Pub Date : 2021-10-13DOI: 10.1109/IECON48115.2021.9589748
O. Safdarzadeh, Martin Weicker, A. Binder
Electrical bearing currents, e.g. in inverted-fed electrical machines, may disturb the performance of the bearings. In this paper the steady-state temperature of the bearing surface at the electrical contact point between the balls and the raceway is derived in the mixed lubrication state. The thermal analysis is presented based on the Holm‘s electric contact model, namely the a-spot. The contact model of Andreason is presented as well for comparison. The results are extended to predict the instantaneous contact surface temperature in an axial bearing (type 51208) at 500 rpm with 1 A average bearing current and with an axial bearing force of 800 N. Moreover the average of the contact surface temperature is obtained for the same bearing in a range of operating points, i.e. a rotating speed from 0 rpm to 3000 rpm, a bearing average current from 0.25 A to 3 A, at an axial bearing force 800 N. The results can be utilized to predict the contact temperature on the bearing surface for any given bearing from the measured bearing voltage.
{"title":"Steady-state Thermal Analysis of the Contact in Bearings Exposed to Electrical Currents","authors":"O. Safdarzadeh, Martin Weicker, A. Binder","doi":"10.1109/IECON48115.2021.9589748","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589748","url":null,"abstract":"Electrical bearing currents, e.g. in inverted-fed electrical machines, may disturb the performance of the bearings. In this paper the steady-state temperature of the bearing surface at the electrical contact point between the balls and the raceway is derived in the mixed lubrication state. The thermal analysis is presented based on the Holm‘s electric contact model, namely the a-spot. The contact model of Andreason is presented as well for comparison. The results are extended to predict the instantaneous contact surface temperature in an axial bearing (type 51208) at 500 rpm with 1 A average bearing current and with an axial bearing force of 800 N. Moreover the average of the contact surface temperature is obtained for the same bearing in a range of operating points, i.e. a rotating speed from 0 rpm to 3000 rpm, a bearing average current from 0.25 A to 3 A, at an axial bearing force 800 N. The results can be utilized to predict the contact temperature on the bearing surface for any given bearing from the measured bearing voltage.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115486340","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589345
Ondrej Suchý, Š. Janouš, J. Talla, Z. Peroutka
The most common control algorithms for PMSM are based on simplified interpretation of the mathematical model, assuming strictly harmonic signals and linear distribution of the magnetic flux of permanent magnets in the air gap. Nevertheless neglected phenomenons in the mathematical mode leads to deterioration of the torque and overall it may lower the efficiency of the machine. Therefore in order to improve efficiency and torque quality, the aforementioned effects needs to be taken into account, when designing mathematical model, where, stator inductance and magnetic flux of permanent magnets are considered a function of the rotor position. the optimal reference current is no longer projected into d, q coordinated system as a static dc value, which significantly increase the demands on the tuning of cascade structure of PI controllers. An alternative is to use predictive control.In this paper we seek for simple and yet robust control with comparable results as a standard solution based on d, q coordinated system and linear controllers. For this purpose we use simple version of predictive control working with limited control action set (FCS-MPC) with precise model defined in rotating d, q reference frame The resulting algorithm provides high quality torque control performance while taking into account Joule losses in the motor.
