In order to accurately forecast the load of power system and enhance the stability of the power network, a novel unascertained mathematics based recurrent neural network (UMRNN) for power intelligence center (PIC) was...In order to accurately forecast the load of power system and enhance the stability of the power network, a novel unascertained mathematics based recurrent neural network (UMRNN) for power intelligence center (PIC) was created through three steps. First, by combining with the general project uncertain element transmission theory (GPUET), the basic definitions of stochastic, fuzzy, and grey uncertain elements were given based on the principal types of uncertain information. Second, a power dynamic alliance including four sectors: generation sector, transmission sector, distribution sector and customers was established. The key factors were amended according to the four transmission topologies of uncertain elements, thus the new factors entered the power intelligence center as the input elements. Finally, in the intelligence handing background of PIC, by performing uncertain and recursive process to the input values of network, and combining unascertained mathematics, the novel load forecasting model was built. Three different approaches were put forward to forecast an eastern regional power grid load in China. The root mean square error (ERMS) demonstrates that the forecasting accuracy of the proposed model UMRNN is 3% higher than that of BP neural network (BPNN), and 5% higher than that of autoregressive integrated moving average (ARIMA). Besides, an example also shows that the average relative error of the first quarter of 2008 forecasted by UMRNN is only 2.59%, which has high precision.展开更多
A two-dimensional steady state model was developed and solved numerically to predict the performance of evaporative condensing regenerator.Two-dimensional parameter distributions of air,solution and refrigerant were c...A two-dimensional steady state model was developed and solved numerically to predict the performance of evaporative condensing regenerator.Two-dimensional parameter distributions of air,solution and refrigerant were calculated by the mathematical model.The solution content first increases and then decreases along the solution flow direction.At y/Hr=0.98(where Hr is the height of regenerator),air humidity increases from 1.99% to 2.348% firstly and then decreases.The experimental results were used to validate mathematical model.It is indicated that the simulation results agree with experimental data well.The results not only show that the mathematical model can be used to predict the performance of regenerator,but also has great value in the design and improvement of evaporative condensing regenerator.展开更多
Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification...Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.展开更多
In order to perfectly reflect the dynamic corrosion of reinforced concrete (RC) cover in practical engineering,an analytic model of non-uniform corrosion induced cracking was presented based on the elastic-plastic fra...In order to perfectly reflect the dynamic corrosion of reinforced concrete (RC) cover in practical engineering,an analytic model of non-uniform corrosion induced cracking was presented based on the elastic-plastic fracture mechanics theory.Comparisons with the published experimental data show that the predictions given by the present model are in good agreement with the results both for natural exposed experiments and short-time indoor tests (the best difference is about 2.7%).Also it obviously provides much better precision than those models under the assumption of uniform corrosion (the maximal improved precision is about 48%).Therefore,it is pointed out that the so-called uniform corrosion models to describe the cover cracking of RC should be adopted cautiously.Finally,the influences of thickness of local rusty layer around the reinforcing steel bar on the critical corrosion-induced crack indexes were investigated.It is found that the thickness of local rusty layer has great effect on the critical mass loss of reinforcing steel,threshold expansion pressure,and time to cover cracking.For local rusty layer thickness with a size of a=0.5 mm,the time to cover cracking will increase by about one times when a/b (a,semi-minor axis;b,semi-major axis) changes from 0.1 to 1 mm.展开更多
The adsorption of Ca（ II ） ions from aqueous solution by ehitosan a-ketoglutaric acid （KCTS） and hydroxamated chitosan a-ketoglutaric acid （HKCTS） was studied in a batch adsorption system. The Langmuir and Freun...The adsorption of Ca（ II ） ions from aqueous solution by ehitosan a-ketoglutaric acid （KCTS） and hydroxamated chitosan a-ketoglutaric acid （HKCTS） was studied in a batch adsorption system. The Langmuir and Freundlich adsorption models were applied to describing the equilibrium isotherms, and isotherm constants were determined. The kinetics of the adsorption with respect to the initial Ca（II） ions concentration, temperature and pH was investigated. The pseudo-first-order and second-order kinetic models were used to describe the kinetic data and the rate constants were evaluated. The results show that the experimental data fit well to the Langmuir isotherms with a high correlation coefficient （R2）. The pseudo-second-order rate expression provides the best fitting kinetic model. The pseudo second-order kinetic model is indicated with the activation energy of 26.22 kJ/mol and 6.16 kJ/mol for KCTS and HKCTS, respectively. It is suggested that the overall rate of adsorption of Ca（ II ） ions is likely to be controlled by the chemical process.展开更多
基金Projects(70572090, 70373017) supported by the National Natural Science Foundation of China
文摘In order to accurately forecast the load of power system and enhance the stability of the power network, a novel unascertained mathematics based recurrent neural network (UMRNN) for power intelligence center (PIC) was created through three steps. First, by combining with the general project uncertain element transmission theory (GPUET), the basic definitions of stochastic, fuzzy, and grey uncertain elements were given based on the principal types of uncertain information. Second, a power dynamic alliance including four sectors: generation sector, transmission sector, distribution sector and customers was established. The key factors were amended according to the four transmission topologies of uncertain elements, thus the new factors entered the power intelligence center as the input elements. Finally, in the intelligence handing background of PIC, by performing uncertain and recursive process to the input values of network, and combining unascertained mathematics, the novel load forecasting model was built. Three different approaches were put forward to forecast an eastern regional power grid load in China. The root mean square error (ERMS) demonstrates that the forecasting accuracy of the proposed model UMRNN is 3% higher than that of BP neural network (BPNN), and 5% higher than that of autoregressive integrated moving average (ARIMA). Besides, an example also shows that the average relative error of the first quarter of 2008 forecasted by UMRNN is only 2.59%, which has high precision.
