污水处理厂出水水质变量区间预测建模
|
摘要
为了实现污水处理厂的有效运行,需要建立能够精确描述水厂行为的模型。根据水厂入水和出水数据,采用径向基函数神经网络建立污水处理过程模型。考虑到建模误差有界,使用参数线性集员辨识算法分别得到隐含层到输出层各神经元连接权值向量的不确定集合描述。与现有的单输出区间预测模型相比,该模型能够根据水厂入水数据同时给出多个出水水质变量的置信区间。这些区间能表征出水变量的存在范围,从而实现水质变量的可靠估计,进而评估出水水质或水厂性能。此外,还将此出水区间预测模型用于污水处理厂的故障检测与隔离,以提高水厂运行的可靠性。实验结果表明文中所提方法的有效性。
To achieve efficient operation of the wastewater treatment plant(WWTP), it is necessary to establish amodel that accurately describes the behavior of the plan. In this paper, the radial basis function neural network(RBFNN) is utilized in the modeling of the WWTP basing on the available influent and effluent data. Consideringthe bounded modeling error, linear-in-parameters set membership identification algorithm is used to describe anuncertain set of each vector representing the weights of the links between all the hidden neurons and one outputneuron. Comparing with the existing methods which are all proposed for a single effluent variable, the method herebuilds a predictor model which can compute confidence intervals for multiple effluent variables simultaneouslyaccording to the values of the influent variables. The confidence intervals can characterize the existence ranges ofthe effluent variables, such that reliable estimates of them are obtained. By the estimates, the effluent quality or theWWTP performance can be evaluated. Besides, the interval predictor model is also applied to the fault detectionand isolation of the WWTP to realize reliable operation. The experiment results show the satisfying performance ofthe proposed method.
To achieve efficient operation of the wastewater treatment plant(WWTP), it is necessary to establish amodel that accurately describes the behavior of the plan. In this paper, the radial basis function neural network(RBFNN) is utilized in the modeling of the WWTP basing on the available influent and effluent data. Consideringthe bounded modeling error, linear-in-parameters set membership identification algorithm is used to describe anuncertain set of each vector representing the weights of the links between all the hidden neurons and one outputneuron. Comparing with the existing methods which are all proposed for a single effluent variable, the method herebuilds a predictor model which can compute confidence intervals for multiple effluent variables simultaneouslyaccording to the values of the influent variables. The confidence intervals can characterize the existence ranges ofthe effluent variables, such that reliable estimates of them are obtained. By the estimates, the effluent quality or theWWTP performance can be evaluated. Besides, the interval predictor model is also applied to the fault detectionand isolation of the WWTP to realize reliable operation. The experiment results show the satisfying performance ofthe proposed method.
引文
[1] Gernaey K V, van Loosdrecht M C M, Henze M, et al. Activated sludge wastewater treatment plant modelling and simulation:state of the art[J]. Environmental Modelling and Software, 2004, 19(9):763-783.
[2] Henze M, Grady C P L, Gujer W, et al. Activated sludge model No. 1:IAWPRC scientific and technical reports No.1[R]. London:IAWPRC, 1987.
[3] Henze M, Gujer W, Mino T, et al. Activated Sludge Models ASM1,ASM2, ASM2d and ASM3[M]. London:IWA Publishing, 2000.
[4] Khataee A R, Kasiri M B. Modeling of biological water and wastewater treatment processes using artificial neural networks[J].Clean-Soil, Air, Water, 2011, 39(8):742-749.
[5] Gü?lüD, Dursun?. Artificial neural network modelling of a largescale wastewater treatment plant operation[J]. Bioprocess and Biosystems Engineering, 2010, 33(9):1051-1058.
[6] Sainz G I, Fuente M J, Vega P. Recurrent neuro-fuzzy modeling of a wastewater treatment plant[J]. European Journal of Control,2004, 10(1):84-96.
[7] Belanche L A, Valdés J J, Comas J, et al. Towards a model of input-output behaviour of wastewater treatment plants using soft computing techniques[J]. Environmental Modelling and Software,1999, 14(5):409-419.
[8] Hamed M M, Khalafallah M G, Hassanien E A. Prediction of wastewater treatment plant performance using artificial neural networks[J]. Environmental Modelling and Software, 2004, 19(10):919-928.
[9] Raduly B, Gernaey K V, Capodaglio A G, et al. Artificial neural networks for rapid WWTP performance evaluation:methodology and case study[J]. Environmental Modelling and Software, 2007,22(8):1208-1216.
[10] Moral H, Aksoy A, Gokcay C F. Modeling of the activated sludge process by using artificial neural networks with automated architecture screening[J]. Computers and Chemical Engineering,2008, 32(10):2471-2478.
[11] Mjalli F S, Al-Asheh S, Alfadala H E. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance[J]. Journal of Environmental Management, 2007, 83(3):329-338.
[12] Lee J W, Suh C, Hong Y S T, et al. Sequential modelling of a fullscale wastewater treatment plant using an artificial neural network[J]. Bioprocess and Biosystems Engineering, 2011, 34(8):963-973.
