Baosteel＇ s Slag Short Flow（BSSF） is an innovative process for steelmaking slag treatment that was developed by Baosteel. The process principles, flow-chart, parameters and component systems of the BSSF for steelma...Baosteel＇ s Slag Short Flow（BSSF） is an innovative process for steelmaking slag treatment that was developed by Baosteel. The process principles, flow-chart, parameters and component systems of the BSSF for steelmaking slag treatment are presented. Characteristics of the finished BSSF slag are summarized by analyzing the slag＇ s physical and chemical performances. Several Utilization methods for the BSSF slag are given.展开更多
Traffic flow prediction in urban areas is essential in the IntelligentTransportation System (ITS). Short Term Traffic Flow (STTF) predictionimpacts traffic flow series, where an estimation of the number of vehicleswil...Traffic flow prediction in urban areas is essential in the IntelligentTransportation System (ITS). Short Term Traffic Flow (STTF) predictionimpacts traffic flow series, where an estimation of the number of vehicleswill appear during the next instance of time per hour. Precise STTF iscritical in Intelligent Transportation System. Various extinct systems aim forshort-term traffic forecasts, ensuring a good precision outcome which was asignificant task over the past few years. The main objective of this paper is topropose a new model to predict STTF for every hour of a day. In this paper,we have proposed a novel hybrid algorithm utilizing Principal ComponentAnalysis (PCA), Stacked Auto-Encoder (SAE), Long Short Term Memory(LSTM), and K-Nearest Neighbors (KNN) named PALKNN. Firstly, PCAremoves unwanted information from the dataset and selects essential features.Secondly, SAE is used to reduce the dimension of input data using onehotencoding so the model can be trained with better speed. Thirdly, LSTMtakes the input from SAE, where the data is sorted in ascending orderbased on the important features and generates the derived value. Finally,KNN Regressor takes information from LSTM to predict traffic flow. Theforecasting performance of the PALKNN model is investigated with OpenRoad Traffic Statistics dataset, Great Britain, UK. This paper enhanced thetraffic flow prediction for every hour of a day with a minimal error value.An extensive experimental analysis was performed on the benchmark dataset.The evaluated results indicate the significant improvement of the proposedPALKNN model over the recent approaches such as KNN, SARIMA, LogisticRegression, RNN, and LSTM in terms of root mean square error (RMSE)of 2.07%, mean square error (MSE) of 4.1%, and mean absolute error (MAE)of 2.04%.展开更多
In order to evaluate the effects of the short blade locations on the anti-cavitation performance of the splittel bladed inducer and the pump, 5 inducers with different short blade locations are designed, Cavitation si...In order to evaluate the effects of the short blade locations on the anti-cavitation performance of the splittel bladed inducer and the pump, 5 inducers with different short blade locations are designed, Cavitation simulatior and experimental tests of the pumps with these inducers are carried out. The algebraic slip mixture model in th CFX software is adopted for cavitation simulation. The results show that there is a vortex at the inlet of the indu（ er. Asymmetric cavitation on the inducer and on the impeller is observed. The analysis shows that the short blad locations have a minor effect on the internal flow field in the inducer and on the external performance of th pump, but have a significant effect on the anti-cavitation performance. It is suggested that the inducer shoul be designed appropriately. The present simulations found an optimal inducer with better anti-cavitatio performance.展开更多
