Integration of TiC-Reinforced Aluminum Matrix Composites with CNN-Based Systems for Automotive Steering Knuckle Applications

  • Authors

    • Kishor Dagale Research Scholar, Department of Mechanical Engineering, Vivekananda Global University, Jaipur, Rajasthan, India
    • Pramod Kumar Professor, Department of Mechanical Engineering, Vivekananda Global University, Jaipur, Rajasthan, India
    • Makarand Shirke Assistant Professor, Amrutvahini College of Engineering, Sangamner, India
    https://doi.org/10.14419/7bjmmc83

    Received date: July 20, 2025

    Accepted date: August 5, 2025

    Published date: August 12, 2025

  • Aluminum matrix composites, Titanium carbide reinforcement, Automated quality control, Deep learning in manufacturing, Lightweight automotive compo-nents, Industry 4.0

  • Abstract

    This study delivers a 35% reduction in steering knuckle failures by an innovative integration between advanced materials and AI-enhanced quality control. We prove that 6061+10%Si+4%TiC aluminum matrix composites behave most optimally with 138 MPa fatigue strength (25% improvement), 86 GPa elastic modulus, and 9.2/10 rating overall while still retaining manufacturability. Our neural network built upon convolutional principles posts 87% defect detection accuracy-the best compared to classical systems (SVM: 75%; RF: 70%)-and it performs inference within 28 milliseconds, allowing for production-line deployment. The amalgamation sees warranty claims go down by 28%, while costs increase by less than 5%, thus setting a new paradigm in the world of safety-critical automotive components. This work is bridging materials science with Industry 4.0 by supplying a validated framework for lightweight and high-reliability automotive design.

  • References

    1. Busarac, N., D. Adamovic, N. Grujovic, and F. Zivic (2022). Lightweight materials for automobiles. IOP Conference Series: Materials Science and Engineering 1271: 012010.
    2. Kumar, A., V. P. Singh, R. C. Singh, S. Kumar, P. Sharma, and M. Gupta (2024). Aluminum metal matrix composites: fabrication and properties. Journal of Materials Science 59: 2644–2711.
    3. Yadollahi, A., and N. Shamsaei (2017). Additive manufacturing of fatigue-resistant materials. International Journal of Fatigue 98: 14–31.
    4. Chukwunweike, J. N., A. N. Anang, A. A. Adeniran, C. E. Okafor, and N. H. Ononiwu (2024). Deep learning for manufacturing quality. World Journal of Advanced Research and Reviews 03: 1272–1295.
    5. Jha, S. B., and R. F. Babiceanu (2023). CNN-based defect detection: a survey. Computers in Industry 148: 103912.
    6. Reddy, P. V., G. S. Kumar, D. M. Krishnudu, P. R. Rao, and K. A. Kumar (2020). Mechanical performance of Al-MMCs. Journal of Bio- and Tri-bo-Corrosion 6: 83.
    7. Surappa, M. K. (2003). Aluminum matrix composites: challenges. Sādhanā 28: 319–334.
    8. Miracle, D. B. (2005). Metal matrix composites. Composites Science and Technology 65: 2526–2540.
    9. Pirso, J., M. Viljus, and S. Letunovits (2007). Cr-Ni-graphite composites. Materials Science Forum 534: 1209–1212.
    10. Wu, R. Z., Z. K. Qu, and M. L. Zhang (2010). Mg-Li alloy reinforcements. Reviews on Advanced Materials Science 24: 35–43.
    11. Vijaya Ramnath, B., C. Elanchezhian, M. Jaivignesh, S. Rajesh, C. Parswajinan, and G. Siddique Ahmed (2014). Al-Al₂O₃-B₄C composites. Mate-rials & Design 58: 332–338.
    12. Singh, R., and A. Kumar (2022). Hybrid Al nanocomposites. Materials Today: Proceedings 56: 200–208.
    13. Cumbajin, E., N. Rodrigues, P. Costa, F. J. G. Silva, and R. D. S. G. Campilho (2023). CNN for surface defects. Journal of Imaging 9: 193.
    14. Czimmermann, T., G. Ciuti, M. Milazzo, M. Chiurazzi, S. Roccella, and C. M. Oddo (2020). Visual defect detection. Sensors 20: 1459.
    15. Ferguson, M., R. Ak, Y. T. T. Lee, and K. H. Law (2017). CNN for casting defects. IEEE Big Data 1726–1735.
    16. Shafiq, M., and Z. Gu (2022). Deep ResNet survey. Applied Sciences 12: 8972.
    17. Khanam, R., M. Hussain, R. Hill, D. Al-Jumeily, and M. Khalaf (2024). CNN for industrial defects. IEEE Access 12: 94250–94295.
    18. Krizhevsky, A., I. Sutskever, and G. E. Hinton (2017). ImageNet classification. Communications of the ACM 60: 84–90.
    19. Szegedy, C., S. Ioffe, V. Vanhoucke, and A. A. Alemi (2017). Inception-v4. Proceedings of the AAAI Conference on Artificial Intelligence 31: 4278–4284.
    20. Kumari, V., and M. K. Majumder (2025). AI-enabled 3D integration. In AI-Enabled Circuit Design, Springer, Cham, 257–308.
    21. Dagale, K., P. Kumar, and M. Harne (2023). Substantial review of the mechanical conditions of hybrid metal matrix composites AL 6063, SiC, and Gr. European Chemical Bulletin 12(Special Issue 5): 726–741.
    22. Dagale, K., and P. Kumar (2024). Analysis and material optimization of steering knuckle using FEM. Common Ground Network: 397–409.

  • Downloads

  • How to Cite

    Dagale, K. ., Kumar, P. ., & Shirke , M. . (2025). Integration of TiC-Reinforced Aluminum Matrix Composites with CNN-Based Systems for Automotive Steering Knuckle Applications. International Journal of Basic and Applied Sciences, 14(SI-2), 141-147. https://doi.org/10.14419/7bjmmc83