Statistical multi-model approach for performance assessment of cooling tower

This paper presents a data-driven model-based assessment strategy to investigate the performance of a cooling tower. In order to achieve this objective, the operations of a cooling tower are first characterized using a data-driven method, multiple models, which presents a set of local models in the format of linear equations. Satisfactory fuzzy c-mean clustering algorithm is used to classify operating data into several groups to build local models. The developed models are then applied to predict the performance of the system based on design input parameters provided by the manufacturer. The tower characteristics are also investigated using the proposed models via the effects of the water/air flow ratio. The predicted results tend to agree well with the calculated tower characteristics using actual measured operating data from an industrial plant. By comparison with the design characteristic curve provided by the manufacturer, the effectiveness of cooling tower can be obtained in the end. A case study conducted in a commercial plant demonstrates the validity of proposed approach. It should be noted that this is the first attempt to assess the cooling efficiency which is deviated from the original design value using operating data for an industrial scale process. Moreover, the evaluated process need not interrupt the normal operation of the cooling tower. This should be of particular interest in industrial applications.

[1]  Gordon Lightbody,et al.  Local Model Network Identification With Gaussian Processes , 2007, IEEE Transactions on Neural Networks.

[2]  Zhenkuang Xue,et al.  Multi-Model Modelling and Predictive Control Based on Local Model Networks , 2006, Control. Intell. Syst..

[3]  M. Hosoz,et al.  Performance prediction of a cooling tower using artificial neural network , 2007 .

[4]  Somchai Wongwises,et al.  AN EXERGY ANALYSIS ON THE PERFORMANCE OF A COUNTERFLOW WET COOLING TOWER , 2007 .

[5]  Giorgia F. Cortinovis,et al.  A systemic approach for optimal cooling tower operation , 2009 .

[6]  J. F. Missenden,et al.  The investigation of cooling tower packing in various arrangements , 2000 .

[7]  Victor Jupp,et al.  Data Collection and Analysis , 2012, Lean Six Sigma for the Office.

[8]  Syed M. Zubair,et al.  A comprehensive design and performance evaluation study of counter flow wet cooling towers , 2004 .

[9]  Robert E. Wilson,et al.  Fundamentals of momentum, heat, and mass transfer , 1969 .

[10]  Dandan Li,et al.  Numerical simulation of shower cooling tower based on artificial neural network , 2008 .

[11]  Ravindra D. Gudi,et al.  Identification of complex nonlinear processes based on fuzzy decomposition of the steady state space , 2003 .

[12]  Xue Zhen.  A Multi-model Identification Algorithm Based on Weighted Cost Function and Application in Thermal Process , 2005 .

[13]  Ralph L. Webb,et al.  Design of Cooling Towers by the Effectiveness-NTU Method , 1989 .

[14]  Detlev G. Kro¨ger,et al.  Cooling tower performance evaluation: Merkel, Poppe, and e-NTU methods of analysis , 2005 .

[15]  R. Sapsford,et al.  Data Collection and Analysis , 1997 .

[16]  Peter Harriott,et al.  Unit Operations of Chemical Engineering , 2004 .

[17]  Abtin Ataei,et al.  PERFORMANCE EVALUATION OF COUNTER-FLOW WET COOLING TOWERS USING EXERGETIC ANALYSIS , 2008 .

[18]  Thomas A. Runkler,et al.  Alternating cluster estimation: a new tool for clustering and function approximation , 1999, IEEE Trans. Fuzzy Syst..

[19]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[20]  M. Boumaza,et al.  Thermal performances investigation of a wet cooling tower , 2007 .

[21]  Pertti Heikkilä,et al.  A COMPREHENSIVE APPROACH TO COOLING TOWER DESIGN , 2001 .

[22]  Mehmet Sait Söylemez,et al.  On the optimum performance of forced draft counter flow cooling towers , 2004 .

[23]  A. Rahman Al-Kassir,et al.  Influence of the cooling circulation water on the efficiency of a thermonuclear plant , 2005 .

[24]  Xiangjiang Zhou,et al.  Optimal operation of a large cooling system based on an empirical model , 2004 .

[25]  Fengzhong Sun,et al.  Performance prediction of wet cooling tower using artificial neural network under cross-wind conditions , 2009 .