To alleviate the concern about the safety and reliability of lithium-ion batteries in electric vehicles, the prediction of remaining useful life (RUL) is attracting growing attention. General deterministic approaches focus more on estimating the expected values of RUL, while the inherent uncertainty in RUL has not been fully addressed. In this paper, two probabilistic prediction methods, linear quantile regression (LQR) and quantile regression random forest (QRRF), are proposed to address the above issues. Using a publicly available dataset from MIT, the performance of the proposed methods is validated, and the uncertainty of RUL is discussed. The results show that both methods achieve good performance in the probabilistic prediction while maintaining acceptable deterministic accuracy. However, due to the notable variations in the signal-to-noise ratio in the battery data at different aging cycles, LQR and QRRF exhibit their better prediction performance in the early and late stages of battery life, respectively.
{"title":"Probabilistic Prediction of Remaining Useful Life of Lithium-ion Batteries","authors":"Renjie Zhang, Jialin Li, Yifei Chen, Shiyi Tan, Jiaxu Jiang, Xinmei Yuan","doi":"10.1109/SPIES55999.2022.10082087","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082087","url":null,"abstract":"To alleviate the concern about the safety and reliability of lithium-ion batteries in electric vehicles, the prediction of remaining useful life (RUL) is attracting growing attention. General deterministic approaches focus more on estimating the expected values of RUL, while the inherent uncertainty in RUL has not been fully addressed. In this paper, two probabilistic prediction methods, linear quantile regression (LQR) and quantile regression random forest (QRRF), are proposed to address the above issues. Using a publicly available dataset from MIT, the performance of the proposed methods is validated, and the uncertainty of RUL is discussed. The results show that both methods achieve good performance in the probabilistic prediction while maintaining acceptable deterministic accuracy. However, due to the notable variations in the signal-to-noise ratio in the battery data at different aging cycles, LQR and QRRF exhibit their better prediction performance in the early and late stages of battery life, respectively.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123700308","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}
The timely and accurate identification of abnormal electrical phenomena (AEP) for vehicle-grid coupling system(VGECS) is critical to guarantee the safe and stable operation of vehicles. The topology of VGECS changes dynamically, hence the types of AEP are complex and varied and the VGECS contains not only the single type AEP, but also the type of compound AEP. At present, there are few identification methods for AEP of VGECS, especially for the compound type AEP. In view of this, a method based on wavelet packet transform and extreme gradient boosting(XGBoost) to identify the AEP of VGECS is proposed in this paper. This method not only identifies the single type AEP, but also enables the identification of compound type AEP. The results show that the proposed method has a high recognition accuracy for AEP. At the same time, the method has good real-time performance, which can meet the practical engineering requirements.
{"title":"An Abnormal Electrical Phenomena Identification Method for Vehicle-grid Electrical Coupling System","authors":"Tao Yang, Fulin Zhou, Feifan Liu, Tengyu Tian, Ruixuan Yang, Jinfei Xiong","doi":"10.1109/SPIES55999.2022.10082261","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082261","url":null,"abstract":"The timely and accurate identification of abnormal electrical phenomena (AEP) for vehicle-grid coupling system(VGECS) is critical to guarantee the safe and stable operation of vehicles. The topology of VGECS changes dynamically, hence the types of AEP are complex and varied and the VGECS contains not only the single type AEP, but also the type of compound AEP. At present, there are few identification methods for AEP of VGECS, especially for the compound type AEP. In view of this, a method based on wavelet packet transform and extreme gradient boosting(XGBoost) to identify the AEP of VGECS is proposed in this paper. This method not only identifies the single type AEP, but also enables the identification of compound type AEP. The results show that the proposed method has a high recognition accuracy for AEP. At the same time, the method has good real-time performance, which can meet the practical engineering requirements.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133010569","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082428
Wenkai Yuan, Laijun Chen, Sicheng Deng, S. Mei
Microgrid is usually a nonlinear system composed of heterogeneous distributed generators and has complex stability problems. The traditional passivity-based control methods are facing challenges due to the complexity and uncertainty of the components in microgrid. In this paper, output-differential (OD) passivity, feedback passification and robust stability control of distributed generators are addressed. First, a sufficient condition for nonlinear systems to be robust OD passive is derived by data-driven matrix inequality (DMI) method. Then, a feedback passification design is proposed to render the system robust OD passive. Based on that, we provide a passivity-based robust control method to guarantee the stability of microgrids. Finally, a numerical example is illustrated to demonstrate the effectiveness of the results.
