Complete protection scheme for fault detection, classification and location estimation in HVDC transmission lines using support vector machines

A novel approach to estimate fault location in current source converter–based HVDC transmission line by Gaussian process regression

“…In this regard, a detailed survey of literature has been carried out for fault detection and classification approaches in HVDC transmission line, 19,[22][23][24][25]37,38 which can be employed to detect the presence of fault (fault instant) and its type at the beginning of proposed fault location algorithm. In this regard, a detailed survey of literature has been carried out for fault detection and classification approaches in HVDC transmission line, 19,[22][23][24][25]37,38 which can be employed to detect the presence of fault (fault instant) and its type at the beginning of proposed fault location algorithm.…”

“…In this regard, a detailed survey of literature has been carried out for fault detection and classification approaches in HVDC transmission line, 19,[22][23][24][25]37,38 which can be employed to detect the presence of fault (fault instant) and its type at the beginning of proposed fault location algorithm. 19,[22][23][24][25]37,38 This feature vector is used as an input to the GPR model to estimate the location of a fault in the transmission line. After successful fault detection and classification, the feature vector is formulated from the faulty input signals, which are accomplished by computing standard deviation of third level Daubechies approximate coefficients of input signals for specified time period as half cycle prior to the occurrence of fault and half cycle later the inception of fault (ie, 20 ms time window).…”

“…33,34 In literature, it has been well known that the transients are produced due to a fault, and the works proposed in previous studies 19,22,34 provide an accurate way to detect/locate the faults by DB4 wavelet. It is described in terms of parameters of scaling and translation of wavelet signal.…”

“…In Hao et al, 14 the fault location is estimated accurately, but this method requires a high value of sampling frequency up to 1000 kHz, and with compromise in sampling frequency up to 250 kHz, the fault location error is raised up to 12 times that of normal. Further, in Johnson and Yadav, 19 an intelligent fault location approach has been studied, which concludes very low fault location mean error of 0.03% along with the lower sampling frequency of 1 kHz. Along with this demerit, this method is also very sensitive to the small disturbances as the SNR of 50 dB also results in an increased error as mentioned previously.…”

Rapid Fault Diagnosis of a Back-to-Back MMC-HVDC Transmission System under AC Line Fault

“…Among the existing fault detection methodologies in voltage source converter-based high-voltage direct current (VSC-HVDC) transmission systems and conventional AC transmission lines, wavelet analysis is universally applied, especially in combination with entropy theory [14,[16][17][18][19][20], and a boundary condition is applied to distinguish internal from external faults [17,[21][22][23]]. An artificial neural network [24] and machine learning [25,26] are utilized to train the proposed fault detection model or algorithm for improved accuracy. As mentioned in Reference [27], previous protection schemes in AC systems cannot be directly applied to an AC/DC hybrid system because of the different pattern in fault current characteristics between AC systems and AC/DC hybrid systems.…”