Research On Fault Diagnosis Of Mine Power Cable Based On IPSO-BP

Mine power cable is a link for transmitting electrical energy in the entire coal mine power system,which affects the stable operation of the coal mine power system.Because of the special operation environment of mine power cables,various short-circuit faults are prone to occur.If the fault is not dealt with in time,it will cause economic losses and casualties due to coal mine power outage and fire accidents.Therefore,it is very essential to study a fast and accurate power cable fault diagnosis method to ensure the power supply safety of coal mine power system.Taking mining power cable as the'research object,this paper studies the fault characteristics of mining power cable,and clarifies the fault types and causes,based on the summary and analysis of the research status of power cable fault diagnosis at home and abroad.On the premise of considering the actual situation,according to the composition and characteristics of the coal mine power supply system,this paper builds the power cable simulation model of the mine 10kV system in PSCAD,simulates different short-circuit fault voltage and current signals,and verifies the feasibility of the simulation model.The wavelet packet transform is used to decompose and reconstruct the mine power cable fault signal.This thesis calculates the energy entropy value of each frequency band,constructs a feature vector representing different short-circuit faults,and extracts the effective information features that reflect the nature o f the fault state,and uses it as a sample set for fault type identification.After the training and testing of the fault diagnosis model based on BP neural network,the fault diagnosis of mine power cable is realized.Aiming at the problem that the BP neural network is easy to fall into the local minimum and the training speed is slow,this paper uses the particle swarm optimization algorithm to optimize the weights and thresholds of the BP neural network.At the same time,this paper adopts the strategy of random inertia weight and asynchronous adjustment of learning factors to optimize the parameters of PSO,which helps BP neural networl to converge to the global best.Finally,BP.PSO-BP and IPSO-BP neural network models were established to classify the mining power cable fault signals,and the diagnostic performance of these three models was comprehensively compared.The experimental results show that the fault diagnosis model based on IPSO-BP improves the accuracy and speed of diagnosis,which improves the problem that it is difficult to accurately and quickly diagnose power cable line faults in coal mine power systems.It provides an effective method for fault diagnosis of mining power cables,and guarantees the safe operation of coal mine power systems to a certain extent.It has certain theoretical research significance and engineering application value.