Fault detection and classification in three phase series compensated transmission line using ANN

Abstract

Series compensation consists of capacitors in series is used in the transmission lines as a tool to improve the performance after disturbed by a fault. Transmission line needs a protection scheme to protect the lines from faults due to natural disturbances, short circuit and open circuit faults. The fault can happen in any location of transmission line and it is important to know which location has been affected. So that, the fault can be eliminated and can maintain the optimum performance. Therefore, in this paper Artificial Neural Network (ANN) is used to detect and classified the fault happen in single line to ground fault and three phase to ground fault. Two different tests of each types of fault have been tested in order to prove the effectiveness of ANN to detect the fault location by using different length and fault resistance. The simulation has been accomplished in MATLAB with ANN fitting tool which build and train the network before evaluated its performance using regression analysis. The analysis shows that the ANN can accurately detect the different types of faults and classified it into the respective category even the random vectors are put on the system are used.

Transmission Line Fault Classification Based on the Combination of Scaled Wavelet Scalograms and CNNs Using a One-Side Sensor for Data Collection

“…In contrast to research initiatives akin to this study, which predicate their analyses on electrical networks possessing a specific set of fundamental components while omitting critical elements integral to the network's fault response dynamics, which have been noted in [1,43,44], and introducing a solution, it is evident that such theories, although potentially proficient [21], remain confined in their applicability to a select category of networks. These theories are inherently limited in their generalizability to more complex and scientifically representative network configurations that exist in practical reality.…”

“…Thus, a fault analysis system must be available to accurately determine the fault type, thereby ensuring the reliability of the system. Consequently, numerous theories and research endeavors have emerged in this field, each employing distinct methodologies and theories [1][2][3][4]. In engineering and other fields, different theories have been employed for diagnosis, such as wavelet analysis [5][6][7], while others have utilized deep learning [8][9][10][11], and neural networks [12][13][14][15], among others.…”

Fault Detection in Three-phase Induction Motor based on Data Acquisition and ANN based Data Processing

“…In [18,25,28,30] data regarding mechanical components (bearings) in electrical motors is analyzed using ANN. Non-mechanical data such as current, voltage, and vibration are also processed using ANN in order to detect faults in electric rotary machines [23,24,25,39].…”