Pub Date : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709491
J. F. Guerreiro, Victor C. Arruda, Hildo Guillardi, J. Pomilio
This work proposes a LCL-filter design method and its current control to grid-connected inverters. It is well known that the LCL filter may excite instabilities due to its resonance characteristics. For instance, in modern grids, the impedance is uncertain and the LCL resonant frequency might be driven towards the control system bandwidth, what might excite instabilities or oscillations. The design methodology proposed in this work ensures that the LCL resonant frequency is within a desired frequency region even under severe grid impedances variations. Along with, the control system is also designed regarding such extreme scenarios. A comparison between active and passive damping techniques is done and a dq reference frame current control is used for evaluation. For experimental purposes, an equivalent single-phase prototype is used for validation of the proposed methodology.
{"title":"LCL Filter Design and Damping Analysis for Grid-Connected Inverters in Modern Uncertain Grid Impedance Conditions","authors":"J. F. Guerreiro, Victor C. Arruda, Hildo Guillardi, J. Pomilio","doi":"10.1109/SPEC52827.2021.9709491","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709491","url":null,"abstract":"This work proposes a LCL-filter design method and its current control to grid-connected inverters. It is well known that the LCL filter may excite instabilities due to its resonance characteristics. For instance, in modern grids, the impedance is uncertain and the LCL resonant frequency might be driven towards the control system bandwidth, what might excite instabilities or oscillations. The design methodology proposed in this work ensures that the LCL resonant frequency is within a desired frequency region even under severe grid impedances variations. Along with, the control system is also designed regarding such extreme scenarios. A comparison between active and passive damping techniques is done and a dq reference frame current control is used for evaluation. For experimental purposes, an equivalent single-phase prototype is used for validation of the proposed methodology.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132551904","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709307
Breno Ventorim Comarella, L. Encarnação
This paper proposes a comparison between three model predictive control strategies Optimal Switching Vector (OSV-MPC), Modulated Model predictive Control (M2PC) and Optimal Switching Sequence (OSS-MPC). OSV-MPC is simple, intuitive to implement and has a fast transient response. However, the technique produces a variable switching frequency. M2PC and OSS-MPC are recent techniques to achieve a fixed switching frequency with the main advantages of OSV-MPC. The strategies will be presented and Matlab®/Simulink simulation comparison, in transient and steady state, will be implemented for a VSI with output LC filter.
{"title":"Comparison of Model Predictive Control Strategies for Voltage Source Inverter with Output LC Filter","authors":"Breno Ventorim Comarella, L. Encarnação","doi":"10.1109/SPEC52827.2021.9709307","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709307","url":null,"abstract":"This paper proposes a comparison between three model predictive control strategies Optimal Switching Vector (OSV-MPC), Modulated Model predictive Control (M2PC) and Optimal Switching Sequence (OSS-MPC). OSV-MPC is simple, intuitive to implement and has a fast transient response. However, the technique produces a variable switching frequency. M2PC and OSS-MPC are recent techniques to achieve a fixed switching frequency with the main advantages of OSV-MPC. The strategies will be presented and Matlab®/Simulink simulation comparison, in transient and steady state, will be implemented for a VSI with output LC filter.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133138286","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709462
E. Mudaheranwa, E. Ntagwirumugara, Delphin Bampire, Amuza Godfrey, R. Byiringiro, Augustin Munyaneza, G. Masengo, M. G. Berwa
For the purposes of this study, the authors simulate an active power filter using Matlab software. The work looks at an active power filter, which is commonly used in electrical systems to decrease the quantity of harmonics occurring. Harmonic voltages or currents are defined as alternating currents or voltages with a frequency that is an integral multiple of the fundamental frequency. Harmonics degrade the degree of power effectiveness and productivity in an industrial or commercial facility by conflicting with the passage of electrons in that facility. Harmonic mitigation devices are a type of device that injects a mirror image waveform of the harmonic component of a distorted waveform, which is an active power filter, into the deformed waveform, thus lowering its harmonic content. Active power filters, despite being a relatively new and expensive technology, have a number of major advantages that should be thoroughly investigated before being applied. The operation of the system is verified using the Matlab/Simulink simulation tool. The active power filter and the Matlab verification technique are explored in greater detail after an overview of harmonic distortion difficulties and the repercussions of these issues for power quality. As a result of the study, the total harmonic distortion of the source current is decreased from 19.5 percent to 0 percent, allowing it to comply with the harmonic standard (IEEE STD. 519-1992) for the first time.
