AI-Driven Digital Twin for Smart Manufacturing: A Dataset-Driven Predictive Maintenance Framework Using a Sample EV Car Model

The literature reviewed here treats Digital Twins as a way to keep a virtual copy of an asset in step with data, and predictive maintenance as the use of data to decide when work is needed. ML is the dominant analysis tool, with tree ensembles common on tabular data and deep models used where signals are rich and data plentiful [15], [16], [22]. In EVs, the strongest results are on battery state estimation and prognosis, often with laboratory or limited vehicle data [32], [34], [35]. Twin studies on batteries, and on machines such as CNC tools and rotating equipment, mix physics-based models with learning [13], [36], [43], [44]. Comparing the studies showed that implementations usually rely on physical or laboratory data, that prediction and visualization are often developed separately, that 3D visualization is rarely documented, and that explanations are uneven. Not all candidate gaps were equally supported, and we marked those that rest on absence of evidence as needing confirmation. We proposed a dataset-driven prototype that uses a sample EV model as a virtual asset and passes CSV records through validation, preprocessing, a Random Forest baseline and a risk estimator into a 3D view and a dashboard. It is not a physical Digital Twin, it uses no real vehicle or sensors, and we report no experimental results. The next steps are to select and document a dataset, run the evaluation described in Sec. 11, and then consider explainability, real-time data and component-level diagnosis. Until those are done, the contribution of this work is the structured review, the gap analysis and the design of the framework.

[1]     M. Grieves and J. Vickers, “Digital twin: Mitigating unpredictable, undesirable emergent behavior in complex systems,” in Transdisciplinary Perspectives on Complex Systems, F.-J. Kahlen, S. Flumerfelt, and A. Alves, Eds. Cham, Switzerland: Springer, 2017, pp. 85–113. [2]     E. Glaessgen and D. Stargel, “The digital twin paradigm for future NASA and U.S. Air Force vehicles,” in Proc. 53rd AIAA/ASME/ASCE/AHS/ASC Struct., Struct. Dyn. Mater. Conf., Honolulu, HI, USA, 2012. [3]     F. Tao, H. Zhang, A. Liu, and A. Y. C. Nee, “Digital twin in industry: State-of-the-art,” IEEE Trans. Ind. Informat., vol. 15, no. 4, pp. 2405–2415, Apr. 2019. [4]     F. Tao, M. Zhang, Y. Liu, and A. Y. C. Nee, “Digital twin driven prognostics and health management for complex equipment,” CIRP Ann., vol. 67, no. 1, pp. 169–172, 2018. [5]     F. Tao, Q. Qi, L. Wang, and A. Y. C. Nee, “Digital twins and cyber–physical systems toward smart manufacturing and Industry 4.0: Correlation and comparison,” Engineering, vol. 5, no. 4, pp. 653–661, 2019. [6]     W. Kritzinger, M. Karner, G. Traar, J. Henjes, and W. Sihn, “Digital twin in manufacturing: A categorical literature review and classification,” IFAC-PapersOnLine, vol. 51, no. 11, pp. 1016–1022, 2018. [7]     D. Jones, C. Snider, A. Nassehi, J. Yon, and B. Hicks, “Characterising the digital twin: A systematic literature review,” CIRP J. Manuf. Sci. Technol., vol. 29, pp. 36–52, 2020. [8]     A. Fuller, Z. Fan, C. Day, and C. Barlow, “Digital twin: Enabling technologies, challenges and open research,” IEEE Access, vol. 8, pp. 108952–108971, 2020. [9]     Y. Lu, C. Liu, K. I.-K. Wang, H. Huang, and X. Xu, “Digital twin-driven smart manufacturing: Connotation, reference model, applications and research issues,” Robot. Comput.-Integr. Manuf., vol. 61, Art. no. 101837, 2020. [10]   Q. Qi et al., “Enabling technologies and tools for digital twin,” J. Manuf. Syst., vol. 58, pp. 3–21, 2021.