工业废水排放总量预测模型研究与仿真  

Research and Simulation on Prediction Model of Total Discharge of Industrial Wastewater

作　　者：张汛 李鹏[2] ZHANG Xun;LI Peng(School of Environmental Science and Engineering,Tianjin University,Tianjin 300072,China;College of Ocean Engineering,Guilin University of Electronic Science and Technology,Beihai Guangxi 536000,China)

机构地区：[1]天津大学环境科学与工程学院,天津300072 [2]桂林电子科技大学海洋工程学院,广西北海536000

出　　处：《计算机仿真》2022年第7期482-486,共5页Computer Simulation

摘　　要：针对采用目前方法对工业废水排放总量进行预测时,获取的数据中存在缺失数据,存在数据完整性差、预测精度低的问题,提出基于灰色GM(1,1)模型的工业废水排放总量预测模型,首先对矢量神经网络进行训练,将可信度引入训练后的矢量神经网络中对缺失数据进行填补,提高数据的完整性。其次采用马尔可夫模型修正GM(1,1)模型,获得灰色GM(1,1)模型,在此基础上根据获取的数据构建工业废水排放总量预测模型,完成工业废水排放总量的预测。实验结果表明,所提方法的数据完整性高,预测精度高。Currently,the problems of missing data,poor data integrity and low prediction accuracy exist when some methods are used to predict the total discharge quantity of industrial wastewater.Therefore,a model of predicting total industrial wastewater discharge based on gray GM(1,1) model was designed.Firstly,the vector neural network was trained,and then the creditability was introduced into it to fill in the missing data,thus improving the data integrity.Secondly,the Markov model was used to modify the GM(1,1) model and thus to obtain a gray GM(1,1) model.On this basis,the obtained data were used to build a model to predict total discharge quantity of industrial wastewater.Finally,the prediction was completed.Experimental results show that the proposed method has high data integrity and high prediction accuracy.

关 键 词：马尔可夫模型 工业废水 废水排放量 预测模型 

分 类 号：F326.4[经济管理—产业经济]