Modeling and optimization of the NO_X generation characteristics of the coal-fired boiler based on interpretable machine learning algorithm

References

• Baghban,A., M.A.Ahmadi, and B.H.Shahraki. 2015. Prediction carbon dioxide solubility in presence of various ionic liquids using computational intelligence approaches[J]. Journal of Supercritical Fluids 98:50–64.
   Web of Science ®Google Scholar
• Israeli,A., L.Rokach, and A.Shabtai. 2019. Constraint learning based gradient boosting trees[J]. Expert Systems with Application 128:287–300.
   Web of Science ®Google Scholar
• Walter,A., and S.S.Wilks. Exploratory data mining and data cleaning[M]. 2003.
   Google Scholar
• Karr,A.F. 2006. Exploratory data mining and data cleaning[J]. Journal of the American Statistical Association 101:399–399.
   Google Scholar
• Ali,A.M., and Z.Chen. 2019. Development of machine learning methods for estimating permeability and porosity of oil reservoirs via petro-physical logs[J]. Petroleum 5:271–84.
   Google Scholar
• Kim,B. S,Kim, T. Y., Park, T. C., & Yeo, Y. K. 2018. Comparative study of estimation methods of NOx emission with selection of input parameters for a coal-fired boiler[J]. Korean Journal of Chemical Engineering 35:1779–90.
   Web of Science ®Google Scholar
• Cortes,C., and V.Vapnik. 1995. Support-vector networks. Learn 20:273–97.
   Google Scholar
• Persson,C., P.Bacher, and T.Shiga. 2017. Multi-site solar power forecasting using gradient boosted regression trees[J]. Solar Energy 150:423–36.
   Web of Science ®Google Scholar
• Qi,C., A.Fourie, and X.Zhao. 2018. Back-analysis method for stope displacements using gradient-boosted regression tree and firefly algorithm[J]. Journal of Computing in Civil Engineering 32:04018031.1–04018031.10.
   Web of Science ®Google Scholar
• Lu,C.J., T.S.Lee, and C.C.Chiu. 2009. Financial time series forecasting using independent component analysis and support vector regression[J]. Decision Support Systems 47:115–25.
   Web of Science ®Google Scholar
• Sun,D., Q.Fang, H.Wang, and H.Zhou. 2007. Experimental and simulation investigations of combustion optimization on a125 MW tangentially anthracite-fired Boiler[M]. Challenges of power engineering and environment, 644–51. Springer: Berlin, Heidelberg.
   Google Scholar
• Ahmed,F.,  H.J. Cho, J.K. Kim. 2015. 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[J]. Korean Journal of Chemical Engineering 32(6):1–8.
   Web of Science ®Google Scholar
• Jiao,F., J.Xu, and L.Yu. 2006. Protein fold recognition using the gradient boost algorithm[J]. Computer System Bioinformatics Conference 2006:43–53.
   Google Scholar
• Hassan, G., Pourkashanian, M., Ingham, D., Ma, L., Newman, P., & Odedra, A. 2013. Predictions of CO and NOx emissions from steam cracking furnaces using GRI2.11 detailed reaction mechanism - ACFD investigation[J]. Computers & Chemical Engineering 58:68–83.
   Web of Science ®Google Scholar
• Wang,G., O.I.Awad, and S.Liu. 2020. NOX emissions prediction based on mutual information and back propagation neural network using correlation quantitative analysis[J]. Energy 198:117286.
   Web of Science ®Google Scholar
• Ma,H., X.Yang, and J.Mao The energy efficiency prediction method based on gradient boosting regression tree[C]. 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2018.
   Google Scholar
• Zhou,H., and K.Cen. 2018. Combustion optimization based on computational intelligence applications: future prospect[M]. Combustion Optimization Based on Computational Intelligence 265–67.
   Google Scholar
• Azamathulla,H.M., A.A.Ghani, and C.K.Chang. 2010. Machine learning approach to predict sediment load-acase study[J]. CLEAN-Soil, Air, Water 38:969–76.
   Web of Science ®Google Scholar
• Amedi,H.R., A.Baghban, and M.A.Ahmadi. 2016. Evolving machine learning models to predict hydrogen sulfide solubility in the presence of various ionic liquids[J]. Journal of Molecular Liquids 216:411–22.
   Web of Science ®Google Scholar
• Song,J., C.E.Romero, Z.Yao, etal. 2017. Aglobally enhanced general regression neural network for on-line multiple emissions prediction of utility boiler[J]. Knowledge-Based Systems 118(FEB.15):4–14.
   Web of Science ®Google Scholar
• Yetilmezsoy, K., Turkdogan, F. I., Temizel, I., & Gunay, A. 2013. Development of ann-based models to predict biogas and methane productions in anaerobic treatment of molasses wastewater[J]. International Journal of Green Energy 10(6–10):885–907.
   Web of Science ®Google Scholar
• Chang, K. Y., Chang, C. Y., Wang, W. J., & Chen, C. Y. 2012. Modeling polarization of aDMFC system via neural network with immune-based particle swarm optimization[J]. International Journal of Green Energy 9(1–4):309–21.
