Time-series analysis is important to a wide range of disciplines transcending both the physical and social sciences for proactive policy decisions. Statistical models have sound theoretical basis and have been success...Time-series analysis is important to a wide range of disciplines transcending both the physical and social sciences for proactive policy decisions. Statistical models have sound theoretical basis and have been successfully used in a number of problem domains in time series forecasting. Due to power and flexibility, Box-Jenkins ARIMA model has gained enormous popularity in many areas and research practice for the last three decades. More recently, the neural networks have been shown to be a promising alternative tool for modeling and forecasting owing to their ability to capture the nonlinearity in the data. However, despite the popularity and the superiority of ARIMA and ANN models, the empirical forecasting performance has been rather mixed so that no single method is best in every situation. In this study, a hybrid ARIMA and neural networks model to time series forecasting is proposed. The basic idea behind the model combination is to use each model’s unique features to capture different patterns in the data. With three real data sets, empirical results evidently show that the hybrid model outperforms ARIMA and ANN model noticeably in terms of forecasting accuracy used in isolation.展开更多
An efficient chlorination roasting process for recovering zinc(Zn)and lead(Pb)from copper smelting slag was proposed.Thermodynamic models were established,illustrating that Zn and Pb in copper smelting slag can be eff...An efficient chlorination roasting process for recovering zinc(Zn)and lead(Pb)from copper smelting slag was proposed.Thermodynamic models were established,illustrating that Zn and Pb in copper smelting slag can be efficiently recycled during the chlorination roasting process.By decreasing the partial pressure of the gaseous products,chlorination was promoted.The Box−Behnken design was applied to assessing the interactive effects of the process variables and optimizing the chlorination roasting process.CaCl_(2) dosage and roasting temperature and time were used as variables,and metal recovery efficiencies were used as responses.When the roasting temperature was 1172℃ with a CaCl_(2) addition amount of 30 wt.%and a roasting time of 100 min,the predicted optimal recovery efficiencies of Zn and Pb were 87.85%and 99.26%,respectively,and the results were validated by experiments under the same conditions.The residual Zn-and Pb-containing phases in the roasting slags were ZnFe_(2)O_(4),Zn_(2)SiO_(4),and PbS.展开更多
This paper introduces a study on modelling surface finish in EDM （Electrical Discharge Machining） of tablet shape punches when using copper as electrode material. In this study, 27 experiments were performed based o...This paper introduces a study on modelling surface finish in EDM （Electrical Discharge Machining） of tablet shape punches when using copper as electrode material. In this study, 27 experiments were performed based on BBD （Box-Behnken Design） and the work-piece material was 9CrSi steel. The input process parameters were the current, the pulse on time, the pulse off time and the voltage. The effects of the input parameters on the surface finish were evaluated by analysing variance. Besides, from the results of the experiments, a regression equation for determining the surface roughness is introduced. Also, the optimum input parameter values were found in order to get the minimum surface roughness.展开更多
文摘Time-series analysis is important to a wide range of disciplines transcending both the physical and social sciences for proactive policy decisions. Statistical models have sound theoretical basis and have been successfully used in a number of problem domains in time series forecasting. Due to power and flexibility, Box-Jenkins ARIMA model has gained enormous popularity in many areas and research practice for the last three decades. More recently, the neural networks have been shown to be a promising alternative tool for modeling and forecasting owing to their ability to capture the nonlinearity in the data. However, despite the popularity and the superiority of ARIMA and ANN models, the empirical forecasting performance has been rather mixed so that no single method is best in every situation. In this study, a hybrid ARIMA and neural networks model to time series forecasting is proposed. The basic idea behind the model combination is to use each model’s unique features to capture different patterns in the data. With three real data sets, empirical results evidently show that the hybrid model outperforms ARIMA and ANN model noticeably in terms of forecasting accuracy used in isolation.
基金The authors are grateful for the financial supports from the National Natural Science Foundation of China(Nos.51620105013,51904351)Innovation-Driven Project of Central South University,China(No.2020CX028)+1 种基金Natural Science Fund for Distinguished Young Scholar of Hunan Province,China(No.2019JJ20031)the National Key R&D Program of China(No.2019YFC1907400)。
文摘An efficient chlorination roasting process for recovering zinc(Zn)and lead(Pb)from copper smelting slag was proposed.Thermodynamic models were established,illustrating that Zn and Pb in copper smelting slag can be efficiently recycled during the chlorination roasting process.By decreasing the partial pressure of the gaseous products,chlorination was promoted.The Box−Behnken design was applied to assessing the interactive effects of the process variables and optimizing the chlorination roasting process.CaCl_(2) dosage and roasting temperature and time were used as variables,and metal recovery efficiencies were used as responses.When the roasting temperature was 1172℃ with a CaCl_(2) addition amount of 30 wt.%and a roasting time of 100 min,the predicted optimal recovery efficiencies of Zn and Pb were 87.85%and 99.26%,respectively,and the results were validated by experiments under the same conditions.The residual Zn-and Pb-containing phases in the roasting slags were ZnFe_(2)O_(4),Zn_(2)SiO_(4),and PbS.
文摘This paper introduces a study on modelling surface finish in EDM （Electrical Discharge Machining） of tablet shape punches when using copper as electrode material. In this study, 27 experiments were performed based on BBD （Box-Behnken Design） and the work-piece material was 9CrSi steel. The input process parameters were the current, the pulse on time, the pulse off time and the voltage. The effects of the input parameters on the surface finish were evaluated by analysing variance. Besides, from the results of the experiments, a regression equation for determining the surface roughness is introduced. Also, the optimum input parameter values were found in order to get the minimum surface roughness.
