Abstract
Bolted-joint tightening affects both structural integrity and line performance in EV chassis assembly, yet production torque tables are often conservative to accommodate variability in joint mechanics and shop-floor conditions. This study uses a deployable digital-twin workflow to reduce torque variants while jointly considering mechanics constraints, AGV-related logistics, and cost/OEE objectives. The workflow couples (i) a torque–preload joint model with vibration and fatigue checks, (ii) an uncertainty-calibrated, value-aware LSTM for quality-risk prediction from torque–angle signatures and context, and (iii) a multi-objective PSO variant for mixed discrete–continuous search with feasibility-first handling. Candidate torque tables are admitted only after verification-twin re-evaluation, which serves as a release gate. In an industrial study covering 5,524 vehicles (Feb 2024–Jan 2025), torque specifications are reduced from 23 variants to 8 (− 65.2%) while keeping the observed reject rate within a ≤ 0.05% cap and meeting Goodman safety ≥ 1.5. Standardization reduces end-effector changeovers by 31% and AGV idle time by 14% at a 42 s takt without increasing fleet size. Cross-platform transfer is evaluated on three EV platforms, and ablations are reported with statistical tests and effect sizes alongside V&V metrics. Reproducibility is supported by a complete nomenclature, fully specified algorithms, and a shareable synthetic dataset with scripts that regenerate all figures and tables.
Data availability
The raw industrial datasets generated and analysed during the current study are not publicly available because they contain proprietary engineering information arising from an industrial collaboration with SAIC-GM-Wuling Automobile Co., Ltd., but may be available from the corresponding author on reasonable request and with permission of SAIC-GM-Wuling Automobile Co., Ltd. To support reproducibility, the de-identified reproduction package containing the processed data necessary to reproduce the reported results, together with the associated code, is publicly available at the GitHub repository https://github.com/Haijun-WANG/iLS-AMOPSO-EV-TorqueDT and has been permanently archived in Zenodo at https://doi.org/10.5281/zenodo.18858541.
References
Yan, X. et al. Preload control methods of threaded fasteners: A review. Chin. J. Mech. Eng. 37, 97. https://doi.org/10.1186/s10033-024-01082-w (2024).
Pai, N. G. & Hess, D. P. Experimental study of loosening of threaded fasteners due to dynamic shear loads. J. Sound Vib. 253(3), 585–602. https://doi.org/10.1006/jsvi.2001.4006 (2002).
Liu, J. H. et al. Study on self-loosening of bolted joints excited by dynamic axial load. Tribol. Int. 115, 432–451. https://doi.org/10.1016/j.triboint.2017.05.037 (2017).
Zhang, J., Li, W. & Feng, J. Critical load determination for preventing rotational loosening in bolted joints under dynamic transverse loads. Eng. Fail. Anal. 160, 108217. https://doi.org/10.1016/j.engfailanal.2024.108217 (2024).
Junker, G. H. New criteria for self-loosening of fasteners under vibration. SAE Tech. Paper https://doi.org/10.4271/690055 (1969).
Lee, H. & Yang, H. Cognitive digital twin for multi-objective production scheduling. J. Manuf. Syst. 59, 1–12. https://doi.org/10.1016/j.jmsy.2025.02.001 (2025).
Izumi, S. et al. Three-dimensional finite element analysis of tightening and loosening mechanism of threaded fastener. Eng. Fail. Anal. 12(4), 604–615. https://doi.org/10.1016/j.engfailanal.2004.09.009 (2005).
Fort, V., Baragetti, S. & Terranova, A. Analytical modeling of self-loosening of bolted joints under transverse loading. J. Press. Vessel Technol. 141, 031205. https://doi.org/10.1115/1.4042798 (2019).
Meiners, M., Kerber, F. & von Enzberg, S. Process curve analysis with machine learning for screw fastening: A case study. Procedia CIRP 97, 166–171. https://doi.org/10.1016/j.procir.2020.05.220 (2021).
Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9 (8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 (1997).
Miguel, L. P. et al. Probabilistic machine learning for tightening torque detection in industrial assembly. Struct. Health Monit. 21 (5), 2136–2151. https://doi.org/10.1177/14759217211054150 (2022).
Pérez-Olguín, I. J. C. et al. Dataset of torque–angle curves for M2 and M3 metric screws. Data 9, 115. https://doi.org/10.3390/data9100115 (2024).
Deb, K. et al. A fast and elitist multi objective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197. https://doi.org/10.1109/4235.996017 (2002).
