基于改进FWA-NN的污水处理过程溶解氧浓度预测
|
摘要
为实现对污水处理过程溶解氧质量浓度的实时准确预测,提出了一种改进的混沌烟花混合优化算法并构建了基于改进算法的神经网络在线软测量模型.结合污水处理过程的数据特征,定义了一项新的样本相似度衡量指标用于提取更具代表性的建模数据.在改进算法中,为提高基本烟花算法初始成员的质量,定义了一种改进的两级正弦混沌映射并利用混沌运动的遍历性精选烟花算法的初始群成员;通过融合混沌算法改进了基本烟花算法的搜索机制,基于设定准则将寻优过程分为两阶段并采用两分群同时进行.测试结果表明改进算法的收敛速度和收敛精度有较大程度提高.将改进的软测量建模方法和样本数据提取方法用于污水处理过程溶解氧质量浓度软测量建模,应用结果表明该模型的均方根误差和平均泛化误差分别为0.0175和0.0118,具有较强的泛化性能.
To realize the quick and accurate measurement of the dissolved oxygen concentration(DO) in wastewater treatment process, a novel chaos-fireworks algorithm(FWA) based hybrid optimization algorithm was proposed and a neural network on-line soft-sensor model was built based on the improved algorithm. According to the property of the data collected from wastewater treatment process, a new measure of similarity degrees between samples was defined to extract more responsive modeling data. In the novel algorithm, a modified two-level sinusoidal chaotic mapping was defined and the initial members of FWA were well selected by utilizing the ergodicity of chaos. As a result, the quality of the initial population in standard FWA was improved. Next, the search mechanism of FWA was modified by introducing chaos optimization algorithm. The optimization procedure was divided into two phases and the population was divided into two subpopulations according to the predefined criterion. Test results confirmed that the improved FWA had higher convergence speed and convergence accuracy. The novel soft-sensor modeling method and the sample data extraction method was used to build a soft sensor model for real-time measuring DO in wastewater treatment process. Application results indicated the root mean square error and the root mean square error of this model were 0.0175 and 0.0118 respectively, it had good generalization ability.
To realize the quick and accurate measurement of the dissolved oxygen concentration(DO) in wastewater treatment process, a novel chaos-fireworks algorithm(FWA) based hybrid optimization algorithm was proposed and a neural network on-line soft-sensor model was built based on the improved algorithm. According to the property of the data collected from wastewater treatment process, a new measure of similarity degrees between samples was defined to extract more responsive modeling data. In the novel algorithm, a modified two-level sinusoidal chaotic mapping was defined and the initial members of FWA were well selected by utilizing the ergodicity of chaos. As a result, the quality of the initial population in standard FWA was improved. Next, the search mechanism of FWA was modified by introducing chaos optimization algorithm. The optimization procedure was divided into two phases and the population was divided into two subpopulations according to the predefined criterion. Test results confirmed that the improved FWA had higher convergence speed and convergence accuracy. The novel soft-sensor modeling method and the sample data extraction method was used to build a soft sensor model for real-time measuring DO in wastewater treatment process. Application results indicated the root mean square error and the root mean square error of this model were 0.0175 and 0.0118 respectively, it had good generalization ability.
引文
[1]Strokal M,Yang H,Zhang Y,et al.Increasing eutrophication in the coastal seas of China from 1970 to 2050[J].Marine Pollution Bulletin,2014,85(1):123-140.
[2]Chang N N,Shiao J C,Gong G C.Diversity of demersal fish in the East China sea:implication of eutrophication and fishery[J].Continental Shelf Research,2012,47(47):42-54.
[3]赵骥,王晓霞,李夕耀,等.DO浓度对EBPR耦合SND处理低C/N污水的影响[J].中国环境科学,2018,38(1):120-128.
[4]Meng F,Yang,A,Zhang G.Effects of dissolved oxygen concentration on photosynthetic bacteria wastewater treatment:Pollutants removal,cell growth and pigments production[J].Bioresource Technology,2017,241:993-997.
[5]张质明,王晓燕,潘润泽.一种改进的不确定性水质模型参数率定方法[J].中国环境科学,2017,37(3):956-962.
