Electromagnetic wave of electrical spark is a potential cause to eletrical equipment failure. This research focused on identificating and comparative analyzing the different types of electromagnetic waveform generated by eletrical equipment failure based on SVM. After analyzing and extracting the features the electromagnetic waveform, a model was built to identificate the type of the elctromagnetic waveform. The collected standard electromagnetic waveforms were used as the imput of the train model and the model accuracy was improved by adjusting training parameters afer analyzing the results, When inputting an unknown type of electromagnetic waveform, SVM may predict the output of the network according to the recognition rule. Then the types of electromagnetic waveforms were identificated by using adjusted models. The result shows that the electromagnetic waveform can be effectively and feasibly identificated based on SVM, which provides a theoretical support on prediction method of gas explosion caused by electrical sparks. Keywords—SVM; features of electromagnetic waveform; waveform identification
[1]
Quan Pan,et al.
Two denoising methods by wavelet transform
,
1999,
IEEE Trans. Signal Process..
[2]
S. Boggs,et al.
Characteristics of GIS disconnector-induced short rise-time transients incident on externally connected power system components
,
1988
.
[3]
S. Gedney.
An anisotropic perfectly matched layer-absorbing medium for the truncation of FDTD lattices
,
1996
.
[4]
Bernard Delyon,et al.
Accuracy analysis for wavelet approximations
,
1995,
IEEE Trans. Neural Networks.
[5]
A. Zeddam,et al.
Measured and Modeled Horizontal Electric Field From Rocket-Triggered Lightning
,
2008,
IEEE Transactions on Electromagnetic Compatibility.