Skip to Main Content
Power systems monitoring is particularly challenging due to the presence of dynamic load changes in normal operation mode of network nodes, as well as the presence of both continuous and discrete variables, noisy information and lack or excess of data. This paper proposes a fault diagnosis framework that is able to locate the set of nodes involved in multiple fault events and detects the type of fault in those nodes. The framework is composed of two phases: In the first phase a probabilistic neural network is trained with the eigenvalues of voltage data collected during symmetrical and unsymmetrical fault disturbances. The eigenvalues are computed from the correlation matrix built from historical data, and are used as neural network inputs. The neural network is able to carry out a first classification/discrimination process of nodes states, obtaining in this way a reduction on data analysis. In the second phase a sample magnitude comparison is used to detect and locate the presence of a fault. A set of simulations are carried out over an electrical power system to show the performance of the proposed framework and a comparison is made against a diagnostic system based on probabilistic logic.