摘要
针对管网末梢水质环境存在信息不确定、非线性的情况,本文结合灰色预测"贫信息"及BP神经网络非线性拟合强的优点,提出了灰色新陈代谢神经网络预测模型。该模型采用灰色新陈代谢GM(1,1)模型对BP网络的输入样本进行预处理,解决了BP网络需要大量学习样本的局限。仿真结果表明,与灰色新陈代谢、BP神经网络相比,灰色新陈代谢神经网络预测精度更高。
The information of terminal tap water environment is uncertainly, nonlinearly, complexly. According to the characteristics of urban drinking water quality, combined with grey predicting model for＂poor information＂is characterized, BP neural network with strong nonlinear fitting capability, and the gray metabolism BP neural network prediction model were proposed, using the data of information renewal model sets as the training and testing samples, the problem that BP network needs a mass of samples to approach nonlinear function better was solved.Simulation results indicate that, compared to the grey information renewal model and BP model, the grey information neural network model is superior in urban drinking water quality prediction.
出处
《自动化与仪器仪表》
2014年第12期4-6,共3页
Automation & Instrumentation
基金
重庆市科技攻关计划项目(cstc2012gg-sfgc40002)
重庆市科研院所创新能力建设计划项目(cstc2012pt-kyys40002)
关键词
灰色新陈代谢
BP神经网络
管网末梢水质预测
Grey information renewal
BP neural network
Terminal tap water quality prediction
