混合神经网络在污水毒性预测中的应用  

Mixed Neural Network and Its Applications in Predicting Wastewater Toxicity

作　　者：廖雪平[1] 罗飞[1] 

机构地区：[1]华南理工大学自动化科学与工程学院,广州510640

出　　处：《化工自动化及仪表》2011年第2期211-213,238,共4页Control and Instruments in Chemical Industry

基　　金：国家自然科学基金(60774032)

摘　　要：分析了污水处理厂污水毒性对其它工艺参数的影响,选取DO、ORP、NH4-N及COD等过程参数为毒性测量的辅助变量。介绍了粒子群算法和混沌算法,运用混沌粒子群算法和BP算法相结合的混合神经网络,对生化池污水毒性进行预测,实现毒性的定量测量和报警。仿真结果表明,混合神经网络的泛化性能和时间复杂度要优于BP神经网络。Basing on assistant variables of DO,ORP,NH4-N and COD selected,the impacts of toxic wastewater on the operating parameters in wastewater treatment plant were analyzed,and both particle swarm optimization algorithm and chaos algorithm were introduced,and a mixed neural network employing both chaos particle swarm optimization and BP algorithm was employed to predict the wastewater toxicity of biochemical pool.Simulation results show that this mixed neural network has better performance than BP algorithm.

关 键 词：污水毒性 混沌粒子群 混合神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]