LS-SVM （least squares support vector machines） are a class of kemel machines emphasizing on primal-dual aspects in a constrained optimization framework. LS-SVMs aim at extending methodologies typical of classical su...LS-SVM （least squares support vector machines） are a class of kemel machines emphasizing on primal-dual aspects in a constrained optimization framework. LS-SVMs aim at extending methodologies typical of classical support vector machines for problems beyond classification and regression. This paper describes a methodology that was developed for the prediction of the critical flashover voltage of polluted insulators by using a LS-SVM. The methodology uses as input variables characteristics of the insulator such as diameter, height, creepage distance, form factor and equivalent salt deposit density. The estimation offlashover performance of polluted insulators is based on field experience and laboratory tests are invaluable as they significantly reduce the time and labour involved in insulators design and selection. The majority of the variables to be predicted are dependent upon several independent variables. The results from this work are useful to predict the contamination severity, critical flashover voltage as a function of contamination severity, arc length, and especially to predict the flashover voltage. The validity of the approach was examined by testing several insulators with different geometries. Moreover, the performance of the proposed approach with other intelligence method based on ANN （artificial neural networks） is compared. It can be concluded that the LS-SVM approach has better generalization ability that assist the measurement and monitoring of contamination severity, flashover voltage and leakage current.展开更多
This contribution starts with the discussion on the classification of energy, and then the behaviors of various thermodynamic processes are analyzed, accompanying with the comparison of the adiabatic compression proce...This contribution starts with the discussion on the classification of energy, and then the behaviors of various thermodynamic processes are analyzed, accompanying with the comparison of the adiabatic compression process of an ideal gas and an elastic rod. All these analyses show that the internal energy of ideal gases exhibits the duality of thermal energy–mechanical energy, that is,the internal energy acts as the thermal energy during the isochoric process, while the internal energy acts as the mechanical energy during the isentropic process. Such behavior of the internal energy is quite different from other types of energy during the energy conversion process because the internal energy of ideal gases exhibits the duality of thermal energy–mechanical energy. Because of this duality, the internal energy of ideal gas is proposed to be refered to as thermodynamic energy rather than thermal energy as indicated in some literature, although it consists of kinetics of the microscopic random motion of particles and can be expressed as the function of temperature only.展开更多
文摘LS-SVM （least squares support vector machines） are a class of kemel machines emphasizing on primal-dual aspects in a constrained optimization framework. LS-SVMs aim at extending methodologies typical of classical support vector machines for problems beyond classification and regression. This paper describes a methodology that was developed for the prediction of the critical flashover voltage of polluted insulators by using a LS-SVM. The methodology uses as input variables characteristics of the insulator such as diameter, height, creepage distance, form factor and equivalent salt deposit density. The estimation offlashover performance of polluted insulators is based on field experience and laboratory tests are invaluable as they significantly reduce the time and labour involved in insulators design and selection. The majority of the variables to be predicted are dependent upon several independent variables. The results from this work are useful to predict the contamination severity, critical flashover voltage as a function of contamination severity, arc length, and especially to predict the flashover voltage. The validity of the approach was examined by testing several insulators with different geometries. Moreover, the performance of the proposed approach with other intelligence method based on ANN （artificial neural networks） is compared. It can be concluded that the LS-SVM approach has better generalization ability that assist the measurement and monitoring of contamination severity, flashover voltage and leakage current.
基金supported by the National Natural Science Foundation of China(51136001 and 51356001)Tsinghua University Initiative Scientific Research Program and Science Fund for Creative Research Groups(51321002)
文摘This contribution starts with the discussion on the classification of energy, and then the behaviors of various thermodynamic processes are analyzed, accompanying with the comparison of the adiabatic compression process of an ideal gas and an elastic rod. All these analyses show that the internal energy of ideal gases exhibits the duality of thermal energy–mechanical energy, that is,the internal energy acts as the thermal energy during the isochoric process, while the internal energy acts as the mechanical energy during the isentropic process. Such behavior of the internal energy is quite different from other types of energy during the energy conversion process because the internal energy of ideal gases exhibits the duality of thermal energy–mechanical energy. Because of this duality, the internal energy of ideal gas is proposed to be refered to as thermodynamic energy rather than thermal energy as indicated in some literature, although it consists of kinetics of the microscopic random motion of particles and can be expressed as the function of temperature only.