[6]Qiu Y,Liu Y,Huang D.Data-driven soft-sensor design for biological wastewater treatment using deep neural networks and genetic algorithms[J].Journal of Chemical Engineering of Japan,2016,49(10):925-936.
[7]胡康,万金泉,马邕文,等.基于模糊神经网络的A2/O工艺出水氨氮在线预测模型[J].中国环境科学,2012,32(2):260-267.
[8]Canete J F,Saz-Orozco P,Baratti R,et al.A soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network[J].Expert Systems with Applications,2016,63:8-19.
[9]史斌,姜继平,王鹏.基于高频在线水质数据异常的突发污染预警[J].中国环境科学,2017,37(11):4394-4400.
[10]Tan Y,Zhu Y C.Fireworks algorithm for optimization[C]//Proceedings of 1st International Conference on Swarm Intelligence.Berlin,Germany:Springer,2010:355-364.
[11]Li J,Zheng S U,Tan Y.Adaptive fireworks algorithm[C]//Proceedings of 2014 IEEE Congress on Evolutionary Computation.Piscataway,NJ,USA:IEEE,2014:3214-3221.
[12]Rajaram R,Palanisamy K,Ramasamy S,et a1.Selective harmonic elimination in PWM inverter using firefly and fireworks algorithm[J].International Journal of Innovative Research in Advanced Engineering,2014,1(8):55-62.
[13]吴琼,曾庆鹏.基于多目标烟花算法的关联规则挖掘[J].模式识别与人工智能,2017,30(4):365-376.
[14]Pavao L V,Costa C B B,Ravagnani M.Large-scale heat exchanger networks synthesis using simulated annealing and the novel rocket fireworks optimization[J].AICHE Journal,2017,63(5):1582-1601.
[15]Zheng S Q,Li J Z,Janecek A.A cooperative framework for fireworks algorithm[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2017,14(1):27-41.
[16]Ma T N,Niu D X.Icing forecasting of high voltage transmission line using weighted least square support vector machine with fireworks algorithm for feature selection[J].Applied Sciences,2016,6(12):438-456.
[17]张以文,吴金涛,赵姝,等.基于改进烟花算法的Web服务组合优化[J].计算机集成制造系统,2016,22(3):422-432.
[18]陈如清,俞金寿.混沌粒子群混合优化算法的研究与应用[J].系统仿真学报,2008,20(3):685-688.
[19]尤勇,王孙安,盛万兴.新型混沌优化方法的研究及应用[J].西安交通大学学报,2003,37(1):69-72.
[20]Li X,Feng Y,Chen H.Electric biological coupling process(EBCP)for wastewater treatment:a general review[J].Desalination and Water Treatment,2017,94:11-24.
[21]宋留,杨冲,张辉,等.造纸废水处理过程的高斯过程回归软测量建模[J].中国环境科学,2018,38(7):2564-2571.
[22]王衫允,马斌,贾方旭,等.AAO污水处理工艺中厌氧氨氧化效能及微生物交互作用[J].中国环境科学,2016,36(7):1988-1996.
[23]赵超,戴坤成,王贵评,等.基于AWLS-SVM的污水处理过程软测量建模[J].仪器仪表学报,2015,36(8):1792-1800.
[24]张姚,韩海成,王伟刚,等.溶解氧对CANON颗粒污泥自养脱氮性能的影响[J].中国环境科学,2017,37(12):4501-4510.
[25]乔俊飞,付文韬,韩红桂.基于SOTSFNN的溶解氧浓度控制方法[J].化工学报,2016,67(3):960-966.
[26]张伟,乔俊飞,李凡军.溶解氧浓度的直接自适应动态神经网络控制方法[J].控制理论与应用,2015,32(1):115-121.
[2]Chang N N,Shiao J C,Gong G C.Diversity of demersal fish in the East China sea:implication of eutrophication and fishery[J].Continental Shelf Research,2012,47(47):42-54.
[3]赵骥,王晓霞,李夕耀,等.DO浓度对EBPR耦合SND处理低C/N污水的影响[J].中国环境科学,2018,38(1):120-128.