In this paper we investigate the one-dimensional hyperbolic mean curvatureflow for closed plane curves. More precisely, we consider a family of closed curves F ： S1 × [0, T ） → R^2 which satisfies the followin...In this paper we investigate the one-dimensional hyperbolic mean curvatureflow for closed plane curves. More precisely, we consider a family of closed curves F ： S1 × [0, T ） → R^2 which satisfies the following evolution equation δ^2F /δt^2 （u, t） = k（u, t）N（u, t）-▽ρ（u, t）, ∨（u, t） ∈ S^1 × [0, T ） with the initial data F （u, 0） = F0（u） and δF/δt （u, 0） = f（u）N0, where k is the mean curvature and N is the unit inner normal vector of the plane curve F （u, t）, f（u） and N0 are the initial velocity and the unit inner normal vector of the initial convex closed curve F0, respectively, and ▽ρ is given by ▽ρ Δ=（δ^2F /δsδt ,δF/δt） T , in which T stands for the unit tangent vector. The above problem is an initial value problem for a system of partial differential equations for F , it can be completely reduced to an initial value problem for a single partial differential equation for its support function. The latter equation is a hyperbolic Monge-Ampere equation. Based on this, we show that there exists a class of initial velocities such that the solution of the above initial value problem exists only at a finite time interval [0, Tmax） and when t goes to Tmax, either the solution convergesto a point or shocks and other propagating discontinuities are generated. Furthermore, we also consider the hyperbolic mean curvature flow with the dissipative terms and obtain the similar equations about the support functions and the curvature of the curve. In the end, we discuss the close relationship between the hyperbolic mean curvature flow and the equations for the evolving relativistic string in the Minkowski space-time R^1,1.展开更多
为建立准确有效的空中交通短期流量预测模型,提高终端区管理效率,以进场交通流为对象进行研究。首先采用自回归移动平均(autoregressive moving average,ARMA)模型对流量时间序列进行初步线性预测,然后通过长短期记忆网络(long short te...为建立准确有效的空中交通短期流量预测模型,提高终端区管理效率,以进场交通流为对象进行研究。首先采用自回归移动平均(autoregressive moving average,ARMA)模型对流量时间序列进行初步线性预测,然后通过长短期记忆网络(long short term memory,LSTM)模型对线性预测后的残差序列进行非线性修正预测。考虑到冗余特征会降低LSTM模型预测精度的问题,采用自编码器(autoencoder,AE)模型对LSTM模型的天气以及流量特征输入进行自适应压缩优化,最后设置对比实验对ARMA-AE-LSTM模型的准确性、鲁棒性以及时效性进行验证。实验结果表明:预测绝对误差在1.3架以内的占比达到75%;LSTM模型的平均每轮迭代时间降低为1.014 s;与其他常用深度学习预测模型相比,ARMA-AE-LSTM模型的均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)以及决定系数(r-squared,R2)评价指标分别改善了45.98%~67.66%、48.56%~67.35%、5.18%~21.07%;恶劣天气影响下,ARMA-AE-LSTM模型的鲁棒性更好。由此可见,该方法能够准确有效快速的预测空中交通流量。展开更多
文摘Baosteel＇ s Slag Short Flow（BSSF） is an innovative process for steelmaking slag treatment that was developed by Baosteel. The process principles, flow-chart, parameters and component systems of the BSSF for steelmaking slag treatment are presented. Characteristics of the finished BSSF slag are summarized by analyzing the slag＇ s physical and chemical performances. Several Utilization methods for the BSSF slag are given.
文摘Traffic flow prediction in urban areas is essential in the IntelligentTransportation System (ITS). Short Term Traffic Flow (STTF) predictionimpacts traffic flow series, where an estimation of the number of vehicleswill appear during the next instance of time per hour. Precise STTF iscritical in Intelligent Transportation System. Various extinct systems aim forshort-term traffic forecasts, ensuring a good precision outcome which was asignificant task over the past few years. The main objective of this paper is topropose a new model to predict STTF for every hour of a day. In this paper,we have proposed a novel hybrid algorithm utilizing Principal ComponentAnalysis (PCA), Stacked Auto-Encoder (SAE), Long Short Term Memory(LSTM), and K-Nearest Neighbors (KNN) named PALKNN. Firstly, PCAremoves unwanted information from the dataset and selects essential features.Secondly, SAE is used to reduce the dimension of input data using onehotencoding so the model can be trained with better speed. Thirdly, LSTMtakes the input from SAE, where the data is sorted in ascending orderbased on the important features and generates the derived value. Finally,KNN Regressor takes information from LSTM to predict traffic flow. Theforecasting performance of the PALKNN model is investigated with OpenRoad Traffic Statistics dataset, Great Britain, UK. This paper enhanced thetraffic flow prediction for every hour of a day with a minimal error value.An extensive experimental analysis was performed on the benchmark dataset.The evaluated results indicate the significant improvement of the proposedPALKNN model over the recent approaches such as KNN, SARIMA, LogisticRegression, RNN, and LSTM in terms of root mean square error (RMSE)of 2.07%, mean square error (MSE) of 4.1%, and mean absolute error (MAE)of 2.04%.
