人工神经网络模型在航道、港口潮水位预报中的应用

Back-propagation artificial neural network model for prediction of tidal water level

利用BP人工神经网络技术,以主要分潮为输入,在合理选择各参数的基础上,通过BP网络模型确定与各分潮调和常数相关的权值,建立起以短期潮水位资料为基础的潮水位预报模型.并利用该模型对珠江口磨刀门水道的大横琴站的潮位进行预报.结果表明,只要资料时间超过15 d就可以很好地预报较长时间的潮位.

The BP artificial neural network technology is applied to establish the model for prediction of tidal water level based on short-term tidal data. By reasonable selection of several parameters, the weights related to harmonic constants of main constituents are determined. The model is used to predict the tidal water level of Dahengqin station. The results show that the three-month tidal level prediction using 15-day training data is ideal and indicate that the BPN is capable of learning the level variations to predict the tidal variation using only very short-term observation data.