As a production quality index of hematite grinding process,particle size(PS)is hard to be measured in real time.To achieve the PS estimation,this paper proposes a novel data driven model of PS using stochastic configu...As a production quality index of hematite grinding process,particle size(PS)is hard to be measured in real time.To achieve the PS estimation,this paper proposes a novel data driven model of PS using stochastic configuration network(SCN)with robust technique,namely,robust SCN(RSCN).Firstly,this paper proves the universal approximation property of RSCN with weighted least squares technique.Secondly,three robust algorithms are presented by employing M-estimation with Huber loss function,M-estimation with interquartile range(IQR)and nonparametric kernel density estimation(NKDE)function respectively to set the penalty weight.Comparison experiments are first carried out based on the UCI standard data sets to verify the effectiveness of these methods,and then the data-driven PS model based on the robust algorithms are established and verified.Experimental results show that the RSCN has an excellent performance for the PS estimation.展开更多
The evolution of chaotic state of Iarenz system on the fa- miliar parameter space cabit is analyzed. Based on the principle of chaos suppression with ntmrestmaat parametric drive, the trodel of detecting weak periodic...The evolution of chaotic state of Iarenz system on the fa- miliar parameter space cabit is analyzed. Based on the principle of chaos suppression with ntmrestmaat parametric drive, the trodel of detecting weak periodic signals in strong noise is Imilt. According to the parametric equivalent relationship obtained using averaging method and rmtmmlization method, the critical values of detection parameters are determined, which lead to a sudden change of system dynamical behavior from periodic orbit to stable equilibritma point. Sinmlation results show that weak periodic signals in strong noise can be detected acomately with the proposed system. The method can obtain aoawate rane of parameter threshold through tlxxtetical analysis, and the detection criterion is rather simple, which is more convenieat for automatic detection.展开更多
Robust flutter analysis considering model uncertain parameters is very important in theory and engineering applications.Modern robust flutter solution based on structured singular value subject to real parametric unce...Robust flutter analysis considering model uncertain parameters is very important in theory and engineering applications.Modern robust flutter solution based on structured singular value subject to real parametric uncertainties may become difficult because the discontinuity and increasing complexity in real mu analysis.It is crucial to solve the worst-case flutter speed accurately and efficiently for real parametric uncertainties.In this paper,robust flutter analysis is formulated as a nonlinear programming problem.With proper nonlinear programming technique and classical flutter analysis method,the worst-case parametric perturbations and the robust flutter solution will be captured by optimization approach.In the derived nonlinear programming problem,the parametric uncertainties are taken as design variables bounded with perturbed intervals,while the flutter speed is selected as the objective function.This model is optimized by the genetic algorithm with promising global optimum performance.The present approach avoids calculating purely real mu and makes robust flutter analysis a plain job.It is illustrated by a special test case that the robust flutter results coincide well with the exhaustive method.It is also demonstrated that the present method can solve the match-point robust flutter solution under constant Mach number accurately and efficiently.This method is implemented in problem with more uncertain parameters and asymmetric perturbation interval.展开更多
Predicting the future course of an epidemic depends on being able to estimate the current numbers of infected individuals.However,while back-projection techniques allow reliable estimation of the numbers of infected i...Predicting the future course of an epidemic depends on being able to estimate the current numbers of infected individuals.However,while back-projection techniques allow reliable estimation of the numbers of infected individuals in the more distant past,they are less reliable in the recent past.We propose two new nonparametric methods to estimate the unobserved numbers of infected individuals in the recent past in an epidemic.The proposed methods are noniterative,easily computed and asymptotically normal with simple variance formulas.Simulations show that the proposed methods are much more robust and accurate than the existing back projection method,especially for the recent past,which is our primary interest.We apply the proposed methods to the 2003 Severe Acute Respiratory Syndorme(SARS) epidemic in Hong Kong.展开更多
基金Projects(61603393,61741318)supported in part by the National Natural Science Foundation of ChinaProject(BK20160275)supported by the Natural Science Foundation of Jiangsu Province,China+1 种基金Project(2015M581885)supported by the Postdoctoral Science Foundation of ChinaProject(PAL-N201706)supported by the Open Project Foundation of State Key Laboratory of Synthetical Automation for Process Industries of Northeastern University,China
文摘As a production quality index of hematite grinding process,particle size(PS)is hard to be measured in real time.To achieve the PS estimation,this paper proposes a novel data driven model of PS using stochastic configuration network(SCN)with robust technique,namely,robust SCN(RSCN).Firstly,this paper proves the universal approximation property of RSCN with weighted least squares technique.Secondly,three robust algorithms are presented by employing M-estimation with Huber loss function,M-estimation with interquartile range(IQR)and nonparametric kernel density estimation(NKDE)function respectively to set the penalty weight.Comparison experiments are first carried out based on the UCI standard data sets to verify the effectiveness of these methods,and then the data-driven PS model based on the robust algorithms are established and verified.Experimental results show that the RSCN has an excellent performance for the PS estimation.
