基于机器学习的船舶轴系安装校调方法研究  

Research on alignment method of ship shafting installation based on machine learning

作　　者：郑瑞栋 朱汉华[1,2] 赵修叁 刘恒[1] 尹志生 ZHENG Ruidong;ZHU Hanhua;ZHAO Xiusan;LIU Heng;YIN Zhisheng(School of Naval Architecture Ocean and Energy Power Engineering,Wuhan University of Technology,Wuhan 430063,China;Sanya Science and Education Innovation Park,Wuhan University of Technology,Sanya 572024,China)

机构地区：[1]武汉理工大学船海与能源动力工程学院,湖北武汉430063 [2]武汉理工大学三亚科教创新园,海南三亚572024

出　　处：《舰船科学技术》2025年第4期59-65,共7页Ship Science and Technology

基　　金：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)。

摘　　要：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 ad-justment 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 accur-ately 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.

关 键 词：船舶长轴系 轴系校调 GA-BP神经网络算法 轴系变位值计算 

分 类 号：U664.21[交通运输工程—船舶及航道工程]