Partial discharge pattern recognition method for high voltage transmission cables based on VMD-IKHA-DBN
Aiming at the current problem of low accuracy of partial discharge pattern recognition in high-voltage transmission cables,this paper proposes a partial discharge pattern recognition method for high-voltage transmission cables based on VMD-IKHA-DBN.Firstly,the causes and types of partial discharges in high-voltage transmission cables are analyzed,and an experimental platform for partial discharges in high-voltage transmission cables is con-structed to collect the original signals.Then the Variational Mode Decomposition(VMD)algorithm is used to com-plete the signal decomposition of partial discharges,and the multi-scale arrangement entropy theory is introduced to construct the sample set of feature vectors.Finally,an Improved Krill Herd Algorithm(IKHA)based on the com-bination of Logistic Chaos Mapping,Dynamic Reverse Learning and Gaussian Variation is proposed to optimize the hyper-parameters of Deep Brief Network(DBN),so as to obtain the IKHA-DBN based high voltage transmission cable partial discharge pattern recognition model based on IKHA-DBN.The experimental results prove that the rec-ognition accuracy of the method proposed in this paper reaches 98.3333%and the recognition efficiency is high,which realizes the efficient and accurate recognition of partial discharge patterns of high-voltage transmission cables,and can give full play to the engineering efficiency in cable operation and inspection work.
NETL
NSTL
万方数据