基金Supported by the National Natural Science Foundation of China(51406185,51276172)the China Scholarship Council Project in 2012(201208330325)+1 种基金the Third Level 151 Talent Project in Zhejiang Provincethe Professional Leader Leading Project in 2013(lj2013005)
文摘In order to evaluate the effects of the short blade locations on the anti-cavitation performance of the splittel bladed inducer and the pump, 5 inducers with different short blade locations are designed, Cavitation simulatior and experimental tests of the pumps with these inducers are carried out. The algebraic slip mixture model in th CFX software is adopted for cavitation simulation. The results show that there is a vortex at the inlet of the indu（ er. Asymmetric cavitation on the inducer and on the impeller is observed. The analysis shows that the short blad locations have a minor effect on the internal flow field in the inducer and on the external performance of th pump, but have a significant effect on the anti-cavitation performance. It is suggested that the inducer shoul be designed appropriately. The present simulations found an optimal inducer with better anti-cavitatio performance.
基金Kong and Wang was supported in part by the NSF of China (10671124)the NCET of China (NCET-05-0390)the work of Liu was supported in part by the NSF of China
文摘In this paper we investigate the one-dimensional hyperbolic mean curvatureflow for closed plane curves. More precisely, we consider a family of closed curves F ： S1 × [0, T ） → R^2 which satisfies the following evolution equation δ^2F /δt^2 （u, t） = k（u, t）N（u, t）-▽ρ（u, t）, ∨（u, t） ∈ S^1 × [0, T ） with the initial data F （u, 0） = F0（u） and δF/δt （u, 0） = f（u）N0, where k is the mean curvature and N is the unit inner normal vector of the plane curve F （u, t）, f（u） and N0 are the initial velocity and the unit inner normal vector of the initial convex closed curve F0, respectively, and ▽ρ is given by ▽ρ Δ=（δ^2F /δsδt ,δF/δt） T , in which T stands for the unit tangent vector. The above problem is an initial value problem for a system of partial differential equations for F , it can be completely reduced to an initial value problem for a single partial differential equation for its support function. The latter equation is a hyperbolic Monge-Ampere equation. Based on this, we show that there exists a class of initial velocities such that the solution of the above initial value problem exists only at a finite time interval [0, Tmax） and when t goes to Tmax, either the solution convergesto a point or shocks and other propagating discontinuities are generated. Furthermore, we also consider the hyperbolic mean curvature flow with the dissipative terms and obtain the similar equations about the support functions and the curvature of the curve. In the end, we discuss the close relationship between the hyperbolic mean curvature flow and the equations for the evolving relativistic string in the Minkowski space-time R^1,1.
文摘为建立准确有效的空中交通短期流量预测模型,提高终端区管理效率,以进场交通流为对象进行研究。首先采用自回归移动平均(autoregressive moving average,ARMA)模型对流量时间序列进行初步线性预测,然后通过长短期记忆网络(long short term memory,LSTM)模型对线性预测后的残差序列进行非线性修正预测。考虑到冗余特征会降低LSTM模型预测精度的问题,采用自编码器(autoencoder,AE)模型对LSTM模型的天气以及流量特征输入进行自适应压缩优化,最后设置对比实验对ARMA-AE-LSTM模型的准确性、鲁棒性以及时效性进行验证。实验结果表明:预测绝对误差在1.3架以内的占比达到75%;LSTM模型的平均每轮迭代时间降低为1.014 s;与其他常用深度学习预测模型相比,ARMA-AE-LSTM模型的均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)以及决定系数(r-squared,R2)评价指标分别改善了45.98%~67.66%、48.56%~67.35%、5.18%~21.07%;恶劣天气影响下,ARMA-AE-LSTM模型的鲁棒性更好。由此可见,该方法能够准确有效快速的预测空中交通流量。
