Transmission Line Fault-Cause Identification Based on Hierarchical Multiview Feature Selection

Abstract

Fault-cause identification plays a significant role in transmission line maintenance and fault disposal. With the increasing types of monitoring data, i.e., micrometeorology and geographic information, multiview learning can be used to realize the information fusion for better fault-cause identification. To reduce the redundant information of different types of monitoring data, in this paper, a hierarchical multiview feature selection (HMVFS) method is proposed to address the challenge of combining waveform and contextual fault features. To enhance the discriminant ability of the model, an ε-dragging technique is introduced to enlarge the boundary between different classes. To effectively select the useful feature subset, two regularization terms, namely l2,1-norm and Frobenius norm penalty, are adopted to conduct the hierarchical feature selection for multiview data. Subsequently, an iterative optimization algorithm is developed to solve our proposed method, and its convergence is theoretically proven. Waveform and contextual features are extracted from yield data and used to evaluate the proposed HMVFS. The experimental results demonstrate the effectiveness of the combined used of fault features and reveal the superior performance and application potential of HMVFS.

Investigation on Pollution-Induced Flashovers of In-Service Insulators in Ethiopian Power Transmission Lines

“…It is not always straightforward to identify line faults resulting from pollution flashovers. However, specific contextual characteristic patterns exist to aid in their identification [2,13,14,16,17]. To identify them from the records of unexplained faults, the verification procedure used in this work focused on identifying patterns that could indicate or agree with the recognized characteristic features of pollution-induced faults.…”

“…To identify them from the records of unexplained faults, the verification procedure used in this work focused on identifying patterns that could indicate or agree with the recognized characteristic features of pollution-induced faults. These include contextual fault details such as the time and season of occurrence and geographical location of the fault, in addition to climatic and environmental conditions of the affected region [2,9,[15][16][17]. Moreover, information extracted from the voltage and current records during the fault, like the fault duration, success of reclosure events, and operational history, can provide valuable insights [2,[15][16][17][18].…”

“…These include contextual fault details such as the time and season of occurrence and geographical location of the fault, in addition to climatic and environmental conditions of the affected region [2,9,[15][16][17]. Moreover, information extracted from the voltage and current records during the fault, like the fault duration, success of reclosure events, and operational history, can provide valuable insights [2,[15][16][17][18].…”

“…Voltage and current magnitudes during the fault, the involved phases, duration of the fault, success of reclosure, and other protection data help to suggest the probable reasons behind the fault's origin [6,7,16,17,24]. The fault features extracted from the fault voltage and current waveforms are easily affected by the pre-fault operating state of the system, and there is no direct link between their characteristics and external causes.…”

“…The insulation of these lines is based on standard porcelain and glass cap-and-pin insulators strings as well as on long-rod polymeric composite insulators made of silicone rubber. A high number Energies 2024, 17,2007 2 of 21 of outages caused by external factors have occurred on these lines, mainly in the form of single line-to-ground faults.…”