Research On Power Network Fault Analysis Technology Based On Optimized BP Neural Network

With the continuous erection of high-voltage,ultra-high-voltage and extra-high-voltage power grids in China,they are playing an increasingly important role in the long-distance transmission of electric energy,but the risks they face are also increasing.Pollution flashover of insulators in high voltage transmission lines is one of the important accidents that endanger the safe and stable operation of power grid.The treatment and prevention of pollution flashover are also important tasks of power departments at all levels.In order to ensure the safe production of power industry and meet the development needs of building smart grid,it is necessary to improve the scientificity and intellectualization of insulator surface contamination monitoring,and take timely preventive measures for contaminated insulators to avoid contamination flashover accidents.Traditional pollution flashover prevention methods mainly through regular cleaning work and adjusting the creepage distance of insulators,not only waste a lot of manpower and material resources,but also can not really grasp the contamination degree of insulator surface.At present,there are many methods to measure the contamination degree of insulators,the most common method is leakage current method.By analyzing the leakage current flowing through the insulator surface,the characteristic quantities that can characterize the contamination degree are analyzed,and the measurement model of the contamination degree is established.The contamination state of the insulator surface can be obtained,which provides the basis for formulating the cleaning and maintenance strategies,and can more effectively guarantee the safety and stability of the transmission line.Firstly,according to the formation principle and harm of pollution flashover,the influence of temperature,humidity and voltage on leakage current is analyzed.Secondly,through the time-frequency analysis of leakage current waveform,seven parameters are selected as the characteristic quantities to characterize the contamination degree.Finally,combined with the advantages of BP neural network and genetic algorithm,the BP neural network model optimized by genetic algorithm is established.The model is trained by selecting effective data,and the effect of the trained model is verified.The experimental results show that the results of BP neural network model optimized by genetic algorithm are more accurate,and can be used for the determination of pollution degree,providing a reference for the anti-pollution flashover work of transmission lines.