Deep Learning for Real-Time Monitoring and Defect Detection in Additive Manufactured Polymer Composites

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 | 02 | Page :
    By

    Dillip Kumar Mohanta,

  • M Khaleel Ullah Khan,

  • Subhajeet Das,

  • Nitish Kumar Choudhary,

  • Rahat Naz,

  • Vishwesh Nagamalla,

  1. Assistant Professor, Department of Mechanical Engineering, Centurion University of Technology and Management, Odisha, India
  2. Associate Professor, Department of Electronics and Communication Engineering, Vignan Institute of Technology and Science, Hyderabad, Telangana, India
  3. Assistant Professor, Department of Computer Science and Engineering – Artificial Intelligence, Brainware University, West Bengal, India
  4. Deputy Controller of Examination, State Board of Technical Education, Patna, Bihar, India
  5. Assistant Professor, School of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, India
  6. Assistant Professor, Department of Artificial Intelligence and Data Science, Sanjivani University, Maharashtra, India

Abstract

Additives Fiber-reinforced polymer composite ADDs have high utility in making lightweight structural components, but due to process-related defects (interlayer delamination and reinforcement stacking) the integrity of consolidation during extrusion-based deposition is frequently compromised. This paper has presented a physics-informed deep learning framework that is applicable to real-time measurements of reinforced thermoplastic composite fabrication. Multimodal sensing was provided with thermal gradient, optical morphology, and acoustics emission signals being used to assess the interlayer bonding behavior at successive cycles of deposition. This approach explicitly captures the influence of melt rheology and interlayer diffusion on consolidation stability during composite layer formation. The proposed monitoring system achieved a defect detection accuracy of 91.8% with a reduced standard deviation of 1.7% across monitored layers. Under stable deposition conditions, the consolidation integrity index remained above 0.85, whereas disturbed extrusion parameters resulted in a decline to 0.38, corresponding to a 44% increase in defect probability. Comparative analysis demonstrated an accuracy improvement of 7.3% over conventional vision-based monitoring techniques. Furthermore, the proposed framework establishes a scalable pathway toward intelligent, process-adaptive quality control in polymer composite additive manufacturing systems. These results suggest that the use of polymer process-structure associations in a deep learning based monitoring framework can be used to increase sensitive consolidation anomalies in the fiber-reinforced thermoplastic systems to facilitate better real-time quality evaluation during additive manufacturing of polymer composite structures.

Keywords: Polymer composites, Additive manufacturing, Defect detection, Interlayer consolidation, Real-time monitoring

How to cite this article:
Dillip Kumar Mohanta, M Khaleel Ullah Khan, Subhajeet Das, Nitish Kumar Choudhary, Rahat Naz, Vishwesh Nagamalla. Deep Learning for Real-Time Monitoring and Defect Detection in Additive Manufactured Polymer Composites. Journal of Polymer & Composites. 2026; 14(02):-.
How to cite this URL:
Dillip Kumar Mohanta, M Khaleel Ullah Khan, Subhajeet Das, Nitish Kumar Choudhary, Rahat Naz, Vishwesh Nagamalla. Deep Learning for Real-Time Monitoring and Defect Detection in Additive Manufactured Polymer Composites. Journal of Polymer & Composites. 2026; 14(02):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=240352


