Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808554
G. N. Lopes, T. S. Menezes, J. Vieira
High Impedance Faults (HIFs) occur due to the contact between an energized conductor and a high impedance surface. Due to the potential dangers caused by HIFs, several methods have been proposed for their identification over the years. Nonetheless, there is still no fully effective technique for their identification. Therefore, this paper proposes indices for evaluating metrics extracted from HIF signals. The goal is to point out the advantages and drawbacks of the selected metrics, aiming to support researchers in developing more effective identification methods. The analyses were performed by using actual HIF signals on soil and vegetation, and the proposed indices are roughness, local inclination, and the global tendency of the metrics. The results revealed relevant characteristics of each metric that can be employed for identifying HIFs, supporting the development of new detection methods.
{"title":"Evaluation of Metrics to Detect High Impedance Faults Using Real Current Signals","authors":"G. N. Lopes, T. S. Menezes, J. Vieira","doi":"10.1109/ICHQP53011.2022.9808554","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808554","url":null,"abstract":"High Impedance Faults (HIFs) occur due to the contact between an energized conductor and a high impedance surface. Due to the potential dangers caused by HIFs, several methods have been proposed for their identification over the years. Nonetheless, there is still no fully effective technique for their identification. Therefore, this paper proposes indices for evaluating metrics extracted from HIF signals. The goal is to point out the advantages and drawbacks of the selected metrics, aiming to support researchers in developing more effective identification methods. The analyses were performed by using actual HIF signals on soil and vegetation, and the proposed indices are roughness, local inclination, and the global tendency of the metrics. The results revealed relevant characteristics of each metric that can be employed for identifying HIFs, supporting the development of new detection methods.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116799625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808614
Y. Y. Chen, G. Chang, G. Y. Li, H. J. Chen, J. Z. Wu
This paper presents an implementation of a measuring system for harmonic analysis of energy-saving lamps. The proposed system includes a hardware circuit design, the LabVIEW-based harmonic analysis algorithm, graphical user interface, and a database for measured data management. In the harmonic analysis, a frequency-domain interpolation method is firstly adopted to determine the system fundamental frequency. Then the fast Fourier transform (FFT) is used to analyze the measured waveforms produced by different lamps. The developed system is tested using different brands of modern energy-saving lighting devices and shows its effectiveness in analyzing the harmonics produced.
{"title":"Development of Harmonics Measurement System for Energy-Saving Lamps-An Educational Platform","authors":"Y. Y. Chen, G. Chang, G. Y. Li, H. J. Chen, J. Z. Wu","doi":"10.1109/ICHQP53011.2022.9808614","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808614","url":null,"abstract":"This paper presents an implementation of a measuring system for harmonic analysis of energy-saving lamps. The proposed system includes a hardware circuit design, the LabVIEW-based harmonic analysis algorithm, graphical user interface, and a database for measured data management. In the harmonic analysis, a frequency-domain interpolation method is firstly adopted to determine the system fundamental frequency. Then the fast Fourier transform (FFT) is used to analyze the measured waveforms produced by different lamps. The developed system is tested using different brands of modern energy-saving lighting devices and shows its effectiveness in analyzing the harmonics produced.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126175397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808722
Ahmadreza Eslami, M. Negnevitsky, E. Franklin, S. Lyden
Harmonics and waveform distortion are substantial power quality concerns for power systems with high penetration of renewable energy generation and non-linear loads. Harmonics and interharmonics should be mitigated for efficient and proper operation of power grids, with high harmonic injection from electric loads and devices. In this paper, an intelligent Active Power Filter (APF) based on Adaptive Linear Neuron (Adaline) is proposed which can provide accurate harmonic estimation and proper mitigation in real-time without any prior knowledge about harmonic/interharmonic orders. A novel formulation is derived, and adaptive learning with momentum is used for training. The proposed APF not only inherits the high adaptability of Adaline APFs but also compensates for their drawbacks by updating weights in the presence of unknown frequency orders. Additionally, an electric topology is proposed where one APF is able to mitigate harmonics of nonlinear loads connected to two adjacent Points of Common Coupling (PCCs). For a radial structure, harmonic currents from the grid are completely mitigated while for a ring structure, only harmonics from one side of the grid are mitigated. Highly varying and distorted load scenarios are studied. Comparison of the proposed APF with the state-of-the- art APFs in the literature proves the effectiveness and suitability of the proposed intelligent APF.
