Pub Date : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621723
Yongjun Zhou, Chaonan Ji, Zhihua Dong, Lin Yang, Shu Zhang
The sequence-to-point model has achieved remarkable results in load disaggregation. It relies on a trained deep neural network to identify the power consumption of a single appliance from aggregate load data. However, the model has an over-fitting phenomenon, which makes the loss of the model to the training set small, and it is difficult to obtain a high accuracy rate in the test set. Therefore, it is necessary to use appropriate methods to modify the model to eliminate over-fitting and achieve a higher appliance recognition rate. As a result, the power prediction deviation for a single appliance is relatively large. For example, in the washing machine, the deviation between the predicted value and the ground value can reach more than 90%. So far, there is no documented method to eliminate the over-fitting phenomenon of this model. Therefore, this paper proposes the use of L2 regularization and Dropout to adjust and modify its network. The results show that the increased network architecture and over-fitting elimination methods can improve the decomposition results. The prediction accuracy rate of a single appliance is improved to more than 10%.
{"title":"Elimination of Overfitting of Non-intrusive Load Monitoring Model","authors":"Yongjun Zhou, Chaonan Ji, Zhihua Dong, Lin Yang, Shu Zhang","doi":"10.1109/ICPSAsia52756.2021.9621723","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621723","url":null,"abstract":"The sequence-to-point model has achieved remarkable results in load disaggregation. It relies on a trained deep neural network to identify the power consumption of a single appliance from aggregate load data. However, the model has an over-fitting phenomenon, which makes the loss of the model to the training set small, and it is difficult to obtain a high accuracy rate in the test set. Therefore, it is necessary to use appropriate methods to modify the model to eliminate over-fitting and achieve a higher appliance recognition rate. As a result, the power prediction deviation for a single appliance is relatively large. For example, in the washing machine, the deviation between the predicted value and the ground value can reach more than 90%. So far, there is no documented method to eliminate the over-fitting phenomenon of this model. Therefore, this paper proposes the use of L2 regularization and Dropout to adjust and modify its network. The results show that the increased network architecture and over-fitting elimination methods can improve the decomposition results. The prediction accuracy rate of a single appliance is improved to more than 10%.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132979584","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621386
Tao Xu, Yong Wang, Hanbing Qu, Pu Zhao, Yan Wang
This paper studies the reliability evaluation algorithm of complex distribution networks. In order to simplify the analysis process, components in the network are divided and equivalent to different virtual devices to eliminate the quantity of devices by the two-step process in fault process. According to the phenomenon of repeated fault analysis during the simulation process, a historical fault list is constructed to store the fault data for subsequent simulation. The data is dynamically updated by sequential list search method within the simulation process. On the basis of above methods, combining with the impact analysis, the reliability assessment method on historical fault is proposed. Finally, by using the proposed method and algorithm, this paper takes a modified RBTS BUS6 system to illustrate the high efficiency and correctness of the proposed method in the paper.
{"title":"A Fast Reliability Assessment Method Based on Sequential Monte Carlo Simulation Considering Historical Fault Data","authors":"Tao Xu, Yong Wang, Hanbing Qu, Pu Zhao, Yan Wang","doi":"10.1109/ICPSAsia52756.2021.9621386","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621386","url":null,"abstract":"This paper studies the reliability evaluation algorithm of complex distribution networks. In order to simplify the analysis process, components in the network are divided and equivalent to different virtual devices to eliminate the quantity of devices by the two-step process in fault process. According to the phenomenon of repeated fault analysis during the simulation process, a historical fault list is constructed to store the fault data for subsequent simulation. The data is dynamically updated by sequential list search method within the simulation process. On the basis of above methods, combining with the impact analysis, the reliability assessment method on historical fault is proposed. Finally, by using the proposed method and algorithm, this paper takes a modified RBTS BUS6 system to illustrate the high efficiency and correctness of the proposed method in the paper.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132585956","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621509
Yuqin Xu, Keyi Xu
The integrated energy system (IES) has great application prospect in future energy system. Due to the high coupling of energy flow in the system, the dispatch operation needs to consider the unified dispatch of multiple energy sources. At present, the operation scheduling research of the integrated energy system mostly focuses on the single-objective optimization problem with the best economic cost, and the environmental protection and efficiency of the system are less considered. A multi-objective optimization scheduling model is proposed in this paper, taking the lowest operating cost, the lowest pollutant emissions, and the highest comprehensive energy utilization rate as objective functions. The Normal Boundary Intersection (NBI) method is adopted to solve this model and the partial small fuzzy set decision is used to get the best solution. Finally, the proposed model is verified on an IES of an industrial park in central China. The case study demonstrates that the proposed optimization scheduling model can generally make the system operation more environmentally friendly and efficient.
