Inverse Estimation of Defect Distribution in Ceramics using Particle Swarm Optimization

Mehedi Hassan  Maruf; Mostafizur  Rahman; Priyam  Chakraborty

doi:10.38032/scse.2026.4.189

Authors

Mehedi Hassan Maruf Department of Mechanical Engineering, Chittagong University of Engineering & Technology (CUET), Chattogram-4349, Bangladesh
Mostafizur Rahman Department of Mechanical Engineering, Chittagong University of Engineering & Technology (CUET), Chattogram-4349, Bangladesh
Priyam Chakraborty Department of Mechanical Engineering, Chittagong University of Engineering & Technology (CUET), Chattogram-4349, Bangladesh

DOI:

https://doi.org/10.38032/scse.2026.4.189

Keywords:

Ceramics, Defect analysis, Weibull distribution, PSO Optimization, YOLO

Abstract

This study presents an automated framework for characterizing defects in ceramics by integrating the YOLO-based computer vision and particle swarm optimization (PSO). A total of 16,215 defects across 886 ceramic samples were analyzed and categorized into surface, crack, and chip types. Bounding box data from the YOLO detection were converted to equivalent crack lengths (5–70 . Thereafter, the Weibull distribution parameters for the crack defects were estimated using PSO, yielding a shape parameter β = 2.188 and scale η = 13.59 indicative of the increasing failure rate of typical brittle materials. In addition, PSO outperformed the traditional maximum likelihood estimation (MLE), with lower Kolmogorov-Smirnov statistics (KS = 0.1091 vs. 0.1092), confirming the superior model fit. Furthermore, the theoretical mean defect size (12.04 ) closely matched the observed data (11.98 ), with a 0.43% error. Hence, validation using probability plots, cumulative distribution analysis, and the Gumbel probability paper demonstrated the robustness of this approach. The framework supports real-time defect characterization and reliability assessment, providing practical relevance for industrial quality control. Overall, this approach enhances inverse defect analysis in ceramics by combining modern computer vision and global optimization for accurate and efficient defect estimation.

Downloads

PDF

Downloads

Download data is not yet available.

References

[1] K. Matsunaga, M. Yoshiya, N. Shibata, H. Ohta, and T. Mizoguchi, “Ceramic science of crystal defect cores,” Journal of the Ceramic Society of Japan, vol. 130, no. 8, pp. 648–667, Aug. 2022, doi: DOI: https://doi.org/10.2109/jcersj2.22080

[2] 10.2109/JCERSJ2.22080.

[3] M. Rahman, T. Maeda, T. Osada, and S. Ozaki, “Finite element analysis of crack propagation, crack-gap-filling, and recovery behavior of mechanical properties in oxidation-induced self-healing ceramics,” Int. J. Solids Struct., vol. 306, Jan. 2025, doi: 10.1016/J.IJSOLSTR.2024.113104. DOI: https://doi.org/10.1016/j.ijsolstr.2024.113104

[4] M. Rahman, T. Maeda, T. Osada, and S. Ozaki, “Method of Determining Kinetic Parameters of Strength Recovery in Self-Healing Ceramic Composites,” Materials, vol. 16, no. 11, Jun. 2023, doi: 10.3390/MA16114079. DOI: https://doi.org/10.3390/ma16114079

[5] C. Elissalde and J. Ravez, “Ferroelectric ceramics: defects and dielectric relaxations,” J. Mater. Chem., vol. 11, no. 8, pp. 1957–1967, Jan. 2001, doi: 10.1039/B010117F. DOI: https://doi.org/10.1039/b010117f

[6] S. Ozaki, Y. Aoki, T. Osada, K. Takeo, and W. Nakao, “Finite element analysis of fracture statistics of ceramics: Effects of grain size and pore size distributions,” Journal of the American Ceramic Society, vol. 101, no. 7, pp. 3191–3204, Jul. 2018, doi: 10.1111/JACE.15468. DOI: https://doi.org/10.1111/jace.15468

[7] M. H. Berger and D. Jeulin, “Statistical analysis of the failure stresses of ceramic fibres: Dependence of the Weibull parameters on the gauge length, diameter variation and fluctuation of defect density,” J. Mater. Sci., vol. 38, no. 13, pp. 2913–2923, Jul. 2003, doi: 10.1023/A:1024405123420/METRICS. DOI: https://doi.org/10.1023/A:1024405123420

