Soft Computing of Biochemical Oxygen Demand Using an Improved T-S Fuzzy Neural Network

doi:10.1016/j.cjche.2014.09.023

›› 2014, Vol. 22 ›› Issue (11/12): 1254-1259.DOI: 10.1016/j.cjche.2014.09.023

• PROCESS SYSTEMS ENGINEERING AND PROCESS SAFETY • Previous Articles Next Articles

Soft Computing of Biochemical Oxygen Demand Using an Improved T-S Fuzzy Neural Network

Junfei Qiao, Wei Li, Honggui Han

College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China

Received:2014-01-03 Revised:2014-03-08 Online:2014-12-24 Published:2014-12-28
Supported by:
Supported by the National Natural Science Foundation of China (61203099, 61034008, 61225016), Beijing Science and Technology Project (Z141100001414005), Beijing Science and Technology Special Project (Z141101004414058), Ph.D. Program Foundation from Ministry of Chinese Education (20121103120020), Beijing Nova Program (Z131104000413007), and Hong Kong Scholar Program (XJ2013018).

Soft Computing of Biochemical Oxygen Demand Using an Improved T-S Fuzzy Neural Network

Junfei Qiao, Wei Li, Honggui Han

College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China

通讯作者: Junfei Qiao
基金资助:
Supported by the National Natural Science Foundation of China (61203099, 61034008, 61225016), Beijing Science and Technology Project (Z141100001414005), Beijing Science and Technology Special Project (Z141101004414058), Ph.D. Program Foundation from Ministry of Chinese Education (20121103120020), Beijing Nova Program (Z131104000413007), and Hong Kong Scholar Program (XJ2013018).

Abstract

Abstract: It is difficult to measure the online values of biochemical oxygen demand (BOD) due to the characteristics of nonlinear dynamics, large lag and uncertainty in wastewater treatment process. In this paper, based on the knowledge representation ability and learning capability, an improved T-S fuzzy neural network (TSFNN) is introduced to predict BOD values by the soft computing method. In this improved TSFNN, a K-means clustering is used to initialize the structure of TSFNN, including the number of fuzzy rules and parameters of membership function. For training TSFNN, a gradient descent method with the momentum item is used to adjust antecedent parameters and consequent parameters. This improved TSFNN is applied to predict the BOD values in effluent of the wastewater treatment process. The simulation results show that the TSFNN with K-means clustering algorithm can measure the BOD values accurately. The algorithm presents better approximation performance than some other methods.

Key words: Biochemical oxygen demand, Wastewater treatment, T-S fuzzy neural network, K-means clustering

摘要： It is difficult to measure the online values of biochemical oxygen demand (BOD) due to the characteristics of nonlinear dynamics, large lag and uncertainty in wastewater treatment process. In this paper, based on the knowledge representation ability and learning capability, an improved T-S fuzzy neural network (TSFNN) is introduced to predict BOD values by the soft computing method. In this improved TSFNN, a K-means clustering is used to initialize the structure of TSFNN, including the number of fuzzy rules and parameters of membership function. For training TSFNN, a gradient descent method with the momentum item is used to adjust antecedent parameters and consequent parameters. This improved TSFNN is applied to predict the BOD values in effluent of the wastewater treatment process. The simulation results show that the TSFNN with K-means clustering algorithm can measure the BOD values accurately. The algorithm presents better approximation performance than some other methods.

关键词: Biochemical oxygen demand, Wastewater treatment, T-S fuzzy neural network, K-means clustering

Junfei Qiao, Wei Li, Honggui Han. Soft Computing of Biochemical Oxygen Demand Using an Improved T-S Fuzzy Neural Network[J]. , 2014, 22(11/12): 1254-1259.

