New Trends in Power Quality Event Analysis: Novelty Detection and Unsupervised Classification

Lazzaretti, André E.; Ferreira, Vitor Hugo; Neto, Hugo Vieira

doi:10.1007/s40313-016-0265-z

Cited by 7 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is necessary to use a scale factor to normalize the two vectors. Equation (10) presents this procedure.…”

Section: Methodsmentioning

confidence: 99%

“…It is the Modal Assurance Criterion (MAC), presented in [60,61]. It is nothing more than the square of Equation (10). MAC values close to 1 indicate strong similarity, while those close to 0 indicate low similarity.…”

Section: Methodsmentioning

confidence: 99%

“…The authors of [8,9] propose density-based algorithms. The performance of these techniques is highly dependent on very large data volumes as shown in the work of [10]. Refs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Clustering Approach for Automatic Oscillographic Records Segmentation

et al. 2021

Self Cite

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

“…Therefore, it is necessary to use a scale factor to normalize the two vectors. Equation (10) presents this procedure.…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A New Clustering Approach for Automatic Oscillographic Records Segmentation

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, it is necessary to monitor PQ disturbances to provide clean power as suggested by IEEE [13,14]. Several studies on the detection and classification of PQ disturbances have been conducted, including the generation of a mathematical model using the discrete wavelet transform-fast Fourier approach [15], fuzzy-wavelets [16], support vector machine algorithms [17], analysis of the real signal database distorted by the disturbance of the measurement system results with the unsupervised classification approach [18] and an intelligent measurement [19]. EMD method and Hilbert transformation were developed for assessment [20].…”

Section: Introductionmentioning

confidence: 99%

Development of empirical mode decomposition based neural network for power quality disturbances classification

et al. 2022

View full text Add to dashboard Cite

The complexity of the electric power network causes a lot of distortion, such as a decrease in power quality (PQ) in the form of voltage variations, harmonics, and frequency fluctuations. Monitoring the distortion source is important to ensure the availability of clean and quality electric power. Therefore, this study aims to classify power quality using a neural network with empirical mode decomposition-based feature extraction. The proposed method consists of 2 main steps, namely feature extraction, and classification. Empirical Mode Decomposition (EMD) was also applied to categorize the PQ disturbances into several intrinsic mode functions (IMF) components, which were extracted using statistical parameters and the Hilbert transformation. The statistical parameters consist of mean, root mean squared, range, standard deviation, kurtosis, crest factor, energy, and skewness, while the Hilbert transformation consists of instantaneous frequency and amplitude. The feature extraction results from both parameters were combined into a set of PQ disturbances and classified using Multi-Layer Feedforward Neural Networks (MLFNN). Training and testing were carried out on 3 feature datasets, namely statistical parameters, Hilbert transforms, and a combination of both as inputs from 3 different MLFNN architectures. The best results were obtained from the combined feature input on the network architecture with 2 layers of ten neurons, by 98.4 %, 97.75, and 97.4 % for precision, recall, and overall accuracy, respectively. The implemented method is used to classify PQ signals reliably for pure sinusoids, harmonics with sag and swell, as well as flicker with 100 % precision

show abstract

“…The first step in the studies centered on automatic detection and classification of PQ disturbances is to obtain several distorted signals to test the systems. Regarding this point, several trends appear in existing studies: generation of waves from mathematical models [8]- [11], use of databases containing real-world signals affected by PQ problems [12] and registration of real-world disturbances using a data acquisition system [13]. Regarding the first trend, several mathematical models have been proposed in existing studies.…”

Section: Introductionmentioning

confidence: 99%

Integral mathematical model of power quality disturbances

Igual

Medrano

Arcega

et al. 2018

2018 18th International Conference on Harmonics and Quality of Power (ICHQP)

View full text Add to dashboard Cite

Power quality (PQ) disturbances lead to severe problems in industries and electrical grids. To mitigate PQ problems, the accurate detection and classification of the possible disturbances are essential. A large number of studies exists in this field. The first research step in these studies is to obtain several distorted signals to test the classification systems. In this regard, the most common trend is the generation of signals from mathematical models. In the literature, we can find several models with significant differences among them. However, to the best of our knowledge, there is no integral model that considers all types of distortions. This work presents an integral mathematical model based on the models found in the literature. The model also includes new types of combined disturbances. Twenty-nine disturbances are considered. Additionally, this work includes a software version of this integral model that is publicly available to be used by any interested researcher. In this way, PQ disturbances can be generated in a fast and automatic way. This software aims to facilitate future studies, supporting researchers in the modelling stage.

show abstract

New Trends in Power Quality Event Analysis: Novelty Detection and Unsupervised Classification

Cited by 7 publications

References 18 publications

A New Clustering Approach for Automatic Oscillographic Records Segmentation

A New Clustering Approach for Automatic Oscillographic Records Segmentation

Development of empirical mode decomposition based neural network for power quality disturbances classification

Integral mathematical model of power quality disturbances

Contact Info

Product

Resources

About