BP及RBF人工神经元网络对臭氧生物活性炭水处理系统建模的比较

Comparative of BP and RBF artificial neural network's function on model building of ozonation and biological activated carbon water purification system.

运用ＢＰ和ＲＢＦ人工神经元网络建立臭氧生物活性炭系统模型，考察了两个网络对水处理系统建模的适应性。研究表明，ＢＰ和ＲＢＦ人工神经元网络的臭氧生物活性炭系统模型准确地描述了系统影响因素的关系，可以求出系统中臭氧的经济投量；用ＢＰ人工神经元网络建立水处理系统模型，泛化能力好，但逼近速度较慢；运用ＲＢＦ人工神经元网络建模，泛化能力较差，但逼近速度快。该项研究克服了运用传统方法建模的不足，为实现水处理系统的优化设计提供了可行的途径。

Through setting up ozonation and biological activated carbon system model by BP and RBF artificial neural networks,the applicability of the two neural networks are investigated to the water purification system.The study shows that these models accurately describe the relationships among the influence factors of the system and economical ozone's dosage can be obtained comparatively though the model;the model established by BP network has a good general ability and a slow impending speed,on the other hand,the model established by RBF neural network has a bad general ability and a fast impending speed.The limitations of the traditional model identification methods were get rid of.A means to realize the water purification system in line control is provided.