   Web of Science ®Google Scholar
• Kong, L., Ding, Y., Zhang, Y., Yuan, L., & Wu, Z. 2009. Application of gain scheduling for modeling the nonlinear dynamic characteristics of NO xemissions from utility boilers[J]. Korean Journal of Chemical Engineering 26:534–41.
   Web of Science ®Google Scholar
• Lv, Y., Liu, J., Yang, T., & Zeng, D. 2013. Anovel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler[J]. Energy 55(jun.15):319–29.
   Web of Science ®Google Scholar
• Zheng,L., F.Zhu, and A.Mohammed. 2017. Attribute and global boosting: arating prediction method in context-aware recommendation[J]. Computer Journal 60: 957–68.
   Web of Science ®Google Scholar
• Zheng,L., H.Zhou, and C.Wang. 2008. Combining Support vector regression and ant colony optimization to reduce NOx emissions in coal-fired utility boilers[J]. Energy & Fuels 22:1034–40.
   Web of Science ®Google Scholar
• Zhe,L.A., B.Ysl, B.Jc, etal. Developing variable moving window PLS models: Using case of NOx emission prediction of coal-fired power plants[J]. Fuel 296:120441.
   Web of Science ®Google Scholar
• Shapley,L.S. 1953. Avalue for n-person games[J]. Contributions to the theory of games. In Annals of mathematical studies, ed. H.W.Kuhn and A.W.Tucker, 307–17. Princeton: Princeton University Press
   Google Scholar
• Falcitelli,M., S.Pasini, and L.Tognotti. 2002. Modelling practical combustion systems and predicting NOx emissions with an integrated CFD based approach[J]. Computers & Chemical Engineering 26:1171–83.
   Web of Science ®Google Scholar
• Miao, M., Kong, H., Deng, B., Chen, L., Yang, H., Lyu, J., & Zhang, M. 2020. Experimental study on N2O and NOx emission characteristics of five high-volatile fuels in bubbling bed combustion[J]. Fuel Processing Technology 208:106517.
   Web of Science ®Google Scholar
• Ahmadi,M.A. 2015. Developing arobust surrogate model of chemical flooding based on the artificial neural network for enhanced oil recovery implications[J]. Mathematical Problemsin Engineering 2015:1–9.
   Web of Science ®Google Scholar
• Ahmadi, M. A., Bahadori, A., & Shadizadeh, S. R. 2015. Arigorous model to predict the amount of dissolved calcium carbonate concentration throughout oil field brines: Side effect of pressure and temperature[J]. Fuel Guildford 139:154–59.
   Web of Science ®Google Scholar
• Ahmadi,M.A., and Alireza. 2016. Applying asophisticated approach to predict CO2 solubility in brines: Application to CO2 sequestration.[J]. International Journal of Low Carbon Technologies 11:325–32.
   Web of Science ®Google Scholar
• Ahmadi,M. A., Ebadi, M., Marghmaleki, P. S., & Fouladi, M. M. 2014. Evolving predictive model to determine condensate-to-gas ratio in retrograded condensate gas reservoirs[J]. Fuel 124:241–57.
   Web of Science ®Google Scholar
• Ahmadi, M. A., Haghbakhsh, R., Soleimani, R., & Bajestani, M. B. 2014. Estimation of H2S solubility in ionic liquids using arigorous method[J]. Journal of Supercritical Fluids The 92:60–69.
   Web of Science ®Google Scholar
• Weiss,M.A. 2014. Data structures and algorithm analysis.[C]. Pearson Education, Edition.
   Google Scholar
• Li,N., and Y.Hu. 2020. The deep convolutional neural network for NOx emission prediction of a coal-fired boiler[J]. IEEE Access 8:85912–22.
   Web of Science ®Google Scholar
• Sami,N.A., and S.Ibrahim. 2021. Forecasting multiphase flowing bottom-hole pressure of vertical oil wells using three machine learning techniques[J]. Petroleum Research5:2096-2495.
   Google Scholar
• Gurram,P., H.Kwon, and C.Davidson. 2015. Shapely value based random subspace selection for hyperspectral image classification[J]. 4975–78. IEEE.
   Google Scholar
• Tan, P., He, B., Zhang, C., Rao, D., Li, S., Fang, Q., & Chen, G. 2019. Dynamic modeling of NOX emission in a660 MW coal-fired boiler with long short-term memory[J]. Energy 176:429–36.
   Web of Science ®Google Scholar
• Tan,P., C.Zhang, and J.Xia. 2015. Estimation of higher heating value of coal based on proximate analysis using support vector regression[J]. Fuel Processing Technology 138:298–304.
   Web of Science ®Google Scholar
• Xie, P. M., Gao, H. Zhang,  Niu Y, Wang X. 2020. Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network[J]. Energy 190:116482.
   Web of Science ®Google Scholar
• Saravanakumar,R., and D.Jena. 2016. Nonlinear control of awind turbine based on nonlinear estimation techniques for maximum power extraction[J]. International Journal of Green Energy 13(1–5):309–19.