{"title":"An Intelligent Active Power Filter to Mitigate Harmonics and Interharmonics","authors":"Ahmadreza Eslami, M. Negnevitsky, E. Franklin, S. Lyden","doi":"10.1109/ICHQP53011.2022.9808722","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808722","url":null,"abstract":"Harmonics and waveform distortion are substantial power quality concerns for power systems with high penetration of renewable energy generation and non-linear loads. Harmonics and interharmonics should be mitigated for efficient and proper operation of power grids, with high harmonic injection from electric loads and devices. In this paper, an intelligent Active Power Filter (APF) based on Adaptive Linear Neuron (Adaline) is proposed which can provide accurate harmonic estimation and proper mitigation in real-time without any prior knowledge about harmonic/interharmonic orders. A novel formulation is derived, and adaptive learning with momentum is used for training. The proposed APF not only inherits the high adaptability of Adaline APFs but also compensates for their drawbacks by updating weights in the presence of unknown frequency orders. Additionally, an electric topology is proposed where one APF is able to mitigate harmonics of nonlinear loads connected to two adjacent Points of Common Coupling (PCCs). For a radial structure, harmonic currents from the grid are completely mitigated while for a ring structure, only harmonics from one side of the grid are mitigated. Highly varying and distorted load scenarios are studied. Comparison of the proposed APF with the state-of-the- art APFs in the literature proves the effectiveness and suitability of the proposed intelligent APF.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115357089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808643
D. F. Resende, C. Duque, E. Nepomuceno, M. Lima, L. Silva
Power quality (PQ) assessment has proven to be important in recent years for the power grid. The influence of the instrumentation transformer frequency response on some PQ metrics can be critical. For example, the measurement of harmonics can exhibit great inaccuracy if the measurement transformers have a frequency response that is not constant in the frequency range of interest. This problem is very similar to that found in communication systems where a non-ideal communication channel distorts the transmitted information. Thus the channel equalization approach can be used to adaptively compensate for the distortions caused by the current and voltage transducers. In the equalization approach, adaptive filtering algorithms such as RLS (Recursive Least Square) and LMS (Least Mean Squares) are commonly used to find the equalization filter coefficients. In this work, the novelty is adaptive channel equalization methodology applied to compensate for the frequency response of instrumentation transformers. Simulated results show that the methodology can reduce significantly the TVE (Total Vector Error) caused by voltage and current transformers.
{"title":"Adaptive Channel Equalization for Frequency Response Correction of Instrument Transformers","authors":"D. F. Resende, C. Duque, E. Nepomuceno, M. Lima, L. Silva","doi":"10.1109/ICHQP53011.2022.9808643","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808643","url":null,"abstract":"Power quality (PQ) assessment has proven to be important in recent years for the power grid. The influence of the instrumentation transformer frequency response on some PQ metrics can be critical. For example, the measurement of harmonics can exhibit great inaccuracy if the measurement transformers have a frequency response that is not constant in the frequency range of interest. This problem is very similar to that found in communication systems where a non-ideal communication channel distorts the transmitted information. Thus the channel equalization approach can be used to adaptively compensate for the distortions caused by the current and voltage transducers. In the equalization approach, adaptive filtering algorithms such as RLS (Recursive Least Square) and LMS (Least Mean Squares) are commonly used to find the equalization filter coefficients. In this work, the novelty is adaptive channel equalization methodology applied to compensate for the frequency response of instrumentation transformers. Simulated results show that the methodology can reduce significantly the TVE (Total Vector Error) caused by voltage and current transformers.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116552455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808642
Alessandra B G Hoffmann, C. H. Beuter, M. Oleskovicz
The Oscillatory Transient (OT) has defined characteristics such as a small duration, considerable variations in the voltage and frequency amplitude and can manifest itself in any part of an Electric Power System (EPS). The switching of Capacitor Banks (CBs) mainly causes the OT. The complete methodology to analyse this kind of disturbance should contemplate the study of detection of the beginning of an OT until the extraction of the main characteristics of the analyzed signal. In this research, Mathematical Morphology (MM) is applied to identify the beginning of an OT, focusing on the expansion, opening, and Dilation-Erosion Difference Filter (DEDF) filter operations. In the sequence, a matching search (MPA–Matching Pursuit Algorithm) was applied to extract parameters from a structured data dictionary. Among the results, the application of DEDF stands out, which better identifies the beginning of OT, allowing the parameters of frequency (f), damping (λ) and angle of phase (ϕ) extracted to represent and characterize the analyzed signals.