{"title":"Reduction of harmonics using Active Power Filters in Electric Power System","authors":"E. Mudaheranwa, E. Ntagwirumugara, Delphin Bampire, Amuza Godfrey, R. Byiringiro, Augustin Munyaneza, G. Masengo, M. G. Berwa","doi":"10.1109/SPEC52827.2021.9709462","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709462","url":null,"abstract":"For the purposes of this study, the authors simulate an active power filter using Matlab software. The work looks at an active power filter, which is commonly used in electrical systems to decrease the quantity of harmonics occurring. Harmonic voltages or currents are defined as alternating currents or voltages with a frequency that is an integral multiple of the fundamental frequency. Harmonics degrade the degree of power effectiveness and productivity in an industrial or commercial facility by conflicting with the passage of electrons in that facility. Harmonic mitigation devices are a type of device that injects a mirror image waveform of the harmonic component of a distorted waveform, which is an active power filter, into the deformed waveform, thus lowering its harmonic content. Active power filters, despite being a relatively new and expensive technology, have a number of major advantages that should be thoroughly investigated before being applied. The operation of the system is verified using the Matlab/Simulink simulation tool. The active power filter and the Matlab verification technique are explored in greater detail after an overview of harmonic distortion difficulties and the repercussions of these issues for power quality. As a result of the study, the total harmonic distortion of the source current is decreased from 19.5 percent to 0 percent, allowing it to comply with the harmonic standard (IEEE STD. 519-1992) for the first time.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"129 Pt 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131185397","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709450
Mariana N. Cunha e Silva, S. M. Silva, I. Pires
The implementation of microgrids including distributed energy resources is an efficient energy solution with regard to saving financial and environmental resources and assisting in the stability and reliability of the power system. However, some unwanted effects such as voltage fluctuations, unbalance, frequency changes and harmonic distortions due to the Distributed Renewable Generations (DRGs) and non-linear loads operations may affect the power quality within the microgrid, making necessary studies and analyzes, to maintain the quality indicators at satisfactory levels. The power quality in systems with distributed generation (DG) is discussed in papers mostly through mathematical and computational modeling and these do not allow the consideration of equipment operation characteristics. It is therefore necessary to complement the theoretical studies with experimental results [1]. This study aims to evaluate the power quality at the connection point where a microgrid was installed on a university campus to characterize the energy scenario to which the microgrid will be submitted. It was found that the system had a monthly average of22.9 voltage sag events, 1.8 interruptions per month, 2.37% of total voltage harmonic distortion, 0.283% of voltage fluctuation, and unbalance below 0.5%.
{"title":"Power Quality Evaluation in a Microgrid Implementation","authors":"Mariana N. Cunha e Silva, S. M. Silva, I. Pires","doi":"10.1109/SPEC52827.2021.9709450","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709450","url":null,"abstract":"The implementation of microgrids including distributed energy resources is an efficient energy solution with regard to saving financial and environmental resources and assisting in the stability and reliability of the power system. However, some unwanted effects such as voltage fluctuations, unbalance, frequency changes and harmonic distortions due to the Distributed Renewable Generations (DRGs) and non-linear loads operations may affect the power quality within the microgrid, making necessary studies and analyzes, to maintain the quality indicators at satisfactory levels. The power quality in systems with distributed generation (DG) is discussed in papers mostly through mathematical and computational modeling and these do not allow the consideration of equipment operation characteristics. It is therefore necessary to complement the theoretical studies with experimental results [1]. This study aims to evaluate the power quality at the connection point where a microgrid was installed on a university campus to characterize the energy scenario to which the microgrid will be submitted. It was found that the system had a monthly average of22.9 voltage sag events, 1.8 interruptions per month, 2.37% of total voltage harmonic distortion, 0.283% of voltage fluctuation, and unbalance below 0.5%.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126859719","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709493
T. Cheng, R. Aguilera, D. Lu, Y. Siwakoti
Zero-sequence injection (ZSI) techniques are widely adopted in Wye- and Delta-connected cascaded H-bridge (CHB) three-phase systems to cope with the unbalanced power generation from each phase. Recent studies have shown that a ZSI can allow a $triangle-$connected CHB converter to cope with a large range of power imbalances among phases when compared to a standard Y-connected CHB converter. The superiority in the electrical performance under unbalanced input power has been well investigated, however the comparative thermal performance for both configurations under same power imbalance condition has not been investigated. In this work, the thermal performance of a CHB converter connected in both $triangle-$configuration and Yconfiguration operating under an unbalanced power condition is studied. For this, the enquired ZSI for both $triangle-$ and Y-connected CHB converters is firstly analyzed. Then, the impact of ZSI on the thermal performance and lifetime expectancy of the power switches in each phase is evaluated and compared for both configurations. The thermal analysis carried out in this work shows that even though a $triangle-$connected CHB converter offer a wider power imbalance operation than Y-connected counterpart from the electrical viewpoint, this is achieved by thermally stressing the power switches in each phase in an uneven manner, and in some case overstressing them. Consequently, there is a trade-off between electrical performance and thermal stress when dealing with power imbalances in $triangle$-connected and Y-connected CHB converters.
