Pollution flashover accidents occur frequently in railway OCS in saline-alkali areas.To accurately predict the pollution flashover voltage of insulators,a pollution flashover warning should be made in advance.Accordin...Pollution flashover accidents occur frequently in railway OCS in saline-alkali areas.To accurately predict the pollution flashover voltage of insulators,a pollution flashover warning should be made in advance.According to the operating environment of insulators along the Qinghai-Tibet railway,the pollution flashover experiments were designed for the cantilever composite insulator FQBG-25/12.Through the experiments,the flashover voltage under the influence of soluble contaminant density(SCD)of different pollution components,non-soluble deposit density(NSDD),temperature(T),and atmospheric pressure(P)was obtained.On this basis,the GA-BP neural network prediction model was established.P,SCD,NSDD,CaSO_(4) mass fraction(w(CaSO_(4))),and T were taken as input parameters,50%flashover voltage(U_(50%))of the insulator was taken as output parameters.The results showed that the prediction deviation was less than 10%,which meets the basic engineering requirements.The results could not only provide early warning for the anti-pollution flashover work of the railway power supply department,but also be used as an auxiliary contrast to verify the accuracy of the results of the experiments,and provide a theoretical basis for the classification of pollution levels in different regions.展开更多
In view of the limitations in the prediction of pollution flashover voltage by least squares regression, a method to predict pollution flashover voltage by robust regression is proposed. According to testing voltage a...In view of the limitations in the prediction of pollution flashover voltage by least squares regression, a method to predict pollution flashover voltage by robust regression is proposed. According to testing voltage and the data of salt deposit density (ρSDD ) and non-soluble deposit density (ρNSDD ), the regression coefficient is solved by a complex weighting least square iteration algorithm. In iterative calculations, the weight function is adopted, in which the weight coefficient is the function of the residual error of last iteration to weaken the influence of singular values on the regression coefficient. The characteristic exponent denoting ρSDD influence and characteristic exponent denoting ρNSDD influence are mapped by the regression coefficient, and thus the pollution flashover voltage of insulators can be predicted. Through the comparison of test results, robust regression results and least squares regression results, the effectiveness of the proposed robust regression-based forecasting method is verified.展开更多
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
Samples of fog water collected in the area of Guangzhou during February, March and April of 2005 are used in this work to study the chemical composition of fog water in polluting fog there. Three typical episodes of p...Samples of fog water collected in the area of Guangzhou during February, March and April of 2005 are used in this work to study the chemical composition of fog water in polluting fog there. Three typical episodes of polluting fog are analyzed in terms of ionic concentration and their possible sources. It is found that the concentration of various ions in fog water is much higher than those in rainwater. Fog not only blocks visual range but contains liquid particles that result in high degree of pollution and are very harmful to human health. SO4= is the anion with the highest concentration in fog water, followed by NO3-. For the cation, Ca++ and NH4+ are the highest in concentration. It is then known that rainwater is more acidic than fog water, indicating that ionic concentration of fog water is much higher than that of rainwater, but there are much more buffering materials in fog water, like NH4+ and Ca++. There is significant enrichment of Ca++, SO4=, and Mg++ in fog water. In the Guangzhou area, fog water from polluting fog is mainly influenced continental environment and human activity. The episodes of serious fog pollution during the time have immediate relationships with the presence of abundant water vapor and large amount of polluting aerosol particles.展开更多
The flashover of insulator strings occurring at normal working voltages undercontaminated/polluted conditions, obviously deserves serious consideration. Though much researchhas been gone into pollution-induced flashov...The flashover of insulator strings occurring at normal working voltages undercontaminated/polluted conditions, obviously deserves serious consideration. Though much researchhas been gone into pollution-induced flashover phenomena but grey areas still exist in ourknowledge. In the present experimental study the breakdown (flashover) voltages across gaps oninsulator top surfaces and gaps between sheds (on the underside of an insulator), also the flashoverstudies on a single unit and a 3-unit insulator strings were carried out. An attempt has been madeto correlate the values obtained for all the cases. From the present investigation it was found thatresistance measurement of individual units of a polluted 3-unit string before and after flashoverindicates that strongly differing resistances could be the cause of flashover of ceramic discinsulator strings.展开更多
基金Supported by the National Natural Science Foundation of China(51767014)the Scientific and Technological Research and Development Program of the China Railway(2017J010-C/2017).