{"title":"Passivity-Based Robust Stability Control of Heterogeneous DGs in Microgrid","authors":"Wenkai Yuan, Laijun Chen, Sicheng Deng, S. Mei","doi":"10.1109/SPIES55999.2022.10082428","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082428","url":null,"abstract":"Microgrid is usually a nonlinear system composed of heterogeneous distributed generators and has complex stability problems. The traditional passivity-based control methods are facing challenges due to the complexity and uncertainty of the components in microgrid. In this paper, output-differential (OD) passivity, feedback passification and robust stability control of distributed generators are addressed. First, a sufficient condition for nonlinear systems to be robust OD passive is derived by data-driven matrix inequality (DMI) method. Then, a feedback passification design is proposed to render the system robust OD passive. Based on that, we provide a passivity-based robust control method to guarantee the stability of microgrids. Finally, a numerical example is illustrated to demonstrate the effectiveness of the results.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130229102","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}
Aiming at the problems of the existing multilevel converters, such as the large number of devices, high loss, and low power density, a novel hybrid multilevel converter (HMC) topology is proposed in this paper. The HMC consists of a three-level neutral-point clamped (NPC) cell configured with Si GTO and a cascaded H-bridge (CHB) cell configured with a mixture of Si IGBT and SiC MOSFET. For this topology, a specific hybrid high-low frequency modulation is proposed to give full play to the advantages of low switching loss of SiC devices and low on-state loss of Si-based devices. In addition, in order to solve the problem of unbalanced capacitor voltage of the hybrid topology sub-modules, an alternate voltage balancing control (AVBC) strategy is proposed. Finally, the feasibility of the HMC topology and modulation is verified by simulation.
{"title":"A Hybrid Multilevel Converter Topology Based on NPC and CHB Series and Its Control Method","authors":"Peng Ren, Chunming Tu, Yuchao Hou, Qi Guo, Zejun Huang, Wenhui Jia","doi":"10.1109/SPIES55999.2022.10082095","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082095","url":null,"abstract":"Aiming at the problems of the existing multilevel converters, such as the large number of devices, high loss, and low power density, a novel hybrid multilevel converter (HMC) topology is proposed in this paper. The HMC consists of a three-level neutral-point clamped (NPC) cell configured with Si GTO and a cascaded H-bridge (CHB) cell configured with a mixture of Si IGBT and SiC MOSFET. For this topology, a specific hybrid high-low frequency modulation is proposed to give full play to the advantages of low switching loss of SiC devices and low on-state loss of Si-based devices. In addition, in order to solve the problem of unbalanced capacitor voltage of the hybrid topology sub-modules, an alternate voltage balancing control (AVBC) strategy is proposed. Finally, the feasibility of the HMC topology and modulation is verified by simulation.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131685481","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082178
Yang Jian, Liu Xiao, Dong Mi, Song Dongran, Li Li, Huang Liansheng
Constant power loads (CPLs) in the DC microgrids will lead to the instability of the bus voltage, so the power variation range needs to be limited. In this paper, a based on machine learning critical value prediction method is proposed for CPLs. Firstly, Pearson correlation analysis is used to find the factors that have effects on CPLs critical value in terms of droop coefficient and bus voltage. Then, support vector machine and Gaussian process regression prediction model of CPLs critical value are established. Finally, different scenarios of DC microgrid are established to verify the proposed algorithms. The results show that machine learning algorithms can accurately predict the critical value of CPLs, and compared with support vector machine, Gaussian process regression method has higher prediction accuracy and universality.
{"title":"Research on Constant Power Loads Stability of DC Microgrid Based on Machine Learning","authors":"Yang Jian, Liu Xiao, Dong Mi, Song Dongran, Li Li, Huang Liansheng","doi":"10.1109/SPIES55999.2022.10082178","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082178","url":null,"abstract":"Constant power loads (CPLs) in the DC microgrids will lead to the instability of the bus voltage, so the power variation range needs to be limited. In this paper, a based on machine learning critical value prediction method is proposed for CPLs. Firstly, Pearson correlation analysis is used to find the factors that have effects on CPLs critical value in terms of droop coefficient and bus voltage. Then, support vector machine and Gaussian process regression prediction model of CPLs critical value are established. Finally, different scenarios of DC microgrid are established to verify the proposed algorithms. The results show that machine learning algorithms can accurately predict the critical value of CPLs, and compared with support vector machine, Gaussian process regression method has higher prediction accuracy and universality.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128993108","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082111
Shuang Qie, Jian Dou, Xuan Liu, Yue Tang, Yupeng Zhang, Yi Zheng
With the increasing application of communication technologies, the distributed secondary control in the islanded microgrids (MGs) is in danger due to previously unheard-of denial-of-service (DoS) attacks. Current studies rarely delve into how DoS attacks affect frequency restoration and active power sharing and their defensive strategies. In this paper, we firstly design the principle of random number generation (RNG) to verify the correctness of the transmission data. Then, the implementation of the RNG-based DoS attack-resilient distributed control strategy is able to effectively detect and mitigate DoS attacks, meanwhile, improving the resilience of MGs. Eventually, an islanded MG test system is simulated by using the MATLAB/Simulink toolbox. The simulation results reveal that the proposed RNG-based DoS attack-resilient strategy is feasible and effective under normal and high-frequency DoS attacks.