{"title":"Evaluation of Thermal Performance of Three-Phase Systems With Zero Sequence Injection","authors":"T. Cheng, R. Aguilera, D. Lu, Y. Siwakoti","doi":"10.1109/SPEC52827.2021.9709493","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709493","url":null,"abstract":"Zero-sequence injection (ZSI) techniques are widely adopted in Wye- and Delta-connected cascaded H-bridge (CHB) three-phase systems to cope with the unbalanced power generation from each phase. Recent studies have shown that a ZSI can allow a $triangle-$connected CHB converter to cope with a large range of power imbalances among phases when compared to a standard Y-connected CHB converter. The superiority in the electrical performance under unbalanced input power has been well investigated, however the comparative thermal performance for both configurations under same power imbalance condition has not been investigated. In this work, the thermal performance of a CHB converter connected in both $triangle-$configuration and Yconfiguration operating under an unbalanced power condition is studied. For this, the enquired ZSI for both $triangle-$ and Y-connected CHB converters is firstly analyzed. Then, the impact of ZSI on the thermal performance and lifetime expectancy of the power switches in each phase is evaluated and compared for both configurations. The thermal analysis carried out in this work shows that even though a $triangle-$connected CHB converter offer a wider power imbalance operation than Y-connected counterpart from the electrical viewpoint, this is achieved by thermally stressing the power switches in each phase in an uneven manner, and in some case overstressing them. Consequently, there is a trade-off between electrical performance and thermal stress when dealing with power imbalances in $triangle$-connected and Y-connected CHB converters.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":" 31","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133019854","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709473
Kenneth Rakwach, P. Musau, A. Nyete
Renewable sources of energy have particular characteristics which make grid integration and long-distance transmission onerous. For one, the existing transmission infrastructure cannot, at its present state, accommodate features of RE for reliable integration with the grid and subsequent transmission. Wind, for example is very unpredictable- the ripple effect of this unpredictability is that the availability of power output will also fluctuate so much so that without auxiliary support, secure, reliable and quality power cannot be dispatched. Another set of complexity is the location of RE power plants that are significantly miles away from the intended Point of Use (PoU) centers. This makes VSC-HVDC the most appropriate technology that can harmonize the challenges of RE integration and transmission in one-fold. The VSC-HVDC transmission link was simulated in a MATLAB environment for offshore wind integration and results reveal the need to adopt VSC-HVDC as the most compatible technology for integrating and transmitting RE.
