Image-Based Crack Morphology Characterisation for Electrical Failure Analysis in Conductive 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

    B. Sathyasri,

  • P. Sudarsanam,

  • B. V. Sai Trinath,

  • P. Vinotha,

  1. Professor, Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India
  2. Associate Professor, Department of Master of Computer Applications, BMS Institute of Technology & Management, Bangalore, Karnataka, India
  3. Assistant Professor, Department of Electrical and Electronics Engineering, School of Engineering, Mohan Babu University, Tirupati, Andhra Pradesh, India
  4. Assistant Professor, Department of Electronics and Communication Engineering, KCG College of Technology, Chennai, Tamil Nadu, India

Abstract

Electrical performance in conductive polymer composites is strongly governed by crack-network evolution, yet failure analysis typically relies on qualitative image inspection or electrical anomaly detection in isolation. This work proposes an end-to-end framework that converts optical/SEM crack imagery into a standardised crack morphology signature and quantitatively links it to electrical degradation indicators. A two-stage learning strategy is adopted: crack-representation pretraining using the public Concrete Crack Images for Classification dataset, followed by composite-specific crack segmentation. The segmented masks are transformed into skeleton-based crack graphs to extract physically interpretable descriptors, including crack density, length and width statistics, branching density, tortuosity, and connectivity. These morphology features are then mapped to electrical indicators (normalised resistance change, impedance magnitude, and partial discharge inception voltage) using a multi-task predictive model with uncertainty estimation. Example results demonstrate consistent segmentation accuracy (IoU ≈ 0.81, Dice ≈ 0.89), reliable morphology quantification, and accurate morphology-driven prediction of electrical degradation (ΔR/R0 MAE ≈ 1.6%, PDIV MAE ≈ 0.22 kV). The proposed approach enables explainable electrical failure interpretation by grounding electrical trends in measurable crack-network morphology, supporting reproducible diagnostics and comparative failure assessment across specimens and damage states.

Keywords: Crack morphology; Conductive polymer composites; Electrical failure analysis; Deep learning segmentation; Piezoresistive and dielectric degradation

How to cite this article:
B. Sathyasri, P. Sudarsanam, B. V. Sai Trinath, P. Vinotha. Image-Based Crack Morphology Characterisation for Electrical Failure Analysis in Conductive Polymer Composites. Journal of Polymer & Composites. 2026; 14(02):-.
How to cite this URL:
B. Sathyasri, P. Sudarsanam, B. V. Sai Trinath, P. Vinotha. Image-Based Crack Morphology Characterisation for Electrical Failure Analysis in Conductive Polymer Composites. Journal of Polymer & Composites. 2026; 14(02):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=242220


