Soft-Sensor of Water Quality Based on Integrated ELM with Meta-Learning
CONG Qiumei1,2,3, YUAN Mingzhe2,3, WANG Hong2,3,4, PANG Qiang2,3, WANG Jingyang2,3
1. School of Information and Control Engineering, Liaoning Shihua University, Fushun 113001, China;
2. Deptartment of Information Service & Intelligent Control, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China;
3. Key laboratory of networked control system, Chinese Academy of Sciences, Shenyang 110016, China;
4. Microcyber Inc. Shenyang 110179, China
A soft-sensor of water quality for wastewater treatment plants, which is based on an integrated model, is presented. The proposed soft-sensor aims to address the difficulty in using a single model to represent the characteristics of wastewater treatment processes with varying operating regimes.The soft-sensor is composed of three layers, in which a predictive sub-model based on FCM-ELMs are the bottom layer, adaptive weighted fusion method fusing predictive values of the sub-model are the middle layer, and a meta-learning mechanism based on information entropy updating fusion weights is the top layer. The meta-learning mechanism can track the dynamic trend of operating conditions of wasterwater treatment plants. The quick learning advantage of ELM results in the soft-sensor showing excellent real-time performance. The adaptive weighted fusion method and meta-learning mechanism improve the model generalization. Simulation results show that the integrated model for COD is more accurate than other models.
丛秋梅, 苑明哲, 王宏, 庞强, 王景杨. 基于元学习的污水水质集成软测量模型[J]. 信息与控制, 2014, 43(2): 248-252.
CONG Qiumei, YUAN Mingzhe, WANG Hong, PANG Qiang, WANG Jingyang. Soft-Sensor of Water Quality Based on Integrated ELM with Meta-Learning. Information and control, 2014, 43(2): 248-252.
鲍林林. 反硝化聚磷菌特性与反硝化除磷工艺研究[D]. 哈尔滨: 哈尔滨工业大学, 2008. Bao L L. Study on the microbiological characteristics and processes of denitrifying phosphorus removal[D]. Harbin: Harbin Institute of Technology, 2008.
[7]
Yao X, Liu Y. Making use of population information in evolutionary artificial neural networks[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 1998, 28(3): 417-425.
[10]
王春生, 吴敏, 曹卫华, 等. 铅锌烧结配料过程的智能集成建模与综合优化方法[J]. 自动化学报, 2009, 35(5): 605-612. Wang C S, Wu M, Cao W H, et al. Intelligent integrated modeling and synthetic optimization for blending process in Lead-Zinc sintering[J]. Acta Automatica Sinica, 2009, 35(5): 605-612.
[4]
Granitto P M, Verdes P F, Ceccatto H A. Neural networks ensembles: Evaluation of aggregation algorithms[J]. Artificial Intelligence, 2005, 163(2): 139-162.
[9]
Su Z Q, Tong W D, Shi L M, et al. A partial least squares-based consensus regression method for the analysis of near-infrared complex spectral data of plant samples[J]. Analytical Letters, 2006, 39(9): 2073-2083.
[2]
Murray-Smith R, Johansen T A. Multiple model approaches to modelling and control[M]. London, UK: Taylor and Francis, 1997.
[14]
姚重华. 环境工程仿真与控制[M]. 北京: 高等教育出版社, 2004. Yao C H. Simulation and control of environmental engineering[M]. Beijing: Higher Education Press, 2004.
[19]
Widmer G. Tracking context changes through meta-learning[J]. Machine Learning, 1997, 27(3): 259-286.
[5]
Windeatt T. Diversity measures for multiple classifier system analysis and design[J]. Information Fusion, 2005, 6(1): 21-36.
[12]
丛秋梅, 赵立杰, 柴天佑. 一类污水处理过程水质多模型在线软测量方法[J]. 东北大学学报: 自然科学版, 2010,31(9): 1221-1225. Cong Q M, Zhao L J, Chai T Y. A multi-model softsensing method of water quality in wastewater treatment process[J]. Journal of Northeastern University: Natural Science, 2010, 31(9): 1221-1225.
[17]
Huang G B, Zhu Q Y, Siew C. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.
[1]
杨维维, 乔俊飞. 基于递归高阶神经网络的污水处理系统建模[J]. 信息与控制, 2011, 40(5): 710-714. Yang W W, Qiao J F. Wastewater treatment system modeling based on high-order recurrent neural network[J]. Information and Control, 2011, 40(5): 710-714.
[6]
Kuncheva L I. Combining pattern classifiers, methods and algorithms[M]. USA: Wiley, 2004.
[13]
索幸仪, 侍洪波. 基于多模型模糊核聚类方法的污水处理过程软测量建模[J]. 华东理工大学学报: 自然科学版, 2010, 36(5): 732-736. Suo X Y, Shi H B. Soft sensor modeling of sewage disposal process based on multi-model fuzzy kernel clustering method[J]. Journal of East China University of Science and Technology: Natural Science Edition, 2010, 36(5): 732- 736.
[18]
Kadlec P. On robust and adaptive soft sensors[D]. Bournemouth University, 2009.
[3]
Breuer L, Huisman J A, Willems P. Assessing the impact of land use change on hydrology by ensemble modeling (LUCHEM). I: Model intercomparison with current land use[J]. Advances in Water Resources, 2009, 32 (2): 129-146.
[8]
Perrone M P, Cooper L N. When networks disagree: Ensemble methods for hybrid neural networks[R]. Providence, Rhode Island, USA: Institute for Brain and Neural Systems, Brown University, 1993.
[11]
Tang J, Chai T Y, Zhao L J, et al. Soft sensor for parameters of mill load based on multi-spectral segments PLS models and on-line additive weighted fusion algorithm[J]. Neurocomputing, 2011, 78(1): 38-47.
[15]
Woo S H, Jeon C O, Yun Y S, et al. On-line estimation of key process variables based on kernel partial least squares in an industrial cokes wastewater treatment plant[J]. Journal of Hazardous Materials, 2009, 161(1): 538-544.
[20]
Baxter J. Learning model bias[J]. Advances in Neural Information Processing Systems, 1996(8): 169-175.