[13] Bagheri M, Mirbagheri S A, Ehteshami M, et al. Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks[J]. Process Safety and Environmental Protection, 2015,93:111-123.
[14] Liu Q, Ibeas A, Vilanova R. Neural network identification of wastewater treatment plants[C]//Proceedings of 23rd Mediterranean Conference on Control and Automation. IEEE,2015:840-846.
[15]?krjanc I. Confidence interval of fuzzy models:an example using a waste-water treatment plant[J]. Chemometrics and Intelligent Laboratory Systems, 2009, 96(2):182-187.
[16] Ni W D, Wang K, Chen T, et al. GPR model with signal preprocessing and bias update for dynamic processes modeling[J].Control Engineering Practice, 2012, 20(12):1281-1292.
[17] Liu Y Q, Huang D P, Li Y. Development of interval soft sensors using enhanced just-in-time learning and inductive confidence predictor[J]. Industrial and Engineering Chemistry, 2012, 51(8):3356-3367.
[18] Liu Y Q, Guo J H, Wang Q L, et al. Prediction of filamentous sludge bulking using a state-based Gaussian processes regression model[J]. Scientific Reports, 2016, 6:31303.
[19]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.Song L, Yang C, Zhang H, et al. Soft-sensor modeling of papermaking wastewater treatment process based on Gaussian process[J]. China Environmental Science, 2018, 38(7):2564-2571.
[20]柴伟,纪镐南.污水处理出水BOD区间预测建模[J].哈尔滨工业大学学报, 2018, 50(2):71-76.Chai W, Ji H N. Interval predictor models for effluent BOD of wastewater treatment[J]. Journal of Harbin Institute of Technology,2018, 50(2):71-76.
[21] Chai W, Guo L H, Li X M, et al. Interval prediction of effluent TP for wastewater treatment plants[C]//Proceedings of 2019 IEEE Conference on Control Technology and Applications. IEEE, 2019:511-516.
[22] Alex J, Beteau J F, Copp J B, et al. Benchmark for evaluating control strategies in wastewater treatment plants[C]//Proceedings of 1999 European Control Conference. IEEE, 1999:3746-3751.
[23] Jeppsson U, Pons M N. The COST benchmark simulation modelcurrent state and future perspective[J]. Control Engineering Practice, 2004, 12(3):299-304.
[24] Mirbagheri S A, Bagheri M, Boudaghpour S, et al. Performance evaluation and modeling of a submerged membrane bioreactor treating combined municipal and industrial wastewater using radial basis function artificial neural networks[J]. Journal of Environmental Health Science and Engineering, 2015, 13:17.
[25] Bezdek J C. Pattern Recognition with Fuzzy Objective Function Algorithms[M]. New York:Plenum Press, 1981.
[26] Milanese M, Vicino A. Optimal estimation theory for dynamic systems with set membership uncertainty:an overview[J].Automatica, 1991, 27(6):997-1009.
[27] Chai W, Sun X F, Qiao J F. Improved zonotopic method to set membership identification for systems with time-varying parameters[J]. IET Control Theory and Applications, 2011, 5(17):2039-2044.
[28] Chai W, Sun X F, Qiao J F. Set membership state estimation with improved zonotopic description of feasible solution set[J].International Journal of Robust and Nonlinear Control, 2013, 23(14):1642-1654.
[29] Fogel E, Huang Y F. On the value of information in system identification–bounded noise case[J]. Automatica, 1982, 18(2):229-238.
[30] Belforte G, Bona B. An improved parameter identification algorithm for signals with unknown but bounded errors[C]//Proceedings of the 7th IFAC/IFORS Symposium on Identification and System Parameter Estimation. IFAC, 1985:1507-1511.
[31] Chai W, Qiao J F. Passive robust fault detection using RBF neural modeling based on set membership identification[J]. Engineering Applications of Artificial Intelligence(a Journal of IFAC), 2014,28:1-12.
[2] Henze M, Grady C P L, Gujer W, et al. Activated sludge model No. 1:IAWPRC scientific and technical reports No.1[R]. London:IAWPRC, 1987.
[3] Henze M, Gujer W, Mino T, et al. Activated Sludge Models ASM1,ASM2, ASM2d and ASM3[M]. London:IWA Publishing, 2000.
[4] Khataee A R, Kasiri M B. Modeling of biological water and wastewater treatment processes using artificial neural networks[J].Clean-Soil, Air, Water, 2011, 39(8):742-749.
[5] Gü?lüD, Dursun?. Artificial neural network modelling of a largescale wastewater treatment plant operation[J]. Bioprocess and Biosystems Engineering, 2010, 33(9):1051-1058.
[6] Sainz G I, Fuente M J, Vega P. Recurrent neuro-fuzzy modeling of a wastewater treatment plant[J]. European Journal of Control,2004, 10(1):84-96.
[7] Belanche L A, Valdés J J, Comas J, et al. Towards a model of input-output behaviour of wastewater treatment plants using soft computing techniques[J]. Environmental Modelling and Software,1999, 14(5):409-419.