文摘Pollution flashover accidents occur frequently in railway OCS in saline-alkali areas.To accurately predict the pollution flashover voltage of insulators,a pollution flashover warning should be made in advance.According to the operating environment of insulators along the Qinghai-Tibet railway,the pollution flashover experiments were designed for the cantilever composite insulator FQBG-25/12.Through the experiments,the flashover voltage under the influence of soluble contaminant density(SCD)of different pollution components,non-soluble deposit density(NSDD),temperature(T),and atmospheric pressure(P)was obtained.On this basis,the GA-BP neural network prediction model was established.P,SCD,NSDD,CaSO_(4) mass fraction(w(CaSO_(4))),and T were taken as input parameters,50%flashover voltage(U_(50%))of the insulator was taken as output parameters.The results showed that the prediction deviation was less than 10%,which meets the basic engineering requirements.The results could not only provide early warning for the anti-pollution flashover work of the railway power supply department,but also be used as an auxiliary contrast to verify the accuracy of the results of the experiments,and provide a theoretical basis for the classification of pollution levels in different regions.
基金supported by Key Scientific and Technical Funds of Zhejiang Electric Power Corporation under Grant ZDK069-2010
文摘In view of the limitations in the prediction of pollution flashover voltage by least squares regression, a method to predict pollution flashover voltage by robust regression is proposed. According to testing voltage and the data of salt deposit density (ρSDD ) and non-soluble deposit density (ρNSDD ), the regression coefficient is solved by a complex weighting least square iteration algorithm. In iterative calculations, the weight function is adopted, in which the weight coefficient is the function of the residual error of last iteration to weaken the influence of singular values on the regression coefficient. The characteristic exponent denoting ρSDD influence and characteristic exponent denoting ρNSDD influence are mapped by the regression coefficient, and thus the pollution flashover voltage of insulators can be predicted. Through the comparison of test results, robust regression results and least squares regression results, the effectiveness of the proposed robust regression-based forecasting method is verified.
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Natural Science Foundation of China (40375002, 40418008, 40775011, U0733004)Project 863 (2006AA06A306, 2006AA06A308)+3 种基金National Basic Research Program of China (973 Program):2005CB422207Natural Science Foundation of Guangdong Province (033029)Project of Key Scientific Research of Guangdong Province (2004A30401002, 2005B32601011)Project of Applied Fundamental Research of Guangzhou (2004J1-0021)
文摘Samples of fog water collected in the area of Guangzhou during February, March and April of 2005 are used in this work to study the chemical composition of fog water in polluting fog there. Three typical episodes of polluting fog are analyzed in terms of ionic concentration and their possible sources. It is found that the concentration of various ions in fog water is much higher than those in rainwater. Fog not only blocks visual range but contains liquid particles that result in high degree of pollution and are very harmful to human health. SO4= is the anion with the highest concentration in fog water, followed by NO3-. For the cation, Ca++ and NH4+ are the highest in concentration. It is then known that rainwater is more acidic than fog water, indicating that ionic concentration of fog water is much higher than that of rainwater, but there are much more buffering materials in fog water, like NH4+ and Ca++. There is significant enrichment of Ca++, SO4=, and Mg++ in fog water. In the Guangzhou area, fog water from polluting fog is mainly influenced continental environment and human activity. The episodes of serious fog pollution during the time have immediate relationships with the presence of abundant water vapor and large amount of polluting aerosol particles.
文摘The flashover of insulator strings occurring at normal working voltages undercontaminated/polluted conditions, obviously deserves serious consideration. Though much researchhas been gone into pollution-induced flashover phenomena but grey areas still exist in ourknowledge. In the present experimental study the breakdown (flashover) voltages across gaps oninsulator top surfaces and gaps between sheds (on the underside of an insulator), also the flashoverstudies on a single unit and a 3-unit insulator strings were carried out. An attempt has been madeto correlate the values obtained for all the cases. From the present investigation it was found thatresistance measurement of individual units of a polluted 3-unit string before and after flashoverindicates that strongly differing resistances could be the cause of flashover of ceramic discinsulator strings.
