In this study, discrete wavelet transform (DWT) and deep neural network (DNN) are utilised for fault location in a series-compensated three-terminal transmission line. The series compensation causes challenges in fault location schemes of the three-terminal transmission lines. The presented fault location method has been extensively tested using the SIMULINK model of a three-terminal transmission line. Features extracted from synchronous measurements of fault currents at the three terminals using DWT are fed to the DNN. Faulted section determination and fault distance calculation are carried out using a single intelligent network simultaneously. Faulted section is determined with 100% accuracy, and the efficiency of algorithm is validated for symmetrical and unsymmetrical faults, and different values of fault resistance, inception angle, and location. The accuracy of the algorithm is acceptable for large fault resistances (above 100 Ω) and fault inception angles near zero. Total mean error for test data is 0.0458% which is much improved with respect to other similar works.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-smt.2018.0036

Fault location on a series-compensated three-terminal transmission line using deep neural networks

Wavelet-alienation based protection scheme for multi-terminal transmission line

Fault location estimation for series-compensated double-circuit transmission line using parameter optimized variational mode decomposition and weighted P-norm random vector functional link network

The faults occurring in different phases at multiple locations and different times are difficult to locate exact location using conventional techniques. This paper develops a fault location estimation approach using fuzzy inference system for multi location phase to ground faults and transforming phase to ground faults in six phase transmission (SPT) line. The six phase current data of SPT line are generated by MATLAB software and processed through butter worth filter, sampling and discrete fourier transform for distance locator. The proposed technique is dependent on single terminal data only. Mamdani fuzzy inference system is employed to make decision. Triangular membership functions are used to design input-output fuzzy sets. Fuzzy inference system has been deployed for the fault distance location using IF-THEN rules. The proposed technique is validated during different multi location and transforming phase to ground faults with wide variations in fault resistance and fault inception angle. Simulations and calculations with MATLAB prove that the fault location method is correct and accurate.

/pdf/fuzzy-inference-system-based-distance-estimation-approach-1m80zlp7cz.pdf

Fuzzy Inference System Based Distance Estimation Approach for Multi Location and Transforming Phase to Ground Faults in Six Phase Transmission Line

This paper presents the fault detection and classification for shunt faults on transmission lines with Static Synchronous Compensator (STATCOM) using fuzzy logic. The fuzzy logic is implemented by using the fuzzy logic toolbox in MATLAB. The 500kV, 60Hz system is simulated using simulink and simpower systems toolbox in MATLAB. The proposed method uses only the three phase currents for fault detection and classification of faulted phase. The system is simulated for various shunt faults with different fault resistances and with different fault locations between 10 percent and 90 percent of the transmission line. The results from the simulation show that fuzzy logic based fault detector and classifier accurately detects and classifies the faults on transmission system. The proposed method is able to detect and classify the faults for varying fault resistances and fault distances from the relaying point.

Fuzzy logic based fault detector and classifier for three phase transmission lines with STATCOM

This paper presents a wavelet fuzzy based protection scheme for a three terminal transmission system, makes use of current signals at three ends of transmission line which are synchronized with the help of global position system clock. A wavelet based multi resolution analysis is used to find the detailed coefficients of the signals which are utilized to calculate fault index. These fault indices are compared with the threshold value to detect and classify faults on transmission system. The approximate decomposition of current signals is utilized to locate the fault using fuzzy logic from their respective terminals. The proposed algorithm has been tested successfully for various faults at different locations.

J. Uday Bhaskar

Papers

Wavelet fuzzy based fault location estimation in a three terminal transmission system