References

[1] H.G. Han, J.F. Qiao, Q.L. Chen, Model predictive control of dissolved oxygen concentration based on a self-organizing RBF neural network, Control. Eng. Pract. 20 (2012) 465-476.
[2] Z.R. Pan, Q. Wang, Based on fuzzy neural network COD soft measuring technique's research, Comput. Meas. Control 19 (7) (2011) 1572-1574.
[3] F. Xu, Y.Y. Wang, X.L. Luo, Soft sensor for inputs and parameters using nonlinear singular state observer in chemical processes, Chin. J. Chem. Eng. 21 (9) (2013) 1038-1047.
[4] W.M. Shao, X.M. Tian, P. Wang, Local partial least squares based online soft sensing method for multi-output processes with adaptive process states division, Chin. J. Chem. Eng. 22 (7) (2014) 828-836.
[5] Y. Lü, H.Z. Yang, A multi-model approach for soft sensor development based on feature extraction using weighted kernel fisher criterion, Chin. J. Chem. Eng. 22 (2) (2014) 146-152.
[6] H.S.Wong, L. Guan, A neural learning approach for adaptive image restoration using a fuzzy model-based network architecture, IEEE Trans. Neural Netw. 12 (3) (2001) 516-531.
[7] Y.R. Huang, S.D. Zhang, Dissolved oxygen intelligent optimization control system in the aeration tank of wastewater treatment, Inf. Control. 40 (3) (2011) 393-400.
[8] X.S. Deng, X.Z. Wang, Incremental learning of dynamic fuzzy neural networks for accurate system modeling, Fuzzy Set. Syst. 160 (2009) 972-987.
[9] H.G. Han, J.F. Qiao, A self-organizing fuzzy neural network based on growing-andpruning algorithm, IEEE Trans. Fuzzy Syst. 18 (6) (2010) 1129-1143.
[10] J.S. Wang, C.S.G. Lee, Self-adaptive recurrent neuro fuzzy control of an autonomous underwater vehicle, IEEE Trans. Robot. Autom. 19 (2) (2003) 283-295.
[11] H.G. Han, X.L. Wu, J.F. Qiao, Nonlinear systems modeling based on self-organizing fuzzy-neural-network with adaptive computation algorithm, IEEE Trans. Cybern. 44 (4) (2014) 554-564.
[12] X.J. Li, J.X. Luo, Z.Q. Huang, W.J.Wang, Fuzzy neural network controller of dissolved oxygen in the wastewater treatment process, Control Eng. China 17 (2010) 64-67 (Suppl.).
[13] J. MacQueen, Some Methods for Classification and Analysis of Multivariate Observations, Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, 1, 1967, pp. 281-297.
[14] R.L. Liu, H.Y. Su, J. Chu, Fuzzy neural network based on hybrid learning algorithm and its application to soft sensor, J. Syst. Simul. 17 (12) (2005) 2878-2881.
[15] T. Takagi, M. Sugeno, Fuzzy identification of systems and its applications to modeling and control, IEEE Trans. Syst. Man Cybern. SMC-15 (1) (1985) 116-132.
[16] S.X. Du, Modeling and control of biological wastewater treatment processes, Control Theory Appl. 19 (5) (2002) 660-666.
[17] J. Alex, L. Benedetti, J. Copp, K.V. Gernaey, U. Jeppsson, I. Nopens, M.N. Pons, C. Rosen, J.P. Steyer, P. Vanrolleghem, J. Alex, L. Benedetti, J. Copp, K.V. Gernaey, U. Jeppsson, I. Nopens, M.N. Pons, C. Rosen, J.P. Steyer, P. Vanrolleghem, Benchmark simulation model no. 1 (BSM1), IWA Taskgroup on Benchmarking of Control Strategies for WWTPs, 2008, pp. 1-61.
[18] M. Henze, C.P.L. Grady, W. Gujor, G.V.R. Marais, T. Mastuo, Activated sludge model no. 1, Int. Association on Water Pollution Research and Control (IAWPRC), Sci. and Tech. Repts., No. 1, London, England2002.
[19] I. Takacs, G.G. Patry, D. Nolasco, A Dynamic Model of the Clarification Thickening Process, Water Res. 25 (1991) 1263-1271.
[20] Z.H. Tong, M.W. Xu, Y.M. Shen, L.Z. Yu, Study on artificial neural network in the sewage disposal model, Chin. J. Sc. Instrum. 26 (8 Suppl.) (2005) 347-348.
[21] Q.M. Cong, T.Y. Chai, W. Yu, Modeling wastewater treatment plant via hierarchical neural networks, Control Theory Appl. 26 (1) (2009) 8-14.
[22] G.Y. Li, Neural Fuzzy Control Theory and Applications, Electronic Industry Press, Beijing, 2009. 291-296.
[23] G. Leng, G. Prasad, T.M. McGinnity, An on-line algorithm for creating self-organizing fuzzy neural networks, Neural Netw. 17 (2004) 1477-1493.
[24] N. Shi, X.M. Liu, Y. Guan, Research on K-means clustering algorithm, Third International Symposium on Intelligent Information Technology and Security Informatics, 2010, pp. 63-67.
[25] X.Y. Wang, Z.W. Liu, Z. Su, Research on BOD soft-sensing compensation method based on neural network, J. Syst. Simul. 21 (Suppl. 2) (2009) 83-85.
[26] M.N. Zhang, H.G. Han, J.F. Qiao, Research on dynamic feed-forward neural network structure based on growing and pruning methods, CAAI Trans. Intell. Syst. 6 (2) (2011) 101-106.
[27] R. Rabee, J.A. Adebayo, S. Miklas, Applying Kohonen self-organizing map as a software sensor to predict biochemical oxygen demand, Water Environ. Res. 80 (1) (2008) 32-40.