{"title":"The Role of HVDC Technology in Transmission Planning with Renewable Energy Integration: A Case of Wind Energy","authors":"Kenneth Rakwach, P. Musau, A. Nyete","doi":"10.1109/SPEC52827.2021.9709473","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709473","url":null,"abstract":"Renewable sources of energy have particular characteristics which make grid integration and long-distance transmission onerous. For one, the existing transmission infrastructure cannot, at its present state, accommodate features of RE for reliable integration with the grid and subsequent transmission. Wind, for example is very unpredictable- the ripple effect of this unpredictability is that the availability of power output will also fluctuate so much so that without auxiliary support, secure, reliable and quality power cannot be dispatched. Another set of complexity is the location of RE power plants that are significantly miles away from the intended Point of Use (PoU) centers. This makes VSC-HVDC the most appropriate technology that can harmonize the challenges of RE integration and transmission in one-fold. The VSC-HVDC transmission link was simulated in a MATLAB environment for offshore wind integration and results reveal the need to adopt VSC-HVDC as the most compatible technology for integrating and transmitting RE.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129879216","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709310
T. Jacob, Bamikole David Oluwatimilehin
Information on the parameter of power system supply is vital to the utilities and the consumers of electricity particularly in the deregulated power industry where competition is key. This paper presents the development of household power quality monitoring system. The quality and quantity of power consumption by a consumer on real time is displayed and stored for future reference, whenever the quality of power is compromised the supply to the end user is interrupted and an alarm is raised at the end user side. This was achieved by using a voltage sensor, current sensor and operational amplifier to measure required fundamental quantities while the derived quantities are determined by micro-controller programmed in C language which displays and store the reading obtained at intervals, also a buzzer and relay was interfaced with the micro-controller to raise alarm and cut-off epileptic power supply. With this project, household equipment and sensitive devices can be operated without the risk of been damaged; also record of power parameters measured can be obtained from the storage unit for further references and data modeling.
{"title":"Development of Household Power Quality Monitoring System","authors":"T. Jacob, Bamikole David Oluwatimilehin","doi":"10.1109/SPEC52827.2021.9709310","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709310","url":null,"abstract":"Information on the parameter of power system supply is vital to the utilities and the consumers of electricity particularly in the deregulated power industry where competition is key. This paper presents the development of household power quality monitoring system. The quality and quantity of power consumption by a consumer on real time is displayed and stored for future reference, whenever the quality of power is compromised the supply to the end user is interrupted and an alarm is raised at the end user side. This was achieved by using a voltage sensor, current sensor and operational amplifier to measure required fundamental quantities while the derived quantities are determined by micro-controller programmed in C language which displays and store the reading obtained at intervals, also a buzzer and relay was interfaced with the micro-controller to raise alarm and cut-off epileptic power supply. With this project, household equipment and sensitive devices can be operated without the risk of been damaged; also record of power parameters measured can be obtained from the storage unit for further references and data modeling.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114207406","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709312
Zhongzheng Lin, U. Madawala, C. Baguley, Yeran Liu, R. Mai
Dynamic wireless power transfer systems (DWPTSs) improve the mileage and reduce the battery weight of electric vehicles (EVs). Generally, DWPTSs use a 3-phase transmitting coil structure to wirelessly charge moving EVs at a constant rate, but this 3-phase coil structure has not been compared with other possible multi-phase coil structures. Therefore, this paper investigates the suitability of possible and non-conventional multi-phase distributed coil structures for DWPTSs, which are compatible with existing EV static wireless charging standards. The principle of travelling waves is utilized to analyze the continuous and constant power profiles produced by multi-phase distributed coil structures. The output power levels and fluctuations, costs, and electro-magnetic interference (EMI) of multi-phase systems are compared, and the results are presented with key findings highlighted.
{"title":"Comparative Study on Multi-Phase Dynamic Wireless Power Transfer Systems","authors":"Zhongzheng Lin, U. Madawala, C. Baguley, Yeran Liu, R. Mai","doi":"10.1109/SPEC52827.2021.9709312","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709312","url":null,"abstract":"Dynamic wireless power transfer systems (DWPTSs) improve the mileage and reduce the battery weight of electric vehicles (EVs). Generally, DWPTSs use a 3-phase transmitting coil structure to wirelessly charge moving EVs at a constant rate, but this 3-phase coil structure has not been compared with other possible multi-phase coil structures. Therefore, this paper investigates the suitability of possible and non-conventional multi-phase distributed coil structures for DWPTSs, which are compatible with existing EV static wireless charging standards. The principle of travelling waves is utilized to analyze the continuous and constant power profiles produced by multi-phase distributed coil structures. The output power levels and fluctuations, costs, and electro-magnetic interference (EMI) of multi-phase systems are compared, and the results are presented with key findings highlighted.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127518883","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709458
Nipuna Rajapaksha, S. Jayasinghe, H. Enshaei, N. Jayarathne
The excellent generalisation ability of the Support Vector Machine (SVM) algorithm has made it one of the most popular statistical learning theories in supervised machine learning. The classification accuracy and effectiveness of SVM is highly sensitive to the kernel function used during the training process. This paper compares linear, polynomial, and Gaussian kernel functions for evaluating their contribution to SVM for accurately and effectively classifying healthy and faulty status of rotating machinery. A three-phase induction motor and a four-stroke diesel engine were considered as the machinery for this study. Acoustic signals coming from these machines were collected using microphones and Fast Fourier Transform (FFT) was used to extract the magnitudes of the dominant frequency components of the signals. The extracted ominant frequency components are considered as acoustic signatures and their variations are taken as condition monitoring parameters. The results show that with the second-order polynomial kernel function, SVM achieved an accuracy of at least 2.4% greater than the other kernel functions with 1.2% less training time. Furthermore, the third-order polynomial kernel function found to be the second best choice.
