Support vector regression （SVR） method is a novel type of learning machine algorithms, which is seldom applied to the development of urban atmospheric quality models under multiple socio-economic factors. This study...Support vector regression （SVR） method is a novel type of learning machine algorithms, which is seldom applied to the development of urban atmospheric quality models under multiple socio-economic factors. This study presents four SVR models by selecting linear, radial basis, spline, and polynomial functions as kernels, respectively for the prediction of urban dust fall levels. The inputs of the models are identified as industrial coal consumption, population density, traffic flow coefficient, and shopping density coefficient. The training and testing results show that the SVR model with radial basis kernel performs better than the other three both in the training and testing processes. In addition, a number of scenario analyses reveal that the most suitable parameters （insensitive loss function e, the parameter to reduce the influence of error C, and discrete level or average distribution of parameters σ） are 0.001, 0.5, and 2 000, respectively.展开更多
The general regression neural network(GRNN) model was proposed to model and predict the length of day(LOD) change, which has very complicated time-varying characteristics. Meanwhile, considering that the axial atmosph...The general regression neural network(GRNN) model was proposed to model and predict the length of day(LOD) change, which has very complicated time-varying characteristics. Meanwhile, considering that the axial atmospheric angular momentum(AAM) function is tightly correlated with the LOD changes, it was introduced into the GRNN prediction model to further improve the accuracy of prediction. Experiments with the observational data of LOD changes show that the prediction accuracy of the GRNN model is 6.1% higher than that of BP network, and after introducing AAM function, the improvement of prediction accuracy further increases to 14.7%. The results show that the GRNN with AAM function is an effective prediction method for LOD changes.展开更多
Traditional gust load factor(GLF)method,inertial wind load(IWL)method and tri-component method(LRC+IWL)cannot accurately analyze the wind-induced responses of super-large cooling towers,so the real combination formula...Traditional gust load factor(GLF)method,inertial wind load(IWL)method and tri-component method(LRC+IWL)cannot accurately analyze the wind-induced responses of super-large cooling towers,so the real combination formulas of fluctuating wind-induced responses and equivalent static wind loads(ESWLSs)were derived based on structural dynamics and random vibration theory.The consistent coupled method(CCM)was presented to compensate the coupled term between background and resonant response.Taking the super-large cooling tower(H=215 m)of nuclear power plant in Jiangxi Province,China,which is the highest and largest in China,as the example,based on modified equivalent beam-net design method,the aero-elastic model for simultaneous pressure and vibration measurement of super-large cooling tower is firstly carried out.Then,combining wind tunnel test and CCM,the effects of self-excited force on the surface pressures and wind-induced responses are discussed,and the wind-induced response characteristics of background component,resonant component,coupled term between background and resonant response,fluctuating responses,and wind vibration coefficients are discussed.It can be concluded that wind-induced response mechanism must be understood to direct the wind resistant design for super-large cooling towers.展开更多
A decomposition model was applied to study the resource-saving and environment-friendly effects of air pollutant emissions(taking industrial SO2 emission as an example) in China.From the results,it is found that 38.93...A decomposition model was applied to study the resource-saving and environment-friendly effects of air pollutant emissions(taking industrial SO2 emission as an example) in China.From the results,it is found that 38.93% and 61.07% are contributed to environment-friendly and resource-saving effects,respectively,by the dramatic decrease in industrial SO2 emission density(nearly 70% from 2001 to 2010).This indicates that China has achieved important progress during the 11th FYP(five-year plan) compared with the 10th FYP.A simultaneous equations model was also employed to analyze the influencing factors by using data from 30 provinces in China.The results imply that the influence of environmental regulation on environment-friendly effect is not obvious during the 10th FYP but obvious during the 11th FYP.Thus,the government should continue promoting the environment-friendly effect by further enhancing environmental regulation and strengthening the role of environmental management.展开更多
基金Projects(2007JT3018, 2008JT1013, 2009FJ4056) supported by the Key Project in Hunan Science and Technology Program, ChinaProject(20090161120014) supported by the New Teachers Sustentation Fund in Doctoral Program, Ministry of Education, China
文摘Support vector regression （SVR） method is a novel type of learning machine algorithms, which is seldom applied to the development of urban atmospheric quality models under multiple socio-economic factors. This study presents four SVR models by selecting linear, radial basis, spline, and polynomial functions as kernels, respectively for the prediction of urban dust fall levels. The inputs of the models are identified as industrial coal consumption, population density, traffic flow coefficient, and shopping density coefficient. The training and testing results show that the SVR model with radial basis kernel performs better than the other three both in the training and testing processes. In addition, a number of scenario analyses reveal that the most suitable parameters （insensitive loss function e, the parameter to reduce the influence of error C, and discrete level or average distribution of parameters σ） are 0.001, 0.5, and 2 000, respectively.
基金Projects(U1231105,10878026)supported by the National Natural Science Foundation of China
文摘The general regression neural network(GRNN) model was proposed to model and predict the length of day(LOD) change, which has very complicated time-varying characteristics. Meanwhile, considering that the axial atmospheric angular momentum(AAM) function is tightly correlated with the LOD changes, it was introduced into the GRNN prediction model to further improve the accuracy of prediction. Experiments with the observational data of LOD changes show that the prediction accuracy of the GRNN model is 6.1% higher than that of BP network, and after introducing AAM function, the improvement of prediction accuracy further increases to 14.7%. The results show that the GRNN with AAM function is an effective prediction method for LOD changes.
基金Projects(50978203,51208254)supported by the National Natural Science Foundation of ChinaProject(BK2012390)supported by Natural Science Foundation of Jiangsu Province,ChinaProject supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions,China
文摘Traditional gust load factor(GLF)method,inertial wind load(IWL)method and tri-component method(LRC+IWL)cannot accurately analyze the wind-induced responses of super-large cooling towers,so the real combination formulas of fluctuating wind-induced responses and equivalent static wind loads(ESWLSs)were derived based on structural dynamics and random vibration theory.The consistent coupled method(CCM)was presented to compensate the coupled term between background and resonant response.Taking the super-large cooling tower(H=215 m)of nuclear power plant in Jiangxi Province,China,which is the highest and largest in China,as the example,based on modified equivalent beam-net design method,the aero-elastic model for simultaneous pressure and vibration measurement of super-large cooling tower is firstly carried out.Then,combining wind tunnel test and CCM,the effects of self-excited force on the surface pressures and wind-induced responses are discussed,and the wind-induced response characteristics of background component,resonant component,coupled term between background and resonant response,fluctuating responses,and wind vibration coefficients are discussed.It can be concluded that wind-induced response mechanism must be understood to direct the wind resistant design for super-large cooling towers.
基金Project(201009066)supported by the R&D Special Fund for Public Welfare of the Ministry of Finance and Ministry of Science and Technology of China
文摘A decomposition model was applied to study the resource-saving and environment-friendly effects of air pollutant emissions(taking industrial SO2 emission as an example) in China.From the results,it is found that 38.93% and 61.07% are contributed to environment-friendly and resource-saving effects,respectively,by the dramatic decrease in industrial SO2 emission density(nearly 70% from 2001 to 2010).This indicates that China has achieved important progress during the 11th FYP(five-year plan) compared with the 10th FYP.A simultaneous equations model was also employed to analyze the influencing factors by using data from 30 provinces in China.The results imply that the influence of environmental regulation on environment-friendly effect is not obvious during the 10th FYP but obvious during the 11th FYP.Thus,the government should continue promoting the environment-friendly effect by further enhancing environmental regulation and strengthening the role of environmental management.
