Improved Fault Classification in Series Compensated Transmission Line: Comparative Evaluation of Chebyshev Neural Network Training Algorithms

Abstract

This paper presents the Chebyshev neural network (ChNN) as an improved artificial intelligence technique for power system protection studies and examines the performances of two ChNN learning algorithms for fault classification of series compensated transmission line. The training algorithms are least-square Levenberg-Marquardt (LSLM) and recursive least-square algorithm with forgetting factor (RLSFF). The performances of these algorithms are assessed based on their generalization capability in relating the fault current parameters with an event of fault in the transmission line. The proposed algorithm is fast in response as it utilizes postfault samples of three phase currents measured at the relaying end corresponding to half-cycle duration only. After being trained with only a small part of the generated fault data, the algorithms have been tested over a large number of fault cases with wide variation of system and fault parameters. Based on the studies carried out in this paper, it has been found that although the RLSFF algorithm is faster for training the ChNN in the fault classification application for series compensated transmission lines, the LSLM algorithm has the best accuracy in testing. The results prove that the proposed ChNN-based method is accurate, fast, easy to design, and immune to the level of compensations. Thus, it is suitable for digital relaying applications.

A Review of Fault Diagnosing Methods in Power Transmission Systems

“…Sci. 2019, 9, [73]. In ChNN polynomials, functional expansion is used to map original input into higher-dimensional space; the hidden layer is interchanged, leaving only one layer in the network as shown in Figure 5 [74].…”

Faults Diagnosis of Self-validating Air Data Sensing System Based on Ensemble EMD and Multiclass RVM

“…Firstly, the SVADS system concludes multiple pressure measuring channels, and each channel has complex faults modes such as the blockage of pressure ports, pipe pressure leak, faults of pressure sensors and faults of circuits; secondly, the faults feature of each mode is nonlinear, which the difficulty in faults feature extraction is bigger; thirdly, the mount of actual faults data is very little, and the small sample problem needs to be solved; lastly, the obtained fault information includes some uncertain extent and the classification results should be uncertain. Presently, some faults diagnosis algorithms have been proposed based on empirical mode decomposition (EMD) [10], neural networks [11], and relevance vector machine (RVM) [12]. Based on the adaptive decomposition of signals in frequency domain, EMD has applied to some feature exaction; however, its mode mixing problem is not suitable for nonlinear faults feature exaction of this paper.…”

“…Construct feature vectors of nonlinear faults. To extract the fault feature and implement the flowing pattern classification, the normalized energy feature and the average cutting ratio feature of IMF components and residual are computed by using equation (9) and (11). The final feature vectors of test sample are then constructed as …”

Classification of Disturbances and Cyber-Attacks in Power Systems Using Heterogeneous Time-Synchronized Data

“…In [17] with the help of wavelet transforms, current phase is decomposed and fed into a particle swarm optimization-based neural network for fault classification. A Chebyshev neural network is examined in [18] on current signals to evaluate the fault classification performance. In [19], the neural network is integrated with a wavelet transform multiresolution analysis technique to extract patterns for faults in shipboard power systems using energy variation of fault signals.…”