The invention discloses a PSO-LSTM-based ship motion prediction method, electronic equipment and a storage medium, and belongs to the technical field of ship engineering. In order to solve the problems of poor prediction precision and low efficiency of a traditional ship motion prediction mode, the method comprises the following steps: constructing a ship motion model, and then collecting ship motion data through simulation; after data cleaning and normalization processing are carried out, the obtained data are divided into a training set and a test set; building an LSTM network, setting structural parameters of the LSTM network, and inputting the obtained training set and test set into the LSTM network for training in a window sliding prediction mode to obtain a trained LSTM network; and carrying out optimization on related hyper-parameters in the network structure by adopting a particle swarm optimization algorithm to obtain an optimal value of the related hyper-parameters of the LSTM network and the optimized LSTM network, and then testing the optimized LSTM network by adopting the obtained test set. The method is accurate in prediction.

    一种基于PSO‑LSTM的船舶运动预测方法、电子设备及存储介质,属于船舶工程技术领域。为解决船舶运动传统预测方式预测精度差,效率低的问题,本发明包括构建船舶运动模型,然后通过仿真采集船舶运动数据;进行数据清洗,归一化处理后,对得到的数据进行划分为训练集和测试集;搭建LSTM网络,设置LSTM网络的结构参数,然后将得到的训练集和测试集采用窗口滑动的预测方式,输入到LSTM网络中进行训练,得到训练后的LSTM网络;采用粒子群优化算法对网络结构中的相关超参数进行寻优,得到LSTM网络相关超参数的最优值及优化后的LSTM网络,然后采用得到的测试集对优化后的LSTM网络进行测试。本发明预测准确。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    PSO-LSTM-based ship motion prediction method, electronic equipment and storage medium


    Weitere Titelangaben:

    一种基于PSO-LSTM的船舶运动预测方法、电子设备及存储介质


    Beteiligte:
    HUANG QITAO (Autor:in) / LIU YIMING (Autor:in) / LIU TIANBO (Autor:in) / LI BOWEN (Autor:in)

    Erscheinungsdatum :

    22.10.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    B63B Schiffe oder sonstige Wasserfahrzeuge , SHIPS OR OTHER WATERBORNE VESSELS



    Ship motion prediction method and device, electronic equipment and readable storage medium

    HAO YINGGANG / JIA XUELI / XU BIN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Conv-Bi-LSTM model-based ship heaving motion prediction system and prediction method

    ZHANG YA / FAN SHIWEI / PING BAOJIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Ship navigation decision prediction method and device, electronic equipment and storage medium

    SHU YAQING / CAI YUAN / GAN LANGXIONG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Ship draught prediction method and system, electronic equipment and readable storage medium

    YU HONGCHU / YI TIANYOU / FAN ZIHAO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Prediction of ship track based on ARIMA-LSTM

    Yu, Chen / Fu, Yuhui | British Library Conference Proceedings | 2022