An Intrusion Signal Recognition Method for Substation Perimeter Security

In order to improve the accuracy of intelligent substation perimeter alarm and reduce the false alarm rate, this paper proposes CEEMDAN combined with wavelet denoising method to preprocess the intrusion signal, using the support vector machine (SVM) as the core algorithm of the classifier, and optimizing the support vector machine (SVM) by the particle swarm (PSO) algorithm, because the particle swarm (PSO) algorithm is easy to achieve the disadvantage of local optimization. We used the gray wolf (GWO) algorithm and particle swarm algorithm (PSO) to optimize the support vector machine (SVM), experimental results show that the method has achieved a certain effect, in the perimeter intrusion signal to provide a scheme.