{"title":"An investigative study of the application of fundamental operations of mathematical morphology in the diagnosis of oscillatory transients","authors":"Alessandra B G Hoffmann, C. H. Beuter, M. Oleskovicz","doi":"10.1109/ICHQP53011.2022.9808642","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808642","url":null,"abstract":"The Oscillatory Transient (OT) has defined characteristics such as a small duration, considerable variations in the voltage and frequency amplitude and can manifest itself in any part of an Electric Power System (EPS). The switching of Capacitor Banks (CBs) mainly causes the OT. The complete methodology to analyse this kind of disturbance should contemplate the study of detection of the beginning of an OT until the extraction of the main characteristics of the analyzed signal. In this research, Mathematical Morphology (MM) is applied to identify the beginning of an OT, focusing on the expansion, opening, and Dilation-Erosion Difference Filter (DEDF) filter operations. In the sequence, a matching search (MPA–Matching Pursuit Algorithm) was applied to extract parameters from a structured data dictionary. Among the results, the application of DEDF stands out, which better identifies the beginning of OT, allowing the parameters of frequency (f), damping (λ) and angle of phase (ϕ) extracted to represent and characterize the analyzed signals.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122691838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808683
T. Antić, T. Capuder
With the development of technologies and the decrease of prices, the number of end-users that decide to invest in distributed energy resources (DERs) continuously grows. Despite the improvement of financial and environmental aspects of the power system operation, a growing share of DERs can cause numerous technical challenges for distribution system operators (DSOs). Besides the integration of DERs, the novel COVID-19 disease created additional challenges for DSOs in 2020 and 2021. Due to a large number of single-phase loads and DERs, the increased consumption, the number of nonlinear loads, and power electronic devices in a distribution network, many challenges are related to power quality (PQ). In this paper, realistic case studies that consider anomalies caused by the COVID-19 pandemic and integration of DERs are presented. By using pandapower and its newly developed extension, different PQ indicators are calculated and the values of voltage magnitude, voltage unbalance factor (VUF), and total harmonic distortion (THD) are compared through different scenarios. In addition, the impact of a transformer’s vector group on the PQ indicators’ propagation through the observed distribution network is analyzed. In a conclusion, the optimal vector group, that successfully mitigates or at least decreases the values of PQ indicators and their propagation is proposed.
{"title":"Analysis of power quality concerning COVID-19-related anomalies and integration of distributed energy resources","authors":"T. Antić, T. Capuder","doi":"10.1109/ICHQP53011.2022.9808683","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808683","url":null,"abstract":"With the development of technologies and the decrease of prices, the number of end-users that decide to invest in distributed energy resources (DERs) continuously grows. Despite the improvement of financial and environmental aspects of the power system operation, a growing share of DERs can cause numerous technical challenges for distribution system operators (DSOs). Besides the integration of DERs, the novel COVID-19 disease created additional challenges for DSOs in 2020 and 2021. Due to a large number of single-phase loads and DERs, the increased consumption, the number of nonlinear loads, and power electronic devices in a distribution network, many challenges are related to power quality (PQ). In this paper, realistic case studies that consider anomalies caused by the COVID-19 pandemic and integration of DERs are presented. By using pandapower and its newly developed extension, different PQ indicators are calculated and the values of voltage magnitude, voltage unbalance factor (VUF), and total harmonic distortion (THD) are compared through different scenarios. In addition, the impact of a transformer’s vector group on the PQ indicators’ propagation through the observed distribution network is analyzed. In a conclusion, the optimal vector group, that successfully mitigates or at least decreases the values of PQ indicators and their propagation is proposed.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117000967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808823
Xiaoxi Wang, H. J. Kaleybar, M. Brenna, D. Zaninelli
With the visible mitigation of the energy crisis, the distribution network is being challenged by the explosive growth of different EVs, and their infrastructures. The integration of such systems may bring forward multiple challenges to the electrical grid due to G2V and V2G capabilities. One of the main challenges is power quality (PQ) issues caused by EV charging infrastructures (EVCIs). The diversity and emergence of new technologies of EVCIs have made remarkable types of bilateral interactions together with reliability and PQ phenomena. The essential aim of this paper is to classify and explain these PQ indices in detail, which gives a comprehensive perspective to engineers and researchers working on potential PQ problems.
{"title":"Power Quality Indicators of Electric Vehicles in Distribution Grid","authors":"Xiaoxi Wang, H. J. Kaleybar, M. Brenna, D. Zaninelli","doi":"10.1109/ICHQP53011.2022.9808823","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808823","url":null,"abstract":"With the visible mitigation of the energy crisis, the distribution network is being challenged by the explosive growth of different EVs, and their infrastructures. The integration of such systems may bring forward multiple challenges to the electrical grid due to G2V and V2G capabilities. One of the main challenges is power quality (PQ) issues caused by EV charging infrastructures (EVCIs). The diversity and emergence of new technologies of EVCIs have made remarkable types of bilateral interactions together with reliability and PQ phenomena. The essential aim of this paper is to classify and explain these PQ indices in detail, which gives a comprehensive perspective to engineers and researchers working on potential PQ problems.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128718782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808607
Yovanny Ramirez, A. Ramirez, G. Lazaroiu
This paper presents a harmonic domain (HD) model of a high-voltage direct current (HVDC) system including controls for DC voltage and reactive power via the secant method. The proportional-integral (PI) control scheme is used to verify the results by the secant method. It is shown that the latter achieves computational savings compared to the PI control scheme. A case study is presented and verified with the PSCAD/EMTDC software tool in terms of harmonics and steady state waveforms.
