الفهرس يوجد فقط 14 صفحة متاحة للعرض العام
 |  | from | 105 |  |  |
| | | from | 105 | | |
المستخلص
Detection of the position and direction of the fault on a transmission line is essential to the proper performance of a power system; it would be desirable to develop a high speed and accurate approach to determine the fault position and direction for different power system conditions. In this thesis a noval position and direction for different module fro protecting transmission line is described. The proposed approach is based on the use of artificial neural network. The neural network used in this approach is Elman neural network. Which is a type of recurrent network. The recurrent connections provide the neural network with memory, that make it suitable for time varying inputs. The designed neural network uses samples of the high frequency current components to discriminate between internal and external faults, and samples of the fundamental components of three phase voltages and currents to distinguish between forward and backward faults. Details of the developed concepts for positional and directional protection, designing procedures, training process, and the results of performance studies with the proposed recurrent neural network are given and analyzed in this thesis.