Abstract: A novel time-span input neural network was developed to accurately predict the trend of the main steam temperature of a 750-t/d waste incineration boiler. Its historical operating data were used to retrieve sensitive parameters for the boiler output steam temperature by correlation analysis. Then, the 15 most sensitive parameters with specified time spans were selected as neural network inputs. An external testing set was introduced to objectively evaluate the neural network prediction capability. The results show that, compared with the traditional prediction method, the time-span input framework model can achieve better prediction performance and has a greater capability for generalization. The maximum average prediction error can be controlled below 0.2 °C and 1.5 °C in the next 60 s and 5 min, respectively. In addition, setting a reasonable terminal training threshold can effectively avoid overfitting. An importance analysis of the parameters indicates that the main steam temperature and the average temperature around the high-temperature superheater are the two most important variables of the input parameters; the former affects the overall prediction and the latter affects the long-term prediction performance.

一种新型时域输入神经网络实现垃圾焚烧锅炉主蒸汽温度的精准预测

[1]Al Shamisi MH, Assi AH, Hejase HAN, 2011. Using MATLAB to develop artificial neural network models for predicting global solar radiation in Al Ain city–UAE. In: Assi AH (Ed.), Engineering Education and Research Using MATLAB. InTech, Rijeka, Croatia.

[2]Bao CL, Zhang JF, 2013. Combustion optimization of power plant boilers based on RBF neural network model. Power Equipment, 27(2):97-100 (in Chinese).

[3]Basheer IA, Hajmeer M, 2000. Artificial neural networks: fundamentals, computing, design, and application. Journal of Microbiological Methods, 43(1):3-31.

[4]Bukovský I, Kolovratník M, 2012. A neural network model for predicting NO_x at the Mělník 1. Acta Polytechnica, 52(3):17-22.

[5]Chavan PD, Sharma T, Mall BK, et al., 2012. Development of data-driven models for fluidized-bed coal gasification process. Fuel, 93:44-51.

[6]Chen DZ, Christensen TH, 2010. Life-cycle assessment (EASEWASTE) of two municipal solid waste incineration technologies in China. Waste Management & Research, 28(6):508-519.

[7]Golgiyaz S, Talu MF, Onat C, 2019. Artificial neural network regression model to predict flue gas temperature and emissions with the spectral norm of flame image. Fuel, 255:115827.

[8]Han L, Zhang ZY, 2012. The application of immune genetic algorithm in main steam temperature of PID control of BP network. Physics Procedia, 24:80-86.

[9]Iliyas SA, Elshafei M, Habib MA, et al., 2013. RBF neural network inferential sensor for process emission monitoring. Control Engineering Practice, 21(7):962-970.

[10]Kabugo JC, Jämsä-Jounela SL, Schiemann R, et al., 2020. Industry 4.0 based process data analytics platform: a waste-to-energy plant case study. International Journal of Electrical Power & Energy Systems, 115:105508.

[11]Kalogirou SA, 2000. Applications of artificial neural-networks for energy systems. Applied Energy, 67(1-2):17-35.

[12]Liukkonen M, Hiltunen T, Hälikkä E, et al., 2011. Modeling of the fluidized bed combustion process and NO_x emissions using self-organizing maps: an application to the diagnosis of process states. Environmental Modelling & Software, 26(5):605-614.

[13]Meher SK, Behera SK, Kim MC, et al., 2015. Multiple decision expert systems for performance analysis of a boiler system. Applied Artificial Intelligence, 29(9):839-858.

[14]National Bureau of Statistics, 2018. China Statistical Yearbook 2018. China Statistics Press, Beijing, China (in Chinese).

[15]Norhayati I, Rashid M, 2018. Adaptive neuro-fuzzy prediction of carbon monoxide emission from a clinical waste incineration plant. Neural Computing and Applications, 30(10):3049-3061.

[16]Oko E, Wang MH, Zhang J, 2015. Neural network approach for predicting drum pressure and level in coal-fired subcritical power plant. Fuel, 151:139-145.

[17]Olden JD, Jackson DA, 2002. Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks. Ecological Modelling, 154(1-2):135-150.

[18]Pai TY, Lo HM, Wan TJ, et al., 2015. Predicting air pollutant emissions from a medical incinerator using grey model and neural network. Applied Mathematical Modelling, 39(5-6):1513-1525.

[19]Shaha AP, Singamsetti MS, Tripathy BK, et al., 2020. Performance prediction and interpretation of a refuse plastic fuel fired boiler. IEEE Access, 8:117467-117482.

[20]Shapiro-Bengtsen S, Andersen FM, Münster M, et al., 2020. Municipal solid waste available to the Chinese energy sector-provincial projections to 2050. Waste Management, 112:52-65.

[21]Smrekar J, Potočnik P, Senegačnik A, 2013. Multi-step-ahead prediction of NO_x emissions for a coal-based boiler. Applied Energy, 106:89-99.

[22]Srivastava N, Hinton G, Krizhevsky A, et al., 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929-1958.

[23]Sung AH, 1998. Ranking importance of input parameters of neural networks. Expert Systems with Applications, 15(3-4):405-411.

[24]Tóth P, Garami A, Csordás B, 2017. Image-based deep neural network prediction of the heat output of a step-grate biomass boiler. Applied Energy, 200:155-169.

[25]Tzafestas SG, Dalianis PJ, Anthopoulos G, 1996. On the overtraining phenomenon of backpropagation neural networks. Mathematics and Computers in Simulation, 40(5-6):507-521.

[26]You HH, Ma ZY, Tang YJ, et al., 2017. Comparison of ANN (MLP), ANFIS, SVM, and RF models for the online classification of heating value of burning municipal solid waste in circulating fluidized bed incinerators. Waste Management, 68:186-197.

[27]Zhao M, Yan WJ, Zheng J, 2010. Combustion optimization modelling for utility boilers based on generalized dynamic fuzzy neural networks. Thermal Power Generation, 39(3):19-22 (in Chinese).

[28]Zhou H, Meng AH, Long YQ, et al., 2014. An overview of characteristics of municipal solid waste fuel in China: physical, chemical composition and heating value. Renewable and Sustainable Energy Reviews, 36:107-122.