[4]Meng F,Yang,A,Zhang G.Effects of dissolved oxygen concentration on photosynthetic bacteria wastewater treatment:Pollutants removal,cell growth and pigments production[J].Bioresource Technology,2017,241:993-997.
[5]张质明,王晓燕,潘润泽.一种改进的不确定性水质模型参数率定方法[J].中国环境科学,2017,37(3):956-962.
[6]Qiu Y,Liu Y,Huang D.Data-driven soft-sensor design for biological wastewater treatment using deep neural networks and genetic algorithms[J].Journal of Chemical Engineering of Japan,2016,49(10):925-936.
[7]胡康,万金泉,马邕文,等.基于模糊神经网络的A2/O工艺出水氨氮在线预测模型[J].中国环境科学,2012,32(2):260-267.
[8]Canete J F,Saz-Orozco P,Baratti R,et al.A soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network[J].Expert Systems with Applications,2016,63:8-19.
[9]史斌,姜继平,王鹏.基于高频在线水质数据异常的突发污染预警[J].中国环境科学,2017,37(11):4394-4400.
[10]Tan Y,Zhu Y C.Fireworks algorithm for optimization[C]//Proceedings of 1st International Conference on Swarm Intelligence.Berlin,Germany:Springer,2010:355-364.
[11]Li J,Zheng S U,Tan Y.Adaptive fireworks algorithm[C]//Proceedings of 2014 IEEE Congress on Evolutionary Computation.Piscataway,NJ,USA:IEEE,2014:3214-3221.
[12]Rajaram R,Palanisamy K,Ramasamy S,et a1.Selective harmonic elimination in PWM inverter using firefly and fireworks algorithm[J].International Journal of Innovative Research in Advanced Engineering,2014,1(8):55-62.
[13]吴琼,曾庆鹏.基于多目标烟花算法的关联规则挖掘[J].模式识别与人工智能,2017,30(4):365-376.
[14]Pavao L V,Costa C B B,Ravagnani M.Large-scale heat exchanger networks synthesis using simulated annealing and the novel rocket fireworks optimization[J].AICHE Journal,2017,63(5):1582-1601.
[15]Zheng S Q,Li J Z,Janecek A.A cooperative framework for fireworks algorithm[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2017,14(1):27-41.
[16]Ma T N,Niu D X.Icing forecasting of high voltage transmission line using weighted least square support vector machine with fireworks algorithm for feature selection[J].Applied Sciences,2016,6(12):438-456.
[17]张以文,吴金涛,赵姝,等.基于改进烟花算法的Web服务组合优化[J].计算机集成制造系统,2016,22(3):422-432.
[18]陈如清,俞金寿.混沌粒子群混合优化算法的研究与应用[J].系统仿真学报,2008,20(3):685-688.
[19]尤勇,王孙安,盛万兴.新型混沌优化方法的研究及应用[J].西安交通大学学报,2003,37(1):69-72.
[20]Li X,Feng Y,Chen H.Electric biological coupling process(EBCP)for wastewater treatment:a general review[J].Desalination and Water Treatment,2017,94:11-24.
[21]宋留,杨冲,张辉,等.造纸废水处理过程的高斯过程回归软测量建模[J].中国环境科学,2018,38(7):2564-2571.
[22]王衫允,马斌,贾方旭,等.AAO污水处理工艺中厌氧氨氧化效能及微生物交互作用[J].中国环境科学,2016,36(7):1988-1996.
[23]赵超,戴坤成,王贵评,等.基于AWLS-SVM的污水处理过程软测量建模[J].仪器仪表学报,2015,36(8):1792-1800.
[24]张姚,韩海成,王伟刚,等.溶解氧对CANON颗粒污泥自养脱氮性能的影响[J].中国环境科学,2017,37(12):4501-4510.
[25]乔俊飞,付文韬,韩红桂.基于SOTSFNN的溶解氧浓度控制方法[J].化工学报,2016,67(3):960-966.
[26]张伟,乔俊飞,李凡军.溶解氧浓度的直接自适应动态神经网络控制方法[J].控制理论与应用,2015,32(1):115-121.