循环流化床锅炉燃烧系统的神经网络模型研究
|
摘要
为了准确预测热电厂锅炉的NO_x排放质量浓度,以某热电厂300 MW亚临界循环流化床锅炉为研究对象,利用并联型快速学习网进行建模。首先以经典的回归数据集测试并联型快速学习网的有效性,将结果与其他神经网络的结果相比较,证明其具有更好的学习能力和稳定性。再以热电厂现场采集的样本数据作为模型的输入输出数据,将该模型的预测结果与极限学习机、快速学习网、核极限学习机和增量型极限学习机的预测结果进行比较。结果表明:并联型快速学习网具有良好的预测精度和泛化能力,能够更准确有效地预测热电厂锅炉的NO_x排放质量浓度。
To accurately predict the NO_x emission from boilers of thermal power plants,a 300 MW subcritical circulating fluidized bed(CFB)boiler was taken as the object of study,for which a model was established using fast learning network with parallel layer perceptron.Firstly,the validity of the proposed network was tested using classical regression data sets,and the results were subsequently compared with other neural networks,so as to examine its learning ability and stability.Then the sample data collected from the thermal power plant were taken as the input and output variables of the model proposed.Finally,the prediction results were compared with those of extreme learning machine,fast learning network,kernel extreme learning machine and incremental extreme learning machine,etc.Results show that the model established based on fast learning network with parallel layer perceptron has a good prediction accuracy and generalization ability,which may accurately and effectively predict the NOxemission from boilers of thermal power plants.
To accurately predict the NO_x emission from boilers of thermal power plants,a 300 MW subcritical circulating fluidized bed(CFB)boiler was taken as the object of study,for which a model was established using fast learning network with parallel layer perceptron.Firstly,the validity of the proposed network was tested using classical regression data sets,and the results were subsequently compared with other neural networks,so as to examine its learning ability and stability.Then the sample data collected from the thermal power plant were taken as the input and output variables of the model proposed.Finally,the prediction results were compared with those of extreme learning machine,fast learning network,kernel extreme learning machine and incremental extreme learning machine,etc.Results show that the model established based on fast learning network with parallel layer perceptron has a good prediction accuracy and generalization ability,which may accurately and effectively predict the NOxemission from boilers of thermal power plants.
引文
[1]欧阳子区,朱建国,吕清刚.无烟煤粉经循环流化床预热后燃烧特性及NOx排放特性实验研究[J].中国电机工程学报,2014,34(11):1748-1754.OUYANG Ziqu,ZHU Jianguo,LQinggang.Experimental study on combustion and NOxemission of pulverized anthracite coal preheated by a circulating fluidized bed[J].Proceedings of the CSEE,2014,34(11):1748-1754.
[2]牛培峰,赵振,马云鹏,等.基于风驱动算法的锅炉NOx排放模型优化[J].动力工程学报,2016,36(9):732-738.NIU Peifeng,ZHAO Zhen,MA Yunpeng,et al.Model improvement for boiler NOxemission based on wind driven optimization algorithm[J].Journal of Chinese Society of Power Engineering,2016,36(9):732-738.
[3]张弦,王宏力.限定记忆极端学习机及其应用[J].控制与决策,2012,27(8):1206-1210.ZHANG Xian,WANG Hongli.Fixed-memory extreme learning machine and its applications[J].Control and Decision,2012,27(8):1206-1210.
[4]魏辉,陆方,罗永浩,等.燃煤锅炉高效、低NOx运行策略的研究[J].动力工程,2008,28(3):361-366.WEI Hui,LU Fang,LUO Yonghao,et al.Research on operation strategy on reducing NOxemissions and improving efficiency of coal-fired boiler[J].Journal of Power Engineering,2008,28(3):361-366.
[5]CAMINHAS W M,VIEIRA D A G,VASCONCELOS J A.Parallel layer perceptron[J].Neurocomputing,2003,55(3/4):771-778.
[6]CULOTTA S,MESSINEO A,MESSINEO S.The application of different model of multi-layer perceptrons in the estimation of wind speed[J].Advanced Materials Research,2012,452-453:690-694.
[7]ZHENG Lilei,DUFFNER S,IDRISSI K,et al.Siamese multi-layer perceptrons for dimensionality reduction and face identification[J].Multimedia Tools&Applications,2016,75(9):5055-5073.
[8]PEA A B,GARCA J A L,PREZ P Y P.An adaptive-network-based fuzzy inference system for project evaluation[J].Ingeniería Y Universidad,2015,19(2):299-313.
[9]HUNTER D,WILAMOWSKI B.Parallel multi-layer neural network architecture with improved efficiency[C]//Proceedings of the 4th International Conference on Human System Interactions.Yokohama,Japan:IEEE,2011:299-304.
[10]GAO Zhenning.Parallel and distributed implementation of a multilayer perceptron neural network on a wireless sensor network[D].Toledo,USA:The University of Toledo,2013.
[11]LI Xiaojun,LI Li.IP core based hardware implementation of multi-layer perceptrons on FPGAs:aparallel approach[J].Advanced Materials Research,2012,433-440:5647-5653.
[12]GARCIA-SALGADO B P,PONOMARYOV V I,ROBLES-GONZALEZ M A.Parallel multilayer perceptron neural network used for hyperspectral image classification[C]//Proceedings of 2016Real-Time Image and Video Processing.Brussels,Belgium:SPIE,2016:98970K.
