The invention discloses a ship fuel consumption prediction method based on an elastic regression network. The ship fuel consumption prediction method comprises the following steps: collecting fuel consumption data and fuel consumption influence factor data; preprocessing the oil consumption data and the oil consumption influence factor data; an elastic regression network is adopted to establish an oil consumption prediction model, and a Lasso regression network and a ridge regression network are adopted in the elastic regression network at the same time. According to the method, the elastic regression network is established by combining the minimum absolute shrinkage, the selection operator regression and the ridge regression model to screen proper influence factors, so that the prediction precision is improved while the complexity of the oil consumption prediction model is reduced. According to the method, the Lasso regression and the ridge regression are combined, so that the elastic regression network has the advantages of the Lasso regression and the ridge regression. The method not only has the advantages of Lasso regression, but also deletes features which have small influence on dependent variables, and solves the problem of multicollinearity among a plurality of feature variables. And the purpose of preventing overfitting by ridge regression is achieved, and the complexity of the model is reduced.

    本发明公开了一种基于弹性回归网络的船舶油耗预测方法,包括以下步骤:采集油耗数据和油耗影响因素数据;对油耗数据和油耗影响因素数据进行预处理;采用弹性回归网络建立油耗预测模型,在弹性回归网络中同时采用Lasso回归网络和岭回归网络。本发明结合最小绝对收缩和选择算子回归和岭回归模型建立了弹性回归网络筛选合适的影响因素,降低了油耗预测模型的复杂度的同时,提高了预测精度。本发明通过结合Lasso回归和岭回归,使弹性回归网络兼有Lasso回归和岭回归的优点。既具有Lasso回归的优点,删除了对因变量影响较小的特征,解决多个特征变量之间的多重共线性问题。又达到了岭回归防止过拟合的目的,减低了模型的复杂度。


    Access

    Download


    Export, share and cite



    Title :

    Ship oil consumption prediction method based on elastic regression network


    Additional title:

    一种基于弹性回归网络的船舶油耗预测方法


    Contributors:
    ZUO YI (author) / LI SHANSHAN (author) / LI XINYU (author) / LI TIESHAN (author) / CHEN JUNLONG (author)

    Publication date :

    2023-09-19


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B63B Schiffe oder sonstige Wasserfahrzeuge , SHIPS OR OTHER WATERBORNE VESSELS / G01D MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE , Anzeigen oder Aufzeichnen in Verbindung mit Messen allgemein / G01F Messen des Volumens, des Durchflussvolumens, des Massendurchflusses oder des Füllstandes , MEASURING VOLUME, VOLUME FLOW, MASS FLOW, OR LIQUID LEVEL / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung




    Oil consumption prediction method for intelligent ship

    WEI DAOXIN / WANG YANG / ZHANG ZHENG et al. | European Patent Office | 2024

    Free access

    Ship energy consumption prediction method based on data driving

    WANG LIPENG / ZHANG ZHI / ZHU QIDAN et al. | European Patent Office | 2021

    Free access

    Ship fuel consumption prediction method based on distributed energy efficiency calculation

    YI MINGJING / YI XIAOBING / HE LIMING et al. | European Patent Office | 2024

    Free access