基于蜂群优化神经网络的环境空气质量预测  

Prediction of Ambient Air Quality Based on Neural Network Optimized by Artificial Bee Colony Algorithm

作　　者：刘笃晋 蒲国林 王光琼 LIU Dujin;PU Guolin;WANG Guangqiong(School of Intelligent Manufacturing,Sichuan University of Arts and Science,Dazhou 635000)

机构地区：[1]四川文理学院智能制造学院,达州635000

出　　处：《计算机与数字工程》2018年第4期639-643,共5页Computer & Digital Engineering

基　　金：国家自然科学基金项目(编号:61152003);四川省教育厅重点项目(编号:16ZA0353);四川省教育厅基金项目(编号:16ZB0360);四川文理学院2015年度特色培育一般项目(编号:2015TP001Y)资助

摘　　要：环境空气质量预测在环境污染防止中具有重要作用,由于环境空气质量预测受多方面因素的影响,预测的精度并不能满足日益发展的需要,通过对人工蜂群算法进行改进,并引入反向传播的神经网络中,以训练误差的倒数作为适应度函数,以随机化方式赋值给蜂群中蜜蜂的初始值作为神经网络的初始权值和阈值,改进的人工蜂群算法所求得的全局最优解即是反向传播神经网络中最优权值和阈值,以此优化的反向传播神经网络进行环境空气质量预测,通过和传统反向传播神经网络、传统人工蜂群算法优化反向传播神经网络算法的实验结果表明,论文提出的优化反向传播神经网络在环境空气质量预测中的整体性能取得了较为理想的结果,完全能用于实际。Environmental air quality prediction plays an important role in the prevention of environmental pollution.Because the prediction ambient air quality is affected by many factors,the accuracy of prediction can not meet the needs of the development.The artificial bee colony algorithm(ABC)is improved and introduced into the back propagation neural network(BP).The reciprocal of the training error is used as the fitness function,and the initial value of the ABC is assigned as the initial weight and the threshold of BP.The global optimal solution obtained by the improved artificial bee colony algorithm(IABC)is the global optimal weight and threshold of the BP.The optimized BP neural network is used to predict the ambient air quality,by comparing the traditional BP neural network,the traditional artificial bee colony optimization back propagation neural network.Experimental results show the optimized BP neural network proposed in this paper has achieved ideal results in ambient air quality prediction,and can be used in practice.

关 键 词：人工蜂群算法 反向传播神经网络 环境空气质量预测 适应度函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]