Vertical hot ring rolling(VHRR) process has the characteristics of nonlinearity,time-variation and being susceptible to disturbance.Furthermore,the ring's growth is quite fast within a short time,and the rolled ri...Vertical hot ring rolling(VHRR) process has the characteristics of nonlinearity,time-variation and being susceptible to disturbance.Furthermore,the ring's growth is quite fast within a short time,and the rolled ring's position is asymmetrical.All of these cause that the ring's dimensions cannot be measured directly.Through analyzing the relationships among the dimensions of ring blanks,the positions of rolls and the ring's inner and outer diameter,the soft measurement model of ring's dimensions is established based on the radial basis function neural network(RBFNN).A mass of data samples are obtained from VHRR finite element(FE) simulations to train and test the soft measurement NN model,and the model's structure parameters are deduced and optimized by genetic algorithm(GA).Finally,the soft measurement system of ring's dimensions is established and validated by the VHRR experiments.The ring's dimensions were measured artificially and calculated by the soft measurement NN model.The results show that the calculation values of GA-RBFNN model are close to the artificial measurement data.In addition,the calculation accuracy of GA-RBFNN model is higher than that of RBFNN model.The research results suggest that the soft measurement NN model has high precision and flexibility.The research can provide practical methods and theoretical guidance for the accurate measurement of VHRR process.展开更多
A computationally efficient soft-output detector with lattice-reduction （LR） for the multiple-input multiple-output （MIMO） systems is proposed. In the proposed scheme, the sorted QR de- composition is applied on t...A computationally efficient soft-output detector with lattice-reduction （LR） for the multiple-input multiple-output （MIMO） systems is proposed. In the proposed scheme, the sorted QR de- composition is applied on the lattice-reduced equivalent channel to obtain the tree structure. With the aid of the boundary control, the stack algorithm searches a small part of the whole search tree to generate a handful of candidate lists in the reduced lattice. The proposed soft-output algorithm achieves near-optimal perfor- mance in a coded MIMO system and the associated computational complexity is substantially lower than that of previously proposed methods.展开更多
【目的】监控加热卷烟雾化基材生产中的质量稳定性,建立快速、同时测定加热卷烟雾化基材中水分、丙二醇、甘油和烟碱含量的近红外分析方法。【方法】采用自举软收缩(Bootstrapping soft shrinkage approach,BOSS)变量选择方法筛选特征...【目的】监控加热卷烟雾化基材生产中的质量稳定性,建立快速、同时测定加热卷烟雾化基材中水分、丙二醇、甘油和烟碱含量的近红外分析方法。【方法】采用自举软收缩(Bootstrapping soft shrinkage approach,BOSS)变量选择方法筛选特征波长变量,结合偏最小二乘法(Partial least squares,PLS)分别建立片状、丝状加热卷烟雾化基材中4种化学成分近红外含量预测模型,并与其他变量选择方法进行对比。【结果】(1)基于BOSS算法优选波长变量所建立的模型预测精度最优,模型R2均大于0.95,RMSECV(Root mean square error of cross-validation,交叉验证均方根误差)均小于0.7%。(2)水分、丙二醇、甘油和烟碱的RMSEP(Root mean square error of cross-prediction,交叉预测均方根误差)均小于0.75%,且验证集RMSEP与建模集RMSECV值相近,各模型均具有较好的预测准确性。(3)各成分模型RSD(Relative standard deviation,相对标准偏差)均小于2%,模型重现性较好。展开更多
基金Project(51205299)supported by the National Natural Science Foundation of ChinaProject(2015M582643)supported by the China Postdoctoral Science Foundation+2 种基金Project(2014BAA008)supported by the Science and Technology Support Program of Hubei Province,ChinaProject(2014-IV-144)supported by the Fundamental Research Funds for the Central Universities of ChinaProject(2012AAA07-01)supported by the Major Science and Technology Achievements Transformation&Industrialization Program of Hubei Province,China
文摘Vertical hot ring rolling(VHRR) process has the characteristics of nonlinearity,time-variation and being susceptible to disturbance.Furthermore,the ring's growth is quite fast within a short time,and the rolled ring's position is asymmetrical.All of these cause that the ring's dimensions cannot be measured directly.Through analyzing the relationships among the dimensions of ring blanks,the positions of rolls and the ring's inner and outer diameter,the soft measurement model of ring's dimensions is established based on the radial basis function neural network(RBFNN).A mass of data samples are obtained from VHRR finite element(FE) simulations to train and test the soft measurement NN model,and the model's structure parameters are deduced and optimized by genetic algorithm(GA).Finally,the soft measurement system of ring's dimensions is established and validated by the VHRR experiments.The ring's dimensions were measured artificially and calculated by the soft measurement NN model.The results show that the calculation values of GA-RBFNN model are close to the artificial measurement data.In addition,the calculation accuracy of GA-RBFNN model is higher than that of RBFNN model.The research results suggest that the soft measurement NN model has high precision and flexibility.The research can provide practical methods and theoretical guidance for the accurate measurement of VHRR process.
文摘A computationally efficient soft-output detector with lattice-reduction （LR） for the multiple-input multiple-output （MIMO） systems is proposed. In the proposed scheme, the sorted QR de- composition is applied on the lattice-reduced equivalent channel to obtain the tree structure. With the aid of the boundary control, the stack algorithm searches a small part of the whole search tree to generate a handful of candidate lists in the reduced lattice. The proposed soft-output algorithm achieves near-optimal perfor- mance in a coded MIMO system and the associated computational complexity is substantially lower than that of previously proposed methods.
文摘【目的】监控加热卷烟雾化基材生产中的质量稳定性,建立快速、同时测定加热卷烟雾化基材中水分、丙二醇、甘油和烟碱含量的近红外分析方法。【方法】采用自举软收缩(Bootstrapping soft shrinkage approach,BOSS)变量选择方法筛选特征波长变量,结合偏最小二乘法(Partial least squares,PLS)分别建立片状、丝状加热卷烟雾化基材中4种化学成分近红外含量预测模型,并与其他变量选择方法进行对比。【结果】(1)基于BOSS算法优选波长变量所建立的模型预测精度最优,模型R2均大于0.95,RMSECV(Root mean square error of cross-validation,交叉验证均方根误差)均小于0.7%。(2)水分、丙二醇、甘油和烟碱的RMSEP(Root mean square error of cross-prediction,交叉预测均方根误差)均小于0.75%,且验证集RMSEP与建模集RMSECV值相近,各模型均具有较好的预测准确性。(3)各成分模型RSD(Relative standard deviation,相对标准偏差)均小于2%,模型重现性较好。
