Prediction of the NO emissions from thermal power plant using long-short term memory neural network

Abstract Coal combustion in thermal power plant is the main source of the NOx emission. An effective prediction model should be established for reducing NOx emission. This paper focuses on the application of long-short term memory (LSTM) neural network in modeling the relationship between operational parameters and NOx emission of a 660 MW boiler. Principal component analysis (PCA) method is used to eliminate the coupling between original variables, then the NOx emission model based on LSTM is established. The dropout strategy and Adam optimizer are adopted to improve the network performance. Compared with the least squares support vector machine (LSSVM), the proposed model has higher prediction accuracy, faster response speed, stronger generalization ability, and is more competitive in the modeling of NOx emission. The difference between the LSTM model and the traditional recurrent neural network (RNN) model is also compared. The results show that the performance of LSTM model is better than that of RNN model under the same model structure and parameters. In addition, a NOx prediction model for high-dimensional data is established and achieves good prediction performance. Thus, LSTM is capable to model the NOx emission for coal-fired boilers and is superior to other traditional modeling methods.

[1]  Hao Zhou,et al.  A comparative study of optimization algorithms for low NOx combustion modification at a coal-fired utility boiler , 2009, Expert Syst. Appl..

[2]  Jizhen Liu,et al.  A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler , 2013 .

[3]  Gang Chen,et al.  Modeling and reduction of NOX emissions for a 700 MW coal-fired boiler with the advanced machine learning method , 2016 .

[4]  Lijun Xu,et al.  Comparative study of computational intelligence approaches for NOx reduction of coal-fired boiler , 2013 .

[5]  Feng Wu,et al.  A comparative study of the multi-objective optimization algorithms for coal-fired boilers , 2011, Expert Syst. Appl..

[6]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[7]  Preeti Manke,et al.  ARTIFICIAL NEURAL NETWORK BASED NITROGEN OXIDES EMISSION PREDICTION AND OPTIMIZATION IN THERMAL POWER PLANT , 2013 .

[8]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[9]  Sungzoon Cho,et al.  Response modeling with support vector machines , 2006, Expert Syst. Appl..

[10]  Bin Chen,et al.  Deep bidirectional learning machine for predicting NOx emissions and boiler efficiency from a coal-fired boiler , 2017 .

[11]  Mika Liukkonen,et al.  Artificial neural networks for analysis of process states in fluidized bed combustion , 2011 .

[12]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[13]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[14]  Shyan-Shu Shieh,et al.  Constrained optimization of combustion in a simulated coal-fired boiler using artificial neural network model and information analysis , 2003 .

[15]  Yaoqi Zhou,et al.  Improving protein disorder prediction by deep bidirectional long short‐term memory recurrent neural networks , 2016, Bioinform..

[16]  Charles J. Weschler,et al.  Ozone’s Impact on Public Health: Contributions from Indoor Exposures to Ozone and Products of Ozone-Initiated Chemistry , 2006, Environmental health perspectives.

[17]  Hui Shi,et al.  Combining Support Vector Regression and Kernel Principal Component Analysis to Monitor NOx Emissions in Coal-Fired Utility Boiler , 2012, 2012 Asia-Pacific Power and Energy Engineering Conference.

[18]  Lipo Wang.  Support vector machines : theory and applications , 2005 .

[19]  Hao Zhou,et al.  Modeling NOx emissions from coal-fired utility boilers using support vector regression with ant colony optimization , 2012, Eng. Appl. Artif. Intell..

[20]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[21]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[22]  Peter Glarborg,et al.  Influence of process parameters on nitrogen oxide formation in pulverized coal burners , 1997 .

[23]  Jaroslaw Krzywanski,et al.  Neurocomputing approach for the prediction of NOx emissions from CFBC in air-fired and oxygen-enriched atmospheres , 2017 .

[24]  Hermann Ney,et al.  LSTM Neural Networks for Language Modeling , 2012, INTERSPEECH.

[25]  Yeong-Koo Yeo,et al.  A real-time model based on least squares support vector machines and output bias update for the prediction of NOx emission from coal-fired power plant , 2015, Korean Journal of Chemical Engineering.

[26]  Qingwei Li,et al.  Improved coal combustion optimization model based on load balance and coal qualities , 2017 .

[27]  Yang Liu,et al.  Optimizing combustion of coal fired boilers for reducing NOx emission using Gaussian Process , 2018, Energy.

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..