Pub Date : 2024-03-03DOI: 10.17775/CSEEJPES.2022.05990
Chenxi Fan;Kaishun Xiahou;Lei Wang;Q. H. Wu
This paper presents a long short-term memory (LSTM)-based fault detection method to detect the multiple open-circuit switch faults of modular multilevel converter (MMC) systems with full-bridge sub-modules (FB-SMs). Eighteen sensor signals of grid voltages, grid currents and capacitance voltages of MMC for single and multi-switch faults are collected as sampling data. The output signal characteristics of four types of single switch faults of FB-SM, as well as double switch faults in the same and different phases of MMC, are analyzed under the conditions of load variations and control command changes. A multi-layer LSTM network is devised to deeply extract the fault characteristics of MMC under different faults and operation conditions, and a Softmax layer detects the fault types. Simulation results have confirmed that the proposed LSTM-based method has better detection performance compared with three other methods: K-nearest neighbor (KNN), naive bayes (NB) and recurrent neural network (RNN). In addition, it is highly robust to model uncertainties and Gaussian noise. The validity of the proposed method is further demonstrated by experiment studies conducted on a hardware-in-the-loop (HIL) testing platform.
{"title":"Data-Driven Fault Detection of Multiple Open-Circuit Faults for MMC Systems Based on Long Short-Term Memory Networks","authors":"Chenxi Fan;Kaishun Xiahou;Lei Wang;Q. H. Wu","doi":"10.17775/CSEEJPES.2022.05990","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2022.05990","url":null,"abstract":"This paper presents a long short-term memory (LSTM)-based fault detection method to detect the multiple open-circuit switch faults of modular multilevel converter (MMC) systems with full-bridge sub-modules (FB-SMs). Eighteen sensor signals of grid voltages, grid currents and capacitance voltages of MMC for single and multi-switch faults are collected as sampling data. The output signal characteristics of four types of single switch faults of FB-SM, as well as double switch faults in the same and different phases of MMC, are analyzed under the conditions of load variations and control command changes. A multi-layer LSTM network is devised to deeply extract the fault characteristics of MMC under different faults and operation conditions, and a Softmax layer detects the fault types. Simulation results have confirmed that the proposed LSTM-based method has better detection performance compared with three other methods: K-nearest neighbor (KNN), naive bayes (NB) and recurrent neural network (RNN). In addition, it is highly robust to model uncertainties and Gaussian noise. The validity of the proposed method is further demonstrated by experiment studies conducted on a hardware-in-the-loop (HIL) testing platform.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520155","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141966191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-03DOI: 10.17775/CSEEJPES.2022.07470
Haoyuan Yan;Tianyang Zhao;Zhanglei Guan
The rapid development of electric vehicles (EVs) is strengthening the bi-directional interactions between electric power networks (EPNs) and transportation networks (TNs) while providing opportunities to enhance the resilience of power systems towards extreme events. To quantify the temporal and spatial flexibility of EVs for charging and discharging, a novel dynamic traffic assignment (DTA) problem is proposed. The DTA problem is based on a link transmission model (LTM) with extended charging links, depicting the interaction between EVs and power systems. It models the charging rates as continuous variables by an energy boundary model. To consider the evacuation requirements of TNs and the uncertainties of traffic conditions, the DTA problem is extended to a two-stage distributionally robust version. It is further incorporated into a two-stage distributionally robust unit commitment problem to balance the enhancement of EPNs and the performance of TNs. The problem is reformulated into a mixed-integer linear programming problem and solved by off-the-shelf commercial solvers. Case studies are performed on two test networks. The effectiveness is verified by the numerical results, e.g., reducing the load shedding amount without increasing the unmet traffic demand.
{"title":"Proactive Resilience Enhancement of Power Systems with Link Transmission Model-Based Dynamic Traffic Assignment Among Electric Vehicles","authors":"Haoyuan Yan;Tianyang Zhao;Zhanglei Guan","doi":"10.17775/CSEEJPES.2022.07470","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2022.07470","url":null,"abstract":"The rapid development of electric vehicles (EVs) is strengthening the bi-directional interactions between electric power networks (EPNs) and transportation networks (TNs) while providing opportunities to enhance the resilience of power systems towards extreme events. To quantify the temporal and spatial flexibility of EVs for charging and discharging, a novel dynamic traffic assignment (DTA) problem is proposed. The DTA problem is based on a link transmission model (LTM) with extended charging links, depicting the interaction between EVs and power systems. It models the charging rates as continuous variables by an energy boundary model. To consider the evacuation requirements of TNs and the uncertainties of traffic conditions, the DTA problem is extended to a two-stage distributionally robust version. It is further incorporated into a two-stage distributionally robust unit commitment problem to balance the enhancement of EPNs and the performance of TNs. The problem is reformulated into a mixed-integer linear programming problem and solved by off-the-shelf commercial solvers. Case studies are performed on two test networks. The effectiveness is verified by the numerical results, e.g., reducing the load shedding amount without increasing the unmet traffic demand.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520179","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141304077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Composite insulators have been widely used in transmission lines. After being removed from transmission lines, their housing silicone material cannot degrade naturally. To tackle this problem, this paper proposes an effective method to recycle waste insulators by pyrolysis to obtain mullite $(mathbf{3}mathbf{Al}_{2}mathbf{O}_{3}cdot mathbf{2}mathbf{SiO}_{2})$