Reliable and timely seizure prediction has been increasingly helpful and indispensable for epileptic patients, ensuring safety and improving life quality. Based on electroencephalogram (EEG), a new patient-specific seizure prediction method is proposed in this paper to detect impending seizures automatically and accurately, using a novel indicator called maximum synchronization modularity. As the first step towards this goal, raw EEG signals are decomposed by multivariate empirical mode decomposition (MEMD). Then graph community detection algorithm is applied to characterize the phase synchronization modularity of sub-band EEG signals. Thus, the deep interaction of scalp electrical activity can be effectively revealed. Finally, radial basis function neural network (RBFNN) is used for the classification. The proposed method achieves an average prediction accuracy of 99.06% and an average sensitivity of 100% on CHB-MIT scalp EEG database, outperforming related works based on the same database.
{"title":"Robust Seizure Prediction Based on Multivariate Empirical Mode Decomposition and Maximum Synchronization Modularity","authors":"Lihan Tang, Menglian Zhao, Xiaolin Yang, Yangtao Dong, Xiaobo Wu","doi":"10.1109/IECON43393.2020.9254475","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254475","url":null,"abstract":"Reliable and timely seizure prediction has been increasingly helpful and indispensable for epileptic patients, ensuring safety and improving life quality. Based on electroencephalogram (EEG), a new patient-specific seizure prediction method is proposed in this paper to detect impending seizures automatically and accurately, using a novel indicator called maximum synchronization modularity. As the first step towards this goal, raw EEG signals are decomposed by multivariate empirical mode decomposition (MEMD). Then graph community detection algorithm is applied to characterize the phase synchronization modularity of sub-band EEG signals. Thus, the deep interaction of scalp electrical activity can be effectively revealed. Finally, radial basis function neural network (RBFNN) is used for the classification. The proposed method achieves an average prediction accuracy of 99.06% and an average sensitivity of 100% on CHB-MIT scalp EEG database, outperforming related works based on the same database.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"32 1","pages":"507-512"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82466180","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254274
Helbert da Rocha, A. Espírito-Santo, R. Abrishambaf
Interoperability is one of the important characteristics of the Internet of Things. The interoperability enables smart things to exchange data in different areas with different levels of interoperability. Industrial Internet of Things is one of them, and it has the focus in the manufacturing process and connected with other associated ideas as Industry 4.0, Cyber-Physical Systems, and Cyber-Physical Production Systems. It is mandatory to define reference architectures models to manage the Industry 4.0 and the Industrial Internet of Things. The reference models enable semantic interoperability. A reference model provides a bottom/top view of an industrial process, going from the business to the physical layer. At the physical layer, it is necessary to combine physical things with digital world representations, extending its functionalities in the manufacturing process. IEEE 1451 family standards has the essential characteristics to support the exchange of information between IoT applications and sensors & actuators, allowing the industry to build digital elements and meets the Industry 4.0 requirements. This paper presents the reference models proposed for Industry 4.0, taking as reference the implementation and adoption of the IEEE 1451 standard as an option to acquire data and communicates inside of an industrial process. However, at this point, IEEE 1451 enables to achieve the syntactic level of interoperability, in this paper is discussed how to achieve the semantic level of interoperability using the IEEE 1451 family of standards.
{"title":"Semantic Interoperability in the Industry 4.0 Using the IEEE 1451 Standard","authors":"Helbert da Rocha, A. Espírito-Santo, R. Abrishambaf","doi":"10.1109/IECON43393.2020.9254274","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254274","url":null,"abstract":"Interoperability is one of the important characteristics of the Internet of Things. The interoperability enables smart things to exchange data in different areas with different levels of interoperability. Industrial Internet of Things is one of them, and it has the focus in the manufacturing process and connected with other associated ideas as Industry 4.0, Cyber-Physical Systems, and Cyber-Physical Production Systems. It is mandatory to define reference architectures models to manage the Industry 4.0 and the Industrial Internet of Things. The reference models enable semantic interoperability. A reference model provides a bottom/top view of an industrial process, going from the business to the physical layer. At the physical layer, it is necessary to combine physical things with digital world representations, extending its functionalities in the manufacturing process. IEEE 1451 family standards has the essential characteristics to support the exchange of information between IoT applications and sensors & actuators, allowing the industry to build digital elements and meets the Industry 4.0 requirements. This paper presents the reference models proposed for Industry 4.0, taking as reference the implementation and adoption of the IEEE 1451 standard as an option to acquire data and communicates inside of an industrial process. However, at this point, IEEE 1451 enables to achieve the syntactic level of interoperability, in this paper is discussed how to achieve the semantic level of interoperability using the IEEE 1451 family of standards.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"252 1","pages":"5243-5248"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76324005","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}
As a renewable and efficient power source, proton exchange membrane fuel cells (PEMFCs) are receiving more and more attention from the world, but it still has shortcomings with poor durability and insufficient reliability, so the purpose of this paper is to effectively improve the reliability and durability of PEMFCs by a data-driven fault diagnosis method. In this method, principal component analysis (PCA) is first adopted to reduce the dimensionality of fault data. Then, a classification method named eXtreme Gradient Boosting (XGBoost) which based on boosting algorithm is used to classify these data. In the end, the experiment is proposed to verify the diagnostic performance of this method. The result shows that the method can effectively identify four healthy states of membrane drying failure, hydrogen leakage failure, normal state as well as unknown state, the diagnostic accuracy can reach 99.72%, and the diagnosis period is 0.17751 s, which is suitable for online implementation.
