SOA优化BP神经网络的水体氨氮预测模型

Prediction Model of Ammonia Nitrogen in Water Based on SOA Optimized BP Neural Network

为提高水体中氨氮的预测精度,本文提出一种基于SOA改进BP神经网络的预测模型。首先,采用具有较好全局搜索能力和局部搜索能力的SOA算法对BP神经网络的初始权值和阈值进行优化,防止其在训练过程中陷入局部最优值,而后采用优化后的权值和阈值作为BP神经网络的初始权值和阈值对其进行训练。仿真结果表明所提出的新模型对水体中的氨氮含量具有更高的预测精度,且提出模型的收敛速度较传统BP神经网络更快,可更好的应用于复杂水体中氨氮的预测。

In order to improve the prediction accuracy of ammonia nitrogen in water,a prediction model based on SOA improved BP neural network is proposed in this paper.First,the SOA algorithm with better global search ability and local search ability is used to optimize the initial weight and threshold of the BP neural network to prevent it from falling into the local optimal value during the training process,and then the optimized weight and threshold.It is trained as the initial weight and threshold of the BP neural network.Simulation results show that the proposed new model has higher prediction accuracy of ammonia nitrogen content in water bodies,and the proposed model has a faster convergence rate than traditional BP neural network,and can be better applied to the prediction of ammonia nitrogen in complex water bodies.