{"title":"Predictive control of PMSM using improved model of the drive","authors":"Ondrej Suchý, Š. Janouš, J. Talla, Z. Peroutka","doi":"10.1109/IECON48115.2021.9589345","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589345","url":null,"abstract":"The most common control algorithms for PMSM are based on simplified interpretation of the mathematical model, assuming strictly harmonic signals and linear distribution of the magnetic flux of permanent magnets in the air gap. Nevertheless neglected phenomenons in the mathematical mode leads to deterioration of the torque and overall it may lower the efficiency of the machine. Therefore in order to improve efficiency and torque quality, the aforementioned effects needs to be taken into account, when designing mathematical model, where, stator inductance and magnetic flux of permanent magnets are considered a function of the rotor position. the optimal reference current is no longer projected into d, q coordinated system as a static dc value, which significantly increase the demands on the tuning of cascade structure of PI controllers. An alternative is to use predictive control.In this paper we seek for simple and yet robust control with comparable results as a standard solution based on d, q coordinated system and linear controllers. For this purpose we use simple version of predictive control working with limited control action set (FCS-MPC) with precise model defined in rotating d, q reference frame The resulting algorithm provides high quality torque control performance while taking into account Joule losses in the motor.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116084742","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589396
Raghda Hariri, F. Sebaaly, Charles Ibrahim, S. Williamson, H. Kanaan
This paper presents a detailed review on different architecture topologies for Electric Vehicle (EV) charging station. The proposed paper enables to have a solid reference on electric transportation charging station topologies on different levels starting from the infrastructure of common bus to types of chargers and power flow uni/bi-directionality. Besides, two detailed comparative analyses on recent proposed EV architecture topologies based multilevel converters as Cascaded H-Bridge (CHB) and Neutral Point Clamped (NPC) converters are elaborated. The presented CHB analysis tackles enhancements’ attempts on charging time, balancing batteries’ State-Of-Charge (SOC), reducing power losses and balancing capacitors’ voltages. However, the presented NPC analysis includes attempts in improving NPC’s limited voltage balance operation, balancing the bipolar DC bus, regulating load disturbances, enhancing power quality and power utilization. The two analyses are summarized in two comparison tables to sum up the aim and the enhancement of each presented attempt.
{"title":"A Survey on Charging Station Architectures for Electric Transportation","authors":"Raghda Hariri, F. Sebaaly, Charles Ibrahim, S. Williamson, H. Kanaan","doi":"10.1109/IECON48115.2021.9589396","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589396","url":null,"abstract":"This paper presents a detailed review on different architecture topologies for Electric Vehicle (EV) charging station. The proposed paper enables to have a solid reference on electric transportation charging station topologies on different levels starting from the infrastructure of common bus to types of chargers and power flow uni/bi-directionality. Besides, two detailed comparative analyses on recent proposed EV architecture topologies based multilevel converters as Cascaded H-Bridge (CHB) and Neutral Point Clamped (NPC) converters are elaborated. The presented CHB analysis tackles enhancements’ attempts on charging time, balancing batteries’ State-Of-Charge (SOC), reducing power losses and balancing capacitors’ voltages. However, the presented NPC analysis includes attempts in improving NPC’s limited voltage balance operation, balancing the bipolar DC bus, regulating load disturbances, enhancing power quality and power utilization. The two analyses are summarized in two comparison tables to sum up the aim and the enhancement of each presented attempt.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"638 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116212537","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589696
H. Kawai, J. Cordier, R. Kennel, S. Doki
This study presents current control algorithm based on a finite control set model predictive control (FCS-MPC) to achieve both high dynamics and current ripple suppression. In the proposed method, the smoothed voltage vectors with a finite set are applied as a control input candidate to avoid a sudden change in output voltage which generates large current ripple. In addition, the smoothness is determined automatically depending on a drive situation and system’s specification. Owing to this, fast transient response is achieved while keeping small current ripple during drive operation. The simulated and experimental results obtained with a permanent magnet synchronous motor (PMSM) show that the proposed method is effective for current ripple reduction and high dynamics control as compared to traditional FCS-MPC approach.
{"title":"Model Predictive Current Control of PMSM drives for Achieving both Fast Transient Response and Ripple Suppression","authors":"H. Kawai, J. Cordier, R. Kennel, S. Doki","doi":"10.1109/IECON48115.2021.9589696","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589696","url":null,"abstract":"This study presents current control algorithm based on a finite control set model predictive control (FCS-MPC) to achieve both high dynamics and current ripple suppression. In the proposed method, the smoothed voltage vectors with a finite set are applied as a control input candidate to avoid a sudden change in output voltage which generates large current ripple. In addition, the smoothness is determined automatically depending on a drive situation and system’s specification. Owing to this, fast transient response is achieved while keeping small current ripple during drive operation. The simulated and experimental results obtained with a permanent magnet synchronous motor (PMSM) show that the proposed method is effective for current ripple reduction and high dynamics control as compared to traditional FCS-MPC approach.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"39 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116412977","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589831
Simon Göltz, Daniel L. Ossig, Weixin Fu, O. Sawodny
This paper describes a novel nonlinear flatness-based state observer for vehicle dynamics control. The differential flatness property of a nonlinear vehicle model is used to derive a state observer for the lateral dynamics of a vehicle. Furthermore, a second state observer for the combined lateral and longitudinal movement is presented. Additionally, the flat outputs and the state transformations to bring both models into observability normal form are shown and the observer equations are derived. For this purpose, it is shown that the description of the vehicle model in suitable coordinates is necessary. The observers are applied to measurement data of a passenger car. The results show very good estimation results in convergence and tracking. The approach enables linear state estimation for a nonlinear vehicle model with a camera based ground sensor.