{"title":"Multi-objective Optimal Dispatching of the Integrated Energy System in the Industrial Park","authors":"Yuqin Xu, Keyi Xu","doi":"10.1109/ICPSAsia52756.2021.9621509","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621509","url":null,"abstract":"The integrated energy system (IES) has great application prospect in future energy system. Due to the high coupling of energy flow in the system, the dispatch operation needs to consider the unified dispatch of multiple energy sources. At present, the operation scheduling research of the integrated energy system mostly focuses on the single-objective optimization problem with the best economic cost, and the environmental protection and efficiency of the system are less considered. A multi-objective optimization scheduling model is proposed in this paper, taking the lowest operating cost, the lowest pollutant emissions, and the highest comprehensive energy utilization rate as objective functions. The Normal Boundary Intersection (NBI) method is adopted to solve this model and the partial small fuzzy set decision is used to get the best solution. Finally, the proposed model is verified on an IES of an industrial park in central China. The case study demonstrates that the proposed optimization scheduling model can generally make the system operation more environmentally friendly and efficient.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131439817","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621757
Pengcheng Cao, Yong Lu, Changbo Lu
The structure of coil in wireless power transfer affects the transmission performance. When a fixed excitation source is matched with appropriate transmitting and receiving coils, the electromagnetic energy can be fully utilized. In order to study the lightweight requirements on special occasions, the relationship between coil turns and receiving performance must be investigated. This paper designs and uses the simplest structure of monolayer planar coils which winded closely by ordinary copper enameled wire and fixed in 25 mm inner diameter, 0.5 mm strand diameter. According to modeling and simulation, the coil parameters and mutual inductance are obtained after the transmitting and receiving coils turns changed respectively, the simulation results are also verified by experiments. Finally, based on experiments, the variation empirical model of receiver voltage is concluded, which can provides a prediction model for the wireless charging power control of lightweight equipment.
{"title":"The Effects of Monolayer Planar Coil Turns Change in Low-Frequency Wireless Power Transfer","authors":"Pengcheng Cao, Yong Lu, Changbo Lu","doi":"10.1109/ICPSAsia52756.2021.9621757","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621757","url":null,"abstract":"The structure of coil in wireless power transfer affects the transmission performance. When a fixed excitation source is matched with appropriate transmitting and receiving coils, the electromagnetic energy can be fully utilized. In order to study the lightweight requirements on special occasions, the relationship between coil turns and receiving performance must be investigated. This paper designs and uses the simplest structure of monolayer planar coils which winded closely by ordinary copper enameled wire and fixed in 25 mm inner diameter, 0.5 mm strand diameter. According to modeling and simulation, the coil parameters and mutual inductance are obtained after the transmitting and receiving coils turns changed respectively, the simulation results are also verified by experiments. Finally, based on experiments, the variation empirical model of receiver voltage is concluded, which can provides a prediction model for the wireless charging power control of lightweight equipment.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128871887","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}
In this paper, an improved steady-state initialization method is proposed for electromagnetic transient analysis of photovoltaic grid-connected system, which enables an EMT simulation to start from steady-state directly. The improved method is based on power flow solution, and it determines the steady state operating characteristics of the system network from the given line and bus data. Then, based on the power flow, the ac system and the filter steady state are obtained by replacing converter bridge with a three-phase voltage. Furthermore, in consideration of the control system steady state, the PI controller initial values are set as the steady state values. EMT simulation for the photovoltaic grid-connected power generation system with 6-bus is performed on Cloud-PSS platform. Comparing with the traditional zero-state initialization method, the proposed method has faster response and smoother transient with necessary accuracy.
