外文翻譯---電站鍋爐熱效率與nox排放響應(yīng)特性建模方法

1、英文原文Modeling and optimization of efficiency and NOxemission at a coal 一 fired utility boilerHuan Zhao, Pei-bong WangSchool of Energy and Environment, Southeast University, Nanjing Jiangsu, China zhaohuan198213@163.com,

2、phwang@scu.cdu.cnAbstract----In order to improve boiler efficiency and to reduce the NOx emission of a coal-fired utility boiler using combustion optimization, a hybrid model, by combining support vector regress

3、ion (SVR) with simplified boiler efficiency model, was proposed to express the relation between operational parameters of the utility boiler and both NOx emission and boiler efficiency. SVR' parameters were determin

4、ed by the grid search method and 5-fold cross validation method. The predicted NOx emission and boiler efficiency from the hybrid model, compared with that of the BPNN-based hybrid model, shows better agreement with the

5、 measured. Then, based on the hybrid model, the modified center particle swarm optimization (CenterPSO) was employed to optimize the two objectives, the one is minimization of NOx emission and maximization of boiler eff

6、iciency and the other one is maximization of boiler efficiency under NOx emission constraint. The optimized results indicate that the proposed method can effectively control NOx emission and improve boiler effi

7、ciency.Keywords-NOx;boiler efficiency; combustion optimizationSVR; CenterPSO I. INTRODUCTION Because of the harmful effects on environment and human health, nitrogen oxides (NOx) emissions, produced by combustors and en

8、gines, have been the subject of restrictive regulations in many countries in recently years[1]. For instance, in the People’s Republic of China, the current NOx emission limit for dry bottom boilers with a capacity of

9、300MW and larger is 650 mg/Nm3 (at 6 vol% O2 dry), and it will decrease in the future [2]. As a consequence, the control of NOx emission is widely concern as the utilization of fossil fuels continues to increase, especi

10、ally in coal-fired power plants. Recently, combustion optimization has been proved to be an effective way to realize low NOx combustion in coal-fired utility setting [2-8]. In view of on-line plant data from distribut

11、ed control system (DCS) and continuous emissions monitoring system (CEMS), the relation between NOx emissions and various operational parameters of the boiler is modeled using artificial intelligence such as neural-netw

12、ork, expert system, fuzzy logic, generalized regression and support vector B. Support Vector Regression Support vector regression (SVR) has been used to solve a nonlinear regression estimation problem by introducing the

13、 alternative loss function. Its basic idea is to map the input data x into a high-dimensional feature space F by nonlinear mapping?, to yield and solve a linear regression problem in this feature space. By this metho

14、d, the unknown function with a tolerance epsilon band between inputs and output can be obtained. Considering the complete SVR theory and equations, please refer to [13]. C. Hybrid Model for NOx Emission and Boiler Effic

15、iency The prediction process of NOx emission and boiler efficiency by SVR and analytical model is schematically shown in Fig.1.In hybrid model, three SVR models having 30 inputs in the view of physical analysis were em

16、ployed to model the relationships between operational parameters and combustion products such as NOx emission, unburned carbon and oxygen content in flue gas.These inputs were the total air flow rate, six elevations of