ML-Driven Defect Detection in Additive Manufacturing of Polymer Composites Using Thermal Imaging

Year : 2025 | Volume : 13 | Special Issue 06 | Page : 201 215
    By

    Harish Reddy Gantla,

  • Vadakattu Prabhakar,

  • Harish Chandra Mohanta,

  • A. Anandhan,

  • Parul Goyal,

  • Radha Seelaboyina,

  1. Associate Professor, Department of Computer Science & Engineering, Vignan Institute of Technology and Science, Telangana, India
  2. Assistant Professor, Department of Computer Science & Engineering, Sreenidhi Institute of Science and Technology, Telangana, India
  3. Professor, Department of Electronics and Communication Engineering, Centurion University of Technology and Management, Odisha, India
  4. Associate Professor, Department of Chemistry, Erode Sengunthar Engineering College, Thudupathi, Perundurai, Tamil Nadu, India
  5. Professor, Department of Computer Science & Engineering, M. M. Engineering College, Maharishi Markandeshwar Deemed to be University, Mullana, Ambala, Haryana, India
  6. Associate Professor, Department of Computer Science and Engineering, Geethanjali College of Engineering and Technology, Hyderabad, Telangana, India

Abstract

Polymer-based flexible biosensors have emerged as a pivotal technology in continuous health monitoring, yet their deployment in real-world settings is often hindered by undetected micro-defects and signal distortion caused during fabrication or usage. Existing diagnostic frameworks typically rely on post-hoc processing or bulky instrumentation, failing to offer scalable, real-time detection during additive manufacturing workflows. This study introduces an end-to-end, thermographic imaging-integrated framework for in-situ defect identification during the additive manufacturing of polymer composites, guided by a lightweight convolutional neural network (CNN) architecture. The system fuses thermal signatures with structural cues to detect anomalies embedded within multilayer flexible substrates. A streamlined fabrication pipeline—including conductive polymer deposition, thermal data capture, and edge-based CNN classification—enables robust, near-instantaneous feedback during biosensor assembly. Experimental evaluations demonstrate that the proposed system achieves a classification accuracy of 96.4% with a latency reduction of 28.3% compared to traditional offline inspection methods. Signal fidelity under deformation stress conditions remains consistently above 92%, even in high-strain regions. This approach not only enhances the reliability and production yield of wearable biosensors but also sets a precedent for embedding explainable AI-driven quality control directly into smart manufacturing cycles—paving the way for self-validating, adaptive biomedical devices suited for the evolving landscape of personalized, IoT-enabled healthcare.

Keywords: Wearable biosensors, thermographic imaging, flexible polymers, deep learning, in-situ defect detection.

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

aWQ6MjI4OTQ3fGZpbGVuYW1lOmY0ZGY2YTk4LWZpLmF2aWZ8c2l6ZTp0aHVtYm5haWw=
How to cite this article:
Harish Reddy Gantla, Vadakattu Prabhakar, Harish Chandra Mohanta, A. Anandhan, Parul Goyal, Radha Seelaboyina. ML-Driven Defect Detection in Additive Manufacturing of Polymer Composites Using Thermal Imaging. Journal of Polymer and Composites. 2025; 13(06):201-215.
How to cite this URL:
Harish Reddy Gantla, Vadakattu Prabhakar, Harish Chandra Mohanta, A. Anandhan, Parul Goyal, Radha Seelaboyina. ML-Driven Defect Detection in Additive Manufacturing of Polymer Composites Using Thermal Imaging. Journal of Polymer and Composites. 2025; 13(06):201-215. Available from: https://journals.stmjournals.com/jopc/article=2025/view=228953


