中长期径流预报中PCA-IBP模型的改进算法研究

The Improved Algorithm of PCA-IBP Model in Medium and Long-Term Runoff Forecast

径流预报的信息有很大的相关性,这是必须在预报工作中避免的,同时,这些信息的维度较高,且以往处理这些信息的数学模型计算复杂度较高.针对以上问题提出了一种混合主成分分析方法(PCA,Principal Component Analysis)和改进BP(Improved Back Propagation)神经网络模型的中长期径流预报模型(PCA-IBP),此种方法可以很好地避免以上不足,可以进一步提高模型计算效率.实际数据验证表明,提出模型预报的精准程度以及效率都较传统的BP神经网络预报模型有所改善.

The runoff forecast information has a very large correlation, which must be avoided in the forecast work. Meanwhile the dimension of the information and the computational complexity of the mathematical model of the information are higher in the past. In this paper, we proposed a mixture of principal PCA （principal component analysis） method and the improved BP （back propagation） neural network model into a medium and long-term runoff forecasting model （PCA-IBP） to solve the above problems. This new method can well avoid the shortcomings mentioned before, and can further improve the efficiency of the model calculation. The actual data shows that the accuracy and efficiency of the proposed model are improved compared with the traditional BP neural network forecasting model.