Application of support vector machines for fault diagnosis in power transmission system

Abstract

Post-fault studies of recent major power failures around the world reveal that maloperation and/or improper coordination of protection system were responsible to some extent. When a major power disturbance occurs, protection and control action are required to stop the power system degradation, restore the system to a normal state and minimise the impact of the disturbance. However, this has indicated the need for improving protection coordination by additional post-fault and corrective studies using intelligent/knowledge-based systems. A process to obtain knowledge-base using support vector machines (SVMs) is presented for ready post-fault diagnosis purpose. SVMs are used as Intelligence tool to identify the faulted line that is emanating and finding the distance from the substation. Also, SVMs are compared with radial basis function neural networks in datasets corresponding to different fault on transmission system. Classification and regression accuracies are is reported for both strategies. The approach is particularly important for post-fault diagnosis of any mal-operation of relays following a disturbance in the neighbouring line connected to the same substation. This may help to improve the fault monitoring/diagnosis process, thus assuring secure operation of the power systems. To validate the proposed approach, results on IEEE 39-Bus New England system are presented for illustration purpose.

Statistical Feature Extraction for Fault Locations in Nonintrusive Fault Detection of Low Voltage Distribution Systems

“…Hence, Gaussian kernel function is reasonably used in this paper. To obtain a good performance, some parameters in SVM have to be chosen carefully [50]. These parameters include:…”

Fault diagnosis of bearing based on relevance vector machine classifier with improved binary bat algorithm for feature selection and parameter optimization

“…Recently, the classifiers, such as Bayesian networks, [2][3][4] artificial neural networks, and support vector machine (SVM), have been widely applied in fault diagnosis field, among which SVM is a machine learning method based on structure risk minimization principle, and it can solve the classification problems with small training samples, high dimensions, and nonlinearity. Until now, SVM has been applied in fault diagnosis of rolling-element bearing, 1 fault diagnosis of turbo-pump rotor, 5 fault diagnosis of rotor-bearing system, 6 fault diagnosis of power transmission system, 7 and so on. Relevance vector machine (RVM) is an intelligent learning technique based on sparse Bayesian framework.…”

Genetic algorithm based support vector machine for on-line voltage stability monitoring

“…This balance gives a better generalization performance than other neural network models. For the past several years, SVM has been successfully applied in solving a large range of practical problems in different areas [15][16][17][18][19][20][21][22][23].…”