Integrating model predictive control with deep learning for sway reduction in ship-to-shore crane operations
Keywords:
deep learning, model predictive control, prediction model, ship-to-shore crane, sway angleAbstract
The sway of the container winch drive system results in significant nonlinearity in Ship-to-Shore (STS) crane operations. As a result, achieving an accurate winch path becomes challenging, raising safety concerns for the operator and increasing the risk of accidents to both goods and equipment. This paper presents a Deep learning-based Model Predictive Control (DMPC) designed to improve the precision of the winch control signal during STS operations, ultimately reducing the load sway amplitude. First, a Long Short-Term Memory (LSTM) is employed to compute a state prediction model that forecasts the load sway angle and winch displacement amplitude. The predicted state serves as input to the DMPC controller, which determines the winch control value through an optimization function. Finally, the proposed solution is tested through two scenarios, yielding promising results that demonstrate its effectiveness.
References
[1] Zhang S, He X, Zhu H, Chen Q, Feng Y. Partially saturated coupled-dissipation control for underactuated overhead cranes. Mechanical Systems and Signal Processing. 2020; 136: 106449. doi: 10.1016/j.ymssp.2019.106449
[2] Lu B, Fang Y, Sun N. Sliding mode control for underactuated overhead cranes suffering from both matched and unmatched disturbances. Mechatronics. 2017; 47: 116–125. doi: 10.1016/j.mechatronics.2017.09.006
[3] Chen H, Fang Y, Sun N. An adaptive tracking control method with swing suppression for 4-dof tower crane systems. Mechanical Systems and Signal Processing. 2019; 123: 426–442. doi: 10.1016/j.ymssp.2018.11.018
[4] Zhong B, Zhan R. Load’s damping swing by trolley’s driving force control for overhead or gantry crane. Advanced Materials Research. 2012; 346: 875–881. doi: 10.4028/www.scientific.net/AMR.346.875
[5] Martin IA, Irani RA. A generalized approach to anti-sway control for shipboard cranes. Mechanical Systems and Signal Processing. 2021;148: 107168. doi: 10.1016/j.ymssp.2020.107168
[6] Suvorov VA, Bahrami MR, Akchurin EE, Chukalkin IA, Ermakov SA, Kan S A. Anti sway tuned control of gantry cranes. SN Applied Sciences. 2021; 3(8): 729. doi: 10.1007/s42452-021-04719-w
[7] Chang CY, Hsu KC. An enhanced adaptive sliding mode fuzzy control for positioning and anti-swing control of the overhead crane system. IEEE International Conference on Systems, Man and Cybernetics. 2007; 2: 992-997. doi: 10.1109/ICSMC.2006.384529
[8] Smoczek J, Szpytko J. Particle swarm optimization-based multivariable generalized predictive control for an overhead crane. IEEE/ASME Transactions on Mechatronics. 2017; 22(1): 258–268. doi: 10.1109/TMECH.2016.2598606
[9] Kusznir T, Smoczek J. Nonlinear Model Predictive Control with Evolutionary Data-Driven Prediction Model and Particle Swarm Optimization Optimizer for an Overhead Crane. Applied Sciences. 2024; 14(12):5112. doi: 10.3390/app14125112
[10] Zhang P, Wu HN, Chen RP, Chan THT. Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: A comparative study. Tunnelling and Underground Space Technology. 2020; 99: 103383. doi: 10.1016/j.tust.2020.103383
[11] Dang XK, Koboević Z, Nguyen HLP, Do VD, Ly S. Artificial Neural Network for Improving the Motion Control Quality of Underwater Remotely Operated Vehicle. NAŠE MORE. 2025; 72(2): 39 - 48. doi: 10.17818/NM/2025/2.1
[12] Liu T, Tang X, Wang H, Yu H, Hu X. Adaptive hierarchical energy management design for a plug-in hybrid electric vehicle. IEEE Transactions on Vehicular Technology. 2019; 68(12): 11513–11522. doi: 10.1109/TVT.2019.2926733
[13] Raj Priyadarshini R, Sivakumar N. Failure prediction, detection & recovery algorithms using MCMC in tree-based network topology to improve coverage and connectivity in 3D-UW environment. Applied Acoustics. 2020; 158: 107053. doi: 10.1016/j.apacoust.2019.107053
