Energy Efficiency Monitoring in a Coal Boiler Based on Optical Variables and Artificial Intelligence

Abstract In this work, we present the fundamentals of the estimation of the energy efficiency in an industrial coal boiler based in novel optical combustion diagnostics variables and several machine learning regression methods. The total radiation Rad t and flame temperature T f were considered. The inclusion of those variables allows to increase the overall performance in the estimation of the energy efficiency. The comparison in the performance of the tested methods for regression, suggest that Extreme Learning Machines in combination with Partial Least Squares for regression, lead to the best performance with a Pearson correlation coefficient R ≈ 0.7 in the test data set.

[1]  Yong Yan,et al.  Condition Monitoring of Combustion Processes Through Flame Imaging and Kernel Principal Component Analysis , 2013 .

[2]  Alejandro J. Rojas,et al.  On the use of flame analysis and optical variables for an optimized operation in ladle furnace preheating process , 2015, 2015 IEEE Conference on Control Applications (CCA).

[3]  Hao Zhou,et al.  Flame stability monitoring and characterization through digital imaging and spectral analysis , 2011 .

[4]  Junghui Chen,et al.  Gaussian process regression based optimal design of combustion systems using flame images , 2013 .

[5]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[6]  Waldemar Wójcik,et al.  Advanced diagnostics of industrial pulverized coal burner using optical methods and artificial intelligence , 2012 .

[7]  Daniel Sbarbaro,et al.  On the spectral bands measurements for combustion monitoring , 2011 .

[8]  Sungzoon Cho,et al.  Semi-supervised support vector regression based on self-training with label uncertainty: An application to virtual metrology in semiconductor manufacturing , 2016, Expert Syst. Appl..

[9]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[10]  Hugo O. Garces,et al.  Radiation measurement based on spectral emissions in industrial flames , 2016 .

[11]  Yan-Lin He,et al.  Soft-sensing model development using PLSR-based dynamic extreme learning machine with an enhanced hidden layer , 2016 .

[12]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[13]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[14]  Luis E. Arias,et al.  Comparative Analysis of a Principal Component Analysis-Based and an Artificial Neural Network-Based Method for Baseline Removal , 2016, Applied spectroscopy.

[15]  Hadi Parastar,et al.  Classification of gas chromatographic fingerprints of saffron using partial least squares discriminant analysis together with different variable selection methods , 2016 .

[16]  Joseph Bentsman.  Technical Committee on Power Generation [Technical Activities] , 2016 .

[17]  Yang Zhang,et al.  Digital colour image processing based measurement of premixed CH4 + air and C2H4 + air flame chemiluminescence , 2011 .

[18]  Zixue Luo,et al.  A Combustion-Monitoring System With 3-D Temperature Reconstruction Based on Flame-Image Processing Technique , 2007, IEEE Transactions on Instrumentation and Measurement.

[19]  Javier Ballester,et al.  Diagnostic techniques for the monitoring and control of practical flames , 2010 .