基于ANN算法的海洋平台动力定位前馈-反馈控制方法  

ANN-Based Feedforward Feedback Control Strategy for Offshore Platform Dynamic Positioning

作　　者：杜君峰[1] 李杰[1] 邬德宇 常安腾 DU Junfeng;LI Jie;WU Deyu;CHANG Anteng(College of Engineering,Ocean University of China,Qingdao 266100,Shandong,China;CCCC Tianjin Channel Bureau Co.,Ltd.,Tianjin 300461,China)

机构地区：[1]中国海洋大学工程学院,山东青岛266100 [2]中交天津航道局有限公司,天津300461

出　　处：《中国海洋平台》2023年第3期22-29,共8页China offshore Platform

基　　金：国家自然科学基金(编号:52101339);山东省重点研发计划(编号:2020ZLYS06)。

摘　　要：鉴于动力定位控制策略中的前馈控制与反馈控制方法具有不同的优缺点,提出一种基于人工神经网络(Artificial Neural Network,ANN)算法的二阶差频波浪力前馈控制与浮体位置反馈控制相结合的动力定位前馈-反馈控制方法,通过低频波浪载荷的超前预测提前做出反应,并对实时位置信息进行反馈控制以纠正前馈信息的误差及其累积效应,从而实现前馈、反馈两种控制模式的优势互补。对某半潜式平台动力定位模式进行数值仿真,验证所提出的前馈-反馈控制方法的可行性和有效性,与单一的前馈或反馈控制相比,平台动力定位的精度和稳定性得到显著提升。In view of the different advantages and disadvantages of feedforward control and feedback control in dynamic positioning control,a feedforward-feedback control method is proposed for dynamic positioning by combining the feedforward control of second-order difference-frequency wave forces with the feedback control of floating body position based on an Artificial Neural Network(ANN)algorithm.The proposed method reacts in advance by predicting the low-frequency wave load,and performs feedback control on the real-time position information to correct the error of the feedforward information and weaken the cumulative effect,so as to realize the complementary advantages of the feedforward and feedback control strategies.Through the numerical simulations of the dynamic positioning of a semi-submersible platform,the feasibility and effectiveness of the proposed feedforward-feedback control method are verified.Compared with the results of feedforward or feedback control alone,the accuracy and stability of the dynamic positioning of the platform are significantly improved by the proposed method.

关 键 词：深水浮式平台 动力定位 波浪前馈控制 前馈-反馈控制 人工神经网络 

分 类 号：U664[交通运输工程—船舶及航道工程]