References

  1. Lu, J. Hou, S. Yuan, X. Yao, Y. Li, and J. Zhu, “Deep learning-assisted real-time defect detection and closed-loop adjustment for additive manufacturing of continuous fiber-reinforced polymer composites,” Robotics and Computer-integrated Manufacturing, vol. 79, p. 102431, Feb. 2023, doi: 10.1016/j.rcim.2022.102431.
  2. Phillips, D. Kumar, Y. Liu, and S. Namilae, “Zero-bias deep neural network for defect detection in composite additive manufacturing using multisource in-situ data,” Jan. 2024, doi: 10.2514/6.2024-0264.
  3. Rhim, “Real-time in-situ thermal monitoring system and defect detection using deep learning applied to additive manufacturing,” May 2024, doi: 10.21741/9781644903131-43.
  4. Wang et al., “A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies.,” Micromachines, vol. 15, no. 1, Dec. 2023, doi: 10.3390/mi15010028.
  5. Kumar, Y. Liu, H. Song, and S. Namilae, “Explainable deep neural network for in-plain defect detection during additive manufacturing,” Rapid Prototyping Journal, vol. 30, no. 1, pp. 49–59, Sep. 2023, doi: 10.1108/rpj-05-2023-0157.
  6. Wang, P. Wang, H. Zhang, X. Chen, M. Chen, and J. Li, “An In-Situ Deep Learning-Based Defect Detection Technology for Additive Manufacturing Process,” Oct. 2023, doi: 10.1109/icicm59499.2023.10366010.
  7. Kunkel, N., Thölken, D., & Behler, K. (2024). Deep Learning-based automated defect classification for Powder Bed Fusion – Laser Beam. European Journal of Materials, 1–13. https://doi.org/10.1080/26889277.2024.2427401
  8. Gabstur, M. Pollák, and P. Baron, “Detection of process errors of additive manufacturing,” MM Science Journal, vol. 2024, no. 3, Jun. 2024, doi: 10.17973/mmsj.2024_06_2023153.
  9. V. Bhandarkar, M. Karnati, and P. Tandon, “Defect detection in 3D-printed polymer parts using deep learning models: a comparative investigation,” Rapid Prototyping Journal, Mar. 2025, doi: 10.1108/rpj-09-2024-0395.
  10. Khanafer, J. Cao, and H. Kokash, “Condition Monitoring in Additive Manufacturing: A Critical Review of Different Approaches,” Journal of manufacturing and materials processing, May 2024, doi: 10.3390/jmmp8030095.
  11. Malashin et al., “Machine Learning in 3D and 4D Printing of Polymer Composites: A Review,” Polymers, vol. 16, no. 22, p. 3125, Nov. 2024, doi: 10.3390/polym16223125.
  12. Moghadam, S. N. Bhatia, F. Davoudi Kakhki, and H. Ichikawa, “Integrating Synthetic Data and Deep Learning for Enhanced Defect Detection and Quality Assurance in Manufacturing Processes,” Jan. 2025, doi: 10.20944/preprints202501.0204.v1.
  13. A. Ashebir et al., “Detecting Multi-Scale Defects in Material Extrusion Additive Manufacturing of Fiber-Reinforced Thermoplastic Composites: A Review of Challenges and Advanced Non-Destructive Testing Techniques,” Polymers, vol. 16, no. 21, p. 2986, Oct. 2024, doi: 10.3390/polym16212986.
  14. C. Mungundungundu, R. Chikore, and A. Chiwanza, “Real-Time Image Processing for Defect Detection in Laser Powder Bed Fusion Using Machine Learning,” International journal of computer science and mobile computing, vol. 14, no. 7, pp. 28–33, Jul. 2025, doi: 10.47760/ijcsmc.2025.v14i07.003.
  15. Jayatwa, M. Mabrok and D. S. Han, “AI Techniques for Anomaly Detection in Polymer-Based 3D Printing: A Review,” 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), Antalya, Turkiye, 2025, pp. 1-6, doi: 10.1109/ACDSA65407.2025.11166574.
  16. Zhang, H. Yang, Z. Yang, and Y. Lu, “Engineering-guided Deep Feature Learning for Manufacturing Process Monitoring,” Journal of Computing and Information Science in Engineering, pp. 1–17, Jul. 2024, doi: 10.1115/1.4066026.
  17. Pike et al., “Accurate and fast anomaly detection in additive composite-based manufacturing using thermal cameras,” Jan. 2025, doi: 10.33599/nasampe/s.25.0260.
  18. Wang et al., “A Novel Depth-Connected Region-Based Convolutional Neural Network for Small Defect Detection in Additive Manufacturing,” Cognitive Computation, vol. 17, no. 1, Dec. 2024, doi: 10.1007/s12559-024-10397-8.
  19. Thakur, S. K. Mishra, S. S. Jose, et al., “Deep learning for object recognition and defect analysis in additive manufacturing,” Discover Materials, vol. 5, Art. no. 206, 2025. Available: http://doi.org/10.1007/s43939-025-00408-2
  20. Shah, D. Suraj, S. M. Reza, M. A. R. B. A. Salam, A. Ashraf, and S. F. Ferdous, “Comparative analysis of deep learning models for defect detection in additive manufacturing using thermal imaging,” Results in Engineering, vol. 28, Dec. 2025, Art. no. 108359. Available: http://doi.org/10.1016/j.rineng.2025.108359
  21. H. Zubayer, Y. Xiong, Y. Wang, and H. M. Imdadul, “Enhancing additive manufacturing precision: Intelligent inspection and optimization for defect-free continuous carbon fiber-reinforced polymer,” Composites Part C: Open Access, vol. 14, Jul. 2024, Art. no. 100451, doi: http://doi.org/10.1016/j.jcomc.2024.100451
  22. Sivasubramanian Palanisamy et al 2023 Mater. Res. Express 10 085503
