DOI QR코드

DOI QR Code

Application of Digital Twin Technology Based on Big Data in Robot Coupling Simulation

빅데이터 기반 디지털 트윈 기술의 로봇 커플링 시뮬레이션 적용

  • Kyung-Ihl Kim (Division of Convergence Management, Korea National University of Transportation)
  • 김경일 (국립한국교통대학교 융합경영학과)
  • Received : 2025.06.02
  • Accepted : 2025.07.20
  • Published : 2025.07.30

Abstract

The purpose of this study is to propose a method to experimentally apply robot coupling simulation using big data-based digital twin technology to minimize the input of manpower other than robots that existing rigid robots have, and to propose a smart factory implementation for smart manufacturing innovation. The purpose of this study was to achieve the research purpose through experiments that include methods to apply algorithms such as deep learning, convolutional neural networks, and recurrent neural networks by advancing the digital twin modeling and prediction techniques proposed so far. In order to verify the effectiveness and feasibility of digital twin technology, an experiment was conducted to conduct robot coupling simulation using a 6-axis robot. Through the robot coupling simulation experiment using big data-based digital twin technology, the effect of manufacturing innovation was discovered, and it showed superior results in path planning, dynamic response, and transport capacity compared to existing physical models. In future studies, since the applicability of digital twin technology and existing physical models may differ depending on specific scenarios and requirements, it is expected that manufacturing innovation can be achieved through the application of digital twin simulation suitable for the manufacturing environment by studying the definition of parameters that can select the scenario to be applied and the method of intelligence.

본 연구는 기존의 경직성 로봇이 갖고 있는 로봇 이외의 인력 투입을 최소화할 수 있도록 빅데이터 기반 디지털 트윈 기술을 적용한 로봇 커플링 시뮬레이션을 실험적으로 적용할 수 방안을 제안하여 스마트제조혁신을 위한 스마트공장 구현을 제안하고자 함에 연구 목적이 있다. 이제까지 제안된 디지털 트윈 모델링 및 예측기법을 고도화하여 딥 러닝, 나선형 신경망, 회귀 신경망과 같은 알고리즘을 적용하는 방법을 포함하는 실험을 통해 연구 목적을 달성하고자 하였다. 디지털 트윈 기술의 효과성과 실현 가능성을 검증하기 위하여 6축 로봇을 이용한 로봇 협력 시뮬레이션을 시행하는 실험을 수행하였다. 빅 데이터 기반의 디지털 트윈 기술의 로봇 커플링 시뮬레이션 실험을 통해 제조혁신의 효과를 발견하였는 바, 경로 계획, 동적 응답 및 운반 용량에서 기존 물리적 모델보다 우위의 결과값을 보였다. 향후 연구에서는 디지털 트윈 기술과 기존 물리적 모델은 특정 시나리오와 요구사항에 따라 적용가능성이 상이할 수 있으므로 적용하고자 하는 시나리오를 선택할 수 있는 패러미터의 정의와 지능화 방법에 대한 연구가 이루어짐으로써 제조환경에 적합한 디지털 트윈 시뮬레이션 적용을 통한 제조 혁신이 달성될 수 있을 것으로 기대한다.

Keywords

Acknowledgement

This was supported by Korea National University of Transportation in 2025

References

  1. Li S., et al. (2019). Particle robotics based on statistical mechanics of loosely coupled components. Nature, 567(7748), 361-365. DOI : 10.1038/s41586-019-1022-9
  2. Mastalli, C., Havoutis, I., Focchi, M., Caldwell, D. G. & Semini, C. (2020). Motion planning for quadrupedal locomotion: Coupled planning, terrain mapping, and whole-body control. IEEE Transactions on Robotics, 36(6), 1635–1648. DOI : 10.1109/TRO.2020.3003464
  3. Thuruthel, T. G., Ansari, Y., Falotico, E. & Laschi, C. (2018). Control strategies for soft robotic manipulators: A survey. Soft Robotics, 5(2), 149–163. DOI : 10.1089/soro.2017.0007
  4. Novak, R., Ingram, M., Marquez, S., Das, D., Delahanty, A., Herland, A. & others. (2020). Robotic fluidic coupling and interrogation of multiple vascularized organ chips. Nature Biomedical Engineering, 4(4), 407–420. DOI : 10.1038/s41551-019-0497-x
  5. Kim, K.-I. (2023). The impact of digital transformation on business financialization: Mediating effect of green technology innovation. Advanced Industrial Science, 2(4), 17–27. DOI : 10.23153/AI-Science.2023.2.4.017
  6. Singh, A. K., Kumar, A., Singh, A., Anshum, A. & Mallick, P. K. (2024). A study on the drug classification using machine learning techniques. Advanced Industrial Science, 3(2), 8–16. DOI : 10.23153/AI-Science.2024.3.2.008
  7. Fossum, T. O., Eidsvik, J., Ellingsen, I., Alver, M. O., Fragoso, G. M., Johnsen, G. & others. (2018). Information‐driven robotic sampling in the coastal ocean. Journal of Field Robotics, 35(7), 1101–1121. DOI : 10.1002/rob.21805
  8. Kim, K.-S. (2022). Big data management in structured storage based on fintech models for IoMT using machine learning techniques. Advanced Industrial Science, 1(1), 7–15. DOI : 10.23153/AI-Science.2022.1.1.007
  9. Giordano, A. M., Ott, C. & Albu-Schäffer, A. (2019). Coordinated control of spacecraft's attitude and end-effector for space robots. IEEE Robotics and Automation Letters, 4(2), 2108–2115. DOI : 10.1109/LRA.2019.2899433
  10. Zhang, X., Liu, J., Feng, J., Liu, Y. & Ju, Z. (2019). Effective capture of nongraspable objects for space robots using geometric cage pairs. IEEE/ASME Transactions on Mechatronics, 25(1), 95–107. DOI : 10.1109/TMECH.2019.2952552
  11. Niu, H., Feng, R., Xie, Y., Jiang, B., Sheng, Y., Yu, Y. & others. (2021). Magworm: A biomimetic magnet embedded worm-like soft robot. Soft Robotics, 8(5), 507–518. DOI : 10.1089/soro.2019.0167
  12. Zhao, B. & Liu, D. (2019). Event-triggered decentralized tracking control of modular reconfigurable robots through adaptive dynamic programming. IEEE Transactions on Industrial Electronics, 67(4), 3054–3064. DOI : 10.1109/TIE.2019.2914571
  13. Pawlowski, B., Sun, J., Xu, J., Liu, Y. & Zhao, J. (2018). Modeling of soft robots actuated by twisted-and-coiled actuators. IEEE/ASME Transactions on Mechatronics, 24(1), 5–15. DOI : 10.1109/TMECH.2018.2873014
  14. Liu, A., Zhang, W.-A., Yu, L., Yan, H. & Zhang, R. (2018). Formation control of multiple mobile robots incorporating an extended state observer and distributed model predictive approach. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50(11), 4587-4597. DOI: 10.1109/TSMC.2018.2855444