{"title":"A Novel Diagnosis Method of Proton Exchange Membrane Fuel Cells Based on the PCA and XGBoost Algorithm","authors":"Hanbin Dang, Rui Ma, Dongdong Zhao, Renyou Xie, Haiyan Li, Yuntian Liu","doi":"10.1109/IECON43393.2020.9255167","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9255167","url":null,"abstract":"As a renewable and efficient power source, proton exchange membrane fuel cells (PEMFCs) are receiving more and more attention from the world, but it still has shortcomings with poor durability and insufficient reliability, so the purpose of this paper is to effectively improve the reliability and durability of PEMFCs by a data-driven fault diagnosis method. In this method, principal component analysis (PCA) is first adopted to reduce the dimensionality of fault data. Then, a classification method named eXtreme Gradient Boosting (XGBoost) which based on boosting algorithm is used to classify these data. In the end, the experiment is proposed to verify the diagnostic performance of this method. The result shows that the method can effectively identify four healthy states of membrane drying failure, hydrogen leakage failure, normal state as well as unknown state, the diagnostic accuracy can reach 99.72%, and the diagnosis period is 0.17751 s, which is suitable for online implementation.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"54 1","pages":"3951-3956"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76365653","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254474
Rohit Chandra, K. R. Krishnanand, H. Thong, Edwin Goh, S. K. Panda, C. Spanos
Modern buildings have multiple distributed electrical resources (DERs) such as renewable energy sources and energy storage devices, flexible loads, and utility connection. Coupled with smart meters and new energy pricing plans, these physical assets present new opportunities for building operators to save energy, reduce operational costs, avoid carbon emissions and improve occupant comfort. The concept of Energy Nodes is proposed to represent the electrical resources and loads within a building and their electrical interactions, which can be programmed/controlled through software. A scaled-down hardware emulation test-bed representing commercial buildings is developed with commercial DER interfaces, controllable loads and Transactive Energy based Energy Management System to realize a cyber-physical Energy Node. Through studies on this test-bed, it is demonstrated that the proposed energy nodes can automatically act based on building operator’s economy preferences, save electricity bills, and provide Demand Response service by reacting to electricity price signals from the markets.
{"title":"Demonstration of Transactive Control of Commercial Buildings as Energy Nodes","authors":"Rohit Chandra, K. R. Krishnanand, H. Thong, Edwin Goh, S. K. Panda, C. Spanos","doi":"10.1109/IECON43393.2020.9254474","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254474","url":null,"abstract":"Modern buildings have multiple distributed electrical resources (DERs) such as renewable energy sources and energy storage devices, flexible loads, and utility connection. Coupled with smart meters and new energy pricing plans, these physical assets present new opportunities for building operators to save energy, reduce operational costs, avoid carbon emissions and improve occupant comfort. The concept of Energy Nodes is proposed to represent the electrical resources and loads within a building and their electrical interactions, which can be programmed/controlled through software. A scaled-down hardware emulation test-bed representing commercial buildings is developed with commercial DER interfaces, controllable loads and Transactive Energy based Energy Management System to realize a cyber-physical Energy Node. Through studies on this test-bed, it is demonstrated that the proposed energy nodes can automatically act based on building operator’s economy preferences, save electricity bills, and provide Demand Response service by reacting to electricity price signals from the markets.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"46 1","pages":"1968-1973"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76171615","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254677
K. Umetani, E. Hiraki
Power conversion technology is characterized by the comparatively small variation of circuit topologies. Because product competitiveness mainly lies in the performance quality as efficiency and low noise emission, the professional skills of this technology commonly require the ability to improve the quality under the restriction of the space, the material resource, and the cost. The conventional teaching method of the power conversion technology is mainly based on the lecture classes and the hands-on classes, which teach the fixed knowledge of the circuit operation. Therefore, this conventional method tends to be insufficient to cover the various practical strategies to improve the quality. To overcome this difficulty, this paper proposes application of the competition-based learning (CBL), in which teams of the students design their power converters and compete on the efficiency. For many professional engineers, competition among companies is the basic motivation to think of strategies to improve product competitiveness. Therefore, the CBL may be effective for teaching design strategies. For promotion of sharing the know-how, the proposed teaching method introduces the events, in which each team share its design strategies with other teams and improve its design based on the know-hows of other teams These events emulate the economic activity, in which a company investigates its competitors’ products to extract the know-how. Along with the basic methodology of the proposed teaching method, this paper also reports the experience of a teaching course.