  23. Yu, Y. Yao, W. Zhang, L. Lu, Q. Gao, P. Zhang, and S. L. Sing, “Defects, monitoring, and AI-enabled control in soft material additive manufacturing: A review,” Virtual and Physical Prototyping, vol. 20, no. 1, 2025, doi: http://doi.org/10.1080/17452759.2025.2588456
  24. Zhao, X. Wang, J. Sun, Y. Wang, Z. Chen, J. Wang, and X. Xu, “Artificial intelligence powered real-time quality monitoring for additive manufacturing in construction,” Construction and Building Materials, vol. 429, May 24, 2024, Art. no. 135894, doi: http://doi.org/10.1016/j.conbuildmat.2024.135894
  25. Segura Ibarra, R.-E.-N. Hossain, R. C. Lamonte, A. L. Moore, and J. Chen, “Enhancing defect detection in additive manufacturing using a conditional autoencoder with skip connections and in situ infrared sensing,” Journal of Manufacturing Processes, vol. 156, pt. A, pp. 268–283, Dec. 26, 2025, doi: http://doi.org/10.1016/j.jmapro.2025.10.099
  26. Charalampous, I. Kostavelis, C. Kopsacheilis, et al., “Vision-based real-time monitoring of extrusion additive manufacturing processes for automatic manufacturing error detection,” The International Journal of Advanced Manufacturing Technology, vol. 115, pp. 3859–3872, 2021, doi: http://doi.org/10.1007/s00170-021-07419-2
  27. Mamodiya, I. Kishor, S. K. Pandey, and A. K. Badhan, “Augmented and virtual reality-driven deep learning for securing critical infrastructures,” in Deep Learning Innovations for Securing Critical Infrastructures, 2025, pp. 12. doi: 10.4018/979-8-3373-0563-9.ch011.
  28. Deshpande, V. Venugopal, M. Kumar, et al., “Deep learning-based image segmentation for defect detection in additive manufacturing: An overview,” The International Journal of Advanced Manufacturing Technology, vol. 134, pp. 2081–2105, 2024, doi: http://doi.org/10.1007/s00170-024-14191-6
  29. Li et al., “Lightweight You Only Look Once-based automatic defect detection in wire arc additive manufacturing,” Materials science in additive manufacturing, vol. 4, no. 4, p. 025210035, Aug. 2025, doi: 10.36922/msam025210035.
  30. Karuppusamy et al., “Real-time monitoring in polymer composites: Internet of things integration for enhanced performance and sustainability — A Review,” Bioresources, vol. 20, no. 3, Jun. 2025, doi: 10.15376/biores.20.3.karuppusamy.
  31. Chen et al., “In-situ process monitoring and adaptive quality enhancement in laser additive manufacturing: A critical review,” Journal of Manufacturing Systems, Apr. 2024, doi: 10.1016/j.jmsy.2024.04.013.
  32. Li, T. Huang, J. Liu, and L. Tan, “Time-series vision transformer based on cross space-time attention for fault diagnosis in fused deposition modelling with reconstruction of layer-wise data,” Journal of Manufacturing Processes, Apr. 2024, doi: 10.1016/j.jmapro.2024.01.082.
  33. Kim, Z. Yang, Y. Lu, and G. Hong, “Self-supervised multi-label melt pool anomaly classification in powder bed fusion additive manufacturing,” Journal of Computing and Information Science in Engineering, pp. 1–34, Apr. 2025, doi: 10.1115/1.4068323.
  34. Nasrin, F. Pourkamali‐Anaraki, and A. M. Peterson, “Application of machine learning in polymer additive manufacturing: A review,” Journal of Polymer Science, Dec. 2023, doi: 10.1002/pol.20230649.
  35. Karimi, S. A. A. B. Tabary, and H. Fayazfar, “In‐depth investigation and industry plan for enhancing surface finishing of 3D printed polymer composite components: A critical review,” Journal of Applied Polymer Science, Mar. 2024, doi: 10.1002/app.55494.
  36. Daghigh, H. Daghigh, T. E. Lacy Jr., and M. Naraghi, “Review of machine learning applications for defect detection in composite materials,” Machine Learning with Applications, vol. 18, Dec. 2024, Art. no. 100600, doi: http://doi.org/10.1016/j.mlwa.2024.100600
  37. A. I. Chellam, B. B. Mansingh, D. S. Alex, and J. S. Binoj, “Prediction and Validation of Mechanical Properties of Areca catechu/Tamarindus indica Fruit Fiber with Nano Coconut Shell Powder Reinforced Hybrid Composites,” Journal of Polymer Materials, vol. 0, no. 0, pp. 1–10, Jan. 2025, doi: 10.32604/jpm.2025.069295.
  38. Manickaraj, K., Thirumalaisamy, R., Palanisamy, S., Ayrilmis, N., Massoud, E. E. S., Palaniappan, M., & Sankar, S. L. (2025). Value-added utilization of agricultural wastes in biocomposite production: Characteristics and applications. Ann NY Acad Sci., 1549, 72–91. https://doi.org/10.1111/nyas.15368
  39. V. Yakovlev et al., “Microscopic Endurance of Rubber Compounds Investigated by In Situ Ultra Small‐Angle X‐Ray Scattering,” Journal of Applied Polymer Science, Aug. 2025, doi: 10.1002/app.57755.
  40. Aka and A. Akşit, “Influence of Jet Formation Dynamics on Fiber Morphology in Electrospinning: An Advanced Image Processing Approach,” Journal of Applied Polymer Science, Jun. 2025, doi: 10.1002/app.57457.
Ahead of Print Subscription Original Research
Volume 14
02
Received 14/03/2026
Accepted 31/03/2026
Published 20/04/2026
Publication Time 37 Days
1

Login


My IP

PlumX Metrics