{"title":"Sensitivity Analysis of SVM Kernel Functions in Machinery Condition Classification","authors":"Nipuna Rajapaksha, S. Jayasinghe, H. Enshaei, N. Jayarathne","doi":"10.1109/SPEC52827.2021.9709458","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709458","url":null,"abstract":"The excellent generalisation ability of the Support Vector Machine (SVM) algorithm has made it one of the most popular statistical learning theories in supervised machine learning. The classification accuracy and effectiveness of SVM is highly sensitive to the kernel function used during the training process. This paper compares linear, polynomial, and Gaussian kernel functions for evaluating their contribution to SVM for accurately and effectively classifying healthy and faulty status of rotating machinery. A three-phase induction motor and a four-stroke diesel engine were considered as the machinery for this study. Acoustic signals coming from these machines were collected using microphones and Fast Fourier Transform (FFT) was used to extract the magnitudes of the dominant frequency components of the signals. The extracted ominant frequency components are considered as acoustic signatures and their variations are taken as condition monitoring parameters. The results show that with the second-order polynomial kernel function, SVM achieved an accuracy of at least 2.4% greater than the other kernel functions with 1.2% less training time. Furthermore, the third-order polynomial kernel function found to be the second best choice.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128878594","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 : 2021-12-06DOI: 10.1109/SPEC52827.2021.9709441
A. Wadsworth, Brandon Pais, Shaun Kyle, D. Thrimawithana, R. Badcock, A. Lapthorn, B. Heffernan, R. Oliver, D. Wallis, Martin Neuberger
Superconducting motors are a solution to electrifying large scale transport (aviation, rail, shipping) due to their superior power density over conventional electric motors. Cooling a superconducting motor and its power converter using the same cryogenic system provides a unique opportunity to increase the converter’s power density. This paper evaluates how conventional power converter components and emerging Gallium Nitride (GaN) technologies would fare at cryogenic temperatures. It is shown that GaN devices have a significant reduction in conduction losses at cryogenic temperatures. The behaviour of integrated circuits varies depending on device technology (CMOS, BJT, JFET), while temperature variation in capacitors depends on their dielectric material.
{"title":"Evaluating Common Electronic Components and GaN HEMTs Under Cryogenic Conditions","authors":"A. Wadsworth, Brandon Pais, Shaun Kyle, D. Thrimawithana, R. Badcock, A. Lapthorn, B. Heffernan, R. Oliver, D. Wallis, Martin Neuberger","doi":"10.1109/SPEC52827.2021.9709441","DOIUrl":"https://doi.org/10.1109/SPEC52827.2021.9709441","url":null,"abstract":"Superconducting motors are a solution to electrifying large scale transport (aviation, rail, shipping) due to their superior power density over conventional electric motors. Cooling a superconducting motor and its power converter using the same cryogenic system provides a unique opportunity to increase the converter’s power density. This paper evaluates how conventional power converter components and emerging Gallium Nitride (GaN) technologies would fare at cryogenic temperatures. It is shown that GaN devices have a significant reduction in conduction losses at cryogenic temperatures. The behaviour of integrated circuits varies depending on device technology (CMOS, BJT, JFET), while temperature variation in capacitors depends on their dielectric material.","PeriodicalId":236251,"journal":{"name":"2021 IEEE Southern Power Electronics Conference (SPEC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125638385","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：