基于舰船运动预报的海浪补偿平台在线自适应模型预测控制策略

doi:10.3901/JME.260692

摘要/Abstract

摘要： 电液伺服Stewart平台能够抵消船舶或海上设备在波浪作用下的运动，为海上作业提供稳定的工作环境。然而，海况的强动态性、Stewart平台各支腿之间的强耦合性以及电液伺服系统参数的非线性，使精确的波浪补偿控制极具挑战。为此，本文提出了一种基于舰船运动预报的在线自适应模型预测控制策略。首先，建立融合一维与二维舰船运动特征的卷积神经网络-长短期记忆网络(One-dimensional-two-dimensional convolutional neural network-long short-term memory，1D-2D-CNN-LSTM)舰船位姿预测模型；然后，构建基于递推最小二乘算法的液压驱动单元自适应模型预测控制(Adaptive model predictive control，AMPC)策略；最后，将舰船位姿预测与自适应模型预测控制相结合，形成海浪补偿预测控制框架。实验结果表明：在 4 级海况随机激励下，与传统模型预测控制(Model predictive control，MPC)波浪补偿算法相比，所提控制策略在六自由度上的平均绝对误差降低了 56%～81%，均方根误差降低了 55%～80%。

关键词: 海浪补偿, 自适应模型预测控制, 舰船运动预测, 电液伺服, Stewart平台

Abstract: The motion of ships or offshore equipment induced by waves is counteracted by the electro-hydraulic servo Stewart platform, thereby providing a stable working environment for offshore operations. However, precise wave compensation control is made extremely challenging by the highly dynamic nature of sea states, the strong coupling among the platform’s legs, and the nonlinear parameters of the electro-hydraulic servo system. To address these issues, an online adaptive model predictive control (AMPC) strategy is proposed based on ship motion prediction. First, a ship pose prediction model is developed using a one-dimensional and two-dimensional feature-fusion convolutional neural network–long short-term memory network (1D-2D-CNN-LSTM). An adaptive model predictive control framework for the hydraulic actuation units is constructed based on a recursive least-squares algorithm. Finally, the ship pose prediction model is integrated with the AMPC approach to form a predictive wave compensation control framework. Experimental results are shown to indicate that under random wave excitation at sea state level 4, the proposed control strategy reduces the mean absolute error by 56%–81% and the root mean square error by 55%–80% across all six degrees of freedom, compared with the conventional model predictive control (MPC) method.

Key words: wave compensation, adaptive model predictive control, ship motion prediction, electro-hydraulic servo, Stewart platform

中图分类号:

TH137

陈夏非, 曾海, 王瑛涛, 姜雪, 刘小平, 张立杰. 基于舰船运动预报的海浪补偿平台在线自适应模型预测控制策略[J]. 机械工程学报, 2026, 62(13): 144-154.

CHEN Xiafei, ZENG Hai, WANG Yingtao, JIANG Xue, LIU Xiaoping, ZHANG Lijie. An Online Adaptive Model Predictive Control Strategy for Wave Compensation Platforms Based on Ship Motion Prediction[J]. Journal of Mechanical Engineering, 2026, 62(13): 144-154.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260692

