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

作　　者：潘赢 贾国庆[1] 郜伟伟 PAN Ying;JIA Guo-qing;GAO Wei-wei(College of Physics and Electronic Information Engineering, Qinghai Nationalities University, Xining 810007, China;Key Laboratory of Wireless Sensor Network and Communication, Shanghai Institute of Microsystem and Information Technology, Shanghai 200050, China)

机构地区：[1]青海民族大学物理与电子信息工程学院,青海西宁810007 [2]中国科学院上海微系统与信息技术研究所,无线传感网与通信重点实验室,上海200050

出　　处：《佳木斯大学学报（自然科学版）》2020年第2期40-44,共5页Journal of Jiamusi University：Natural Science Edition

基　　金：中国科学院无线传感网与通信重点实验室开放基金(2016002);青海民族大学校级重点项目5G中干扰消除关键技术研究(2019XJZ09)。

摘　　要：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.

关 键 词：BP神经网络 海鸥优化算法 水质 氨氮预测 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]