   Web of Science ®Google Scholar
• Rodríguez-Pérez,R., and J.Bajorath. 2020a. Interpretation of machine learning models using shapley values: Application to compound potency and multi-target activity predictions[J]. 34:1013–26.
   Google Scholar
• Rodríguez-Pérez,R., and J.Bajorath. 2020b. Interpretation of machine learning models using shapley values: Application to compound potency and multi-target activity predictions[J]. Journal of Computer-Aided Molecular Design 34:1013–26.
   PubMed Web of Science ®Google Scholar
• Dabiri,S., and M.Abbas. 2018. Evaluation of the gradient boosting of regression trees method on estimating the car following behavior[C]. Transportation Research Board Meeting Transportation Research Board, 2672(45):136-146.
   Google Scholar
• Dal Secco,S., O.Juan, and M.Louis-Louisy. 2015. Using agenetic algorithm and CFD to identify low NOx configurations in an industrial boiler[J]. Fuel 158:672–83.
   Web of Science ®Google Scholar
• Fan,S., T.Kind, T.Cajka, etal. 2019. Systematic Error Removal using Random Forest (SERRF) for normalizing large-scale untargeted lipidomics data[J]. Analytical Chemistry 91:3590–96.
   PubMed Web of Science ®Google Scholar
• Lundberg,S., S.I.Lee, and A.Unified. 2017a. Approach to interpreting model predictions[J]. 4768–77.
   Google Scholar
• Lundberg,S., S.I.Lee, and A.Unified. 2017b. Approach to interpreting model predictions[J]. Advances in Neural Information Processing Systems 30 (NIPS) 4768–77.
   Google Scholar
• Vinu Kiran,S., S.Prasanna Devi, and S.Manivannan. 2016. Incentive compatible E-mandi with large scale consumer producer matching using bigdata based on gale-shapely algorithm for perishable commodities SCM[J]. Procedia Computer Science 87:215–20.
   Google Scholar
• Wang,S.C. 2003. Interdisciplinary computing in Java programming. Springer Science& Business Media. (pp. 81-100). Springer, Boston, MA.
   Google Scholar
• Lundberg,S.M., G.Erion, H.Chen, A.DeGrave, J.M.Prutkin, B.Nair, etal. 2020. From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence 2:56–67.
   PubMedGoogle Scholar
• Moosavi,S.R., D.A.Wood, M.A.Ahmadi, etal. 2019. ANN-based prediction of laboratory-scale performance of CO2-foam flooding for improving oil recovery[J]. Natural Resources Research 28:1619–37.
   Web of Science ®Google Scholar
• Peng,T., X.Ji, Z.Cheng, etal. 2016. Modeling and reduction of NOX emissions for a700MW coal-fired boiler with the advanced machine learning method[J]. Energy 94:672–79.
   Web of Science ®Google Scholar
• Yang,T., K.Ma, Y.Lv, and Y.Bai. 2020. Real-time dynamic prediction model of NOX emission of coal-fired boilers under variable load conditions[J]. Fuel 274:117811.
   Web of Science ®Google Scholar
• Wang,X., Z.Lu, and H.Zhou. 2009. Neural network model on NOx Emission with furnace temperature distribution in a boiler[J]. Energy Technology 3:133–48.
   Google Scholar
• Ma,Y., P.Niu, and S.Yan. 2018. Amodified online sequential extreme learning machine for building circulation fluidized bed boiler’s NOX emission model[J]. Applied Mathematics and Computation 334:214–26.
   Web of Science ®Google Scholar
• Wang,Y., and Y.Zhou. 2020. Numerical optimization of the influence of multiple deep air-staged combustion on the NOx emission in an opposed firing utility boiler using lean coal[J]. Fuel 269:116996.
   Web of Science ®Google Scholar
• Zhang,Y., Y.Ding, Z.Wu, L.Kong, and T.Chou. 2007. Modeling and coordinative optimization of NOX emission and efficiency of utility boilers with neural network[J]. Korean Journal of Chemical Engineering 24:1118–23.
   Web of Science ®Google Scholar
• Zheng,Y., X.Gao, and C.Sheng. 2017. Impact of co-firing lean coal on NO xemission of a large-scale pulverized coal-fired utility boiler during partial load operation[J]. Korean Journal of Chemical Engineering 34:1273–80.
   Web of Science ®Google Scholar
• Xu,Y.Y., Y.Zhang, and J.C.Wang. 2013. Application of CFD in the optimal design of aSCR - DeNOx system for a300MW coal-fired power plant - ScienceDirect[J]. Computers & Chemical Engineering 49:50–60.
   Web of Science ®Google Scholar
• Zhou, H., Zhao, J. P., Zheng, L. G., Wang, C. L., & Cen, K. F. 2012. Modeling NOx emissions from coal-fired utility boilers using support vector regression with ant colony optimization[J]. Engineering Applications of Artificial Intelligence 25(1):147–58.
   Web of Science ®Google Scholar