Review. Journal of Polymer Materials. 2025;42(1):1-31. doi:10.32604/jpm.2025.058936
  16. Premakumari SBN, Sundaram G, Rivera M, Wheeler P, Guzmán REP. Reinforcement Q-Learning-Based Adaptive Encryption Model for Cyberthreat Mitigation in Wireless Sensor Networks. Sensors. 2025;25(7):2056. doi:10.3390/s25072056
  17. H. Uddin et al., "Advances in natural fiber polymer and PLA composites through artificial intelligence and machine learning integration," Journal of Polymer Research, vol. 32, art. 76, 2025. [Online]. Available: https://doi.org/10.1007/s10965-025-03776-5
  18. Herath M, Emmanuel C, Jeewantha J, Epaarachchi J, Leng J. Distributed sensing based real‐time process monitoring of shape memory polymer components. Journal of Applied Polymer Science. 2022;139(22). doi:10.1002/app.52247
  19. Prathumrat P, Nikzad M, Arablouei R, Okhawilai M. Shape memory liquid crystalline polymers: Stimuli‐responsiveness, advanced technologies, and key applications. Polymers for Advanced Technologies. 2024;35(8). doi:10.1002/pat.6531
  20. Palaniappan M, Palanisamy S, Murugesan TM, Alrasheedi NH, Ataya S, Tadepalli S, et al. Novel Ficus retusa L. aerial root fiber: a sustainable alternative for synthetic fibres in polymer composites reinforcement. Biomass Conversion and Biorefinery. 2024;15(5):7585-7601. doi:10.1007/s13399-024-05495-4
  21. Palanisamy S, Kalimuthu M, Azeez A, Palaniappan M, Dharmalingam S, Nagarajan R, et al. Wear Properties and Post-Moisture Absorption Mechanical Behavior of Kenaf/Banana-Fiber-Reinforced Epoxy Composites. Fibers. 2022;10(4):32. doi:10.3390/fib10040032
  22. Kim S, Lee SN, Melvin AA, Choi JW. Stimuli-Responsive Polymer Actuator for Soft Robotics. Polymers. 2024;16(18):2660. doi:10.3390/polym16182660
  23. Jamaludin FH, Nordin NS, Li X, Wong JW, Lim Z, Wang L, et al. Recent Advances in the Field of Shape-Memory Polymer from Bio-Based Precursors: Review and Perspective. Polymer Reviews. 2024;65(1):199-249. doi:10.1080/15583724.2024.2427827
  24. Dewang Y, Sharma V, Baliyan VK, Soundappan T, Singla YK. Research Progress in Electroactive Polymers for Soft Robotics and Artificial Muscle Applications. Polymers. 2025;17(6):746. doi:10.3390/polym17060746
  25. Hassan H, Hallez H, Thielemans W, Vandeginste V. A review of electro-active shape memory polymer composites: Materials engineering strategies for shape memory enhancement. European Polymer Journal. 2024;208:112861. doi:10.1016/j.eurpolymj.2024.112861
  26. Huang Y, Zhao W, Ren H, Jiang L, Ouyang Y, Xu W, et al. Enhanced shape memory performance and numerical simulation of knitted‐fabric reinforced polymer composites with weft yarns. Polymer Composites. 2024;45(18):16916-16928. doi:10.1002/pc.28940
  27. Rao RK, Gautham S, Sasmal S. A Comprehensive Review on Carbon Nanotubes Based Smart Nanocomposites Sensors for Various Novel Sensing Applications. Polymer Reviews. 2024;64(2):575-638. doi:10.1080/15583724.2024.2308889
  28. M. Firouzjaei, R. Scaciota, and S. Samarakoon, "Multi-Task Lifelong Reinforcement Learning for Wireless Sensor Networks," presented at the Centre for Wireless Communication, University of Oulu, Finland, 2025.
  29. Almeshaal M, Palanisamy S, Murugesan TM, Palaniappan M, Santulli C. Physico-chemical characterization of Grewia Monticola Sond (GMS) fibers for prospective application in biocomposites. Journal of Natural Fibers. 2022;19(17):15276-15290. doi:10.1080/15440478.2022.2123076
  30. Gökalp Y, Eti S, Dinçer H, Yüksel S. A novel approach to prioritizing health technology investments using integrated AI-based ranking model. Journal of Health Organization and Management. 2025;39(6):819-841. doi:10.1108/jhom-05-2024-0190
Support