AI-Assisted Defect Detection in Polymer Composite Insulators Using an Optimised Ensemble Deep Learning Framework for Structural Health Monitoring

Year : 2025 | Volume : 13 | Special Issue 06 | Page : 253 261
    By

    Hari Krishnan G,

  • Mohandass G,

  • Umashankar G,

  • Ram Prasad Reddy M,

  • Ravindra G,

  1. Associate Professor, Department of Electrical and Electronics Engineering, School of Engineering, Mohan Babu University, Tirupati, Andhra Pradesh, India
  2. Professor, Department of Biomedical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamil Nadu, India
  3. Assistant Professor, Department of Biomedical Engineering, GRT Institute of Engineering and Technology, Chennai, Tamil Nadu, India
  4. Professor, Department of Biomedical Engineering, GRT Institute of Engineering and Technology, Chennai, Andhra Pradesh, India
  5. Assistant Professor, Department of Electrical and Electronics Engineering, Sri Venkateswara College of Engineering and Technology, Chittoor, Andhra Pradesh, India

Abstract

Polymer composite insulators, particularly those made from silicone rubber and epoxy resins, are increasingly adopted in high-voltage transmission systems due to their superior electrical insulation, lightweight design, hydrophobicity, and environmental durability. Despite their advantages, these materials are susceptible to surface degradation, mechanical cracking, and flashover under prolonged exposure to environmental pollutants, thermal stress, and electrical aging. Accurate, real-time condition assessment of these composite insulators is critical for ensuring operational safety, preventing grid failure, and extending material lifespan. This study proposes an intelligent image-based inspection framework specifically tailored for polymer composite insulators used in high-voltage networks. The framework integrates an optimized ensemble of VGG16 and ResNet50 convolutional neural networks to detect and classify physical defects such as broken surfaces and flashover burn marks—symptoms directly linked to polymer degradation and loss of dielectric properties. The method was trained on high-resolution field images of polymer insulators and demonstrated classification accuracies exceeding 91%, with strong precision and recall across all fault classes. By enabling non-destructive, automated evaluation of surface-level deterioration in polymer composites, this approach provides valuable insights into failure mechanisms and supports risk-based maintenance strategies. It offers a promising tool for advancing structural health monitoring in polymer engineering, particularly within the context of electrical insulation materials in smart grids.

Keywords: Polymer composite insulators, high-voltage electrical systems, surface degradation, deep learning classification, structural health monitoring, silicone rubber, epoxy resin, flashover detection, non-destructive evaluation, predictive maintenance

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

How to cite this article:
Hari Krishnan G, Mohandass G, Umashankar G, Ram Prasad Reddy M, 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(06):253-261.
How to cite this URL:
Hari Krishnan G, Mohandass G, Umashankar G, Ram Prasad Reddy M, 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(06):253-261. Available from: https://journals.stmjournals.com/jopc/article=2025/view=227140


