The breakdown voltage plays an important role in evaluating residual life of stator insulation in generator.In this paper,we discussed BP neural network that was used to predict the breakdown voltage of stator insulat...The breakdown voltage plays an important role in evaluating residual life of stator insulation in generator.In this paper,we discussed BP neural network that was used to predict the breakdown voltage of stator insulation in generator of 300MW/18kV.At first the neural network has been trained by the samples that include the varieties of dielectric loss factor tanδ,the partial discharge parameters and breakdown voltage.Then we tried to predict the breakdown voltage of samples and stator insulations subjected to multi-stress aging by the trained neural network.We found that it's feasible and accurate to predict the voltage.This method can be applied to predict breakdown voltage of other generators which have the same insulation structure and material.展开更多
Objective To investigate the characteristic parameters employed to describe the aging extent of stator insulation of large generator and study the aging laws. Methods Multi stress aging tests of model generator sta...Objective To investigate the characteristic parameters employed to describe the aging extent of stator insulation of large generator and study the aging laws. Methods Multi stress aging tests of model generator stator bar specimens were performed and PD measurements were conducted using digital PD detector with frequency range from 40?kHz to 400?kHz at different aging stage. Results From the test results of model specimens it was found that the skewness of phase resolved PD distribution might be taken as the characterization parameters for aging extent assessment of generator insulation. Furthermore, the measurement results of actual generator stator bars showed that the method based on statistical parameters of PD distributions are prospective for aging extent assessment and residual lifetime estimation of large generator insulation. Conclusion Statistical parameters of phase resolved PD distribution was proposed for aging extent assessment of large generator insulation.展开更多
Method IEEE 841 is used to test endurance of insulation system of stators to 100% humidity at 40 ℃ for168 h. Insulation resistance after this test between phases or between phase and frame has not been lover as 5 ...Method IEEE 841 is used to test endurance of insulation system of stators to 100% humidity at 40 ℃ for168 h. Insulation resistance after this test between phases or between phase and frame has not been lover as 5 × 10^6 Ohm. Some producers of motors use this method for determining quality of impregation resin. On such test insulation resistance between phases was lover as between phase and frame. Because between phases is only wire insulation impregnating resins on insulation resistance of insulation system an impregnating resin we observe influence of type of wires and after humidity test. With diagnostic of insulation, the state is dealt. We compare our impregnation resin with competitive impregnation resin. We made test on twisted coils prepared after STN IEC from two parallel wires. In this test, we succeed in demonstrating that the main influence on insulation resistance of insulation system wire and impregnation resin has insulation of wire. Impregnation resin has influenced on data dispersion.展开更多
基金This research was supported by the Key Technology R&D Programof State Power Corporation of China During the Tenth-Five-Year Plan Period.
文摘The breakdown voltage plays an important role in evaluating residual life of stator insulation in generator.In this paper,we discussed BP neural network that was used to predict the breakdown voltage of stator insulation in generator of 300MW/18kV.At first the neural network has been trained by the samples that include the varieties of dielectric loss factor tanδ,the partial discharge parameters and breakdown voltage.Then we tried to predict the breakdown voltage of samples and stator insulations subjected to multi-stress aging by the trained neural network.We found that it's feasible and accurate to predict the voltage.This method can be applied to predict breakdown voltage of other generators which have the same insulation structure and material.
基金ThisworkwassupportedbytheNationalNaturalScienceFoundationofChina (No .5 983 72 60 )
文摘Objective To investigate the characteristic parameters employed to describe the aging extent of stator insulation of large generator and study the aging laws. Methods Multi stress aging tests of model generator stator bar specimens were performed and PD measurements were conducted using digital PD detector with frequency range from 40?kHz to 400?kHz at different aging stage. Results From the test results of model specimens it was found that the skewness of phase resolved PD distribution might be taken as the characterization parameters for aging extent assessment of generator insulation. Furthermore, the measurement results of actual generator stator bars showed that the method based on statistical parameters of PD distributions are prospective for aging extent assessment and residual lifetime estimation of large generator insulation. Conclusion Statistical parameters of phase resolved PD distribution was proposed for aging extent assessment of large generator insulation.
文摘Method IEEE 841 is used to test endurance of insulation system of stators to 100% humidity at 40 ℃ for168 h. Insulation resistance after this test between phases or between phase and frame has not been lover as 5 × 10^6 Ohm. Some producers of motors use this method for determining quality of impregation resin. On such test insulation resistance between phases was lover as between phase and frame. Because between phases is only wire insulation impregnating resins on insulation resistance of insulation system an impregnating resin we observe influence of type of wires and after humidity test. With diagnostic of insulation, the state is dealt. We compare our impregnation resin with competitive impregnation resin. We made test on twisted coils prepared after STN IEC from two parallel wires. In this test, we succeed in demonstrating that the main influence on insulation resistance of insulation system wire and impregnation resin has insulation of wire. Impregnation resin has influenced on data dispersion.