Soft Computing of Biochemical Oxygen Demand Using an Improved T-S Fuzzy Neural Network

Soft Computing of Biochemical Oxygen Demand Using an Improved T-S Fuzzy Neural Network

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Chaoyi Yin, Jingyuan Ma, Jian Qiu, Ruifang Liu, Long Ba. Mass-producible low-cost flexible electronic fabrics for azo dye wastewater treatment by electrocoagulation [J]. Chinese Journal of Chemical Engineering, 2023, 59(7): 222-230.
[2]	Yuxi Chai, Yanan Zhang, Yannan Tan, Zhiwei Li, Huangzhao Wei, Chenglin Sun, Haibo Jin, Zhao Mu, Lei Ma. Life cycle assessment of high concentration organic wastewater treatment by catalytic wet air oxidation [J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 80-88.
[3]	Zhongwei Tan, Xingguo Xu, Yu Wan, Chengjun Kang, Zhaoqiang Zhang, Zhenxia Zhao, Fang Shen, Kungang Chai, Hongbing Ji. Efficient recovery of aromatic compounds from the wastewater of styrene monomer and propylene oxide co-production plant via hypercrosslinked aryl-rich starch-β-cyclodextrin polymeric sorbent [J]. Chinese Journal of Chemical Engineering, 2022, 49(9): 150-160.
[4]	Zhengguo Xu, Xiaochong Wang, Shuying Sun. Performance of a synthetic resin for lithium adsorption in waste liquid of extracting aluminum from fly-ash [J]. Chinese Journal of Chemical Engineering, 2022, 44(4): 115-123.
[5]	Chen Zhao, Yahan Ye, Xianfu Chen, Xiaowei Da, Minghui Qiu, Yiqun Fan. Charged modified tight ceramic ultrafiltration membranes for treatment of cationic dye wastewater [J]. Chinese Journal of Chemical Engineering, 2022, 41(1): 267-277.
[6]	Shaimaa T. Kadhum, Ghayda Yassen Alkindi, Talib M. Albayati. Eco friendly adsorbents for removal of phenol from aqueous solution employing nanoparticle zero-valent iron synthesized from modified green tea bio-waste and supported on silty clay [J]. Chinese Journal of Chemical Engineering, 2021, 36(8): 19-28.
[7]	Alfarooq O. Basheer, Marlia M. Hanafiah, Mohammed Abdulhakim Alsaadi, Y. Al-Douri, Abbas A. Al-Raad. Synthesis and optimization of high surface area mesoporous date palm fiber-based nanostructured powder activated carbon for aluminum removal [J]. Chinese Journal of Chemical Engineering, 2021, 32(4): 472-484.
[8]	Sri Juari Santosa, Dwi Puji Astuti. Reusable high performance of calcined Mg/Al hydrotalcite for the removal of Navy Blue and Yellow F3G dyes [J]. Chinese Journal of Chemical Engineering, 2021, 38(10): 247-254.
[9]	Alejandra Alicia Peláez-Cid, Vincent Romero-Hernández, Ana María Herrera-González, Alejandro Bautista-Hernández, Oscar Core?o-Alonso. Synthesis of activated carbons from black sapote seeds, characterization and application in the elimination of heavy metals and textile dyes [J]. Chinese Journal of Chemical Engineering, 2020, 28(2): 613-623.
[10]	Wei Wei, Pengfei Xia, Zaiwen Liu, Min Zuo. A modified active disturbance rejection control for a wastewater treatment process [J]. Chinese Journal of Chemical Engineering, 2020, 28(10): 2607-2619.
[11]	Xiaoqiang Jia, Dayao Jin, Chen Li, Wenyu Lu. Characterization and analysis of petrochemical wastewater through particle size distribution, biodegradability, and chemical composition [J]. Chin.J.Chem.Eng., 2019, 27(2): 444-451.
[12]	Abdellah Benzaouak, Nour-Eddine Touach, V. M. Ortiz-Martínez, M. J. Salar-García, F. Hernández-Fernández, A. P. de los Ríos, Mohammed El Mahi, El Mostapha Lotfi. Ferroelectric solid solution Li_1-xTa_1-xW_xO₃ as potential photocatalysts in microbial fuel cells: Effect of the W content [J]. Chin.J.Chem.Eng., 2018, 26(9): 1985-1991.
[13]	Honggui Han, Xiaolong Wu, Luming Ge, Junfei Qiao. A sludge volume index (SVI) model based on the multivariate local quadratic polynomial regression method [J]. Chin.J.Chem.Eng., 2018, 26(5): 1071-1077.
[14]	Saad H. Ammar, Ahmed S. Akbar. Oilfield produced water treatment in internal-loop airlift reactor using electrocoagulation/flotation technique [J]. Chin.J.Chem.Eng., 2018, 26(4): 879-885.
[15]	Sajjad Haydar, Mehwish Anis, Gul E Hina, Javed Anwar Aziz, Mudasar Arbi. An innovative design of septic tank for wastewater treatment and its performance evaluation: An applicable model for developing countries [J]. Chin.J.Chem.Eng., 2018, 26(4): 886-891.