Conventional principal component analysis(PCA) can obtain low-dimensional representations of original data space, but the selection of principal components(PCs) based on variance is subjective, which may lead to infor...Conventional principal component analysis(PCA) can obtain low-dimensional representations of original data space, but the selection of principal components(PCs) based on variance is subjective, which may lead to information loss and poor monitoring performance. To address dimension reduction and information preservation simultaneously, this paper proposes a novel PC selection scheme named full variable expression. On the basis of the proposed relevance of variables with each principal component, key principal components can be determined.All the key principal components serve as a low-dimensional representation of the entire original variables, preserving the information of original data space without information loss. A squared Mahalanobis distance, which is introduced as the monitoring statistic, is calculated directly in the key principal component space for fault detection. To test the modeling and monitoring performance of the proposed method, a numerical example and the Tennessee Eastman benchmark are used.展开更多
In the last century, there has been a significant development in the evaluation of methods to predict ground movement due to underground extraction. Some remarkable developments in three-dimensional computational meth...In the last century, there has been a significant development in the evaluation of methods to predict ground movement due to underground extraction. Some remarkable developments in three-dimensional computational methods have been supported in civil engineering, subsidence engineering and mining engineering practice. However, ground movement problem due to mining extraction sequence is effectively four dimensional （4D）. A rational prediction is getting more and more important for long-term underground mining planning. Hence, computer-based analytical methods that realistically simulate spatially distributed time-dependent ground movement process are needed for the reliable long-term underground mining planning to minimize the surface environmental damages. In this research, a new computational system is developed to simulate four-dimensional （4D） ground movement by combining a stochastic medium theory, Knothe time-delay model and geographic information system （GIS） technology. All the calculations are implemented by a computational program, in which the components of GIS are used to fulfill the spatial-temporal analysis model. In this paper a tight coupling strategy based on component object model of GIS technology is used to overcome the problems of complex three-dimensional extraction model and spatial data integration. Moreover, the implementation of computational of the interfaces of the developed tool is described. The GIS based developed tool is validated by two study cases. The developed computational tool and models are achieved within the GIS system so the effective and efficient calculation methodology can be obtained, so the simulation problems of 4D ground movement due to underground mining extraction sequence can be solved by implementation of the developed tool in GIS.展开更多
A noval molecular structural expression method,three-dimensional vector of atomic interac-tion field(3D-VAIF),has been newly developed based on electrostatic and steric interaction between different types of atoms.Fea...A noval molecular structural expression method,three-dimensional vector of atomic interac-tion field(3D-VAIF),has been newly developed based on electrostatic and steric interaction between different types of atoms.Feature descriptors of single amino acid,i.e.principal component scores of struc-tural information for amino acids(SSIA),are obtained through calculation of structural information of 20 coded amino acids using principal component analy-sis(PCA)method,and the strict tests are performed on the property of SSIA by three quantitative struc-ture-activity relationships(QSARs)/quantitative se-quence-activity models(QSAMs)models of 58 ngio-tensin-converting enzymes(ACE),48 bitter tasting thresholds(BTT)and 31 bradykinin potentiating pentapeptides(BPP).Cumulative multiple correlation coefficients(Rc2um)are 0.789,0.856 and 0.838;and corresponding cross-validated correlation coefficients(QL2OO)are 0.773,0.837 and 0.815,respectively.Good results indicate that SSIA are better than tradi-tional descriptors of amino acid in quantitative se-quence-activity relationships of peptide analogues.展开更多
基金Supported by the National Natural Science Foundation of China(No.61374140)Shanghai Pujiang Program(Project No.12PJ1402200)
文摘Conventional principal component analysis(PCA) can obtain low-dimensional representations of original data space, but the selection of principal components(PCs) based on variance is subjective, which may lead to information loss and poor monitoring performance. To address dimension reduction and information preservation simultaneously, this paper proposes a novel PC selection scheme named full variable expression. On the basis of the proposed relevance of variables with each principal component, key principal components can be determined.All the key principal components serve as a low-dimensional representation of the entire original variables, preserving the information of original data space without information loss. A squared Mahalanobis distance, which is introduced as the monitoring statistic, is calculated directly in the key principal component space for fault detection. To test the modeling and monitoring performance of the proposed method, a numerical example and the Tennessee Eastman benchmark are used.
文摘In the last century, there has been a significant development in the evaluation of methods to predict ground movement due to underground extraction. Some remarkable developments in three-dimensional computational methods have been supported in civil engineering, subsidence engineering and mining engineering practice. However, ground movement problem due to mining extraction sequence is effectively four dimensional （4D）. A rational prediction is getting more and more important for long-term underground mining planning. Hence, computer-based analytical methods that realistically simulate spatially distributed time-dependent ground movement process are needed for the reliable long-term underground mining planning to minimize the surface environmental damages. In this research, a new computational system is developed to simulate four-dimensional （4D） ground movement by combining a stochastic medium theory, Knothe time-delay model and geographic information system （GIS） technology. All the calculations are implemented by a computational program, in which the components of GIS are used to fulfill the spatial-temporal analysis model. In this paper a tight coupling strategy based on component object model of GIS technology is used to overcome the problems of complex three-dimensional extraction model and spatial data integration. Moreover, the implementation of computational of the interfaces of the developed tool is described. The GIS based developed tool is validated by two study cases. The developed computational tool and models are achieved within the GIS system so the effective and efficient calculation methodology can be obtained, so the simulation problems of 4D ground movement due to underground mining extraction sequence can be solved by implementation of the developed tool in GIS.
基金This work was supported by Fok-Yingtung Educational Foundation(Grant No.98-7-6)Na-tional Chunhui Project Foundation(Grant No.99-4-4+37)+1 种基金Chongqing Applied Fundamental Science Fund(Grant No.01-3-6)Chongqing University Innovation Foundation of Science and Technology(Grant No.03-5-6+04-9-1).
文摘A noval molecular structural expression method,three-dimensional vector of atomic interac-tion field(3D-VAIF),has been newly developed based on electrostatic and steric interaction between different types of atoms.Feature descriptors of single amino acid,i.e.principal component scores of struc-tural information for amino acids(SSIA),are obtained through calculation of structural information of 20 coded amino acids using principal component analy-sis(PCA)method,and the strict tests are performed on the property of SSIA by three quantitative struc-ture-activity relationships(QSARs)/quantitative se-quence-activity models(QSAMs)models of 58 ngio-tensin-converting enzymes(ACE),48 bitter tasting thresholds(BTT)and 31 bradykinin potentiating pentapeptides(BPP).Cumulative multiple correlation coefficients(Rc2um)are 0.789,0.856 and 0.838;and corresponding cross-validated correlation coefficients(QL2OO)are 0.773,0.837 and 0.815,respectively.Good results indicate that SSIA are better than tradi-tional descriptors of amino acid in quantitative se-quence-activity relationships of peptide analogues.
