基于遗传算法的BOD神经网络软测量  

NN Soft-Measuring for BOD Predict Based on GA

作　　者：田奕[1,2] 乔俊飞[1] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100022 [2]华北科技学院电子信息工程系,北京101601

出　　处：《计算机技术与发展》2009年第3期127-129,133,共4页Computer Technology and Development

基　　金：国家自然科学基金(60674066)

摘　　要：针对污水处理过程中关键水质参数无法在线监测的问题,提出基于遗传算法和BP神经网络相结合的污水水质软测量方法,该方法采用遗传算法优化神经网络结构和权、阈值分布,再用BP算法对神经网络进行训练,得到最优的建模网络。仿真结果表明该方法可以避免单独使用BP网络容易陷入局部最小的问题,并能加快全局收敛速度,对水质参数BOD(生化需氧量)预测实时性好、稳定性高、精度高,可用于污水水质的在线预测。Considering that on-line information of some essential wastewater parameters is inaccessible in monitoring and controlling wastewater treatment processes, a soft-measuring technique applied to wastewater quality measurement is put forward based on genetic algorithm（GA） and BP neural networks. This method applies genetic algorithm to optimize structure, weights and thresholds of the neural network,then uses BP algorithm to train the neural network in order to get to the superior network. The simulation results show that the new method can avoid getting into the part minimum problem caused by using BP neural network alone and accelerate the overall converging speed. This model, which is of good real-time property, good stability and high precision, can he applied to on-line predict wastewater BOD.

关 键 词：污水处理 软测量 遗传算法 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]