The invention discloses a ship motion attitude prediction method based on multiple combinations, and the method comprises the steps: selecting a hidden layer node number, an initial learning rate and a maximum training frequency as hyper-parameters of a neural network needing to be optimized, and determining an initialization parameter and a fitness function of a whale optimization algorithm; training the GRU neural network by using a whale optimization algorithm to obtain an optimized WGRU neural network model; decomposing the original ship attitude data by using complete set empirical mode decomposition, and training the WGRU network by using the decomposed data to obtain a CWGRU combined prediction model; the prediction result of the CWGRU combined prediction model is the minimum in root mean square error and average absolute percentage error, and the correlation coefficient is the highest; due to the fact that the CEEMD algorithm is used for decomposing original ship attitude data, the algorithm has a better prediction effect on ship motion attitudes with non-stationary and non-linear characteristics.

    本发明公开的基于多组合的船舶运动姿态预测方法,选择隐藏层节点数、初始学习率、最大训练次数作为需要优化的神经网络的超参数,确定鲸鱼优化算法的初始化参数及适应度函数;利用鲸鱼优化算法对GRU神经网络进行训练,得到优化后的WGRU神经网络模型;利用完全集合经验模态分解对原始船舶姿态数据进行分解,使用分解后的数据对WGRU网络进行训练,得到CWGRU组合预测模型;本发明的CWGRU组合预测模型的预测结果在均方根误差及平均绝对百分比误差上均为最小,相关系数最高;由于使用了CEEMD算法对原始船舶姿态数据进行了分解,使得算法对于具有非平稳、非线性特征的船舶运动姿态具有更好的预测效果。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Ship motion attitude prediction method based on multiple combinations


    Weitere Titelangaben:

    基于多组合的船舶运动姿态预测方法


    Beteiligte:
    HE XIANDENG (Autor:in) / LIU XINGYUAN (Autor:in) / YI YUNHUI (Autor:in) / ZHU CHANGHUA (Autor:in) / KWON DONG-HYO (Autor:in) / CHEN NAN (Autor:in)

    Erscheinungsdatum :

    2023-04-21


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B63B Schiffe oder sonstige Wasserfahrzeuge , SHIPS OR OTHER WATERBORNE VESSELS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES



    Ship rolling motion attitude control system based on multiple learning algorithms

    SONG WEIWEI / TAN YINCHAO / ZHANG LINGLONG et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Strong-adaptability ship future motion attitude prediction method and system based on real sea conditions

    CHEN ZHANYANG / LIU XINGYUN / MA ZHAO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Ship attitude prediction method based on SCA-HHO-GRU model

    JIANG YANSHU / JIA MINGQI | Europäisches Patentamt | 2023

    Freier Zugriff

    MULTI-SHIP MOTION ATTITUDE REAL-TIME MONITORING SYSTEM

    ZAN YINGFEI / YUAN LIHAO / HAN DUANFENG | Europäisches Patentamt | 2023

    Freier Zugriff

    Follow-up test ship model motion attitude control mechanism

    LI HUI / ZOU JIAN / LIU NING et al. | Europäisches Patentamt | 2023

    Freier Zugriff