http://www.cjmenet.com.cn/CN/Y2026/V62/I13/144

参考文献

[1] YIN R，XIE W，WEN Y，et al. Robust wave compensation controller design for an active hexapod platform with time-varying input delays[J]. Ocean Engineering，2023，274：114084.
[2] ZHOU Z，WANG H，ZHANG B，et al. Multibody dynamic analysis of float-over installation based on active multi-dimensional motion compensation equipment[J]. Ocean Engineering，2023，285：115330.
[3] ZHAO S，GAO Z，MENG X，et al. Multibody coupled dynamic response analysis of a dual barge float-over operation system with motion compensation equipment under a passive operational mode[J]. Ocean Engineering， 2023，269：113499.
[4] WANG L，GUO F，LU W，et al. Non-inertial system dynamic modeling of 3UPS/S ship stability platform[J]. Journal of Mechanical Engineering，2020，56(1)：20-29.
[5] WANG L，CUI S，MA C，et al. Compound impedance control of a hydraulic driven parallel 3UPS/S manipulator[J]. Chinese Journal of Mechanical Engineering，2020，33(1)：56.
[6] QIN L，BAI X，LUO H，et al. Review on recent research and technical challenges of floatover installation operation[J]. Ocean Engineering，2022，253：11378.
[7] BA K，MA G，YU B，et al. A nonlinear model-based variable impedance parameters control for position-based impedance control system of hydraulic drive unit[J]. International Journal of Control，Automation and Systems，2020，18(7)：1806-1817.
[8] 张立杰，王力航，李玉昆，等. 液压伺服系统闭环刚度特性分析与试验研究[J]. 机械工程学报，2018，54(16)：170-177. ZHANG Lijie，WANG Lihang，LI Yukun，et al. Analysis and experimental study on closed-loop stiffness of hydraulic servo system[J]. Journal of Mechanical Engineering，2018，54(16)：170-177.
[9] JIAO Z，CHEN X，LIU X，et al. An experimental study on outer frame position control of hydraulic flight motion simulator with model compensation[J]. IEEE/ASME Transactions on Mechatronics，2022，27(5)：3419-3428.
[10] CAI Y，ZHENG S，LIU W，et al. Sliding-mode control of ship-mounted Stewart platforms for wave compensation using velocity feedforward[J]. Ocean Engineering，2021，236：109477.
[11] CAI Y，ZHENG S，LIU W，et al. Adaptive robust dual-loop control scheme of ship-mounted Stewart platforms for wave compensation[J]. Mechanism and Machine Theory，2021，164：104406.
[12] LIU J，CHEN X. Adaptive control based on neural network and beetle antennae search algorithm for an active heave compensation system[J]. International Journal of Control，Automation and Systems，2022，20(2)：515-525.
[13] CHEN W，WANG S，LI J，et al. An ADRC-based triple-loop control strategy of ship-mounted Stewart platform for six-DOF wave compensation[J]. Mechanism and Machine Theory，2023，164：105289.
[14] DU Z，CHEN X，ZHANG Q，et al. An extended state observer-based sliding mode control method for hydraulic servo system of marine stabilized platforms[J]. Ocean Engineering，2023，279：114386.
[15] LENG J，XU C，LI M，et al. Control strategy for performing predictions for a semi-active compensation system[J]. Ocean Engineering，2021，239：109816.
[16] YA T，DU J，LI J. PTESO based robust stabilization control and its application to 3-DOF ship-borne parallel platform[J]. Ocean Engineering，2023，284：115202.
[17] LI W，WU C，LIN S，et al. Active heave compensation of marine winch based on hybrid neural network prediction and sliding mode controller with a high-gain observer[J]. Ocean Engineering，2025，322：120448.
[18] WANG Y，LU X，GAO Y，et al. An anti-swing control method combining deep learning prediction models with a multistate fractional-order terminal sliding mode controller for wave motion compensation devices[J]. Mechanical Systems and Signal Processing，2025，223：111819.
[19] HU L，ZHANG M，YUAN Z M，et al. Predictive control of a heaving compensation system based on machine learning prediction algorithm[J]. Journal of Marine Science and Engineering，2023，11(4)：821.
[20] LÓPEZ F C，FERNÁNDEZ R Á. Predictive model for energy consumption of battery electric vehicle with consideration of self-uncertainty route factors[J]. Journal of Cleaner Production，2020，276：124188.
[21] WU J，ZHOU H，LIU Z，et al. Ride comfort optimization via speed planning and preview semi-active suspension control for autonomous vehicles on uneven roads[J]. IEEE Transactions on Vehicular Technology，2020，69(8)：8343-8355.
[22] XU S，PENG H. Design，analysis，and experiments of preview path tracking control for autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems，2020，21(1)：48-58.
[23] CAI M，WANG Y，WANG S，et al. Prediction-based seabed terrain following control for an underwater vehicle-manipulator system[J]. IEEE Transactions on Systems，Man，and Cybernetics：Systems，2021，51(8)：4751-4760.
[24] YANG D，LIU T，SONG D，et al. A real time multi-objective optimization Guided-MPC strategy for power-split hybrid electric bus based on velocity prediction[J]. Energy，2023，276：127583.
[25] TRIANTAFYLLOU M，BODSON M，ATHANS M. Real time estimation of ship motions using kalman filtering techniques[J]. IEEE Journal of Oceanic Engineering，1983，8(1)：9-20.
[26] JIANG H，DUAN S，HUANG L，et al. Scale effects in AR model real-time ship motion prediction[J]. Ocean Engineering，2020，203：107202.
[27] HUANG L，DENG X，BO Y，et al. Evolutionary optimization assisted delayed deep cycle reservoir modeling method with its application to ship heave motion prediction[J]. ISA Transactions，2022，126：638-648.
[28] LIU Y，DUAN W，HUANG L，et al. The input vector space optimization for LSTM deep learning model in real-time prediction of ship motions[J]. Ocean Engineering，2020，213：107681.
[29] LIANG P，LI Y，WANG B，et al. Remaining useful life prediction via a deep adaptive transformer framework enhanced by graph attention network[J]. International Journal of Fatigue，2023，174：107722.
[30] SUN Q，TANG Z，GAO J，et al. Short-term ship motion attitude prediction based on LSTM and GPR[J]. Applied Ocean Research，2022，118：102927.
[31] WANG L，XU X，SU Q，et al. Automatic gear shift strategy for manual transmission of mine truck based on Bi-LSTM network[J]. Expert Systems with Applications，2022，209：118197.
[32] LIN Y，LIN Z，LIAO Y，et al. Forecasting the realized volatility of stock price index: A hybrid model integrating CEEMDAN and LSTM[J]. Expert Systems with Applications，2022，206：117736.
[33] QIANG H，JIN S，FENG X，et al. Model predictive control of a shipborne hydraulic parallel stabilized platform based on ship motion prediction[J]. IEEE Access，2020，8：181880-181892.