Anzeige
Erschienen in:
2015 | OriginalPaper | Buchkapitel
8. Classification of Voltage Security States Using Supervised ANNs
verfasst von : Kabir Chakraborty, Abhijit Chakrabarti
Erschienen in: Soft Computing Techniques in Voltage Security Analysis
Verlag: Springer India
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Kohonen’s self-organizing feature map (SOFM) may lead to a few incorrect results because of the absence of supervision in the learning stage, since it is an unsupervised learning artificial neural network. In this chapter, learning vector quantization (LVQ), radial basis function (RBF), and probabilistic neural network (PNN) have been used as the monitoring tool in the state classification task, and these three topics (LVQ, RBF, and PNN) have been given in-depth treatments. The proposed learning vector quantization- and radial basis function-based monitoring have been found to upgrade the accuracy of the electrical power network’s security state classification as compared to that by SOFM, but there are also some misclassifications, whereas PNN brings about one hundred percent classification accuracy without any misclassification.