[13]HUANG Guangbin,ZHU Qinyu,SIEW C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1/3):489-501.
[14]DING Shifei,ZHAO Han,ZHANG Yanan,et al.Extreme learning machine:algorithm,theory and applications[J].Artificial Intelligence Review,2015,44(1):103-115.
[15]JAVED K,GOURIVEAU R,ZERHOUNI N.SWELM:a summation wavelet extreme learning machine algorithm with a priori parameter initialization[J].Neurocomputing,2014,123:299-307.
[16]DUDEK G.Extreme learning machine for function approximation-interval problem of input weights and biases[C]//Proceedings of the 2nd International Conference on Cybernetics.Gdynia,Poland:IEEE,2015:62-67.
[17]HUANG G B,SIEW C K.Extreme learning machine:RBF network case[C]//Proceedings of the 8th Control,Automation,Robotics and Vision Conference.China:IEEE,2012:1029-1036.
[18]IOSIFIDIS A,TEFAS A,PITAS I.Dynamic action recognition based on dynemes and extreme learning machine[J].Pattern Recognition Letters,2013,34(15):1890-1898.
[19]LI Guoqiang,NIU Peifeng,DUAN Xiaolong,et al.Fast learning network:a novel artificial neural network with a fast learning speed[J].Neural Computing and Applications,2014,24(7/8):1683-1695.
[2]牛培峰,赵振,马云鹏,等.基于风驱动算法的锅炉NOx排放模型优化[J].动力工程学报,2016,36(9):732-738.NIU Peifeng,ZHAO Zhen,MA Yunpeng,et al.Model improvement for boiler NOxemission based on wind driven optimization algorithm[J].Journal of Chinese Society of Power Engineering,2016,36(9):732-738.
[3]张弦,王宏力.限定记忆极端学习机及其应用[J].控制与决策,2012,27(8):1206-1210.ZHANG Xian,WANG Hongli.Fixed-memory extreme learning machine and its applications[J].Control and Decision,2012,27(8):1206-1210.
[4]魏辉,陆方,罗永浩,等.燃煤锅炉高效、低NOx运行策略的研究[J].动力工程,2008,28(3):361-366.WEI Hui,LU Fang,LUO Yonghao,et al.Research on operation strategy on reducing NOxemissions and improving efficiency of coal-fired boiler[J].Journal of Power Engineering,2008,28(3):361-366.
[5]CAMINHAS W M,VIEIRA D A G,VASCONCELOS J A.Parallel layer perceptron[J].Neurocomputing,2003,55(3/4):771-778.
[6]CULOTTA S,MESSINEO A,MESSINEO S.The application of different model of multi-layer perceptrons in the estimation of wind speed[J].Advanced Materials Research,2012,452-453:690-694.
[7]ZHENG Lilei,DUFFNER S,IDRISSI K,et al.Siamese multi-layer perceptrons for dimensionality reduction and face identification[J].Multimedia Tools&Applications,2016,75(9):5055-5073.
[8]PEA A B,GARCA J A L,PREZ P Y P.An adaptive-network-based fuzzy inference system for project evaluation[J].Ingeniería Y Universidad,2015,19(2):299-313.
[9]HUNTER D,WILAMOWSKI B.Parallel multi-layer neural network architecture with improved efficiency[C]//Proceedings of the 4th International Conference on Human System Interactions.Yokohama,Japan:IEEE,2011:299-304.
[10]GAO Zhenning.Parallel and distributed implementation of a multilayer perceptron neural network on a wireless sensor network[D].Toledo,USA:The University of Toledo,2013.
[11]LI Xiaojun,LI Li.IP core based hardware implementation of multi-layer perceptrons on FPGAs:aparallel approach[J].Advanced Materials Research,2012,433-440:5647-5653.
[12]GARCIA-SALGADO B P,PONOMARYOV V I,ROBLES-GONZALEZ M A.Parallel multilayer perceptron neural network used for hyperspectral image classification[C]//Proceedings of 2016Real-Time Image and Video Processing.Brussels,Belgium:SPIE,2016:98970K.
[13]HUANG Guangbin,ZHU Qinyu,SIEW C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1/3):489-501.
[14]DING Shifei,ZHAO Han,ZHANG Yanan,et al.Extreme learning machine:algorithm,theory and applications[J].Artificial Intelligence Review,2015,44(1):103-115.
[15]JAVED K,GOURIVEAU R,ZERHOUNI N.SWELM:a summation wavelet extreme learning machine algorithm with a priori parameter initialization[J].Neurocomputing,2014,123:299-307.
[16]DUDEK G.Extreme learning machine for function approximation-interval problem of input weights and biases[C]//Proceedings of the 2nd International Conference on Cybernetics.Gdynia,Poland:IEEE,2015:62-67.
[17]HUANG G B,SIEW C K.Extreme learning machine:RBF network case[C]//Proceedings of the 8th Control,Automation,Robotics and Vision Conference.China:IEEE,2012:1029-1036.
[18]IOSIFIDIS A,TEFAS A,PITAS I.Dynamic action recognition based on dynemes and extreme learning machine[J].Pattern Recognition Letters,2013,34(15):1890-1898.
[19]LI Guoqiang,NIU Peifeng,DUAN Xiaolong,et al.Fast learning network:a novel artificial neural network with a fast learning speed[J].Neural Computing and Applications,2014,24(7/8):1683-1695.