A Time-Frequency Transform Based Fault Detectionand Classificationof STATCOM Integrated Single Circuit Transmission Line

Abstract

<p align="center"> </p><p align="center"> </p><table width="593" border="1" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="387"><p>This paper discusses the time-frequency transform based fault detection and classification of STATCOM (Static synchronous compensator) integrated single circuit transmission line. Here, fast-discrete S-Transform (FDST) based time-frequency transformation is proposed for evaluation of fault detection and classification including STATCOM in transmission line. The STATCOM is placed at mid-point of transmission line. The system starts processing by extracting the current signals from both end of current transformer (CT) connected in transmission line. The current signals from CT’s are fed to FDST to compute the spectral energy (SE) of phase current at both end of the line. The differential spectral energy (DSE) is evaluated by subtracting the SE obtained from sending end and SE obtained from receiving end of the line. The DSE is the key indicator for deciding the fault pattern detection and classification of transmission line. This proposed scheme is simulated using MATLAB simulink R2010a version and successfully tested under various parameter condition such as fault resistance (Rf),source impedance (SI), fault inception angle (FIA) and reverse flow of current. The proposed approach is simple, reliable and efficient as the processing speed is very fast to detect the fault within a cycle period of FDT (fault detection time).</p></td></tr></tbody></table>

Integrated Classification Algorithm for Unbalanced Data Streams Based on Joint Nonnegative Matrix Factorization

“…The imbalance in a category refers to the imbalance in the sample size of a category and its subcategories, or the data of a category has multiple different terms that are not so important, as shown in Figures 1(c) and 1(d). A large number of studies have shown that the imbalance of data between categories is not the only factor affecting classification learning, and the imbalance of data within categories is a key factor affecting the effect of classification [21]. Therefore, the classification problem of unbalanced data is mainly due to the complexity of the data distribution, as shown in Figures 1(b) and 1(c) (data overlap) and Figure 1(d) (small fragmentation problem); all of these problems will directly affect the classifier's learning result.…”