Fault Analysis Of Transmission Line Based On RPROP Neural Network

With the development of national economy and power network,the reliability of the power supply is more and more attentive,the transmission line as the important component of power network,its operation directly affects the reliability of the whole power network.Most transmission lines are directly exposed to the natural environment,so they are the easiest part of the failure of power system.When the fault occurs,the relay protection device correct action is on the premise that the system can first accurately and quickly identify the fault phase line.In view of this,this thesis presents a transmission line fault type identification method based on RPROP neural network and wavelet analysis theory,in order to verify the feasibility of RPROP neural network and wavelet analysis theory in fault diagnosis and relay protection of transmission lines,and improving the accuracy and speed of fault type identification.This thesis systematically expounds the theory of wavelet analysis and RPROP neural network,including the current research status of fault diagnosis of transmission line and the development and application of wavelet transform.In this thesis,the feature type of wavelet transform energy is combined with RPROP neural network to identify the fault type of transmission line.Firstly,the characteristics of fault types of transmission lines are analyzed,according to their characteristics,the fault transient voltage signals are decomposed and the energy ratio of each frequency band is calculated by wavelet transform.Secondly,the three-layer RPROP fault diagnosis network is constructed according to the actual needs,that is,the input layer,the hidden layer and the output layer are all layers,and the ratio of the energy of each frequency band coefficient of the transient voltage extracted by wavelet analysis is used as the fault diagnosis network of the input,the network output for the fault type corresponding to the four binary code.Finally,the fault data samples are used to train and test the network,and some fault samples are simulated and verified.According to the experimental results of simulation verification,the feasibility of RPROP network in fault diagnosis of transmission line is determined.At the same time,the diagnosis result of RPROP network is compared with the traditional BP network,and the conclusion show that RPROP network algorithm is superior to traditional BP diagnosis network in fault diagnosis of transmission line.