摘要
在造纸废水处理过程建立出水COD预测模型中,针对BP算法易陷入局部极小、收敛速度慢等缺点,根据遗传算法(Genetic Algorithm—GA)具有全局寻优的特点,将两者结合起来形成一种训练神经网络的混合算法——GA-BP算法;仿真结果表明,预测模型具有较强的学习能力和泛化能力,同时,建立的GA-BP模型预测输出的平均误差仅为0.88%,说明此模型可以有效、可靠地预测造纸废水出水COD。
A combining algorithm for neural network training is presented by combining BP algorithm and genetic algorithm in forecasting COD of papermaking wastewater treatment process according to the advantage of the globe optimal searching of genetic algorithm,in order to overcome the shortcomings that BP algorithm is usually trapped to a local optimum and it has a low speed of convergence weights.The simulative results indicated that the model has good ability both in learning and generalization,with the average relative errors of test data are 0.88%,indicates that this algorithm can effectively and reliably be used in the forecasting COD of papermaking wastewater treatment process by analyzing the results of real examples.This algorism can also effectively be used in other industrial wastewater treatment process.
出处
《中国造纸学报》
CAS
CSCD
北大核心
2010年第1期67-71,共5页
Transactions of China Pulp and Paper
基金
广东省"节能减排"重大专项项目(项目编号:2008A080800003)
广东省科学技术厅资助
关键词
遗传算法
BP网络
造纸废水处理
genetic algorithm
BP algorithm
papermaking wastewater treatment
