A new approach for clustering in desulfurization system based on modified framework for gypsum slurry quality monitoring

Abstract Wet flue gas desulfurization (WFGD) is very important in reduction of SO2 emission in power plant for its lower investment cost, higher desulfurization efficiency and useful by-products. Healthy slurry works as the premise of performance analysis and optimization in WFGD system. However, little research has been conducted on monitoring gypsum slurry quality deterioration. In this paper, an on-line clustering framework has been proposed to monitor gypsum slurry quality in desulfurization system based on data mining. Compound parameter γ , is put forward to remove the influences to slurry quality from gas volume and inlet SO2 concentration to CaCO3 slurry flow. Thus, after the simplification, desulfurization efficiency, pH value and γ are taken as parameters for gypsum slurry quality monitoring. A new clustering method, EKFCM, based on improved fuzzy clustering algorithm, Kmeans and fuzzy C-means combined with entropy theory is proposed. EKFCM is superior to basic FCM in finding the clustering number without prior knowledge when dealing with off-line data, verified by a self-defined function with validity indexes comparison. A new rule, Sub-TDFO, with time decay inserted into “first in first out” in the subset, is proposed to the framework for on-line learning. Another self-defined function is added to the former one for on-line process simulation to verify the effectiveness of the proposed framework. Then, WFGD system in a 600 MW unit is worked as the clustering case study for gypsum slurry quality on-line monitoring and quantization. The clustering results from the proposed on-line framework can be applied to illustrate the process of gypsum slurry quality variation. Moreover, this method be used in other industry processes data for its on-line features.

[1]  Fabrizio Scala,et al.  Modeling flue gas desulfurization by spray-dry absorption , 2004 .

[2]  Masahiko Matsukata,et al.  Simultaneous dry reforming and desulfurization of biomethane with non-equilibrium electric discharge at ambient temperature , 2010 .

[3]  Manel Guerrero Zapata,et al.  A fuzzy anomaly detection system based on hybrid PSO-Kmeans algorithm in content-centric networks , 2015, Neurocomputing.

[4]  Diane Thomas,et al.  Process Simulation of Sulphur Dioxide Abatement with Hydrogen Peroxide Solutions in a Packed Column , 2005 .

[5]  Kim Dam-Johansen,et al.  Experimental investigation and modeling of a wet flue gas desulfurization pilot plant , 1998 .

[6]  Alfred O. Hero,et al.  Adaptive evolutionary clustering , 2011, Data Mining and Knowledge Discovery.

[7]  R. del Valle-Zermeño,et al.  Synergistic effect of the parameters affecting wet flue gas desulfurization using magnesium oxides by-products , 2015 .

[8]  Sandro Vega-Pons,et al.  A Survey of Clustering Ensemble Algorithms , 2011, Int. J. Pattern Recognit. Artif. Intell..

[9]  Gautam Kundu,et al.  Modeling of a novel multi-stage bubble column scrubber for flue gas desulfurization☆ , 2002 .

[10]  Zheng Yao,et al.  A new approach for function approximation in boiler combustion optimization based on modified structural AOSVR , 2009, Expert Syst. Appl..

[11]  Raj K. Rajamani,et al.  A comparative study of three turbulence-closure models for the hydrocyclone problem , 2005 .

[12]  Wu Fang,et al.  Optimized fuzzy C-means clustering algorithm for the interpretation of the near-infrared spectra of rocks , 2017 .

[13]  R. del Valle-Zermeño,et al.  Transposition of wet flue gas desulfurization using MgO by-products: From laboratory discontinuous batch reactor to pilot scrubber , 2015 .

[14]  Jorge Islas,et al.  Abatement costs of SO2-control options in the Mexican electric-power sector , 2008 .

[15]  Tony Parry,et al.  Multiscale Shannon’s Entropy Modeling of Orientation and Distance in Steel Fiber Micro-Tomography Data , 2017, IEEE Transactions on Image Processing.

[16]  L. Kallinikos,et al.  Simulation of the operation of an industrial wet flue gas desulfurization system , 2010 .

[17]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[18]  Hirofumi Kikkawa,et al.  New wet FGD process using granular limestone , 2002 .

[19]  Adil M. Bagirov,et al.  A new nonsmooth optimization algorithm for minimum sum-of-squares clustering problems , 2006, Eur. J. Oper. Res..

[20]  Caiting Li,et al.  Optimal design of a wet-type desulphurization absorber by the numerical simulation method , 2014 .

[21]  Paul S. Bradley,et al.  Clustering via Concave Minimization , 1996, NIPS.

[22]  Krzysztof Galos,et al.  Flue-gas desulphurisation products from Polish coal-fired power-plants , 2003 .

[23]  Pinaki Mitra,et al.  Efficient Algorithm for the Extraction of Association Rules in Data Mining , 2006, ICCSA.

[24]  Yi Liu,et al.  Numerical Simulation Research for the Optimization of the Wet Flue Gas Desulfurization Tower , 2012 .

[25]  Tapio Westerlund,et al.  Optimization of a Wet Flue Gas Desulfurization Scrubber through Mathematical Modeling of Limestone Dissolution Experiments , 2015 .

[26]  Miroslav Jicha,et al.  Influence of the Lime Slurry Droplet Spectrum on the Efficiency of Semi-Dry Flue Gas Desulfurization , 2013 .

[27]  Adil M. Bagirov,et al.  Fast modified global k-means algorithm for incremental cluster construction , 2011, Pattern Recognit..

[28]  Naihua Wang,et al.  Effect of Humidification Water on Semi-Dry Flue Gas Desulfurization , 2011 .

[29]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[30]  W. Rybak,et al.  Unburned carbon from lignite fly ash as an adsorbent for SO2 removal , 2016 .

[31]  Francesco Pepe,et al.  SO2 absorption in a bubbling reactor using limestone suspensions , 1994 .

[32]  Shien Hui,et al.  Experimental study on desulfurization efficiency and gas-liquid mass transfer in a new liquid-screen desulfurization system , 2010 .

[33]  Thibaut Neveux,et al.  Wet Industrial Flue Gas Desulfurization Unit: Model Development and Validation on Industrial Data , 2011 .

[34]  Sabino De Gisi,et al.  Enhancing the recovery of gypsum in limestone-based wet flue gas desulfurization with high energy ball milling process: A feasibility study , 2017 .

[35]  Tutut Herawan,et al.  The Algorithm Expansion for Starting Point Determination Using Clustering Algorithm Method with Fuzzy C-Means , 2016, SCDM.

[36]  Yong Hui Li,et al.  Experimental Study on Fluid Mechanics of Nozzle and Ammonia Desulfurization of Iron and Steel Sintering Furnace , 2013 .

[37]  V. Cortés,et al.  Pilot-Plant Technical Assessment of Wet Flue Gas Desulfurization Using Limestone. , 2006 .

[38]  Myung Gyu Lee,et al.  Mineral carbonation of flue gas desulfurization gypsum for CO2 sequestration , 2012 .

[39]  Jiye Liang,et al.  A cluster centers initialization method for clustering categorical data , 2012, Expert Syst. Appl..