基于神经网络的船舶稳性预报研究

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

本站小编 Free考研考试/2024-01-16

-->

蒋柴丞,李楷,马坤.基于神经网络的船舶稳性预报研究[J].,2023,63(5):518-523

基于神经网络的船舶稳性预报研究

Study of ship stability prediction based on neural network

DOI：10.7511/dllgxb202305011

中文关键词:径向基函数神经网络船舶稳性预报第二代完整稳性失效概率输入特征选取

英文关键词:radial basis function neural network prediction of ship stability the second generation intact stability failure probability selection of input features

基金项目:国家自然科学基金资助项目(51509033)；中央高校基本科研业务费专项资金资助项目(DUT19JC51).

作者	单位
蒋柴丞,李楷,马坤

摘要点击次数:132

全文下载次数:154

中文摘要:

为省略船舶稳性计算中横摇阻尼以及船舶阻力等参数的复杂计算过程，提出一种采用径向基函数(RBF)神经网络对第二代完整稳性失效概率预报的方法．研究包括过度加速度、瘫船稳性以及骑浪/横甩3种失效模式．通过研究船舶相关参数对各失效模式失效概率的影响，确定采用RBF神经网络对每种失效模式进行预报时输入特征的选取，从而降低训练时长．使用训练后的网络对样本船稳性进行预报，采用均方误差和平均绝对百分比误差对预报结果进行评估．对3种失效模式预报结果的平均绝对百分比误差分别为6.49%、7.09%、5.70%，均小于10%，表明采用RBF神经网络可较为精准地对船舶稳性进行预报．

英文摘要:

In order to avoid the complicated calculation process of roll damping and ship resistance in the calculation of ship stability, a method is proposed for predicting the failure probability of the second generation intact stability by using radial basis function (RBF) neural network. Three failure modes are included: excessive acceleration, dead-ship stability and surf-riding/broaching. By studying the influence of ship-related parameters on the failure probability of each failure mode, the input features when using RBF neural network to predict each failure mode are determined, thereby reducing the training time. The trained network is used to predict the stability of the sample ship, and the mean square error (MSE) and the mean absolute percentage error (MAPE) are used to evaluate the predicted values. For the prediction values of the three failure modes, the MAPE values are 6.49%, 7.09% and 5.70%, which are all less than 10%, indicating that the RBF neural network can be used to predict the ship stability more accurately.

查看全文查看/发表评论下载PDF阅读器

关闭

基于神经网络的船舶稳性预报研究

本站小编 Free考研考试/2024-01-16

相关话题/

领限时大额优惠券,享本站正版考研考试资料!