References

  1. Yoon, J., Kwon, N., Lee, Y., Kim, S., Lee, T., and Choi, J.-W., “Nanotechnology-Based Wearable Electrochemical Biosensor for Disease Diagnosis,” ACS Sensors, vol. 10, no. 3, pp. 1675–1689, Mar. 2025, doi: 10.1021/acssensors.4c03371.
  2. Murugesan Chandran, M., Veerapandian, M., Dhanasekaran, B., Govindaraju, S., and Yun, K., “Advanced nanomaterials for health monitoring and diagnostics in next-generation wearable sensors,” Mater. Sci. Eng. R Rep., vol. 165, p. 101015, 2025, doi: 10.1016/j.mser.2025.101015.
  3. Abhinav, V., Basu, P., Verma, S. S., Verma, J., Das, A., Kumari, S., Yadav, P. R., and Kumar, V., “Advancements in Wearable and Implantable BioMEMS Devices: Transforming Healthcare Through Technology,” Micromachines, vol. 16, no. 5, p. 522, 2025, doi: 10.3390/mi16050522.
  4. Pereira, C. R., Pereira, A. M., Teixeira, J. S., Sousa, A. R., Queirós, G. P., Costa, R. S., and Nunes, M. S., “Advanced energy storage systems as power sources for biosensing technologies,” 2025, doi: 10.1016/bs.pmbts.2025.05.012.
  5. Cha, S., Choi, M. Y., Kim, M. J., Sim, S. B., Haizan, I., and Choi, J.-H., “Electrochemical Microneedles for Real-Time Monitoring in Interstitial Fluid: Emerging Technologies and Future Directions,” Biosensors, vol. 15, no. 6, p. 380, 2025, doi: 10.3390/bios15060380.
  6. Mu, G., et al., “Recent advancements in wearable sensors: integration with machine learning for human–machine interaction,” RSC Adv., vol. 15, pp. 7844–7854, Mar. 2025, doi: 10.1039/D5RA00167F.
  7. Duan, H., Peng, S., He, S., Tang, S.-Y., Wang, C. H., and Li, M., “Wearable Electrochemical Biosensors for Advanced Healthcare Monitoring,” Adv. Sci., vol. 12, no. 2, p. 2411433, Nov. 2024, doi: 10.1002/advs.202411433.
  8. Jiao, Y., and Yu, X., “Recent advances in wearable electrochemical sensors for in situ detection of biochemical markers,” Sci. China Mater., vol. 68, pp. 755–774, Feb. 2025, doi: 10.1007/s40843-024-2960-1.
  9. Dervisevic, M., Esser, L., Chen, Y., Alba, M., Prieto-Simon, B., and Voelcker, N. H., “High-density microneedle array-based wearable electrochemical biosensor for detection of insulin in interstitial fluid,” Biosens. Bioelectron., p. 116995, 2024, doi: 10.1016/j.bios.2024.116995.
  10. Flynn, C. D., Chang, D., Mahmud, A., Yousefi, H., Das, J., Riordan, K. T., Sargent, E. H., and Kelley, S. O., “Nanobiosensors for precision medicine,” Nat. Rev. Bioeng., vol. 1, pp. 560–577, 2023.
  11. Wu, J., Liu, H., Chen, W., Ma, B., and Ju, H., “Next-generation biosensing technologies,” Nat. Rev. Bioeng., vol. 1, pp. 346–361, 2023.
  12. Saha, T., Del Caño, R., Mahato, K., De la Paz, E., Chen, C., Ding, S., Yin, L., and Wang, J., “Advances in wearable biosensor interfaces,” Chem. Rev., vol. 123, pp. 7854–7876, 2023.
  13. Li, S., Zhang, H., Zhu, M., Kuang, Z., Li, X., Miao, S., Zhang, Z., Lou, X., Li, H., and Xia, F., “Functional nanomaterials for wearable biosensors,” Chem. Rev., vol. 123, pp. 7953–7982, 2023.
  14. Dezhakam, E., Khalilzadeh, B., Mahdipour, M., Isildak, I., Yousefi, H., Ahmadi, M., Naseri, A., and Rahbarghazi, R., “Wearable biosensors for continuous health monitoring,” Biosens. Bioelectron., vol. 222, p. 114980, 2023.
  15. Ye, C., Lukas, H., Wang, M., Lee, Y., and Gao, W., “Molecularly imprinted polymer-based wearable biosensors,” Chem. Soc. Rev., vol. 53, pp. 7960–7982, 2024.
