Journal of Shanghai Maritime University, Volume. 46, Issue 2, 137(2025)

Adaptive neural network sliding mode anti-sway control of shipborne cranes

CHEN Zhimei1, WANG Yanfang1、*, ZHU Dongke2, SHAO Xuejuan1, and ZHANG Jinggang1
Author Affiliations
  • 1School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, Shanxi, China
  • 2Taiyuan Heavy Industry Co., Ltd., Taiyuan 030024, Shanxi, China
  • show less

    Aiming at the problem of underactuated shipborne jib cranes subjected to persistent uncertain upper-bound disturbances, an adaptive radial basis function neural network (ARBNN) hierarchical sliding mode control (HSMC) method (called ARBFNN-HSMC method) is proposed. The dynamical model of the ship-crane-payload complex system affected by sustained sea waves is established using the Lagrangian method and converted into the standard form of an underactuated system. HSMC method is employed to design the control law, compensating for system parameter perturbations. ARBFNN is used to approximate and compensate for disturbances with uncertain upper bounds caused by external nonlinear disturbances. The asymptotic stability of the system is proven using the Lyapunov function. Simulation results demonstrate that the proposed method exhibits strong robustness under persistent unknown disturbances and effectively achieves the dual objectives of payload positioning and oscillation elimination.

    Tools

    Get Citation

    Copy Citation Text

    CHEN Zhimei, WANG Yanfang, ZHU Dongke, SHAO Xuejuan, ZHANG Jinggang. Adaptive neural network sliding mode anti-sway control of shipborne cranes[J]. Journal of Shanghai Maritime University, 2025, 46(2): 137

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Jan. 17, 2024

    Accepted: Aug. 22, 2025

    Published Online: Aug. 22, 2025

    The Author Email: WANG Yanfang (s202115110211@stu.tyust.edu.cn)

    DOI:10.13340/j.jsmu.202401170010

    Topics