[8] Hamed M M, Khalafallah M G, Hassanien E A. Prediction of wastewater treatment plant performance using artificial neural networks[J]. Environmental Modelling and Software, 2004, 19(10):919-928.
[9] Raduly B, Gernaey K V, Capodaglio A G, et al. Artificial neural networks for rapid WWTP performance evaluation:methodology and case study[J]. Environmental Modelling and Software, 2007,22(8):1208-1216.
[10] Moral H, Aksoy A, Gokcay C F. Modeling of the activated sludge process by using artificial neural networks with automated architecture screening[J]. Computers and Chemical Engineering,2008, 32(10):2471-2478.
[11] Mjalli F S, Al-Asheh S, Alfadala H E. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance[J]. Journal of Environmental Management, 2007, 83(3):329-338.
[12] Lee J W, Suh C, Hong Y S T, et al. Sequential modelling of a fullscale wastewater treatment plant using an artificial neural network[J]. Bioprocess and Biosystems Engineering, 2011, 34(8):963-973.
[13] Bagheri M, Mirbagheri S A, Ehteshami M, et al. Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks[J]. Process Safety and Environmental Protection, 2015,93:111-123.
[14] Liu Q, Ibeas A, Vilanova R. Neural network identification of wastewater treatment plants[C]//Proceedings of 23rd Mediterranean Conference on Control and Automation. IEEE,2015:840-846.
[15]?krjanc I. Confidence interval of fuzzy models:an example using a waste-water treatment plant[J]. Chemometrics and Intelligent Laboratory Systems, 2009, 96(2):182-187.
[16] Ni W D, Wang K, Chen T, et al. GPR model with signal preprocessing and bias update for dynamic processes modeling[J].Control Engineering Practice, 2012, 20(12):1281-1292.
[17] Liu Y Q, Huang D P, Li Y. Development of interval soft sensors using enhanced just-in-time learning and inductive confidence predictor[J]. Industrial and Engineering Chemistry, 2012, 51(8):3356-3367.
[18] Liu Y Q, Guo J H, Wang Q L, et al. Prediction of filamentous sludge bulking using a state-based Gaussian processes regression model[J]. Scientific Reports, 2016, 6:31303.
[19]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.Song L, Yang C, Zhang H, et al. Soft-sensor modeling of papermaking wastewater treatment process based on Gaussian process[J]. China Environmental Science, 2018, 38(7):2564-2571.
[20]柴伟,纪镐南.污水处理出水BOD区间预测建模[J].哈尔滨工业大学学报, 2018, 50(2):71-76.Chai W, Ji H N. Interval predictor models for effluent BOD of wastewater treatment[J]. Journal of Harbin Institute of Technology,2018, 50(2):71-76.
[21] Chai W, Guo L H, Li X M, et al. Interval prediction of effluent TP for wastewater treatment plants[C]//Proceedings of 2019 IEEE Conference on Control Technology and Applications. IEEE, 2019:511-516.
[22] Alex J, Beteau J F, Copp J B, et al. Benchmark for evaluating control strategies in wastewater treatment plants[C]//Proceedings of 1999 European Control Conference. IEEE, 1999:3746-3751.
[23] Jeppsson U, Pons M N. The COST benchmark simulation modelcurrent state and future perspective[J]. Control Engineering Practice, 2004, 12(3):299-304.
[24] Mirbagheri S A, Bagheri M, Boudaghpour S, et al. Performance evaluation and modeling of a submerged membrane bioreactor treating combined municipal and industrial wastewater using radial basis function artificial neural networks[J]. Journal of Environmental Health Science and Engineering, 2015, 13:17.
[25] Bezdek J C. Pattern Recognition with Fuzzy Objective Function Algorithms[M]. New York:Plenum Press, 1981.
[26] Milanese M, Vicino A. Optimal estimation theory for dynamic systems with set membership uncertainty:an overview[J].Automatica, 1991, 27(6):997-1009.
[27] Chai W, Sun X F, Qiao J F. Improved zonotopic method to set membership identification for systems with time-varying parameters[J]. IET Control Theory and Applications, 2011, 5(17):2039-2044.
[28] Chai W, Sun X F, Qiao J F. Set membership state estimation with improved zonotopic description of feasible solution set[J].International Journal of Robust and Nonlinear Control, 2013, 23(14):1642-1654.
[29] Fogel E, Huang Y F. On the value of information in system identification–bounded noise case[J]. Automatica, 1982, 18(2):229-238.
[30] Belforte G, Bona B. An improved parameter identification algorithm for signals with unknown but bounded errors[C]//Proceedings of the 7th IFAC/IFORS Symposium on Identification and System Parameter Estimation. IFAC, 1985:1507-1511.
[31] Chai W, Qiao J F. Passive robust fault detection using RBF neural modeling based on set membership identification[J]. Engineering Applications of Artificial Intelligence(a Journal of IFAC), 2014,28:1-12.