[8] M. Rahman, T. Maeda, T. Osada, and S. Ozaki, “Finite Element Analysis of R-Curve Behavior in Ceramics Using the Damage Model Based on the Cohesive-Zone Relationship,” International Journal of Ceramic Engineering and Science, vol. 7, no. 5, Sep. 2025, doi: 10.1002/CES2.70025. DOI: https://doi.org/10.1002/ces2.70025

[9] L. Xu et al., “Detecting defects in fused deposition modeling based on improved YOLO v4,” Mater. Res. Express, vol. 10, no. 9, p. 095304, Sep. 2023, doi: 10.1088/2053-1591/ACF6F9. DOI: https://doi.org/10.1088/2053-1591/acf6f9

[10] J. H. Kim, N. Kim, Y. W. Park, and C. S. Won, “Object Detection and Classification Based on YOLO-V5 with Improved Maritime Dataset,” Journal of Marine Science and Engineering 2022, Vol. 10, Page 377, vol. 10, no. 3, p. 377, Mar. 2022, doi: 10.3390/JMSE10030377. DOI: https://doi.org/10.3390/jmse10030377

[11] “Multiple objects segmentation based on maximum-likelihood estimation and optimum entropy-distribution (MLE-OED) | IEEE Conference Publication | IEEE Xplore.” Accessed: Sep. 29, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/1044856

[12] X. Jun, H. T. Tsui, and X. Deshen, “Multiple objects segmentation based on Maximum-likelihood Estimation and Optimum Entropy-distribution(MLE-OED),” Proceedings - International Conference on Pattern Recognition, vol. 16, no. 1, pp. 707–710, 2002, doi: 10.1109/ICPR.2002.1044856. DOI: https://doi.org/10.1109/ICPR.2002.1044856

[13] R. Harikrishnan, P. M. Mohite, and C. S. Upadhyay, “Generalized Weibull model-based statistical tensile strength of carbon fibres,” Archive of Applied Mechanics, vol. 88, no. 9, pp. 1617–1636, Sep. 2018, doi: 10.1007/S00419-018-1391-9. DOI: https://doi.org/10.1007/s00419-018-1391-9

[14] M. E. H. Bourahli, “Uni- and bimodal Weibull distribution for analyzing the tensile strength of Diss fibers,” Journal of Natural Fibers, vol. 15, no. 6, pp. 843–852, Nov. 2018, doi: 10.1080/15440478.2017.1371094. DOI: https://doi.org/10.1080/15440478.2017.1371094

[15] M. Rahman, M. A. Rahman, M. S. Rabbi, and S. Ozaki, “A comprehensive review on oxidation-induced self-healing ceramic composites for high-temperature applications,” Int. J. Appl. Ceram. Technol., vol. 22, no. 5, p. e15165, Sep. 2025, doi: 10.1111/IJAC.15165. DOI: https://doi.org/10.1111/ijac.15165

[16] T. Maeda, T. Osada, and S. Ozaki, “Reliability evaluation scheme for ceramics based on defect size distribution inversely estimated from standardized tests,” Journal of the American Ceramic Society, vol. 108, no. 9, p. e20660, Sep. 2025, doi: 10.1111/JACE.20660. DOI: https://doi.org/10.1111/jace.20660

[17] M. Jain, V. Saihjpal, N. Singh, and S. B. Singh, “An Overview of Variants and Advancements of PSO Algorithm,” Applied Sciences 2022, Vol. 12, Page 8392, vol. 12, no. 17, p. 8392, Aug. 2022, doi: 10.3390/APP12178392. DOI: https://doi.org/10.3390/app12178392

[18] S. Ozaki, K. Yamagata, C. Ito, T. Kohata, and T. Osada, “Finite element analysis of fracture behavior in ceramics: Prediction of strength distribution using microstructural features,” Journal of the American Ceramic Society, vol. 105, no. 3, pp. 2182–2195, Mar. 2022, doi: 10.1111/JACE.18201. DOI: https://doi.org/10.1111/jace.18201

[19] M. Kesharaju and R. Nagarajah, “Particle Swarm Optimization approach to defect detection in armour ceramics,” Ultrasonics, vol. 75, pp. 124–131, Mar. 2017, doi: 10.1016/J.ULTRAS.2016.07.008. DOI: https://doi.org/10.1016/j.ultras.2016.07.008

[20] H. W. Lilliefors, “On the Kolmogorov-Smirnov Test for the Exponential Distribution with Mean Unknown,” J. Am. Stat. Assoc., vol. 64, no. 325, pp. 387–389, 1969, doi: 10.1080/01621459.1969.10500983. DOI: https://doi.org/10.1080/01621459.1969.10500983