基金Project(PHR201007127) supported by Academic Human Resources Development Fund of Institutions of Higher Learning under the Jurisdiction of Beijing Municipality, China Project(bsbe2010-05) supported by the Opening Funds of State Key Laboratory of Building Safety and Built Environment, China Project supported by the Doctoral Startup Foundation of Beijing University of Civil Engineering and Architecture, China
文摘A two-dimensional steady state model was developed and solved numerically to predict the performance of evaporative condensing regenerator.Two-dimensional parameter distributions of air,solution and refrigerant were calculated by the mathematical model.The solution content first increases and then decreases along the solution flow direction.At y/Hr=0.98(where Hr is the height of regenerator),air humidity increases from 1.99% to 2.348% firstly and then decreases.The experimental results were used to validate mathematical model.It is indicated that the simulation results agree with experimental data well.The results not only show that the mathematical model can be used to predict the performance of regenerator,but also has great value in the design and improvement of evaporative condensing regenerator.
文摘Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
基金Project(50925829) supported by the National Science Fund for Distinguished Young Scholars of ChinaProject(50908148) supported by the National Natural Science Foundation of ChinaProjects(2009-K4-23,2010-11-33) supported by the Research of Ministry of Housing and Urban Rural Development of China
文摘In order to perfectly reflect the dynamic corrosion of reinforced concrete (RC) cover in practical engineering,an analytic model of non-uniform corrosion induced cracking was presented based on the elastic-plastic fracture mechanics theory.Comparisons with the published experimental data show that the predictions given by the present model are in good agreement with the results both for natural exposed experiments and short-time indoor tests (the best difference is about 2.7%).Also it obviously provides much better precision than those models under the assumption of uniform corrosion (the maximal improved precision is about 48%).Therefore,it is pointed out that the so-called uniform corrosion models to describe the cover cracking of RC should be adopted cautiously.Finally,the influences of thickness of local rusty layer around the reinforcing steel bar on the critical corrosion-induced crack indexes were investigated.It is found that the thickness of local rusty layer has great effect on the critical mass loss of reinforcing steel,threshold expansion pressure,and time to cover cracking.For local rusty layer thickness with a size of a=0.5 mm,the time to cover cracking will increase by about one times when a/b (a,semi-minor axis;b,semi-major axis) changes from 0.1 to 1 mm.
基金Project(20376085) supported by the National Natural Science Foundation of China
文摘The adsorption of Ca（ II ） ions from aqueous solution by ehitosan a-ketoglutaric acid （KCTS） and hydroxamated chitosan a-ketoglutaric acid （HKCTS） was studied in a batch adsorption system. The Langmuir and Freundlich adsorption models were applied to describing the equilibrium isotherms, and isotherm constants were determined. The kinetics of the adsorption with respect to the initial Ca（II） ions concentration, temperature and pH was investigated. The pseudo-first-order and second-order kinetic models were used to describe the kinetic data and the rate constants were evaluated. The results show that the experimental data fit well to the Langmuir isotherms with a high correlation coefficient （R2）. The pseudo-second-order rate expression provides the best fitting kinetic model. The pseudo second-order kinetic model is indicated with the activation energy of 26.22 kJ/mol and 6.16 kJ/mol for KCTS and HKCTS, respectively. It is suggested that the overall rate of adsorption of Ca（ II ） ions is likely to be controlled by the chemical process.
