基于ARIMA-BP神经网络模型海流流速预测研究

Current Prediction Research Based on ARIMA-BP Neural Network Abstract

海流是一种具有广阔应用前景的无污染可再生能源,结合ARIMA时间序列预测模型和BP神经网络预测模型的优点,构建ARMA-BP神经网络混合模型,对海流流速预测问题进行研究。采用神经网络模型得出海流流速的残差值对时间序列模型的预测值进行修正,提高了海流流速预测的精度。

Current is a type of renewable energy without pollution and with big and wide developing prospect. Based on time series prediction model and the advantage of BP neural network model, this paper builds ARIMA -BP neural network mixed model for current velocity. Derived neural network model of ocean current velocity residuals time series model predicted values were corrected to improve the current velocity prediction accuracy..