{"title":"Random Number Generation Based DoS Attack-resilient Distributed Secondary Control Strategy","authors":"Shuang Qie, Jian Dou, Xuan Liu, Yue Tang, Yupeng Zhang, Yi Zheng","doi":"10.1109/SPIES55999.2022.10082111","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082111","url":null,"abstract":"With the increasing application of communication technologies, the distributed secondary control in the islanded microgrids (MGs) is in danger due to previously unheard-of denial-of-service (DoS) attacks. Current studies rarely delve into how DoS attacks affect frequency restoration and active power sharing and their defensive strategies. In this paper, we firstly design the principle of random number generation (RNG) to verify the correctness of the transmission data. Then, the implementation of the RNG-based DoS attack-resilient distributed control strategy is able to effectively detect and mitigate DoS attacks, meanwhile, improving the resilience of MGs. Eventually, an islanded MG test system is simulated by using the MATLAB/Simulink toolbox. The simulation results reveal that the proposed RNG-based DoS attack-resilient strategy is feasible and effective under normal and high-frequency DoS attacks.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129078946","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082612
Luo Qi-Quan, Lei Yuan-lin, Huang Yuan-feng, Fan Zhipeng
In this paper, an on-line monitoring system of DC intelligent circuit breaker based on ARM and FPGA is designed. The system integrates the functions of fault recording, fault diagnosis, fault logging, and current monitoring. Considering the minimum breaking time of the circuit breaker reaches 2ms, collecting enough fault current data within 2ms is a problem in system design. To solve it, the system utilizes the property that FPGA does not occupy CPU and the high-speed throughput rate of AD7606 to realize high-speed sampling of current at the speed of 100 KSPS. ARM's rich hardware resources and perfect development environment ensure the control of the system and current data transmission. After verification, the results show that the recording rate of the system reaches 100KSPS, the time scale accuracy of the current recording data is up to 1ms, and the current monitoring error reaches 0.2%.
{"title":"On-line Monitoring System of DC Intelligent Circuit Breaker Based on ARM and FPGA","authors":"Luo Qi-Quan, Lei Yuan-lin, Huang Yuan-feng, Fan Zhipeng","doi":"10.1109/SPIES55999.2022.10082612","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082612","url":null,"abstract":"In this paper, an on-line monitoring system of DC intelligent circuit breaker based on ARM and FPGA is designed. The system integrates the functions of fault recording, fault diagnosis, fault logging, and current monitoring. Considering the minimum breaking time of the circuit breaker reaches 2ms, collecting enough fault current data within 2ms is a problem in system design. To solve it, the system utilizes the property that FPGA does not occupy CPU and the high-speed throughput rate of AD7606 to realize high-speed sampling of current at the speed of 100 KSPS. ARM's rich hardware resources and perfect development environment ensure the control of the system and current data transmission. After verification, the results show that the recording rate of the system reaches 100KSPS, the time scale accuracy of the current recording data is up to 1ms, and the current monitoring error reaches 0.2%.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"163 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129268996","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}
The increasing market penetration of electric vehicles (EVs) has brought many challenges to the operation of power systems. It is essential to find a way to properly guide EVs’ charging and discharging behaviors and motivate the EVs with vehicle-to-grid (V2G) potential to participate in the scheduling. This paper proposes a game-based bargaining model for trading between EVs and the hybrid AC/DC microgrid. In this model, EVs act as followers and aim to find the optimal charging and discharging solution that maximizes the payoff function while satisfying the orderly charging and discharging constraints. The hybrid AC/DC microgrid takes the leader position and sets the trading price with the objective of minimizing its operation cost. The model is solved iteratively to obtain the Nash equilibrium. A case study has been carried out to illustrate the effectiveness of the proposed model.