{"title":"Research on Initialization of EMT Simulation for Photovoltaic Grid-Connected System","authors":"Zhihong Liu, Peng Cong, Zhiwei Xu, Yafei Zhang, Yankan Song, Ying Chen","doi":"10.1109/ICPSAsia52756.2021.9621577","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621577","url":null,"abstract":"In this paper, an improved steady-state initialization method is proposed for electromagnetic transient analysis of photovoltaic grid-connected system, which enables an EMT simulation to start from steady-state directly. The improved method is based on power flow solution, and it determines the steady state operating characteristics of the system network from the given line and bus data. Then, based on the power flow, the ac system and the filter steady state are obtained by replacing converter bridge with a three-phase voltage. Furthermore, in consideration of the control system steady state, the PI controller initial values are set as the steady state values. EMT simulation for the photovoltaic grid-connected power generation system with 6-bus is performed on Cloud-PSS platform. Comparing with the traditional zero-state initialization method, the proposed method has faster response and smoother transient with necessary accuracy.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115231087","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621515
Shaorong Cai, Y. Tao, Li Shen, Zhenlin Ni, Jianliang Gao, Wenju Liang, Y. Wen
Based on the single machine model, the key factors affecting the frequency response of the system are studied, the expressions of the initial frequency change rate and the maximum frequency deviation after large disturbance are derived, and the mechanism of improving the frequency stability of conventional units and new energy frequency response, DC frequency modulation, load frequency response, emergency control and other factors is analyzed. According to the frequency response characteristics of Southwest Power Grid, the over-frequency generator tripping scheme is designed from the aspects of high frequency generator tripping object, starting threshold, generator tripping capacity, etc., and the coordination principle of high cycle generator tripping, generator overspeed protection and low frequency load shedding is proposed. The effectiveness of the proposed scheme is verified by practical examples.
{"title":"Frequency Characteristics of Southwest Power Grid and Scheme of Over-Frequency Generator Tripping","authors":"Shaorong Cai, Y. Tao, Li Shen, Zhenlin Ni, Jianliang Gao, Wenju Liang, Y. Wen","doi":"10.1109/ICPSAsia52756.2021.9621515","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621515","url":null,"abstract":"Based on the single machine model, the key factors affecting the frequency response of the system are studied, the expressions of the initial frequency change rate and the maximum frequency deviation after large disturbance are derived, and the mechanism of improving the frequency stability of conventional units and new energy frequency response, DC frequency modulation, load frequency response, emergency control and other factors is analyzed. According to the frequency response characteristics of Southwest Power Grid, the over-frequency generator tripping scheme is designed from the aspects of high frequency generator tripping object, starting threshold, generator tripping capacity, etc., and the coordination principle of high cycle generator tripping, generator overspeed protection and low frequency load shedding is proposed. The effectiveness of the proposed scheme is verified by practical examples.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124190033","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621663
Yu Zhou, Xuecen Zhang, Yi Tang, Zhuowen Mu, Xuesong Shao, Yue Li, Qixin Cai
Electricity theft is a severe issue that causes huge revenue loss for utility companies and influences stable operation of power system. With the development of big data analysis, electricity theft detection (ETD) based on data-driven method has received massive attention. However, since available data in low-voltage (LV) network is usually sparse and imbalanced, most of the existing data-driven ETD methods are not applicable to residential customers. In light of this issue, we proposed a convolution neural network (CNN) and data augmentation method for ETD. This method applies kernel density estimator (KDE) and monte carlo method to expand dataset. Then CNN model is implemented on the dataset for classification. Experiment using realistic electricity usage data has been conducted to verify the effectiveness of this method, results show that this method can achieve high performance in terms of different metrics.
