SAMSE 2018 IOP Conf. Series: Materials Science and Engineering 490 (2019) 062027
IOP Publishing doi:10.1088/1757-899X/490/6/062027
only effectively reduces the complex collinearity between variables, but also reduces the spatial dimension of the model, and the prediction accuracy and dynamic stability of the model are significantly improved, achieving the overall improvement and breakthrough of the model performance by virtue of the integration advantages. 2) Data-driving soft-sensor model method: As the time series data continues to increase, the prediction accuracy of the model based on long-term historical data will decrease. Taking the actual industrial process as the background, combined with the dynamic change characteristics of the process, the method can adaptively iteratively update the model parameters through deviation feedback, and maintain the generalization performance of the soft-sensor model in real time, thus ensuring the continuous efficient and stable operation of the equipment, and monitoring the energy conservation and emission reduction as well as sustainable development of the enterprise. Acknowledgements Financial supports of this work by National Natural Science Foundation of China (U1609214), Major Projects for Science and Technology Development of Zhejiang Province, China (2015C02037), Zhejiang Science and Technology Program key projects, China (2017C03010), and Zhejiang Province Research Project of Public Welfare Technology Application (2016C33105). References [1]Bourgeois W, Burgess J E, Stuetz R M. 2010. On ϋ line monitoring of wastewater quality: a review[J]. Journal of Chemical Technology & Biotechnology, 76: 337-348 [2]Choi D J, Park H. 2001.A hybrid artificial neural network as a software sensor for optimal control of a wastewater treatment process[J]. Water Research, 35: 3959-3967 [3]Cristianini N, Shawe T J. 2000. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M], Cambridge University Press, 112-120 [4]Dürenmatt D J, Gujer W. 2012. Data-driven modeling approaches to support wastewater treatment plant operation. Environmental Modeling & Software. 30: 47-56 [5]Fortuna L, Graziani S, Rizzo A, et al.2007. Soft Sensors for Monitoring and Control of Industrial Processes[M]. Springer-Verlag: London, 34-45 [6]Haimi H, Mulas M, Corona F, et al. 2013. Data-derived soft-sensors for biological wastewater treatment plants: An overview[J]. Environmental Modelling & Software, 47: 88-107 [7]Huang Mingzhi, Ma Yongwen, Wan Jinquan, et al. 2015. A sensor-software based on a genetic algorithm based neural fuzzy system for modeling and simulating a wastewater treatment process[J]. Applied Soft Computing, 27: 1-10 [8]Jolliffe I T. 2002. Principal Component Analysis (second edition)[M]. Springer-Verlag, 168-176 [9]Kennedy J, Eberhart R C. 1995. Particle swarm optimization[C]. Proceedings of IEEE International Conference on Neural Networks. Perth, Australia, 1942-1948 [10]Langergraber G, Fleischmann N, Hofstaedter F, et al. 2004. Monitoring of a paper mill wastewater treatment plant using UV/VIS spectroscopy[J], Water Science and Technology, 49: 9-14 [11]Liu Bo, Wan Jinquan, Huang Mingzhi, et al. 2015. Online Prediction Model for Effluent VFA from Anaerobic Wastewater Treatment System Based on PCA-LSSVM[J]. Journal of Environmental Sciences, 35(6): 1768-1778 [12]Liu Lin, Ma Yiwen, Wan Jinquan, et al. 2017. Soft-sensor Model of Anaerobic Treatment Process of Wastewater Based on Pso-SVM[J], Journal of Environmental Science, 37(6): 2122-2129 [13]Ruggeri B, Tommasi T, Sanfilippo S. 2015.BioH2 & BioCH4 Through Anaerobic Digestion From Research To Full-Scale Applications[M]. Springer-Verlag, 1-24 [14]Souza F A A, Aráujo R, Mendes J. 2016. Review of soft sensor methods for regression applications. Chemometrics and Intelligent Laboratory Systems, 152: 69-79 [15]Sun Jun, Cheng Zhong, Yang Ruiqin, et al. 2017. PCA-PSO-LSSVM-based Soft-sensor of Effluent COD of the Anaerobic Treatment System for Papermaking Wastewater [J].Computer and Applied Chemistry, 34(9): 706-710 [16]Tang Wei, Bai Zhixiong, Gao Xiang. 2017. Dissolved Oxygen Concentration Control System Based on Adaptive Mutation Differential Evolution Algorithm[J]. Paper China, 36 (6): 49-54
9
Made with FlippingBook Digital Publishing Software