{"title":"A Game Theory-Based Bargaining Model between Electric Vehicles and the Hybrid AC/DC Microgrid","authors":"Yuxuan Ai, Yibin Qiu, Qi Li, Lanjia Huang, Wei-rong Chen","doi":"10.1109/SPIES55999.2022.10082513","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082513","url":null,"abstract":"The increasing market penetration of electric vehicles (EVs) has brought many challenges to the operation of power systems. It is essential to find a way to properly guide EVs’ charging and discharging behaviors and motivate the EVs with vehicle-to-grid (V2G) potential to participate in the scheduling. This paper proposes a game-based bargaining model for trading between EVs and the hybrid AC/DC microgrid. In this model, EVs act as followers and aim to find the optimal charging and discharging solution that maximizes the payoff function while satisfying the orderly charging and discharging constraints. The hybrid AC/DC microgrid takes the leader position and sets the trading price with the objective of minimizing its operation cost. The model is solved iteratively to obtain the Nash equilibrium. A case study has been carried out to illustrate the effectiveness of the proposed model.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128811904","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082268
Yuhang Sun, Kang Xie, Yi Li, Baozhong Zhou, Shijie Sun, Jiguang Zhang
To reduce carbon emissions, renewable energies (REs) are significantly increasing, whose intermittent and uncertainty bring huge operation risks to the power system. More regulation resources are needed to balance the power generation and the power consumption. However, the traditional fossil energy generators are phasing out and cannot provide enough regulation capacity. With advances in information and communication technologies, flexible loads can be utilized to provide regulation services for the power system. Before flexible loads participate in regulating, it is necessary for power system operators to obtain their schedule potential in advance. Schedule potential evaluation of flexible loads is a huge challenge due to the variety of their types and operation modes. To address this issue, a large number of studies have given different evaluation methods. This paper investigates the schedule potential evaluation methods of different types of flexible loads, including model-based methods, grey box-based methods and big data-based methods. On this basis, some suggestions on the schedule potential evaluation of flexible loads are proposed to improve the accuracy in power system regulation services.
{"title":"Review of Evaluating Schedule Potential of Flexible Loads in Regulation Services of Power Systems","authors":"Yuhang Sun, Kang Xie, Yi Li, Baozhong Zhou, Shijie Sun, Jiguang Zhang","doi":"10.1109/SPIES55999.2022.10082268","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082268","url":null,"abstract":"To reduce carbon emissions, renewable energies (REs) are significantly increasing, whose intermittent and uncertainty bring huge operation risks to the power system. More regulation resources are needed to balance the power generation and the power consumption. However, the traditional fossil energy generators are phasing out and cannot provide enough regulation capacity. With advances in information and communication technologies, flexible loads can be utilized to provide regulation services for the power system. Before flexible loads participate in regulating, it is necessary for power system operators to obtain their schedule potential in advance. Schedule potential evaluation of flexible loads is a huge challenge due to the variety of their types and operation modes. To address this issue, a large number of studies have given different evaluation methods. This paper investigates the schedule potential evaluation methods of different types of flexible loads, including model-based methods, grey box-based methods and big data-based methods. On this basis, some suggestions on the schedule potential evaluation of flexible loads are proposed to improve the accuracy in power system regulation services.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126691999","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 : 2022-12-09DOI: 10.1109/SPIES55999.2022.10082410
Yuancheng Qin, Xianqiang Li, Boyu Ren, Qin Yan, Kang He
Obtaining the breakdown voltage of the air gap by the artificial intelligence algorithm is helpful to reduce the workload of the test. In this paper, the support vector machine (SVM) is used to predict the positive 50% switching impulse breakdown voltage (U50%+) between tubular buses in 220kV substations. The features reflecting the electric field distribution are extracted from the shortest discharge path of the air gap, and the breakdown voltage prediction models are established. The predicted results indicate that the range of U50%+ of the tubular bus gap in the 220kV substations with a gap distance of 3.325 meters is 1540kV-1589kV. The predicted value is within the range of breakdown voltage recommended in the IEC standard. This method may provide a reference for air gap insulation prediction engineering applications.
{"title":"Prediction of Switching Impulse Breakdown Voltage of the Air Gap Between Tubular Buses in Substation","authors":"Yuancheng Qin, Xianqiang Li, Boyu Ren, Qin Yan, Kang He","doi":"10.1109/SPIES55999.2022.10082410","DOIUrl":"https://doi.org/10.1109/SPIES55999.2022.10082410","url":null,"abstract":"Obtaining the breakdown voltage of the air gap by the artificial intelligence algorithm is helpful to reduce the workload of the test. In this paper, the support vector machine (SVM) is used to predict the positive 50% switching impulse breakdown voltage (U50%+) between tubular buses in 220kV substations. The features reflecting the electric field distribution are extracted from the shortest discharge path of the air gap, and the breakdown voltage prediction models are established. The predicted results indicate that the range of U50%+ of the tubular bus gap in the 220kV substations with a gap distance of 3.325 meters is 1540kV-1589kV. The predicted value is within the range of breakdown voltage recommended in the IEC standard. This method may provide a reference for air gap insulation prediction engineering applications.","PeriodicalId":412421,"journal":{"name":"2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123259935","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：