Development of a Multisegment Coal Mill Model Using an Evolutionary Computation Technique

This paper presents a multisegment coal mill model that covers the whole milling process from mill startup to shutdown. This multisegment mathematical model is derived through analysis of energy transferring, heat exchange, and mass flow balances. The work presented in the paper focuses on modeling E-type vertical spindle coal mills that are widely used in coal-fired power plants. An evolutionary computation technique is adopted to identify the unknown model parameters using the on-site measurement data. The identified parameters are then validated with different sets of online measured data. Validation results indicate that the model is accurate enough to represent the whole process of coal mill dynamics and can be used for prediction of the mill dynamic performance. Therefore, the model can be used for online monitoring, fault detection, and control to improve the efficiency of combustion.

[1]  K. E. Bollinger,et al.  The Experimental Determination of Coal Mill Models , 1983, IEEE Power Engineering Review.

[2]  David H. Scott.  Coal pulverisers - performancs and safety , 1995 .

[3]  C. L. Karr,et al.  Computer modelling of mineral processing equipment using fuzzy mathematics , 1996 .

[4]  G. Oluwande,et al.  Coal Mill Modeling by Machine Learning Based on on-Site Measurements , 2002, IEEE Power Engineering Review.

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  Ecevit Bilgili,et al.  Population balance modeling of non-linear effects in milling processes , 2005 .

[7]  Charles L. Karr,et al.  Genetic algorithms for modelling, design, and process control , 1993, CIKM '93.

[8]  Fengnian Shi,et al.  Applying discrete element modelling to vertical and horizontal shaft impact crushers , 2003 .

[9]  G. Oluwande,et al.  Coal Mill Modeling by Machine Learning Based on on-Site Measurements , 2002 .

[10]  Vahid Rashtchi,et al.  Using a genetic algorithm for parameter identification of transformer R-L-C-M model , 2006 .

[11]  Nw Rees,et al.  Modelling of Vertical Spindle Mills in Coal Fired Power Plants , 1994 .

[12]  J. Wang,et al.  Identification of pneumatic cylinder friction parameters using genetic algorithms , 2004, IEEE/ASME Transactions on Mechatronics.

[13]  Madina Hamiane.  Identification of a Pulverized Fuel Mill From Normal Operating Records Using a Multivariable Polynomial Matrix Model , 2000 .