{"title":"Convolutional Neural Network and Data Augmentation Method for Electricity Theft Detection","authors":"Yu Zhou, Xuecen Zhang, Yi Tang, Zhuowen Mu, Xuesong Shao, Yue Li, Qixin Cai","doi":"10.1109/ICPSAsia52756.2021.9621663","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621663","url":null,"abstract":"Electricity theft is a severe issue that causes huge revenue loss for utility companies and influences stable operation of power system. With the development of big data analysis, electricity theft detection (ETD) based on data-driven method has received massive attention. However, since available data in low-voltage (LV) network is usually sparse and imbalanced, most of the existing data-driven ETD methods are not applicable to residential customers. In light of this issue, we proposed a convolution neural network (CNN) and data augmentation method for ETD. This method applies kernel density estimator (KDE) and monte carlo method to expand dataset. Then CNN model is implemented on the dataset for classification. Experiment using realistic electricity usage data has been conducted to verify the effectiveness of this method, results show that this method can achieve high performance in terms of different metrics.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124235841","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621470
Likai Liu, Zechun Hu, Jian Ning, Yilin Wen
The rapid development of renewable energy has increased the peak to valley difference of the netload, making the netload follwing being a new challenge to the power system. Electric boiler with thermal storage (EBTS) occupies a nonnegligible part of the load in the winter season in Northern China. EBTS operation optimization can not only save its own energy cost but also reduce the peak shaving and valley filling pressure of the system. To this end, the operation optimization of EBTS for providing the power balancing service is studied in this paper, which mainly includes three parts: First, the joint probability distribution between the predicted and actual temperatures is built by utilizing the Copula theory; Secondly, the actual temperatures are sampled based on the predicted temperatures of the next day, and the scenario set is generated by clustering these samples, where K-means clustering method are used; Thirdly, the stochastic operation optimization model of EBTS considering the uncertainty of outdoor temperature is constructed. Through the case study, it is found that the proposed method can save the total operation cost of the EBTS compared with the deterministic EBTS operation optimization model.
{"title":"Data-Driven Scheduling of Electric Boiler with Thermal Storage for Providing Power Balancing Service","authors":"Likai Liu, Zechun Hu, Jian Ning, Yilin Wen","doi":"10.1109/ICPSAsia52756.2021.9621470","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621470","url":null,"abstract":"The rapid development of renewable energy has increased the peak to valley difference of the netload, making the netload follwing being a new challenge to the power system. Electric boiler with thermal storage (EBTS) occupies a nonnegligible part of the load in the winter season in Northern China. EBTS operation optimization can not only save its own energy cost but also reduce the peak shaving and valley filling pressure of the system. To this end, the operation optimization of EBTS for providing the power balancing service is studied in this paper, which mainly includes three parts: First, the joint probability distribution between the predicted and actual temperatures is built by utilizing the Copula theory; Secondly, the actual temperatures are sampled based on the predicted temperatures of the next day, and the scenario set is generated by clustering these samples, where K-means clustering method are used; Thirdly, the stochastic operation optimization model of EBTS considering the uncertainty of outdoor temperature is constructed. Through the case study, it is found that the proposed method can save the total operation cost of the EBTS compared with the deterministic EBTS operation optimization model.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124544336","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 : 2021-07-18DOI: 10.1109/ICPSAsia52756.2021.9621502
Bohan Xu, Yue Xiang, Li Pan, Mengqiu Fang, Junyong Liu, You-bo Liu, Tianhao Wang
With the rapid development of distributed renewable energy, the traditional energy node model has been difficult to adapt to the energy information coupling system. Aiming at the problem that traditional energy node model is difficult to combine information flow and energy flow to establish a rapid response mechanism, this paper uses machine learning to build an agent model based on data and model, which can balance disturbance automatically and tend to run well automatically. Firstly, the scheduling objective and energy converter of the multi-energy system (MES) are modeled, then the agent model is introduced, the observation variables and action space of agent are defined, and the reward function is constructed. After that, the solution process of DDPG algorithm is introduced, and the parameter of DDPG algorithm is completed. Finally, an example is given to verify the effectiveness of the proposed method.
