Synchronous generators are important components of power systems and are necessary to maintain its normal and stable operation.To perform the fault diagnosis of mild inter-turn short circuit in the excitation winding ...Synchronous generators are important components of power systems and are necessary to maintain its normal and stable operation.To perform the fault diagnosis of mild inter-turn short circuit in the excitation winding of a synchronous generator,a gate recurrent unit-convolutional neural network(GRU-CNN)model whose structural parameters were determined by improved particle swarm optimization(IPSO)is proposed.The outputs of the model are the excitation current and reactive power.The total offset distance,which is the fusion of the offset distance of the excitation current and offset distance of the reactive power,was selected as the fault judgment criterion.The fusion weights of the excitation current and reactive power were determined using the anti-entropy weighting method.The fault-warning threshold and fault-warning ratio were set according to the normal total offset distance,and the fault warning time was set according to the actual situation.The fault-warning time and fault-warning ratio were used to avoid misdiagnosis.The proposed method was verified experimentally.展开更多
Due to the harsh actual operating environment of the permanent magnet wind turbine,it is easy to break down and difficult to monitor.Therefore,the electromagnetic characteristics identification of major fault types of...Due to the harsh actual operating environment of the permanent magnet wind turbine,it is easy to break down and difficult to monitor.Therefore,the electromagnetic characteristics identification of major fault types of large-scale permanent magnet wind turbines is studied in this paper.The typical faults of rotor eccentricity,stator winding short circuit and permanent magnet demagnetization of permanent magnet wind turbines are analyzed theoretically.The wavelet analysis algorithm is used to decompose and reconstruct the abnormal electromagnetic signal waveform band,and the characteristic frequency of the electromagnetic signal is obtained when the fault occurs.In order to verify the effectiveness of the proposed method,a 3.680MW permanent magnet wind turbine was taken as the research object.Its physical simulation model was established,and an external circuit was built to carry out field co-simulation.The results show that the motor fault type can be determined by detecting the change rule of fault characteristic frequency in the spectrum diagram,and the electromagnetic characteristic analysis can be applied to the early monitoring of the permanent magnet wind turbine fault.展开更多
文摘Synchronous generators are important components of power systems and are necessary to maintain its normal and stable operation.To perform the fault diagnosis of mild inter-turn short circuit in the excitation winding of a synchronous generator,a gate recurrent unit-convolutional neural network(GRU-CNN)model whose structural parameters were determined by improved particle swarm optimization(IPSO)is proposed.The outputs of the model are the excitation current and reactive power.The total offset distance,which is the fusion of the offset distance of the excitation current and offset distance of the reactive power,was selected as the fault judgment criterion.The fusion weights of the excitation current and reactive power were determined using the anti-entropy weighting method.The fault-warning threshold and fault-warning ratio were set according to the normal total offset distance,and the fault warning time was set according to the actual situation.The fault-warning time and fault-warning ratio were used to avoid misdiagnosis.The proposed method was verified experimentally.
基金supported by the National Natural Science Foundation of China(U22A20215 and 51537007)the Natural Science Foundation of LiaoNing Province(2021-YQ-09).
文摘Due to the harsh actual operating environment of the permanent magnet wind turbine,it is easy to break down and difficult to monitor.Therefore,the electromagnetic characteristics identification of major fault types of large-scale permanent magnet wind turbines is studied in this paper.The typical faults of rotor eccentricity,stator winding short circuit and permanent magnet demagnetization of permanent magnet wind turbines are analyzed theoretically.The wavelet analysis algorithm is used to decompose and reconstruct the abnormal electromagnetic signal waveform band,and the characteristic frequency of the electromagnetic signal is obtained when the fault occurs.In order to verify the effectiveness of the proposed method,a 3.680MW permanent magnet wind turbine was taken as the research object.Its physical simulation model was established,and an external circuit was built to carry out field co-simulation.The results show that the motor fault type can be determined by detecting the change rule of fault characteristic frequency in the spectrum diagram,and the electromagnetic characteristic analysis can be applied to the early monitoring of the permanent magnet wind turbine fault.
