Underground MV Network Failures’ Waveform Characteristics—An Investigation

Louro, Miguel; Ferreira, L. S.

doi:10.3390/en14051216

Cited by 5 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is estimated that the time between the very first PD and permanent earth fault (with 50% probability) is 12 days [37]. Detailed analysis of transient earth fault in Portuguese power system is presented in [38]. According to the analysis, it is possible to detect transient earth faults before the permanent earth fault, however, further research, e.g., regarding time before failure is needed.…”

Section: Transient Earth Faultsmentioning

confidence: 99%

Monitoring, Detection and Locating of Transient Earth Fault Using Zero-Sequence Current and Cable Screen Earthing Current in Medium Voltage Cable and Mixed Feeders

Łowczowski

Olejnik

2022

Energies

View full text Add to dashboard Cite

This paper presents the final development of an expert system utilizing a measurement of cable screen earthing transient current. The developed system allows for identification and location of earth fault in underground cable and mixed lines (underground cable and overhead line) and monitoring of an earthing system and cable screen connections. The unique feature of the developed earth fault locating system is the possibility of identification of line type and branch of the MV underground cable or mixed feeder under earth fault conditions. As a result, the time to remove failure can be greatly reduced and the number of earth fault indicators installed in the distribution network can also be reduced. Unfortunately, in order to operate properly, the previously developed system requires a fundamental—50 Hz component of the measured zero-sequence cable core current and cable screen earthing current; therefore, short transient earth faults without steady-state earth fault currents cannot be localized and categorized even though the transient earth faults have a negative impact on the power system. According to measurements performed by the authors, transient earth faults are relatively frequent, which causes stress to insulation. The number of transient earth faults may be reduced by ensuring proper maintenance of the distribution system. Unfortunately, because of the very large area of the distribution feeder, often in the range of tens of kilometers or even around a hundred kilometers, and many potential causes of earth faults, it is very difficult to localize the transient earth fault and determine the cause of the earth fault. Herein, we present the possible causes of transient earth faults and methods developed for the analysis of transient earth faults. Moreover, the novel algorithm for transient earth fault detection and location is proposed. The proposed algorithm has a self-learning capability and can identify branches of the distribution feeder under transient earth fault conditions. The effectiveness of the proposed algorithm is confirmed thanks to the performed network experiment.

show abstract

Section: Transient Earth Faultsmentioning

confidence: 99%

Monitoring, Detection and Locating of Transient Earth Fault Using Zero-Sequence Current and Cable Screen Earthing Current in Medium Voltage Cable and Mixed Feeders

Łowczowski

Olejnik

2022

Energies

View full text Add to dashboard Cite

show abstract

“…The remaining features are determined by carrying out a signal processing of the oscillography records. Details for the signal processing are not presented in this paper due to its complexity, but a detailed explanation on the extraction of each feature can be found in [10]. An example of the observed frequency of Feature 1 (fault type) is presented in Figure 3; however, the depiction of all features would be a lengthy exercise and would not bring any new development relative to [10].…”

Section: Data and Featuresmentioning

confidence: 99%

“…Details for the signal processing are not presented in this paper due to its complexity, but a detailed explanation on the extraction of each feature can be found in [10]. An example of the observed frequency of Feature 1 (fault type) is presented in Figure 3; however, the depiction of all features would be a lengthy exercise and would not bring any new development relative to [10]. The features are used in all the assessments in this paper and will be referenced by their number for simplicity reasons.…”

Section: Data and Featuresmentioning

confidence: 99%

“…The detection of incipient faults is also the subject of [9], in which they demonstrate the corresponding relationship to permanent faults. This paper's authors have carried out an analysis on the waveform characteristics most common in failures occurring in the Portuguese MV cable network [10], which are related to ageing but also to external factors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Underground MV Network Failure Types by Applying Machine Learning Methods to Indirect Observations

Louro

Ferreira²

2022

Energies

Self Cite

View full text Add to dashboard Cite

Electrical utilities performance is measured by various indicators, of which the most important are very dependent on the interruption time after a failure in the network has occurred, such as SAIDI. Therefore, they are constantly looking for new techniques to decrease the fault location and repair times. A possibility to innovate in this field is to estimate the failed network component when a fault occurs. This paper presents the conclusion of an analysis carried out by the authors with the aim to estimate failure types of underground MV networks based on observable indirect variables. The variables needed to carry out the analysis must be available shortly after the failure occurrence, which is facilitated by a smart-grid infrastructure, to allow for a quick estimation. This paper uses the groundwork already carried out by the authors on ambient variables, historical variables, and disturbance recordings to design an estimator to predict between four MV cable network failure types. The paper presents relevant analyses on the design and performance of various machine learning classification algorithms for estimation of the types of MV cable network failures using real-world data. Optimization of performance was carried out, resulting in an estimator with an overall 68% accuracy rate. Accuracy rates of 94% for cable failure, 63% for excavations, and 79% secondary busbar failures were achieved; as for cable joints, the accuracy was poor due to the difficulty to identify a feature that can be used to separate this failure type from cable failures. Future work to improve that accuracy is discussed.

show abstract

“…As mentioned in the abstract, these oscillographic databases are immense and the scientific community has been working on this topic to find solutions that allow a better use them for knowledge generation purposes. Works [1][2][3] are prominent examples in the literature.…”

Section: Introductionmentioning

confidence: 99%

A New Clustering Approach for Automatic Oscillographic Records Segmentation

et al. 2021

View full text Add to dashboard Cite

The analysis of waveforms related to transient events is an important task in power system maintenance. Currently, electric power systems are monitored by several event recorders called phasor measurement units (PMUs) which generate a large amount of data. The number of records is so high that it makes human analysis infeasible. An alternative way of solving this problem is to group events in similar classes so that it is no longer necessary to analyze all the events, but only the most representative of each class. Several automatic clustering algorithms have been proposed in the literature. Most of these algorithms use validation indexes to rank the partitioning quality and, consequently, find the optimal number of clusters. However, this issue remains open, as each index has its own performance highly dependent on the data spatial distribution. The main contribution of this paper is the development of a methodology that optimizes the results of any clustering algorithm, regardless of data spatial distribution. The proposal is to evaluate the internal correlation of each cluster to proceed or not in a new partitioning round. In summary, the traditional validation indexes will continue to be used in the cluster’s partition process, but it is the internal correlation measure of each one that will define the stopping splitting criteria. This approach was tested in a real waveforms database using the K-means algorithm with the Silhouette and also the Davies–Bouldin validation indexes. The results were compared with a specific methodology for that database and were shown to be totally consistent.

show abstract

Underground MV Network Failures’ Waveform Characteristics—An Investigation

Cited by 5 publications

References 19 publications

Monitoring, Detection and Locating of Transient Earth Fault Using Zero-Sequence Current and Cable Screen Earthing Current in Medium Voltage Cable and Mixed Feeders

Monitoring, Detection and Locating of Transient Earth Fault Using Zero-Sequence Current and Cable Screen Earthing Current in Medium Voltage Cable and Mixed Feeders

Estimation of Underground MV Network Failure Types by Applying Machine Learning Methods to Indirect Observations

A New Clustering Approach for Automatic Oscillographic Records Segmentation

Contact Info

Product

Resources

About