基于长短期记忆网络的冰载荷反演研究

Study on Ice Load Inversion Based on LSTM Networks

长期以来,对实际航行中冰载荷的精确测量一直没有得到很好的解决。为了更好地解决上述问题,本文提出了一种基于数据的冰荷载反演新方法。建立反演模型的训练数据由有限元计算生成,并进行了详细描述。采用改进的灰狼优化算法对LSTM网络结构进行优化,成功地训练出了一种有效的基于LSTM网络的冰荷载反演模型,并且通过具体算例对该方法的有效性进行了说明。

Precise measurement of ice loads in actual navigation has not been worked out well for along time. To solve the problem better, a new method of ice load inversion based on data is proposedin the paper. The training data to establish the inversion model are generated by finite element calcu-lation. The process of training data generation is described explicitly. The structures of LSTM net-works are optimized by the refined grey wolf optimizer algorithm. A valid ice load inversion modelbased on LSTM networks is trained successfully. The general conclusions and results are illustratedby the concrete calculation samples.