“…The comparative analysis are listed in Table , to evaluate the practicality and achievability of the proposed CS and SAE based on DNN algorithms is matched with recently revealing approaches . The comparative results are shown in Table .…”
Section: Resultsmentioning
confidence: 99%
“…The SSD‐based method shows significantly high classification accuracy for single PQD while for complex PQD needs to be improved. In Ribeiro et al, 20 single‐ and multi‐PQD classes were investigated, and 100% classification rates were achieved of single and multiple PQD such as sag, swell, notch, impulsive, transient, oscillatory transient, harmonics + sag, harmonics + swell, notch + swell, and harmonics + notch + swell; however, other classes need to improve. The comparative results indicate that the proposed scheme is desirable to classify the multiple disturbances.…”
Section: Resultsmentioning
confidence: 99%
“…In the real power system network, multiple power quality (MPQ) disturbances have been occurred due to power failure, capacitors switching, power electronic circuits, etc . Many methods have been revealed for the detection and classification of single PQD signal .…”
Summary
This paper presents a recently established compressed sensing (CS) and sparse autoencoder (SAE) based on deep learning (DL) method for classification of single and multiple power quality disturbances (PQDs). The CS technique is paying considerable attention in recent years due to below sampling rate comparatively Nyquist sampling. Initially, the CS technique is applied to extract the features of PQD waveforms. The extracted features are applied as inputs to the sparse autoencoder based on DL for classification of nine single and 22 combined classes of PQDs. The DL helps to remove a redundant feature and improves classification performance. Finally, backpropagation is applied to fine‐tune the entire network. The effectiveness of the proposed algorithm has been tested with more than 6580 numbers of real and synthetic single and multiple PQD data, and the results are recorded. High correct classification rate is obtained with noise and without noise level. Noise level was considered from 20 to 50 dB. The performance of the proposed technique has been assessed by comparing the results against recently reported methods. Results show that the proposed CS‐ and SAE‐based DL algorithms can be efficiently used for single and multiple PQDs classifications.
“…The comparative analysis are listed in Table , to evaluate the practicality and achievability of the proposed CS and SAE based on DNN algorithms is matched with recently revealing approaches . The comparative results are shown in Table .…”
Section: Resultsmentioning
confidence: 99%
“…The SSD‐based method shows significantly high classification accuracy for single PQD while for complex PQD needs to be improved. In Ribeiro et al, 20 single‐ and multi‐PQD classes were investigated, and 100% classification rates were achieved of single and multiple PQD such as sag, swell, notch, impulsive, transient, oscillatory transient, harmonics + sag, harmonics + swell, notch + swell, and harmonics + notch + swell; however, other classes need to improve. The comparative results indicate that the proposed scheme is desirable to classify the multiple disturbances.…”
Section: Resultsmentioning
confidence: 99%
“…In the real power system network, multiple power quality (MPQ) disturbances have been occurred due to power failure, capacitors switching, power electronic circuits, etc . Many methods have been revealed for the detection and classification of single PQD signal .…”
Summary
This paper presents a recently established compressed sensing (CS) and sparse autoencoder (SAE) based on deep learning (DL) method for classification of single and multiple power quality disturbances (PQDs). The CS technique is paying considerable attention in recent years due to below sampling rate comparatively Nyquist sampling. Initially, the CS technique is applied to extract the features of PQD waveforms. The extracted features are applied as inputs to the sparse autoencoder based on DL for classification of nine single and 22 combined classes of PQDs. The DL helps to remove a redundant feature and improves classification performance. Finally, backpropagation is applied to fine‐tune the entire network. The effectiveness of the proposed algorithm has been tested with more than 6580 numbers of real and synthetic single and multiple PQD data, and the results are recorded. High correct classification rate is obtained with noise and without noise level. Noise level was considered from 20 to 50 dB. The performance of the proposed technique has been assessed by comparing the results against recently reported methods. Results show that the proposed CS‐ and SAE‐based DL algorithms can be efficiently used for single and multiple PQDs classifications.
“…Classical approach with static filters is not able to answer to all new needs in data analysis of PQ measurement data. Work [3] presents a real-time monitoring system for power quality, able to classify 20 disturbance classes, including multiple and single disturbances. Work presented in [4] deals with the calibration procedures of the measurement channel and the verification of the measurement characteristics and validation of the measurement algorithms.…”
This paper presents the noise reduction of power quality measurement with time-frequency (T-F) depth analysis. Noise reduction is achieved with wavelet transformation by decomposition, thresholding and lossless reconstruction of signal. Three main problems with T-F noise reduction with wavelet transformation are: defining thresholding levels, level of decomposition and number of wavelet vanishing moment. In this analysis decomposition level and number of vanishing moments are defined via simulation for pure sinusoid signal, these values are used for signals with perturbations and they provide reasonable results. Analysis is conducted by simulating various change of parameters and then approved by laboratory measurement with calibrators and precision measurement equipment. The paper describes a method for noise reduction of signal without prior knowledge of noise level or signal amplitude. Proposed method is able to separate noise without adding phase shift for diverse signal conditions, harmonics, interharmonics, dips, swells and dynamic variations.
“…O problema de detecção e classificação de distúrbios de qualidade de energia elétrica (QEE) (FERREIRA, 2010;NAGATA et al, 2018;RIBEIRO et al, 2018).…”
<p><em>Os distúrbios de qualidade de energia elétrica levam a vários inconvenientes, como um aumento da tensão no sistema e nos equipamentos e consequentes perdas; limitação da capacidade de produção; temperaturas operacionais mais altas, falhas prematuras e redução da expectativa de vida das máquinas; mau funcionamento do equipamento e interrupções não planejadas. A detecção e classificação em tempo real de distúrbios são de grande importância para os sistemas de energia. Este artigo propõe o modelo fuzzy evolutivo Takagi-Sugeno (eTS) para a detecção de distúrbios combinado com um método híbrido de seleção de características utilizando o filtro Hodrick-Prescott e a Transformada Rápida de Fourier aplicados sobre uma janela deslizante de sinais de tensão. Os distúrbios spike, notch, inter-harmônico, interrupção curta e harmônico foram considerados. O desempenho de classificação em termos da raiz quadrada do erro quadrático médio (RMSE) e do índice de erro não dimensional (NDEI) mostrou resultados encorajadores. Além disso, o sistema de monitoramento de distúrbios eTS proposto, baseado em fluxo de dados, mostrou ser capaz de aprender novos padrões de distúrbios automaticamente pela adaptação on-line dos parâmetros e estrutura das regras fuzzy.</em></p><p> </p><p><em>Abstract</em></p><p><em>Power quality disturbances lead to several drawbacks such as an increase in line and equipment voltage and consequent ohmic losses; limitation of the production capacity; higher operating temperatures, premature fails, and reduction of life expectancy of machines; malfunction of equipment; and unplanned outages. Real-time detection and classification of disturbances are of great importance for power systems. This paper proposes an evolving Takagi-Sugeno fuzzy model (eTS) framework for disturbance detection combined with a hybrid Hodrick-Prescott and Fast Fourier Transform feature selection method applied over a sliding window of voltage signals. The spike, notch, inter-harmonic, short interruption and harmonic disturbances were considered. Classification performance in terms of the root mean squared error (RMSE) and non-dimensional error index (NDEI) have shown encouraging results. Moreover, the proposed data stream-based eTS disturbance monitoring system has shown to be able to learn new disturbance patterns automatically by online adapting the parameters and structure of fuzzy rules.</em></p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.