Research On Key Technology Of Identification And Location Of Composite Voltage Sag Source With Waveform Distortion

As more and more clean energy sources such as solar and wind power are connected to the power grid,the problem of voltage sags in the power grid continues to increase.The disturbance sources of voltage sags show a compound superposition situation and become more complex,which will bring a lot of challenge to sag monitoring and control.The analysis and treatment of sag sources need to be guided by the type of sag source and the location where the sag occurs,while the traditional single sag source identification method cannot meet the requirements for the identification of composite sag sources,especially considering the identification of composite sag sources under the influence of waveform distortion,there is no mature and effective plan.At the same time,the determination of the voltage sag fault type in the power system cannot provide complete information for the management of sags and the definition of responsibilities.It increases the accurate location information of the voltage sag source and realizes the identification and location of the compound sag source,which is the voltage sag provide more comprehensive guidance on the management and prevention of the power system to ensure the long-term stable operation of the power system.Firstly,the background and significance of this thesis are described,the main sources of sag and the harm brought by them are introduced.The advantages and disadvantages of the existing algorithms for voltage sag identification and location are analyzed.In the identification of the sag source,this thesis takes the sag source waveform as the research object,eight simulation models such as short circuit fault,transformer switching,large induction motor start and short circuit fault,are constructed to explore the causes of voltage sag and compare the waveform characteristics of different types of voltage sag sources,at the same time,the wave distortion characteristics of different types of sag source wave transmitted by different types of transformers are studied.Aiming at the problem that the identification method of single sag source can not meet the requirements of the compound sag source identification,and considering that there is no mature and effective scheme for the identification of composit e sag source under the influence of waveform distortion,a new method based on CNN-XGBoost is proposed.The method uses convolutional neural network to extract voltage sag data features adaptively,effectively reducing the time of feature optimization proc ess,and applying migration learning to the field of voltage sag source identification,avoiding the problem of model training fitting due to the lack of data sets in practical engineering,and training and recognition of CNN output features through XGBoost integrated learning classifier,The accuracy of CNN-XGBoost recognition is improved.The simulation and experimental results show that the CNN-XGBoost method proposed in this thesis has a high recognition accuracy when identifying composite descent source.In the case of considering waveform distortion,the accuracy of the proposed method is higher than other methods.The accuracy of this method is not affected before and after waveform distortion,this verifies the effectiveness of this method.In view of the problem that the accuracy of voltage source location is not high only by single characteristic quantity,this thesis proposes an improved particle swarm optimization algorithm based on particle swarm optimization algorithm,and establishes a voltage sag source location method based on IPSO-SVM.The simulation results show that the accuracy of the method is higher than that of the single feature,and the accuracy of IPSO-SVM is higher than that of SVM,Random Forest,BP Neural Network,KELM and PSO-SVM.In order to further verify the effectiveness of the proposed method,this thesis builds a test platform composed of HSB1030 three-phase standard source,NI PXIE-8840 console,NI PXIE-1070 case,NI PXIE-6341 data acquisition card and Lab VIEW upper monitor.The software of virtual voltage sag source identification and positioning system is developed based on Lab VIEW,and the structure and function design of the system are given.The program realizes the functions of data acquisition,data storage,voltage sag source identification and location,and completes the test and experiment of identification module and positioning module based on simulation and test data.