{"title":"Secant Method Applied to Control of HVDC in the Harmonic Domain","authors":"Yovanny Ramirez, A. Ramirez, G. Lazaroiu","doi":"10.1109/ICHQP53011.2022.9808607","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808607","url":null,"abstract":"This paper presents a harmonic domain (HD) model of a high-voltage direct current (HVDC) system including controls for DC voltage and reactive power via the secant method. The proportional-integral (PI) control scheme is used to verify the results by the secant method. It is shown that the latter achieves computational savings compared to the PI control scheme. A case study is presented and verified with the PSCAD/EMTDC software tool in terms of harmonics and steady state waveforms.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124683025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808705
F. Napolitano, F. Tossani, A. Borghetti, A. Andreotti
The paper compares two computational tools for the calculation of the overvoltages induced by indirect lightnings, namely LIOV and CiLIV. Both tools were already validated against experimental results and with each other, showing a good agreement, in general. Some limited discrepancies in the voltage waveforms have been documented in previous papers due to different assumptions and numerical issues that the present contribution aims at assessing. Moreover, this paper compares the results of both calculation tools with those reported in the literature for a reduced-scale experiment and for the case of a power line with surge arresters installed every 500 m.
{"title":"Comparison between two Calculation Tools for the Appraisal of Lightning Induced Voltages","authors":"F. Napolitano, F. Tossani, A. Borghetti, A. Andreotti","doi":"10.1109/ICHQP53011.2022.9808705","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808705","url":null,"abstract":"The paper compares two computational tools for the calculation of the overvoltages induced by indirect lightnings, namely LIOV and CiLIV. Both tools were already validated against experimental results and with each other, showing a good agreement, in general. Some limited discrepancies in the voltage waveforms have been documented in previous papers due to different assumptions and numerical issues that the present contribution aims at assessing. Moreover, this paper compares the results of both calculation tools with those reported in the literature for a reduced-scale experiment and for the case of a power line with surge arresters installed every 500 m.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"503 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130386407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.1109/ICHQP53011.2022.9808673
Rafael S. Salles, G. C. S. Almeida, P. F. Ribeiro
The electrical power systems have gone through a process of transformations that will remain characterized by a wide penetration of renewable sources, electronic devices, and computerization. In this context, Power Quality (PQ) is associated with several challenges for the sector, presenting new issues and new scenarios for old problems. Signal processing (SP) plays an essential role in PQ applications as a tool that helps measure, characterize, and visualize electrical grid disturbances. At the same time, artificial intelligence (AI) is becomming more and more useful to classification tasks regarding PQ disturbances . This work aims to employ a transfer learning methodology for PQ disturbances classification. Wavelet scalograms of the signal are created using CWT for feature extraction of time-frequency signatures. The 2-D images of this representation are used to train and test pre-trained CNN models’ performance. The work aims to contribute to PQ disturbances classification through innovative methods and assess the performance of different CNNs models that have a significant role in image classification. The performance of four network models is assessed: ResNet-18, VGG-19, Inception-v3, and ResNet-101. Discussion and consideration about the results provide evaluation of the methodology.
{"title":"Classification of Scalogram Signatures for Power Quality Disturbances Using Transfer Learning","authors":"Rafael S. Salles, G. C. S. Almeida, P. F. Ribeiro","doi":"10.1109/ICHQP53011.2022.9808673","DOIUrl":"https://doi.org/10.1109/ICHQP53011.2022.9808673","url":null,"abstract":"The electrical power systems have gone through a process of transformations that will remain characterized by a wide penetration of renewable sources, electronic devices, and computerization. In this context, Power Quality (PQ) is associated with several challenges for the sector, presenting new issues and new scenarios for old problems. Signal processing (SP) plays an essential role in PQ applications as a tool that helps measure, characterize, and visualize electrical grid disturbances. At the same time, artificial intelligence (AI) is becomming more and more useful to classification tasks regarding PQ disturbances . This work aims to employ a transfer learning methodology for PQ disturbances classification. Wavelet scalograms of the signal are created using CWT for feature extraction of time-frequency signatures. The 2-D images of this representation are used to train and test pre-trained CNN models’ performance. The work aims to contribute to PQ disturbances classification through innovative methods and assess the performance of different CNNs models that have a significant role in image classification. The performance of four network models is assessed: ResNet-18, VGG-19, Inception-v3, and ResNet-101. Discussion and consideration about the results provide evaluation of the methodology.","PeriodicalId":249133,"journal":{"name":"2022 20th International Conference on Harmonics & Quality of Power (ICHQP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114524611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：