This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-i...This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.展开更多
Estimating the intensity of outbursts of coal and gas is important as the intensity and frequency of outbursts of coal and gas tend to increase in deep mining. Fully understanding the major factors contributing to coa...Estimating the intensity of outbursts of coal and gas is important as the intensity and frequency of outbursts of coal and gas tend to increase in deep mining. Fully understanding the major factors contributing to coal and gas outbursts is significant in the evaluation of the intensity of the outburst. In this paper, we discuss the correlation between these major factors and the intensity of the outburst using Analysis of Variance(ANOVA) and Contingency Table Analysis(CTA). Regression analysis is used to evaluate the impact of these major factors on the intensity of outbursts based on physical experiments. Based on the evaluation, two simple models in terms of multiple linear and nonlinear regression were constructed for the prediction of the intensity of the outburst. The results show that the gas pressure and initial moisture in the coal mass could be the most significant factors compared to the weakest factor-porosity. The P values from Fisher's exact test in CTA are: moisture(0.019), geostress(0.290), porosity(0.650), and gas pressure(0.031). P values from ANOVA are moisture(0.094), geostress(0.077), porosity(0.420), and gas pressure(0.051). Furthermore, the multiple nonlinear regression model(RMSE: 3.870) is more accurate than the linear regression model(RMSE: 4.091).展开更多
A study on the validity of volume equations currently used for three timber species, Entandrophragma cylindricum, Erythrophleum ivorensis and Pericopsis elata （Sapelli, Tali and Assamela respectively） in south east ...A study on the validity of volume equations currently used for three timber species, Entandrophragma cylindricum, Erythrophleum ivorensis and Pericopsis elata （Sapelli, Tali and Assamela respectively） in south east Cameroon, was conducted between the months of July and September, 2007 to evaluate their suitability for the site. Twenty-two percent sampling intensity was conducted within annual allowable cuts and diameter readings taken on standing trees with the aid of a wide band Relascope. A non linear regression equation model was employed to compute volume equations and the student＇s t-test for the analysis of the existing models. Based on individual tree volumes within stands, new equations for the three species were constructed. A comparison was made between the new equations and those that were being used at the site. Results indicated a total standing volume of 0.007 m3/ha obtained for the three species （Sapelli 0.003 m3/ha, Tali 0.002 m3/ha and Assamela 0.002 m3/ha）. Two new volume equation models [B] and [C] were retained for their goodness-of-fit with [B] for Assamela and [C] for Sapelli and Tali. Results also showed that a total volume of 0.005 m3/ha was underestimated for the three species （Sapelli 0.002 m3/ha, Tali 0.001 m3/ha and Assamela 0.002 m3/ha） when existing volume equations were applied. It is imperative to construct new volume equations that are compatible with the ecological characteristics of the site using representative samples. Setting-up appropriate methods for their validation shall also serve as checks to future management errors.展开更多
文摘This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.
基金provided by the Natural Science Foundation Project(Key)of Chongqing(No.cstc2013jjB0012)the National Natural Science Foundation of China(No.51434003)the National Natural Science Foundation of China(No.51474040)
文摘Estimating the intensity of outbursts of coal and gas is important as the intensity and frequency of outbursts of coal and gas tend to increase in deep mining. Fully understanding the major factors contributing to coal and gas outbursts is significant in the evaluation of the intensity of the outburst. In this paper, we discuss the correlation between these major factors and the intensity of the outburst using Analysis of Variance(ANOVA) and Contingency Table Analysis(CTA). Regression analysis is used to evaluate the impact of these major factors on the intensity of outbursts based on physical experiments. Based on the evaluation, two simple models in terms of multiple linear and nonlinear regression were constructed for the prediction of the intensity of the outburst. The results show that the gas pressure and initial moisture in the coal mass could be the most significant factors compared to the weakest factor-porosity. The P values from Fisher's exact test in CTA are: moisture(0.019), geostress(0.290), porosity(0.650), and gas pressure(0.031). P values from ANOVA are moisture(0.094), geostress(0.077), porosity(0.420), and gas pressure(0.051). Furthermore, the multiple nonlinear regression model(RMSE: 3.870) is more accurate than the linear regression model(RMSE: 4.091).
文摘A study on the validity of volume equations currently used for three timber species, Entandrophragma cylindricum, Erythrophleum ivorensis and Pericopsis elata （Sapelli, Tali and Assamela respectively） in south east Cameroon, was conducted between the months of July and September, 2007 to evaluate their suitability for the site. Twenty-two percent sampling intensity was conducted within annual allowable cuts and diameter readings taken on standing trees with the aid of a wide band Relascope. A non linear regression equation model was employed to compute volume equations and the student＇s t-test for the analysis of the existing models. Based on individual tree volumes within stands, new equations for the three species were constructed. A comparison was made between the new equations and those that were being used at the site. Results indicated a total standing volume of 0.007 m3/ha obtained for the three species （Sapelli 0.003 m3/ha, Tali 0.002 m3/ha and Assamela 0.002 m3/ha）. Two new volume equation models [B] and [C] were retained for their goodness-of-fit with [B] for Assamela and [C] for Sapelli and Tali. Results also showed that a total volume of 0.005 m3/ha was underestimated for the three species （Sapelli 0.002 m3/ha, Tali 0.001 m3/ha and Assamela 0.002 m3/ha） when existing volume equations were applied. It is imperative to construct new volume equations that are compatible with the ecological characteristics of the site using representative samples. Setting-up appropriate methods for their validation shall also serve as checks to future management errors.
