AI-Driven Multi-Objective Optimization of Conductive Polymer Composites for High-Performance Flexible Electronics

Year : 2025 | Volume : 13 | Special Issue 06 | Page : 734 745
    By

    Sivakumar M.,

  • Thirumoorthy P.,

  • Narasimman V.,

  • Sreedevi S.L.,

  • Karthikeyan T.,

  • Dinesh S.,

  1. Associate Professor, Department of Electronics and Communication Engineering, Dhanalakshmi College of Engineering, Chennai, Tamil Nadu, India
  2. Associate Professor, Department of Electrical and Electronics Engineering, Dhanalakshmi College of Engineering, Chennai, Tamil Nadu, India
  3. Assistant Professor, Department of Computer Science and Engineering (Cyber Security), Arunai Engineering College, Tiruvannamalai, Tamil Nadu, India
  4. Assistant Professor, Department of Electrical and Electronics Engineering, PERI Institute of Technology, Chennai, Tamil Nadu, India
  5. Associate Professor, Department of Electronics and Communication Engineering, Infant Jesus College of Engineering, Thoothukudi, Tamil Nadu, India
  6. Associate Professor, Department of Mechanical Engineering, Dhanalakshmi College of Engineering, Chennai, Tamil Nadu, India

Abstract

The development of conductive polymer composites (CPCs) is critical for advancing flexible and wearable electronic technologies. However, the conventional trial-and-error approach to material formulation is time-consuming and often inefficient due to the high-dimensional nature of the design space. This study introduces a novel AI-driven framework that integrates machine learning (ML) with multi-objective optimization to accelerate the discovery of high-performance CPCs. A dataset of 1,000 experimentally reported formulations was compiled, capturing key variables such as filler type, volume fraction, polymer modulus, and processing conditions. These were used to train ML models, including Artificial Neural Networks (ANN), Random Forests (RF), and Support Vector Machines (SVM), with ANN demonstrating superior performance (R² = 0.93) in predicting electrical conductivity. To explore optimal formulations, Bayesian Optimization (BO) and Genetic Algorithms (GA) were employed, enabling trade-offs among electrical conductivity, mechanical elongation, and thermal stability. The optimized CPC achieved conductivities above 1000 S/m, elongation over 150%, and thermal stability beyond 250 °C—surpassing traditionally designed materials. Experimental synthesis of select AI-predicted formulations confirmed model accuracy within a 10% margin, validating the framework’s practical applicability. This study presents a scalable and adaptive pathway for materials discovery, shifting from empirical guesswork to intelligent design. The integration of AI with materials informatics offers transformative potential in engineering next-generation CPCs for applications in soft robotics, bioelectronics, and stretchable sensing systems.

Keywords: Conductive polymer composites; flexible electronics; machine learning; materials informatics; multi-objective optimization

[This article belongs to Special Issue under section in Journal of Polymer & Composites (jopc)]

aWQ6MjM0NTMwfGZpbGVuYW1lOjczYzBlYmQ3LWZpLmF2aWZ8c2l6ZTp0aHVtYm5haWw=
How to cite this article:
Sivakumar M., Thirumoorthy P., Narasimman V., Sreedevi S.L., Karthikeyan T., Dinesh S.. AI-Driven Multi-Objective Optimization of Conductive Polymer Composites for High-Performance Flexible Electronics. Journal of Polymer & Composites. 2025; 13(06):734-745.
How to cite this URL:
Sivakumar M., Thirumoorthy P., Narasimman V., Sreedevi S.L., Karthikeyan T., Dinesh S.. AI-Driven Multi-Objective Optimization of Conductive Polymer Composites for High-Performance Flexible Electronics. Journal of Polymer & Composites. 2025; 13(06):734-745. Available from: https://journals.stmjournals.com/jopc/article=2025/view=234533