References

  1. Tang, P. Zhang, Y. Zhao, and Z. Zhong, “Deep learning-based semantic segmentation for morphological fractography,” Engineering Fracture Mechanics, vol. 303, Art. no. 110149, Jun. 2024.
  2. M. Azad, A. U. R. Shah, M. N. Prabhakar, and H. S. Kim, “Deep Learning-Based Microscopic Damage Assessment of Fiber-Reinforced Polymer Composites,” Materials, vol. 17, no. 21, Art. no. 5265, Oct. 2024.
  3. Xu and C. Liu, “Physics-guided deep learning for damage detection in CFRP composite structures,” Composite Structures, vol. 331, Art. no. 117889, Mar. 2024.
  4. Cheng, J. Liu, K. Zheng, Z. Wu, L. Shi, and X. Hu, “Monitoring of damage evolution in carbon fiber reinforced polymer composites by electrical impedance tomography,” NDT & E International, vol. 148, Art. no. 103239, Dec. 2024.
  5. S. Akmanov, S. V. Lomov, M. Y. Spasennykh, and S. G. Abaimov, “Machine learning for crack detection in an anisotropic electrically conductive nano-engineered composite interleave with realistic geometry,” International Journal of Engineering Science, vol. 205, Art. no. 104171, Dec. 2024.
  6. Jovarauskaite, G. Monastyreckis, L. Mishnaevsky Jr., and D. Zeleniakiene, “Self-sensing composites with damage mapping using 3D carbon fibre grid,” Composites Part B: Engineering, vol. 295, Art. no. 112182, Apr. 2025.
  7. Dong, E. Bilotti, H. Zhang, C. S. Boland, and D. G. Papageorgiou, “High performing piezoresistive MoS, epoxy strain sensors for structural health monitoring,” Polymer, vol. 309, Art. no. 127449, Sep. 2024.
  8. Zarzoso, A. Mikhalchan, D. Mocerino, P. Romero-Rodriguez, R. Losada, J. J. Vilatela, and C. González, “Strain sensing of structural composites by integrated piezoresistive CNT yarn sensors,” Composites Part B: Engineering, vol. 286, Art. no. 111752, Nov. 2024.
  9. Wang, B. Du, Y. Chen, X. Lin, and X. Kong, “Electrical insulation and dielectric properties of aramid fiber reinforced epoxy composites under mechanical stress,” Composites Science and Technology, vol. 255, Art. no. 110733, Aug. 2024.
  10. Gupta, E. Ruzicka, B. C. Benicewicz, R. Sundararaman, and L. S. Schadler, “Dielectric Properties of Polymer Nanocomposite Interphases Using Electrostatic Force Microscopy and Machine Learning,” ACS Applied Electronic Materials, vol. 5, no. 2, pp. 794–802, Jan. 2023.
  11. Ç. F. Özgenel, “Concrete Crack Images for Classification,” Mendeley Data, v2, Jul. 2019.
  12. Raja MR, Krishnan GH, Mohammad A, Cheerla S. Dual temporal gated multi-graph convolution network based neurodegenerative disease detection and severity prediction. Biomedical Signal Processing and Control. 2026;112(Pt A):108566.
  13. Nesteena KN, Krishnan GH, Parthiban V, Krishna S, Sarkar S. In Silico Identification of 9-Amino Camptothecin as a Dual Inhibitor of VEGF-A and VEGF-B in N1–N8 Breast Cancer. Biotechnology and Applied Biochemistry. 2025 Oct 28. Online ahead of print.
  14. Mohandass G, Sridhathan C, Krishnan GH, Nandhini I. Optimized dense back-projection joint attention network for automatic seizure detection from EEG signal. Computer Methods in Biomechanics and Biomedical Engineering. 2025. Published online (Nov 2025).
  15. Krishnan GH, Sheeba S, Mohandass G, Kumar NMG, Reddy MRP. Automated Blood Cell Counting and Disease Identification Using Image Processing: Implications for Polymer Composite-Based Biomedical Diagnostic Devices. Journal of Polymer and Composites. 2025;13(06):262–270.
  16. Krishnan GH, Umashankar G, Sheeba S, Reddy MRP, Prasanth BV. Dual-Stream Deep Learning Framework for Brain CT Image Classification and Implications for Polymer Composite Neuro Implant Evaluation. Journal of Polymer and Composites. 2025;13(06):172–179.
  17. Krishnan GH, Mohandass G, Umashankar G, Reddy MRP, Ravindra G. AI-Assisted Defect Detection in Polymer Composite Insulators Using an Optimised Ensemble Deep Learning Framework for Structural Health Monitoring. Journal of Polymer and Composites. 2025;13(05).
  18. Mohandass G, Krishnan GH, Selvaraj D, Sridhathan C. Lung Cancer Classification using Optimized Attention-based Convolutional Neural Network with DenseNet-201 Transfer Learning Model on CT image. Biomedical Signal Processing and Control. 2024 Sep;95:106330.