Browse Figures

References

  1. Yang et al., “Research on Position and Recognition Algorithms for Insulators Based on EfficientDet,” 2021 International Conference on Electrical Materials and Power Equipment (ICEMPE), Chongqing, China, 2021, pp. 1-4, doi: 10.1109/ICEMPE51623.2021.9509077.
  2. She, Y. Fan, M. Xu, J. Wang, J. Xue and J. Ou, “Insulator Breakage Detection Utilizing a Convolutional Neural Network Ensemble Implemented With Small Sample Data Augmentation and Transfer Learning,” in IEEE Transactions on Power Delivery, vol. 37, no. 4, pp. 2787-2796, Aug. 2022, doi: 10.1109/TPWRD.2021.3116600.
  3. H. Krishnan, K. Sukanya, J. S. S. Reddy, K. S. P. Reddy, N. Niharika and M. S. S. Kiran, “CNN based Image Processing for Crack Detection on HT Insulator’s Surface,” 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), Coimbatore, India, 2023, pp. 618-621, doi: 10.1109/ICSCSS57650.2023.10169853.
  4. Pratik Kulkarni. INSULATOR DEFECT DETECTION. https://kaggle.com/competitions/insulator-defect-detection, 2022. Kaggle.
  5. Reddy, Nagarjuna A., G. Hari Krishnan, and D. Raghuram. “Real time patient health monitoring using raspberry PI.” Research Journal of Pharmaceutical Biological and Chemical Sciences6 (2016): 570-575.
  6. Abinaya, Hari Krishnan, G, R. J Hemalatha, G Mohandass. “Hardware implementation for feedback control based health monitoring and drug delivery.” Biomedicine (India) 37.1 (2017): 123-126.
  7. Sudhakar, G. Hari Krishnan, N. R. Krishnamoorthy, B. Janney J, M. Pradeepa and J. P. Raghavi, “Sleep Disorder Diagnosis using EEG based Deep Learning Techniques,” 2021 Seventh International conference on Bio Signals, Images, and Instrumentation (ICBSII), Chennai, India, 2021, pp. 1-4, doi: 10.1109/ICBSII51839.2021.9445158.
  8. Mohandass, G. H. Krishnan, C. Sridhathan, et al., “Lung cancer classification using optimized attention-based convolutional neural network with DenseNet-201 transfer learning model on CT image,” Biomedical Signal Processing and Control, vol. 95, p. 106351, Sep. 2024, doi: 10.1016/j.bspc.2024.106351.
  9. Santhosh, A. V. Juliet, and G. H. Krishnan, “Predictive analysis of identification and disease condition monitoring using bioimpedance data (Retracted Article),” Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 2, pp. 2955–2963, Feb. 2021, doi: 10.1007/s12652-020-01988-3.
  10. Santhosh, A. V. Juliet, and G. H. Krishnan, “Simulation of signal generation and measuring circuit and real-time IoT based electrical bio impedance cardiac monitoring system,” in Intelligent Computing, Information and Control Systems (ICICCS 2019), vol. 1039, pp. 701–706, 2020, doi: 10.1007/978-981-32-9817-0_74.
  11. N. Reddy, G. H. Krishnan, and D. Raghuram, “Real time patient health monitoring using Raspberry PI,” Research Journal of Pharmaceutical, Biological and Chemical Sciences, vol. 7, no. 6, pp. 570–575, Nov.–Dec. 2016.
  12. H. Krishnan, G. Umashankar, and S. Abraham, “Cerebrovascular disorder diagnosis using MR angiography,” Biomedical Research-India, vol. 27, no. 3, pp. 773–775, 2016.
  13. Mohandass, R. A. Natarajan, and G. H. Krishnan, “Comparative analysis of optical coherence tomography retinal images using multidimensional and cluster methods,” Biomedical Research-India, vol. 26, no. 2, pp. 273–285, Apr.–Jun. 2015.
  14. Sabarivani and G. H. Krishnan, “Home health assistive system for critical care patients,” Research Journal of Pharmaceutical, Biological and Chemical Sciences, vol. 6, no. 2, pp. 629–633, Mar.–Apr. 2015.
  15. H. Krishnan, R. A. Natarajan, and A. Nanda, “Impact of upper limb joint fluid variation on inflammatory diseases diagnosis,” Journal of Electrical Engineering & Technology, vol. 9, no. 6, pp. 2114–2117, Nov. 2014, doi: 10.5370/JEET.2014.9.6.2114.
  16. H. Krishnan, R. A. Natarajan, and A. Nanda, “Microcontroller based non invasive diagnosis of knee joint diseases,” in 2014 International Conference on Information Communication and Embedded Systems (ICICES), pp. 1–5, 2014, doi: 10.1109/ICICES.2014.7033973.
  17. Almeshaal, M., Palanisamy, S., Murugesan, T. M., Palaniappan, M., & Santulli, C. (2022). Physico-chemical characterization of Grewia Monticola Sond (GMS) fibers for prospective application in biocomposites. Journal of Natural Fibers, 19(17), 15276–15290.
  18. Palanisamy, S.; Kalimuthu, M.; Azeez, A.; Palaniappan, M.; Dharmalingam, S.; Nagarajan, R.; Santulli, C. Wear Properties and Post-Moisture Absorption Mechanical Behavior of Kenaf/Banana-Fiber-Reinforced Epoxy Composites. Fibers 2022, 10, 32. https://doi.org/10.3390/fib10040032.
  19. Palaniappan, M., Palanisamy, S., Murugesan, T.M. et al. Novel Ficus retusa aerial root fiber: a sustainable alternative for synthetic fibres in polymer composites reinforcement. Biomass Conv. Bioref. 15, 7585–7601 (2025). https://doi.org/10.1007/s13399-024-05495-4,
  20. Palaniappan, M., Palanisamy, S., Khan, R. et al. Synthesis and suitability characterization of microcrystalline cellulose from Citrus x sinensis sweet orange peel fruit waste-based biomass for polymer composite applications. J Polym Res 31, 105 (2024). https://doi.org/10.1007/s10965-024-03946-0.
  21. Palanisamy, S., Kalimuthu, M., Palaniappan, M., Alavudeen, A., Rajini, N., Santulli, C., … Al-Lohedan, H. (2021). Characterization of Acacia caesia Bark Fibers (ACBFs). Journal of Natural Fibers, 19(15), 10241–10252. https://doi.org/10.1080/15440478.2021.1993493.
Special Issue Subscription Original Research
Volume 13
Special Issue 06
Received 26/08/2025
Accepted 05/09/2025
Published 15/09/2025
Publication Time 20 Days
332

Login


My IP

PlumX Metrics