{"title":"Nonlinear Flatness-Based Observer for Vehicle Dynamics Control","authors":"Simon Göltz, Daniel L. Ossig, Weixin Fu, O. Sawodny","doi":"10.1109/IECON48115.2021.9589831","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589831","url":null,"abstract":"This paper describes a novel nonlinear flatness-based state observer for vehicle dynamics control. The differential flatness property of a nonlinear vehicle model is used to derive a state observer for the lateral dynamics of a vehicle. Furthermore, a second state observer for the combined lateral and longitudinal movement is presented. Additionally, the flat outputs and the state transformations to bring both models into observability normal form are shown and the observer equations are derived. For this purpose, it is shown that the description of the vehicle model in suitable coordinates is necessary. The observers are applied to measurement data of a passenger car. The results show very good estimation results in convergence and tracking. The approach enables linear state estimation for a nonlinear vehicle model with a camera based ground sensor.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"618 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122695720","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589295
Vidyasagar Tummakuri, T. Chelliah, D. Ronanki
Following the successful commercialization of road-going electric vehicles, zero-emission electric marine vessels are gaining industry focus for absolute battery operation. Due to the low energy density of lithium-ion batteries, low propulsion-powered marine vessels operated frequently over short distances are found suitable for complete battery propulsion. In this paper, a modular multilevel converter (MMC) with symmetrically decentralized onboard battery banks is proposed as a marine traction inverter for a multi-purpose harbor vessel. A novel mathematical model of the marine vessel is proposed to size the propulsion motor, and generate torque-speed commands corresponding to vessel speed during the maneuver. A brief analytical discussion has presented on the selection of motor-converter configuration for marine propulsion application, considering three-phase low-voltage permanent magnet synchronous motor (PMSM) with a two-level inverter and three-phase medium-voltage PMSM with MMC. A short endurance marine drive cycle is simulated with low-speed high torque three-phase PMSM driven by MMC with integrated battery modules (BM). This study leveraged MATLAB/Simulink environment to analyze the operational performance of MMC and BMs during various phases of the short endurance marine drive cycle.
{"title":"Short Endurance Drive Cycle Analysis of MMC Based Absolute Battery Operated Harbor Vessel","authors":"Vidyasagar Tummakuri, T. Chelliah, D. Ronanki","doi":"10.1109/IECON48115.2021.9589295","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589295","url":null,"abstract":"Following the successful commercialization of road-going electric vehicles, zero-emission electric marine vessels are gaining industry focus for absolute battery operation. Due to the low energy density of lithium-ion batteries, low propulsion-powered marine vessels operated frequently over short distances are found suitable for complete battery propulsion. In this paper, a modular multilevel converter (MMC) with symmetrically decentralized onboard battery banks is proposed as a marine traction inverter for a multi-purpose harbor vessel. A novel mathematical model of the marine vessel is proposed to size the propulsion motor, and generate torque-speed commands corresponding to vessel speed during the maneuver. A brief analytical discussion has presented on the selection of motor-converter configuration for marine propulsion application, considering three-phase low-voltage permanent magnet synchronous motor (PMSM) with a two-level inverter and three-phase medium-voltage PMSM with MMC. A short endurance marine drive cycle is simulated with low-speed high torque three-phase PMSM driven by MMC with integrated battery modules (BM). This study leveraged MATLAB/Simulink environment to analyze the operational performance of MMC and BMs during various phases of the short endurance marine drive cycle.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122961393","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589400
X. Hao, Huan Zhang, Jibin Song, Ming Liu, Chengbin Ma
With the development of technology in modern society, more and more electrical and electronic instruments has been invented and used in factories and our daily life. Power supply is the basic and important need of any electrical and electronic appliance, but energy storage technologies for mobile use is far from satisfactory. For instance, one of the most important performance of Electric Vehicle(EV) is the range ability. Because of the constraints of battery capacity and charging consumes a long period of time, range anxiety is the fatal shortcoming of EV.Wireless power transfer(WPT) technology could alleviate the shortcoming of range anxiety to a large extent. With the WPT system’ spread, the charging process could be happening wherever and whenever the EV is parked.In the research area of WPT system, circuits design, coil design, compensation topology and control methods are the four most important parts. Improving the power transfer capacity(including power capacity and the range of transfer distance), system’s reliability and efficiency of the system are the main purposes of this research. By applying medium-frequency and optimized coil design as well as specially designed control strategy, a medium-frequency high-power WPT system is realized.
