Generative AI and DFMEA for Optimized Lithium-Ion Battery Pack Design in Electric Two-Wheelers
Keywords:
Generative AI, DFMEA, Electric Vehicles, Battery Optimization, Risk MitigationAbstract
Electric two-wheelers are rapidly emerging as a key component of sustainable transportation, where lithium-ion battery packs play a critical role in determining performance, safety, and efficiency. However, conventional battery design approaches face challenges related to thermal instability, structural limitations, and difficulty in optimizing multiple parameters under real-world operating conditions. This study proposes an integrated framework that combines generative artificial intelligence (AI) with Design Failure Mode and Effects Analysis (DFMEA) to improve battery pack design and enhance risk mitigation. Generative AI is used to explore multiple design configurations based on predefined constraints, while DFMEA systematically evaluates potential failure modes using severity, occurrence, and detection parameters. The proposed approach achieves a reduction of 15–20% in peak temperature, a 10–15% improvement in energy density, and a 12–18% decrease in overall battery weight. In addition, Risk Priority Numbers (RPNs) for critical failure modes are reduced by 25–35%, indicating improved system safety and reliability. These results demonstrate that integrating AI-driven design optimization with structured risk assessment enables the development of safer, more efficient, and high-performance battery systems for next-generation electric vehicles.
Downloads
References
[1] S. Kench, I. Squires, A. Dahari, F. Brosa Planella, S. A. Roberts, and S. J. Cooper,
“Li-ion battery design through microstructural optimization using generative AI,” Matter, vol. 7, no. 12, pp. 4260–4269, 2024.
[2] J. Hu, P. Fu, Z. Wei, et al., “Early prediction of lithium-ion battery degradation with a generative pre-trained transformer,” Nature Communications, vol. 17, 2026.
[3] S. Shayan Mousavi Masouleh et al., “Artificial intelligence enabled optimization of battery-grade lithium carbonate production,” Digital Discovery, vol. 3, pp. 2320–2326, 2024.
[4] H. Alzamer, R. Jaafreh, J. G. Kim, and K. Hamad, “Artificial intelligence and Li-ion batteries: Advances in electrolyte materials discovery,” Crystals, vol. 15, no. 2, 2025.
[5] X. Gao, “Transformation of lithium battery material design and optimization based on artificial intelligence,” Academic Journal of Materials & Chemistry, vol. 5, no. 2, pp. 18–22, 2024.
[6] Y. Zhang et al., “AI-driven exploration and design of inorganic battery materials,” Renewable and Sustainable Energy Reviews, vol. 229, 2026.
[7] Y. Liu et al., “Generating comprehensive lithium battery charging data with generative AI,” Applied Energy, vol. 377, 2025.
[8] A. Gayon-Lombardo et al., “Deep kernel Bayesian optimisation for electrode microstructure design using generative adversarial networks,” arXiv preprint, 2025.
[9] M. Zohair et al., “Chemical foundation model guided design of high ionic conductivity electrolyte formulations,” arXiv preprint, 2025.
[10] S. Liu et al., “Expert-guided LLM reasoning for battery discovery: From AI-driven hypothesis to synthesis,” arXiv preprint, 2025.
[11] X. Zhang et al., “A physics-driven generative model for lithium-ion battery diagnostics,” Applied Energy, vol. 391, 2025.
[12] D. Datta et al., “Generative AI for discovering porous oxide materials for next-generation energy storage,” Cell Reports Physical Science, 2025.
[13] A. Manoharan et al., “Optimizing lithium-ion battery manufacturing with digitalization and AI-driven frameworks,” International Journal of Advanced Manufacturing Technology, 2026.
[14] L. Dhangaonkar and M. Narlawar, “Assessing Power Sector Reforms in India: Regulatory Performance, Distribution Stress and Reform Pathways,” International Research Journal of Innovation in Science and Technology (IRJIST), vol. 1, no. 1, pp. 30–39, 2026.
[15] S. N. Kamble, P. M. Bagade, S. H. Sarje, A. A. Tamboli, and A. A. Somatkar, “Risk Mitigation Strategies for Controlled Descent Device Used for Emergency Rescue,” International Journal of Basic and Applied Sciences, vol. 14, SI-2, pp. 189–198, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rohit S. Jadhav, Harsh A. Khutekar (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Research Journal of Innovation in Science and Technology (IRJIST) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors retain the copyright of their work and grant the journal the right of first publication. Proper attribution to the authors and the journal is required for any reuse of the published content.