Hu, W. & Yen, G. G. Adaptive multi objective particle swarm optimization based on parallel cell coordinate system. IEEE Trans. Evol. Comput. 19 (1), 1–18. https://doi.org/10.1109/TEVC.2013.2296151 (2015).
Yen, G. G. & Daneshyari, M. Dynamic multiple swarms in multi objective particle swarm optimization. IEEE Trans. Syst. Man Cybern. A Syst. Hum. 39(4), 890–911. https://doi.org/10.1109/TSMCA.2009.2013915 (2009).
Wen, C. & Ma, H. A two-stage hypervolume-based evolutionary algorithm for many-objective optimization. Mathematics 11, 4247. https://doi.org/10.3390/math11204247 (2023).
Zhao, J. et al. A many-objective evolutionary algorithm based on three states. Sci. Rep. 14, 70145. https://doi.org/10.1038/s41598-024-70145-8 (2024).
Llopis-Albert, C. et al. Digital twin-based approach for a multi-objective optimal design of wind turbine gearboxes. Mathematics 12, 1383. https://doi.org/10.3390/math12091383 (2024).
Lu, Y. et al. Digital twin-driven smart manufacturing: Connotation, reference model, applications and research issues. Robot. Comput. Integr. Manuf. 61, 101837. https://doi.org/10.1016/j.rcim.2019.101837 (2020).
Molter, J. et al. The digital twin—A production-related review. J. Manuf. Syst. 74, 103–127. https://doi.org/10.1016/j.jmsy.2024.04.027 (2024).
Zheng, Z., Wang, Y. & Zhang, L. Fastening reliability analysis of bolted joint anti-self-loosening under dynamic loads. Eng. Fail. Anal. 158, 106916. https://doi.org/10.1016/j.engfailanal.2023.106916 (2023).
Chen, J. C. et al. Simultaneous scheduling optimization for machines and multiple-load AGVs in a digital-twin-based environment. J. Ind. Manag. Optim. 21, 1175–1196. https://doi.org/10.3934/jimo.2025117 (2025).
Mbasso, W. F. et al. Digital twins in renewable energy systems: A comprehensive review of concepts, applications, and future directions. Energy Strategy Rev. 61, 101814. https://doi.org/10.1016/j.esr.2025.101814 (2025).
Mbasso, W. F. et al. Digital-twin-enabled, time-aware anomaly detection for industrial cyber-physical systems. Digit. Twins Appl. https://doi.org/10.1049/dgt2.70016 (2026).
Liu, M. et al. Review of digital twin about concepts, technologies, and industrial applications. J. Manuf. Syst. 58, 346–361. https://doi.org/10.1016/j.jmsy.2020.06.017 (2021).
Fuller, A. et al. Digital twin: Enabling technologies, challenges and open research. IEEE Access 8, 108952–108971. https://doi.org/10.1109/ACCESS.2020.2998358 (2020).
Li, Z., Strong, M. & Liu, H. A modified hypervolume-based expected improvement for multi-objective optimization. Struct. Multidiscip. Optim. 58, 1125–1141. https://doi.org/10.1007/s00158-018-2006-3 (2018).
Wilson, E. B. Probable inference, the law of succession, and statistical inference. J. Am. Stat. Assoc. 22(158), 209–212. https://doi.org/10.1080/01621459.1927.10502953 (1927).
Persson, E. V. Clamp force accuracy in threaded fastener joints using torque-based strategies. SAE Technical Paper https://doi.org/10.4271/2021-01-5073 (2021).
Acknowledgements
Funding. This work was supported by the Guangxi Science and Technology Major Project (Grant No. AA24206071) and the Guangxi Basic Ability Enhancement Program for Young and Middle-aged University Teachers (Grant No. 2024KY1454). We sincerely appreciate all the engineers and project participants for their invaluable contributions and support.
Funding
This work was supported by the Guangxi Science and Technology Major Project (Grant No. AA24206071) and the Guangxi Basic Ability Enhancement Program for Young and Middle-aged University Teachers (Grant No. 2024KY1454). The authors sincerely appreciate all engineers and project participants for their invaluable contributions and support.
Author information
Authors and Affiliations
Contributions
Haijun Wang conceived the study, carried out the main analysis, and drafted the manuscript. Zhijie Huang, Zhengxin Lan, Tie Xu, Hao Chen, Deyang Luo, and Danhua Chen contributed to study design, data collection, result discussion, and manuscript revision. All authors reviewed the manuscript and approved the final version.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wang, H., Huang, Z., Lan, Z. et al. A deployable digital twin framework for bolt-torque specification compression in EV chassis assembly. Sci Rep (2026). https://doi.org/10.1038/s41598-026-43641-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-43641-2