{"title":"Optimal Coil Design and Control Strategy for a High-power and Medium-frequency Wireless Power Transfer System","authors":"X. Hao, Huan Zhang, Jibin Song, Ming Liu, Chengbin Ma","doi":"10.1109/IECON48115.2021.9589400","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589400","url":null,"abstract":"With the development of technology in modern society, more and more electrical and electronic instruments has been invented and used in factories and our daily life. Power supply is the basic and important need of any electrical and electronic appliance, but energy storage technologies for mobile use is far from satisfactory. For instance, one of the most important performance of Electric Vehicle(EV) is the range ability. Because of the constraints of battery capacity and charging consumes a long period of time, range anxiety is the fatal shortcoming of EV.Wireless power transfer(WPT) technology could alleviate the shortcoming of range anxiety to a large extent. With the WPT system’ spread, the charging process could be happening wherever and whenever the EV is parked.In the research area of WPT system, circuits design, coil design, compensation topology and control methods are the four most important parts. Improving the power transfer capacity(including power capacity and the range of transfer distance), system’s reliability and efficiency of the system are the main purposes of this research. By applying medium-frequency and optimized coil design as well as specially designed control strategy, a medium-frequency high-power WPT system is realized.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122975413","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589453
Abdelhak Borhani, H. Ouadi, Mohamed Najoui
The number of Electric vehicles in the world increases rapidly. To satisfy the vehicles owners, a sufficient number of charging stations will be required especially for smart buildings. The sizing of EV infrastructure in residential parking will support the deployment of the electric vehicles. This paper presents a model for optimizing the number of EV charging stations combining the multi-types charging stations and charging strategies. The objective of the optimization model is to find the suitable number of each station type while minimizing the annualized social cost, which includes the investment cost, operation and maintenance costs. The optimization problem was solved with particle swarm optimization (PSO) algorithm. The results show the impact of using different charging station types on the social cost.
{"title":"Optimal Sizing of Electric Vehicle Charging Stations in Residential Parking","authors":"Abdelhak Borhani, H. Ouadi, Mohamed Najoui","doi":"10.1109/IECON48115.2021.9589453","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589453","url":null,"abstract":"The number of Electric vehicles in the world increases rapidly. To satisfy the vehicles owners, a sufficient number of charging stations will be required especially for smart buildings. The sizing of EV infrastructure in residential parking will support the deployment of the electric vehicles. This paper presents a model for optimizing the number of EV charging stations combining the multi-types charging stations and charging strategies. The objective of the optimization model is to find the suitable number of each station type while minimizing the annualized social cost, which includes the investment cost, operation and maintenance costs. The optimization problem was solved with particle swarm optimization (PSO) algorithm. The results show the impact of using different charging station types on the social cost.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114147011","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589158
Z. Feng, R. Peña-Alzola, Paschalis Seisopoulos, M. Syed, E. Guillo-Sansano, P. Norman, G. Burt
Power hardware-in-the-loop (PHIL) simulation leverages the real-time emulation of a large-scale complex power system, while also enabling the in-depth investigation of novel actual power components and their interactions with the emulated power grid. The dynamics and non-ideal characteristics (e.g., time delay, non-unity gain, and limited bandwidth) of the power interface result in stability and accuracy issues within the PHIL closed-loop simulations. In this paper, a compensation method is proposed to compensate for the non-ideal power interface by maximizing its bandwidth, maintaining its unity-gain characteristic, and compensating for its phase-shift over the frequencies of interest. The accuracy of power signals synchronization and the transparency of power transfer within the PHIL configuration are assessed by employing the error metrics. In conjunction with the frequency-domain stability analysis and the time-domain simulations, a case study is made to validate the proposed compensation method.
