PV arc-fault feature extraction and detection based on bayesian support vector machines

Abstract

In a PV system, DC arc is regarded as a serious fault, which might cause circuit damage and trigger fires. The arc fault, however, is hard to detect due to the special fields of photovoltaic systems: constant direct current without zerocrossing point, sophisticated components leading to noise interruption, and usually occupying large area. Therefore, detectable characteristics are of great importance to diagnosis and alarm of fault arcs in PV systems. In this paper, we presented a classification method of separating arcing and non-arcing in the feature space. First, data sets of current signal were sampled by designing field experiments with "pull apart" method for arc ignition. Then seven features in both time and frequency domains were defined and two of them in each domain were selected to train BSVM. In order to simplify the computation, the trained BSVM network was replaced by a separating line, which was proved to have a better performance of classification. Testing results showed that this method could diagnose fault arcs with high accuracy. But whether this method is suitable for other PV systems needs to be verified in further work.

DC Arc Fault Detection Methods in MEA Distribution Systems

“…Gao et al [36] samples current signal data during a DC series arc through field experiments on a PV power station and utilises feature extraction both in time and frequency domains to classify arcing and non-arcing. This data was then used to train Bayesian support vector machines (BSVM) with two selected features and achieved the classification of arcing and non-arcing by a separating line in the feature space.…”

“…Broadband noise [27] Aircraft EPS Series/Parallel AC Harmonic ratios [28] Power Substation Parallel AC Mahalanobis [29] Circuit Interrupters Series AC General arc FDI [11] Aircraft EPS Series/Parallel AC/DC Sliding DFT window [33] Spacecraft EPS Series/Parallel AC/DC Frequency component [34] Aircraft EPS Series DC ANN [35] Spacecraft EPS Series DC BSVM [36] PV Series DC DTW [37] AC Distribution Series DC Time-Frequency STFT [38] PV Series DC WT [39] Circuit Interrupters Series/Parallel DC DSP [40] PV Series DC HMM [41] MEA EPS Series DC…”

Fast Arc Detection Technology Based on Fractal Dimension for SADA Slip Ring in Satellite Power System

“…The fractal dimension characteristics of the current and voltage signals are also the valid eigenvalues for arc identification [24][25][26]. Some researchers also used a combination of machine learning and artificial intelligence algorithms [27,28]. For example, a fault detection algorithm based on multiresolution signal decomposition was used for feature extraction in [29], and a two-stage support vector machine (SVM) classifier was used to perform decision making.…”

Kalman filter–based approach for detection of series arc fault in photovoltaic systems

“…14 In Alam et al, 15 time domain reflectometry has used as an approach to detect arc fault in PV systems. 22 However, large computation burden, uninterpretable results, and complexity are some of their limitations. From the other limitations for this group, signal characteristics variation due to maximum power point tracking (MPPT) impact and dependency on threshold setting can be addressed.…”

“…Artificial intelligence-based methods are another groups of arc faults recognition methods. 22 However, large computation burden, uninterpretable results, and complexity are some of their limitations.…”