文摘The evolution of chaotic state of Iarenz system on the fa- miliar parameter space cabit is analyzed. Based on the principle of chaos suppression with ntmrestmaat parametric drive, the trodel of detecting weak periodic signals in strong noise is Imilt. According to the parametric equivalent relationship obtained using averaging method and rmtmmlization method, the critical values of detection parameters are determined, which lead to a sudden change of system dynamical behavior from periodic orbit to stable equilibritma point. Sinmlation results show that weak periodic signals in strong noise can be detected acomately with the proposed system. The method can obtain aoawate rane of parameter threshold through tlxxtetical analysis, and the detection criterion is rather simple, which is more convenieat for automatic detection.
基金supported by the National Natural Science Foundation of China (Grant Nos. 11072198 and 11102162) "111" Project of China(Grant No. B07050)
文摘Robust flutter analysis considering model uncertain parameters is very important in theory and engineering applications.Modern robust flutter solution based on structured singular value subject to real parametric uncertainties may become difficult because the discontinuity and increasing complexity in real mu analysis.It is crucial to solve the worst-case flutter speed accurately and efficiently for real parametric uncertainties.In this paper,robust flutter analysis is formulated as a nonlinear programming problem.With proper nonlinear programming technique and classical flutter analysis method,the worst-case parametric perturbations and the robust flutter solution will be captured by optimization approach.In the derived nonlinear programming problem,the parametric uncertainties are taken as design variables bounded with perturbed intervals,while the flutter speed is selected as the objective function.This model is optimized by the genetic algorithm with promising global optimum performance.The present approach avoids calculating purely real mu and makes robust flutter analysis a plain job.It is illustrated by a special test case that the robust flutter results coincide well with the exhaustive method.It is also demonstrated that the present method can solve the match-point robust flutter solution under constant Mach number accurately and efficiently.This method is implemented in problem with more uncertain parameters and asymmetric perturbation interval.
基金supported in part by National Natural Science Foundation of China(Grant Nos. 10771148,11071197)supported by an RGC grant,the Chief Executive Community Project and Hong Kong Jockey Club Charities Trust
文摘Predicting the future course of an epidemic depends on being able to estimate the current numbers of infected individuals.However,while back-projection techniques allow reliable estimation of the numbers of infected individuals in the more distant past,they are less reliable in the recent past.We propose two new nonparametric methods to estimate the unobserved numbers of infected individuals in the recent past in an epidemic.The proposed methods are noniterative,easily computed and asymptotically normal with simple variance formulas.Simulations show that the proposed methods are much more robust and accurate than the existing back projection method,especially for the recent past,which is our primary interest.We apply the proposed methods to the 2003 Severe Acute Respiratory Syndorme(SARS) epidemic in Hong Kong.