{"title":"Agent-Based Optimal Cooperative Operation of Multi-energy System","authors":"Bohan Xu, Yue Xiang, Li Pan, Mengqiu Fang, Junyong Liu, You-bo Liu, Tianhao Wang","doi":"10.1109/ICPSAsia52756.2021.9621502","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621502","url":null,"abstract":"With the rapid development of distributed renewable energy, the traditional energy node model has been difficult to adapt to the energy information coupling system. Aiming at the problem that traditional energy node model is difficult to combine information flow and energy flow to establish a rapid response mechanism, this paper uses machine learning to build an agent model based on data and model, which can balance disturbance automatically and tend to run well automatically. Firstly, the scheduling objective and energy converter of the multi-energy system (MES) are modeled, then the agent model is introduced, the observation variables and action space of agent are defined, and the reward function is constructed. After that, the solution process of DDPG algorithm is introduced, and the parameter of DDPG algorithm is completed. Finally, an example is given to verify the effectiveness of the proposed method.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114886987","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}
In the DC transmission system, due to the limitations of technology, a large number of harmonics will be generated and reactive power will be consumed when the converter performs current conversion. In order not to burden the power grid, each converter station will automatically put in the corresponding AC filter bank on the AC side according to the transmission power during operation. To analyze the fault information of the circuit breaker in time, this paper proposes a fault diagnosis method for the AC filter circuit breaker of the converter station based on the combination of RBF neural network and expert experience method. For fault diagnosis based on RBF neural network, the recorded waveform of AC filter circuit breaker is used as input, and the judgement of whether the waveform is abnormal is used as output. For fault diagnosis based on expert experience method, an expert experience library is established, and the waveform of the AC filter circuit breaker is also used as the expert diagnosis input, whether the waveform is abnormal is used as the output. It is mainly based on the threshold of the current difference, the failure threshold of the closing resistance, etc. to determine whether the AC filter circuit breaker has a potential fault. The example results show that this method can find the potential fault information of the AC filter circuit breaker and issue an early warning before the protection device operates.
{"title":"Diagnosis Method of AC Filter Circuit Breaker in Converter Station Based on RBF Neural Network and Expert Experience Method","authors":"Bingjiang Chai, Lei Shi, Ruopeng Liu, Chunxiang Mao, Jiayu Kang, Zhixian Zhang","doi":"10.1109/ICPSAsia52756.2021.9621611","DOIUrl":"https://doi.org/10.1109/ICPSAsia52756.2021.9621611","url":null,"abstract":"In the DC transmission system, due to the limitations of technology, a large number of harmonics will be generated and reactive power will be consumed when the converter performs current conversion. In order not to burden the power grid, each converter station will automatically put in the corresponding AC filter bank on the AC side according to the transmission power during operation. To analyze the fault information of the circuit breaker in time, this paper proposes a fault diagnosis method for the AC filter circuit breaker of the converter station based on the combination of RBF neural network and expert experience method. For fault diagnosis based on RBF neural network, the recorded waveform of AC filter circuit breaker is used as input, and the judgement of whether the waveform is abnormal is used as output. For fault diagnosis based on expert experience method, an expert experience library is established, and the waveform of the AC filter circuit breaker is also used as the expert diagnosis input, whether the waveform is abnormal is used as the output. It is mainly based on the threshold of the current difference, the failure threshold of the closing resistance, etc. to determine whether the AC filter circuit breaker has a potential fault. The example results show that this method can find the potential fault information of the AC filter circuit breaker and issue an early warning before the protection device operates.","PeriodicalId":296085,"journal":{"name":"2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114973402","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：