  16. Bai, J., Liu, D., Tian, X., Wang, Y., Cui, B., Yang, Y., Dai, S., Lin, W., Zhu, J., Wang, J., Xu, A., Gu, Z., and Zhang, S., “Wearable biosensors based on fiber-integrated electrodes for multiplexed sweat analysis,” Sci. Adv., vol. 10, p. eadl1856, 2024.
  17. Wang, X., Zhou, J., and Wang, H., “Flexible Electrochemical Biosensors for In Vivo Real-Time Monitoring,” Cell Rep. Phys. Sci., vol. 5, p. 101801, 2024.
  18. Wang, Y., Duan, H., Yalikun, Y., Cheng, S., and Li, M., “Smart wearable platforms for noninvasive health monitoring,” Talanta, vol. 266, p. 125026, 2024.
  19. Duan, H., Tang, S.-Y., Goda, K., and Li, M., “Electrochemical sensing technologies for wearable biosensor systems,” Biosens. Bioelectron., vol. 246, p. 115918, 2024.
  20. A. I. Azizan, S. Taufik, M. N. Norizan, and J. I. A. Rashid, “Flexible and transparent wearable electrochemical sensors,” Biosens. Bioelectron.: X, vol. 13, p. 100291, 2023.
  21. Liu, Z. Cai, Y. Ye, M. Zhou, H. Liao, and Y. Yi, “An overview of flexible sensors: Development, application, and challenges,” Sensors, vol. 23, p. 817, 2023, doi: 10.3390/s23020817.
  22. Hu, Z. Ma, F. Zhao, and S. Guo, “Recent advances in self-powered wearable flexible sensors for human gaits analysis,” Nanomaterials, vol. 14, p. 1173, 2024, doi: 10.3390/nano14071173.
  23. Gao, Z. Yang, J. Choi, C. Wang, G. Dai, and J. Yang, “Triboelectric nanogenerators for preventive health monitoring,” Nanomaterials, vol. 14, p. 336, 2024, doi: 10.3390/nano14020336.
  24. Chen, K. Lv, R. Zhao, Y. Lu, and P. Chen, “Flexible and stable GaN piezoelectric sensor for motion monitoring and fall warning,” Nanomaterials, vol. 14, p. 2044, 2024, doi: 10.3390/nano14092044.
  25. Duan, Y. Zhang, Y. Zhang, P. Zhu, and Y. Mao, “Recent advances of stretchable nanomaterial-based hydrogels for wearable sensors and electrophysiological signals monitoring,” Nanomaterials, vol. 14, p. 1398, 2024, doi: 10.3390/nano14071398.
  26. Qu et al., “Electric resistance of elastic strain sensors—Fundamental mechanisms and experimental validation,” Nanomaterials, vol. 13, p. 1813, 2023, doi: 10.3390/nano13101813.
  27. Tajitsu et al., “Application of braided piezoelectric poly-L-lactic acid cord sensor to sleep bruxism detection system with less physical or mental stress,” Micromachines, vol. 15, p. 86, 2023, doi: 10.3390/mi15010086.
  28. Zou et al., “Hybrid pressure sensor based on carbon nano-onions and hierarchical microstructures with synergistic enhancement mechanism for multi-parameter sleep monitoring,” Nanomaterials, vol. 13, p. 2692, 2023, doi: 10.3390/nano13152692.
  29. Cao et al., “Self-healable PEDOT:PSS-PVA nanocomposite hydrogel strain sensor for human motion monitoring,” Nanomaterials, vol. 13, p. 2465, 2023, doi: 10.3390/nano13132465.
  30. Z. Cao, X. Xu, C. He, and Z. Peng, “Electrospun nanofibers hybrid wrinkled micropyramidal architectures for elastic self-powered tactile and motion sensors,” Nanomaterials, vol. 13, p. 1181, 2023, doi: 10.3390/nano13071181.
Special Issue Subscription Original Research
Volume 13
Special Issue 06
Received 13/07/2025
Accepted 01/08/2025
Published 14/08/2025
Publication Time 32 Days
226

Login


My IP

PlumX Metrics