  19. H. Krishnan, S. Prabhu, M. Himabindu, N. V. Karthikeya Reddy, S. Mounika and S. Santhosh, “Comparative Analysis Fault Detection in HT Electrical Insulators using Modified Transfer Learning based ResNet50, EfficientNetB0, and VGG16 through Image Processing,” 2024 10th International Conference on Electrical Energy Systems (ICEES), Chennai, India, 2024, pp. 1-5.
  20. Umashankar G, Krishnan GH, Sudhakar T, Mohandass G, Devaraju T, Devika V, Banu SS. Eye Blink Based Biometric Authentication System. In: 2023 International Conference on Bio Signals, Images, and Instrumentation (ICBSII). 2023:1–4.
  21. Krishnan GH, Sukanya K, Sainath Reddy JS, Surya Prakash Reddy KS, Niharika N, Siva Sai Kiran MS. CNN based image processing for crack detection on HT insulator’s surface. In: 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS). 2023:618–621.
  22. Ganesan, N. E. Edwin Paul, G. Hari Krishnan, S. Aarthi and I. Kumara Swamy, “Detecting Diabetes Mellitus from Tongue Image Hybrid Features and Neural Netowrk Classifier,” 2022 IEEE 4th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), Goa, India, 2022, pp. 425-427,
  23. Santhosh S, Juliet AV, Krishnan GH. Predictive analysis of identification and disease condition monitoring using bioimpedance data. Journal of Ambient Intelligence and Humanized Computing. 2021;12(2):2955–2963.
  24. Santhosh S, Vimala Juliet A, Krishnan GH. Simulation of Signal Generation and Measuring Circuit and Real Time IoT Based Electrical Bio Impedance Cardiac Monitoring System. In: Pandian A, Ntalianis K, Palanisamy R, eds. Intelligent Computing, Information and Control Systems (ICICCS 2019). Advances in Intelligent Systems and Computing. Vol 1039. Springer; 2020:701–706.
  25. Sudhakar T, Hari Krishnan G, Santosh S, Meenakshi S, Thomas L. Prosthetic arm control using processing device, a comparative approach. Biomedical Research. 2018;29(13):2906–2911.
  26. Krishnan H, Natarajan RA, Nanda A. Impact of upper limb joint fluid variation on inflammatory diseases diagnosis. Journal of Electrical Engineering & Technology. 2014;9(6):2114–2117.
  27. Krishnan GH, Natarajan RA, Nanda A. Microcontroller based non invasive diagnosis of knee joint diseases. In: 2014 International Conference on Information Communication and Embedded Systems (ICICES). 2014:1–5.
  28. Guru Anand V, Hari Krishna G, Mohandass G, Hemalatha RJ, Sundaram S. Predicting grade of prostate cancer using image analysis software. In: Proceedings of the 2nd International Conference on Trendz in Information Sciences & Computing (TISC-2010). 2010:122–124.
  29. Manickaraj, R. Thirumalaisamy, S. Palanisamy, N. Ayrilmis, E. E. Massoud, M. Palaniappan, and S. L. Sankar, “Value-added utilization of agricultural wastes in biocomposite production: Characteristics and applications,” Ann. N. Y. Acad. Sci., vol. 1549, no. 1, pp. 72–91, Jul. 2025. doi: 10.1111/nyas.15368.
  30. Palanisamy, M. Kalimuthu, S. Dharmalingam, A. Alavudeen, R. Nagarajan, S. O. Ismail, S. Siengchin, F. Mohammad, and H. A. Al-Lohedan, “Effects of fiber loadings and lengths on mechanical properties of Sansevieria Cylindrica fiber reinforced natural rubber biocomposites,” Mater. Res. Express, vol. 10, no. 8, p. 085503, Aug. 2023. doi: 10.1088/2053-1591/acefb0.
  31. Palaniappan, S. Palanisamy, T. Murugesan, S. Tadepalli, R. Khan, S. Ataya, and C. Santulli, “Influence of washing with sodium lauryl sulphate (SLS) surfactant on different properties of ramie fibres,” BioResources, vol. 19, no. 2, pp. 2609–2625, 2024. doi: 10.15376/biores.19.2.2609-2625.
  32. Ramasubbu, A. Kayambu, S. Palanisamy, and N. Ayrilmis, “Mechanical properties of epoxy composites reinforced with Areca catechu fibers containing silicon carbide,” BioResources, vol. 19, no. 2, pp. 2353–2370, 2024. doi: 10.15376/biores.19.2.2353-2370.
  33. Ayrilmis, G. Kanat, E. Yildiz Avsar, S. Palanisamy, and A. Ashori, “Utilizing waste manhole covers and fibreboard as reinforcing fillers for thermoplastic composites,” J. Reinf. Plast. Compos., vol. 44, no. 17–18, pp. 1108–1118, Sep. 2025. doi: 10.1177/07316844241238507.
  34. Mylsamy, K. Aruchamy, S. K. M. Shanmugam, S. Palanisamy, and N. Ayrilmis, “Improving performance of composites: Natural and synthetic fibre hybridisation techniques in composite materials – A review,” Mater. Chem. Phys., vol. 334, p. 130439, Apr. 2025. doi: 10.1016/j.matchemphys.2025.130439.
Ahead of Print Subscription Original Research
Volume 14
02
Received 25/02/2026
Accepted 14/03/2026
Published 30/04/2026
Publication Time 64 Days
2

Login


My IP

PlumX Metrics