针对大型船舶长轴系装调效率较低，并且校中工作复杂的问题，开展基于机器学习的中间轴承校调方法研究。选取GA-BP神经网络算法作为机器学习模型，对船舶在设计、装调等过程中可能遇到的问题进行分析，并获得相关有效数据，用以训练船舶轴系校调机器学习模型。本文以某型船舶轴系校调为模型进行选取验证，结果表明，机器学习模型能够通过已有数据较为精确的识别轴系目前校中状态及安装高度，从而能够对船舶校调工作减少误差，有助于提升船舶长轴系安装质量及安装效率。
Aiming at the problem of low efficiency and complex calibration work of large ship shafting system, the adjustment method of middle bearing based on machine learning was studied. The GA-BP neural network algorithm is selected as the machine learning model to analyze the problems that may be encountered in the process of ship design, assembly and adjustment, and obtain relevant effective data for training the ship shafting adjustment machine learning model. In this paper, a certain type of ship shafting alignment is selected and verified. The results show that the machine learning model can accurately identify the current shafting alignment state and installation height through the existing data, so as to reduce the error of ship alignment work and help to improve the installation quality and efficiency of ship shafting.
2025,47(4): 59-65 收稿日期：2024-5-14
DOI：10.3404/j.issn.1672-7649.2025.04.010
分类号：U664.21
基金项目：国家自然科学基金资助项目（U2341284）；武汉理工大学三亚科教创新园开放基金（2022KF0019）
作者简介：郑瑞栋(1999-),男,硕士研究生,研究方向为船舶轴系校中
参考文献：
[1] MENG C L, DONG L Y, WANG D H, et al. Propeller hydrodynamic excitation influenced by shafting whirling vibration considering different nonuniform inflow conditions: A numerical study[J]. Ocean Engineering, 2023, 288(1): 116021-116038.
[2] JIAN W C, WEN J B, LIANG S, et al. A real-time shaft alignment monitoring method adapting to ship hull deformation for marine propulsion system[J]. Mechanical Systems and Signal Processing, 2023, 197: 110366-110391.
[3] CHANG M H, JUANG S H. Theoretical design study on shafting alignment calculation for high-speed craft[J]. Shipbuilding, 2014, 65(3): 31-47.
[4] 曲智. 船舶推进轴系负荷测试系统开发[D]. 大连: 大连理工大学, 2013.
[5] 贺威. 不同对中状态下的轴系动态负荷测量方法研究[D]. 上海: 上海交通大学, 2020.
[6] 王飞翔. 大型船舶推进轴系负荷测量及调整关键技术研究[D]. 大连: 大连理工大学, 2016
[7] 宋汉江, 孙玲, 孙锋. 船舶轴系设计中校验评估的配置化实现方法[J]. 中国舰船研究, 2021, 16(S1): 114-120.
SONG H J, SUN L, SUN F. Configuration-based realization method for verification evaluation in shafting design of ships[J]. Chinese Journal of Ship Research, 2021, 16(S1): 114-120.
[8] MAGALHAES D L, DE SS MARTINS D H C, CASTRO B M, et al. Machine learning performance comparison for main propulsive shafting systems alignment[J]. Ocean Engineering, 2023, 280: 114556-114564.
[9] DENG Y, LI Y, ZHU H, et al. Displacement values calculation method for ship multi-support shafting based on transfer learning[J]. Journal of Marine Science and Engineering, 2023, 12(1): 36-52.
[10] 王博文. 考虑校中状态的推进轴系动态性能分析与实验研究[D]. 武汉: 武汉理工大学, 2023.
[11] 徐海峰, 陈恒强. 基于Lab VIEW的轴系校中程序开发及案例分析[J]. 船舶工程, 2022, 44(S1): 386-389.
XU H F, SUN H Q. Development of shafting alignment program based on the LabVIEW and case analyses[J]. SHIP ENGINEERING, 2022, 44(S1): 386-389.
[12] 杨金中. 基于船台校装的舰船轴系校中技术研究[D]. 武汉: 华中科技大学, 2012.
[13] 代丽华, 张志敏. 基于MOGA的船舶推进轴系校中优化方法[J]. 船舶工程, 2022, 44(2): 65-68.
DAI L H, ZHANG Z M. Optimization method of ship propulsion shafting alignment based on MOGA[J]. Ship Engineering, 2022, 44(2): 65-68.
[14] 郭鹏, 华宏星, 陈锋, 等. 动态因素对轴系校中的影响分析[J]. 噪声与振动控制, 2020(5): 65-71.
GUO P, HUA H X, CHEN F, et al. Analysis of the influence of dynamic factors on shafting alignment[J]. Noise and Vibration Control, 2020(5): 65-71.