Browse Figures

References

  1. Hossain MT, Shahid MA, Mahmud N, Darda MA, Samad AB. Techniques, applications, and prospects of recycled polyethylene terephthalate bottles: A review. J Thermoplast Compos Mater. 2024;37:1268–86.
  2. Xu Y, Wang Q, Zou W, Zhang X, Sun Y, Kan Y, et al. Recent progress in all-solution-processed organic solar cells. Chin J Chem. 2024;42:190–8.
  3. Shahid MA, Hossain MT, Hossain I, Limon MGM, Rabbani M, Rahim A. Research and development on phase change material-integrated cloth: A review. J Ind Text. 2024;54:15280837241262518.
  4. Hossain MT, Repon MR, Shahid MA, Ali A, Islam T. Progress, prospects and challenges of MXene integrated optoelectronics devices. ChemElectroChem. 2024;11:e202400008.
  5. Murugappan K, Castell MR. Bridging electrode gaps with conducting polymers around the electrical percolation threshold. Electrochem Commun. 2018;87:40–3.
  6. Armitage BI, Murugappan K, Lefferts MJ, Cowsik A, Castell MR. Conducting polymer percolation gas sensor on a flexible substrate. J Mater Chem C. 2020;8:12669 76.
  7. Wu D, Li Z, Du Y, Zhang L, Huang Y, Sun J, et al. Compression-induced electrical percolation and enhanced mechanical properties of polydimethylsiloxane-based nanocomposites. J Mater Sci. 2020;55:10611 25.
  8. Das S, Kumar A, Narayan K. Confinement highlights the different electrical transport mechanisms prevailing in conducting polymers. Phys Rev Mater. 2022;6:025602.
  9. Hossain MT, Shahid MA, Ali A. Development of nanofibrous membrane from recycled polyethylene terephthalate bottle by electrospinning. OpenNano. 2022;8:100089.
  10. Shahid MA, Saha C, Miah MS, Hossain MT. Incorporation of MPCM on cotton fabric for potential application in hospital bed sheets. Heliyon. 2023;9:e16412.
  11. Hoque MIU, Holze R. Intrinsically conducting polymer composites as active masses in supercapacitors. Polymers. 2023;15:730.
  12. Saha C, Shahid MA, Prasad RK. Evaluation of thermal and moisture management properties of PCM treated denim fabrics. J Text Appar Technol Manag. 2021;12:1–6.
  13. Naysmith A, Mian NS, Rana S. Development of conductive textile fabric using Plackett–Burman optimized green synthesized silver nanoparticles and in situ polymerized polypyrrole. Green Chem Lett Rev. 2023;16:2158690.
  14. Yan Y, Jiang Y, Ng ELL, Zhang Y, Owh C, Wang F, et al. Progress and opportunities in additive manufacturing of electrically conductive polymer composites. Mater Today Adv. 2023;17:100333.
  15. Nandee R, Chowdhury MA, Shahid A, Hossain N, Rana M. Band gap formation of 2D material in graphene: Prospect and challenges. Results Eng. 2022;15:100474.
  16. Palsaniya S, Mukherji S. Enhanced dielectric and electrostatic energy density of electronic conductive organic-metal oxide frameworks at ultra-high frequency. Carbon. 2022;196:749–62.
  17. Zhang L, Du W, Nautiyal A, Liu Z, Zhang X. Recent progress on nanostructured conducting polymers and composites: Synthesis, application and future aspects. Sci China Mater. 2018;61:303–52.
  18. Xia X, Weng GJ, Hou D, Wen W. Tailoring the frequency-dependent electrical conductivity and dielectric permittivity of CNT-polymer nanocomposites with nanosized particles. Int J Eng Sci. 2019;142:1–19.
  19. Khanna VK. Extreme-Temperature and Harsh-Environment Electronics: Physics, Technology and Applications. Bristol (UK): IOP Publishing; 2023.
  20. Luo Y, Abidian MR, Ahn JH, Akinwande D, Andrews AM, Antonietti M, et al. Technology roadmap for flexible sensors. ACS Nano. 2023;17:5211–95.
Special Issue Subscription Original Research
Volume 13
Special Issue 06
Received 05/06/2025
Accepted 23/06/2025
Published 27/09/2025
Publication Time 114 Days
119

Login


My IP

PlumX Metrics