Abstract
The current digital twin system is extremely dependent on the integrity of the data when performing data analysis, and in the process of data collection and transmission, the phenomenon of data loss is very easy to occur. In this paper, the types of missing data are classified according to the size of missing data. For long-term data missing, it is processed in segments. For short-term data missing, the training of random forest algorithm model and the prediction of missing values are carried out according to different missing data sizes, And filled in the prediction using missing values from the wind power data twin system, which shows a good filling effect and helps to solve the problem of missing data filling in the digital twin system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hinchy, E.P., O’Dowd, N.P., McCarthy, C.T.: Using open-source microcontrollers to enable digital twin communication for smart manufacturing. Procedia Manufacturing 38, 1213–1219 (2019)
Dabrowski, J.J., Rahman, A.: Sequence-to-sequence imputation of missing sensor data. In: AI 2019: Advances in Artificial Intelligence: 32nd Australasian Joint Conference, Adelaide, SA, Australia, December 2–5, 2019, Proceedings 32, pp. 265–276. Springer International Publishing (2019)
Poddar, S., Jacob, M.: Clustering of data with missing entries. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2831–2835. IEEE (2018, April)
Chen, P.Y., Wu, W., Garnier-Villarreal, M., et al.: Testing measurement invariance with ordinal missing data: a comparison of estimators and missing data techniques. Multivar. Behav. Res. 55(1), 87–101 (2020)
Liu, L., Xu, Z., Gao, C., et al.: Digital twin-driven rear axle assembly torque prediction and online control. Sensors 22(19), 7282 (2022)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Park, M., Jung, D., Lee, S., et al.: Heatwave damage prediction using random forest model in Korea. Appl. Sci. 10(22), 8237 (2020)
Acknowledgements
The paper was funded by Shanghai Industrial Development Innovation Project “Digital Twin Health Prediction System of Space Docking Mechanism Driven by Hybrid Mathematics and Physics” (Grant No. XTCX-KJ-2022-03), Key Research Project on Military Civilian Integration "Digital Twin Predictive Control System Driven by Hybrid Data and Mechanism" (2022YFF1400303). And it was supported by Science and Technology Department of Xinjiang Uygur Autonomous Region under Grant (2021B01003-2).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, B. et al. (2024). Processing Method for Missing Data in Digital Twin System. In: Wang, Y., Yu, T., Wang, K. (eds) Advanced Manufacturing and Automation XIII. IWAMA 2023. Lecture Notes in Electrical Engineering, vol 1154. Springer, Singapore. https://doi.org/10.1007/978-981-97-0665-5_18
Download citation
DOI: https://doi.org/10.1007/978-981-97-0665-5_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0664-8
Online ISBN: 978-981-97-0665-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)