TY  - JOUR
AU  - Bai, Yuting
AU  - Hu, Jiyuan
AU  - Tursun, Eziz
AU  - Yimit, Hurxida
PY  - 2026
DA  - 2026/01/08
TI  - Data-Driven Operational Assessment Method and Digital Twin System for Unmanned Surface Vehicles
JO  - ICCK Transactions on Machine Intelligence
T2  - ICCK Transactions on Machine Intelligence
JF  - ICCK Transactions on Machine Intelligence
VL  - 2
IS  - 1
SP  - 38
EP  - 52
DO  - 10.62762/TMI.2025.444910
UR  - https://www.icck.org/article/abs/TMI.2025.444910
KW  - unmanned surface vehicles
KW  - data-driven
KW  - state evaluation
KW  - digital twin
KW  - multi-source temporal modeling
KW  - model fusion
AB  - To address the challenge of effectively leveraging multi-source data for automated operational assessment of Unmanned Surface Vehicles (USVs) and utilizing digital technologies for monitoring and control, this paper proposes a data-driven state assessment method for surface unmanned systems and develops a digital twin system tailored for USVs. First, a dual-channel feature modeling mechanism is constructed by integrating physically interpretable statistical features with temporal convolutional features. Second, a complementary modeling strategy is adopted using CatBoost for static classification and GRU for dynamic modeling, while a Covariance Intersection (CI) fusion strategy is introduced to enhance the classification performance and adaptability of the model. Finally, a digital twin system is designed that incorporates Position Estimation, Attitude Estimation, and State Evaluation, enabling real-time monitoring and multidimensional visualization of USV operational states. Experimental results demonstrate that the proposed method outperforms baseline approaches in terms of accuracy, F1-score, and other key metrics, exhibiting strong generalization capability and promising potential for practical deployment.
SN  - 3068-7403
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Bai2026DataDriven,
  author = {Yuting Bai and Jiyuan Hu and Eziz Tursun and Hurxida Yimit},
  title = {Data-Driven Operational Assessment Method and Digital Twin System for Unmanned Surface Vehicles},
  journal = {ICCK Transactions on Machine Intelligence},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {38-52},
  doi = {10.62762/TMI.2025.444910},
  url = {https://www.icck.org/article/abs/TMI.2025.444910},
  abstract = {To address the challenge of effectively leveraging multi-source data for automated operational assessment of Unmanned Surface Vehicles (USVs) and utilizing digital technologies for monitoring and control, this paper proposes a data-driven state assessment method for surface unmanned systems and develops a digital twin system tailored for USVs. First, a dual-channel feature modeling mechanism is constructed by integrating physically interpretable statistical features with temporal convolutional features. Second, a complementary modeling strategy is adopted using CatBoost for static classification and GRU for dynamic modeling, while a Covariance Intersection (CI) fusion strategy is introduced to enhance the classification performance and adaptability of the model. Finally, a digital twin system is designed that incorporates Position Estimation, Attitude Estimation, and State Evaluation, enabling real-time monitoring and multidimensional visualization of USV operational states. Experimental results demonstrate that the proposed method outperforms baseline approaches in terms of accuracy, F1-score, and other key metrics, exhibiting strong generalization capability and promising potential for practical deployment.},
  keywords = {unmanned surface vehicles, data-driven, state evaluation, digital twin, multi-source temporal modeling, model fusion},
  issn = {3068-7403},
  publisher = {Institute of Central Computation and Knowledge}
}