A new model-based approach for power plant Tube-ball mill condition monitoring and fault detection

With the fast growth in intermittent renewable power generation, unprecedented demands for power plant operation flexibility have posed new challenges to the ageing conventional power plants in the UK. Adding biomass to coal for co-fired power generation has become widely implemented practices in order to meet the emission regulation targets. These have impacted the coal mill and power plant operation safety and reliability. The Vertical Spindle mill model was developed through the authors’ work before 2007. From then, the new research progress has been made in modelling and condition monitoring for Tube-ball mills and is reported in the paper. A mathematical model for Tube-ball milling process is developed by applying engineering principles combined with model unknown parameter identifications using a computational intelligent algorithm. The model describes the whole milling process from the mill idle status, start-up to normal grinding and shut-down. The model is verified using on-site measurement data and on-line test. The on-line model is used for mill condition monitoring in two ways: (i) to compare the predicted and measured mill output pressure and temperatures and to raise alarms if there are big discrepancies; and (ii) to monitor the mill model parameter variation patterns which detect the potential faults and mill malfunctions.

[1]  K. E. Bollinger,et al.  Field Test Results for Multi-Variable Control of a Coal-Mill , 1986, IEEE Transactions on Power Systems.

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

[3]  Leonard G. Austin,et al.  Introduction to the mathematical description of grinding as a rate process , 1971 .

[4]  Leonard G. Austin,et al.  An analysis of ball-and-race milling part II. The babcock E 1.7 mill , 1982 .

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

[6]  Jan Dimon Bendtsen,et al.  Derivation and validation of a coal mill model for control , 2009 .

[7]  Leonard G. Austin,et al.  An analysis of ball-and-race milling. Part I. The hardgrove mill , 1981 .

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

[9]  Jan Poland,et al.  Coal Mill Modeling for Monitoring and Control , 2011 .

[10]  Jianlin Wei,et al.  Mathematic modeling and condition monitoring of power station tube-ball mill systems , 2009, 2009 American Control Conference.

[11]  Q.H. Wu,et al.  Development of a Multisegment Coal Mill Model Using an Evolutionary Computation Technique , 2007, IEEE Transactions on Energy Conversion.

[12]  Jan Poland,et al.  Nonlinear coal mill modeling and its application to model predictive control , 2013 .

[13]  Mathias Jesper Dahl-Soerensen,et al.  Pulverized Fuel Control using Biased Flow Measurements , 2009 .

[14]  K. S. Bhambare,et al.  CFD modeling of MPS coal mill with moisture evaporation , 2010 .

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

[16]  J. Waddington,et al.  Determination of mill and boiler characteristics and their effect on steam pressure control , 1980 .

[17]  Q. Henry Wu,et al.  Multisegment pulverised coal mill model and online implementation for condition monitoring , 2006, Int. J. Model. Identif. Control..

[18]  Leonard G. Austin,et al.  An analysis of ball-and-race milling part III. Scale-up to industrial mills , 1982 .

[19]  Ping Ma,et al.  Coal mass estimation of the coal mill based on two-step multi-sensor fusion , 2005, 2005 International Conference on Machine Learning and Cybernetics.

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