[14] Li S, Song X, Lu H, Zeng L, Shi M, Liu F. Friend recommendation for cross marketing in online brand community based on intelligent attention allocation link prediction algorithm. Expert Systems with Applications. 2020; 139: 112839. doi: 10.1016/j.eswa.2019.112839
[15] Zhang M, Zhang Y, Chen H, Cheng X. Model-independent PD-SMC method with payload swing suppression for 3D overhead crane systems. Mechanical Systems and Signal Processing. 2019;129: 381–393. doi: 10.1016/j.ymssp.2019.04.046
[16] Golovin I, Palis S. Robust control for active damping of elastic gantry crane vibrations. Mechanical Systems and Signal Processing. 2019; 121: 264–278. doi: 10.1016/j.ymssp.2018.11.005
[17] Yongming B, Jiange Y, Xiaolei X, Lu W, Lishan Z. Research on elastic dynamic model of trolley system for anti-sway control system of bridge crane. Procedia CIRP. 2018; 78: 285–288. doi: 10.1016/j.procir.2018.08.325
[18] Wang L, Zhang Q, Sun Y, Qing X. Moving Load Identification for STS Cranes Based on Hybrid Weighted Regularization Method. In Journal of Physics: Conference Series. 2020; 1549: 1-10. doi: 10.1088/1742-6596/1549/4/042109
[19] Jung M, Costa Mendes PR, Önnheim M, Gustavsson E. Model predictive control when utilizing LSTM as dynamic models. Engineering Applications of Artificial Intelligence. 2023; 123: 106226. doi: 10.1016/j.engappai.2023.106226
[20] Jeong SK, Ji DH, Oh JY, Seo JM, Choi HS. Disturbance learning controller design for unmanned surface vehicle using LSTM technique of recurrent neural network. Journal of Intelligent and Fuzzy Systems. 2021; 40: 8001–8011. doi: 10.3233/JIFS-189622
[21] Chauhan A, Kukkar Y, Nagrath P, Gupta K, Hemanth JD. Integrating LSTM and NLP techniques for essay generation. Intelligent Decision Technologies. 2024; 18(1): 571–584. doi: 10.3233/IDT-230424
[22] Pham TA, Dang XK, Koboević Z, Do VD, Pham TDA. Maritime data mining for marine safety based on deep learning: Southern Vietnam case study. NAŠE MORE. 2024; 71: 21–29. doi: 10.17818/NM/2024/1.4
[23] Cheng H, Xie Z, Shi Y, Xiong N. Multi-step data prediction in wireless sensor networks based on one-dimensional CNN and bidirectional LSTM. IEEE Access. 2019; 7: 117883–117896. doi: 10.1109/ACCESS.2019.2937098
[24] Dang XK, Corchado JM, Le VV, Do VD. Non-parametric Vibration-based Structural Damage Detection for Coastal Structures: Multi-Dimension to Single Input Convolutional Neural Network Approach. Advances in Electrical and Computer Engineering. 2024; 24(4): 3-18. doi: 10.4316/AECE.2024.04001
[25] Cao Y, Li T, Hao L. Nonlinear model predictive control of shipboard boom cranes based on moving horizon state estimation. Journal of Marine Science and Engineering. 2023; 11(1): 1–17. doi: 10.3390/jmse11010004
[26] Chandriah KK, Naraganahalli RV. RNN/LSTM with modified Adam optimizer in deep learning approach for automobile spare parts demand forecasting. Multimedia Tools and Applications. 2021; 80(17): 26145–26159. doi: 10.1007/s11042-021-10913-0
[27] Redwannewaz AA, Alam T, Murad Reis G, Bobadilla L, Smith RN. Long-Term Autonomy for AUVs Operating under Uncertainties in Dynamic Marine Environments. IEEE Robotics and Automation Letters. 2021; 6(4): 6313–6320. doi: 10.1109/LRA.2021.3091697
[28] Wen X, Li W. Time series prediction based on LSTM-Attention-LSTM model. IEEE Access. 2023; 11: 48322–48331. doi: 10.1109/ACCESS.2023.3276628
[29] Dang XK, Nguyen TD, Do VD, Nguyen NT. Control Parameter Optimization of the Automatic Voltage Regulator for Marine Synchronous Generator Based on Genetic. In 11th International Conference on Coastal and Ocean Engineering (ICCOE-2024). 2024: 442. doi: 10.1007/978-981-96-0181-3_40
[30] Jakovlev S, Eglynas T, Voznak M. Application of Neural Network Predictive Control Methods to Solve the Shipping Container Sway Control Problem in Quay Cranes. IEEE Access. 2021; 9:78253-78265. doi: 10.1109/ACCESS.2021. 308392
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Xuan-Kien Dang, Viet-Dung Do, Ngoc-Truc Nguyen, Soi Ly
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