{"title":"Interface Compensation for More Accurate Power Transfer and Signal Synchronization within Power Hardware-in-the-Loop Simulation","authors":"Z. Feng, R. Peña-Alzola, Paschalis Seisopoulos, M. Syed, E. Guillo-Sansano, P. Norman, G. Burt","doi":"10.1109/IECON48115.2021.9589158","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589158","url":null,"abstract":"Power hardware-in-the-loop (PHIL) simulation leverages the real-time emulation of a large-scale complex power system, while also enabling the in-depth investigation of novel actual power components and their interactions with the emulated power grid. The dynamics and non-ideal characteristics (e.g., time delay, non-unity gain, and limited bandwidth) of the power interface result in stability and accuracy issues within the PHIL closed-loop simulations. In this paper, a compensation method is proposed to compensate for the non-ideal power interface by maximizing its bandwidth, maintaining its unity-gain characteristic, and compensating for its phase-shift over the frequencies of interest. The accuracy of power signals synchronization and the transparency of power transfer within the PHIL configuration are assessed by employing the error metrics. In conjunction with the frequency-domain stability analysis and the time-domain simulations, a case study is made to validate the proposed compensation method.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114170312","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 : 2021-10-13DOI: 10.1109/IECON48115.2021.9589794
Xinyi Wang, Bo Yang, Qi Liu, Tiankai Jin, Cailian Chen
In photovoltaic (PV) systems, machine learning-based methods have been used for fault detection and diagnosis in the past years, which require large amounts of data. However, fault types in a single PV station are usually insufficient in practice. Due to insufficient and non-identically distributed data, packet loss and privacy concerns, it is difficult to train a model for diagnosing all fault types. To address these issues, in this paper, we propose a decentralized federated learning (FL)-based fault diagnosis method for insulated gate bipolar transistor (IGBT) open-circuits in PV inverters. All PV stations use the convolutional neural network (CNN) to train local diagnosis models. By aggregating neighboring model parameters, each PV station benefits from the fault diagnosis knowledge learned from neighbors and achieves diagnosing all fault types without sharing original data. Extensive experiments are conducted in terms of non-identical data distributions, various transmission channel conditions and whether to use the FL framework. The results are as follows: 1) Using data with non-identical distributions, the collaboratively trained model diagnoses faults accurately and robustly; 2) The continuous transmission and aggregation of model parameters in multiple rounds make it possible to obtain ideal training results even in the presence of packet loss; 3) The proposed method allows each PV station to diagnose all fault types without original data sharing, which protects data privacy.
{"title":"Collaboratively Diagnosing IGBT Open-circuit Faults in Photovoltaic Inverters: A Decentralized Federated Learning-based Method","authors":"Xinyi Wang, Bo Yang, Qi Liu, Tiankai Jin, Cailian Chen","doi":"10.1109/IECON48115.2021.9589794","DOIUrl":"https://doi.org/10.1109/IECON48115.2021.9589794","url":null,"abstract":"In photovoltaic (PV) systems, machine learning-based methods have been used for fault detection and diagnosis in the past years, which require large amounts of data. However, fault types in a single PV station are usually insufficient in practice. Due to insufficient and non-identically distributed data, packet loss and privacy concerns, it is difficult to train a model for diagnosing all fault types. To address these issues, in this paper, we propose a decentralized federated learning (FL)-based fault diagnosis method for insulated gate bipolar transistor (IGBT) open-circuits in PV inverters. All PV stations use the convolutional neural network (CNN) to train local diagnosis models. By aggregating neighboring model parameters, each PV station benefits from the fault diagnosis knowledge learned from neighbors and achieves diagnosing all fault types without sharing original data. Extensive experiments are conducted in terms of non-identical data distributions, various transmission channel conditions and whether to use the FL framework. The results are as follows: 1) Using data with non-identical distributions, the collaboratively trained model diagnoses faults accurately and robustly; 2) The continuous transmission and aggregation of model parameters in multiple rounds make it possible to obtain ideal training results even in the presence of packet loss; 3) The proposed method allows each PV station to diagnose all fault types without original data sharing, which protects data privacy.","PeriodicalId":443337,"journal":{"name":"IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114400009","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：