{"title":"Competition-Based Learning of Power Converter Design Emulating Product Development Activity","authors":"K. Umetani, E. Hiraki","doi":"10.1109/IECON43393.2020.9254677","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254677","url":null,"abstract":"Power conversion technology is characterized by the comparatively small variation of circuit topologies. Because product competitiveness mainly lies in the performance quality as efficiency and low noise emission, the professional skills of this technology commonly require the ability to improve the quality under the restriction of the space, the material resource, and the cost. The conventional teaching method of the power conversion technology is mainly based on the lecture classes and the hands-on classes, which teach the fixed knowledge of the circuit operation. Therefore, this conventional method tends to be insufficient to cover the various practical strategies to improve the quality. To overcome this difficulty, this paper proposes application of the competition-based learning (CBL), in which teams of the students design their power converters and compete on the efficiency. For many professional engineers, competition among companies is the basic motivation to think of strategies to improve product competitiveness. Therefore, the CBL may be effective for teaching design strategies. For promotion of sharing the know-how, the proposed teaching method introduces the events, in which each team share its design strategies with other teams and improve its design based on the know-hows of other teams These events emulate the economic activity, in which a company investigates its competitors’ products to extract the know-how. Along with the basic methodology of the proposed teaching method, this paper also reports the experience of a teaching course.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"45 1","pages":"3339-3344"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86849344","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9255046
Zhenyu Wu, Jun Zhang, Yufeng Yue, Mingxing Wen, Zichen Jiang, Haoyuan Zhang, Danwei W. Wang
Repetitive environment is a challenging scenario for mobile robot global localization due to its highly similar structures and lack of distinctive features. Existing solutions in such environments rely heavily on pre-installed infrastructures, which are neither flexible nor cost-effective. Besides, few of the previous research have been focused on the implementation of infrastructure-free localization approaches in repetitive scenarios. Thus, this paper serves as a survey to investigate the problem of infrastructure-free mobile robot global localization with low-cost and efficient sensors in repetitive environments. Three of the most popular infrastructure-free localization methods, namely LiDAR-based localization (LBL), vision-based localization (VBL), and magnetic field-based localization (MFL), are analyzed and evaluated. Extensive global localization experiments are conducted in real-world repetitive scenarios and the results demonstrate that VBL methods perform slightly better than LBL and MFL methods. The overall evaluations indicate that infrastructure-free global localization in repetitive environment is still a challenging problem which deserves more research efforts to develop new solutions.
{"title":"Infrastructure-Free Global Localization in Repetitive Environments: An Overview","authors":"Zhenyu Wu, Jun Zhang, Yufeng Yue, Mingxing Wen, Zichen Jiang, Haoyuan Zhang, Danwei W. Wang","doi":"10.1109/IECON43393.2020.9255046","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9255046","url":null,"abstract":"Repetitive environment is a challenging scenario for mobile robot global localization due to its highly similar structures and lack of distinctive features. Existing solutions in such environments rely heavily on pre-installed infrastructures, which are neither flexible nor cost-effective. Besides, few of the previous research have been focused on the implementation of infrastructure-free localization approaches in repetitive scenarios. Thus, this paper serves as a survey to investigate the problem of infrastructure-free mobile robot global localization with low-cost and efficient sensors in repetitive environments. Three of the most popular infrastructure-free localization methods, namely LiDAR-based localization (LBL), vision-based localization (VBL), and magnetic field-based localization (MFL), are analyzed and evaluated. Extensive global localization experiments are conducted in real-world repetitive scenarios and the results demonstrate that VBL methods perform slightly better than LBL and MFL methods. The overall evaluations indicate that infrastructure-free global localization in repetitive environment is still a challenging problem which deserves more research efforts to develop new solutions.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"1 1","pages":"626-631"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86992399","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}
Due to the non-linear operating characteristics of wind turbines generation (WTG), traditional control methods cannot give full play to their ability to response the system frequency, resulting in poorer frequency characteristics of the system after wind power is connected to the grid. Therefore, this paper proposes a coordinated control method for wind farms. At the wind farm level, a method for grouping control of wind turbines under different wind speeds is proposed. Different WTGs use different load reduction coefficients, which improves the stability of wind turbines and avoids the second drop in frequency. At the level of WTGs, the equivalent inertial time constant of the wind turbine is calculated, which provides a theoretical basis for the control method. A controller based on adaptive fuzzy control is designed, which dynamically changes the control coefficient in different stages of frequency response, improves the active output of wind turbines participating in the inertial frequency modulation stage, and reduces the static error of primary frequency modulation. The simulation model of the proposed control strategy was applied to simulate different frequency fluctuations. The results show that the frequency response of the WTG after grid connection is significantly improved, proving the effectiveness and robustness of the proposed method.
{"title":"Coordination Control Based on Virtual Inertial Time Constant and Fuzzy Logic control for Power System with Wind Farm","authors":"Qunying Liu, Yongda Si, X. Huo, Shuheng Chen, Fan Zhang, Chang-Hua Zhang","doi":"10.1109/IECON43393.2020.9255083","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9255083","url":null,"abstract":"Due to the non-linear operating characteristics of wind turbines generation (WTG), traditional control methods cannot give full play to their ability to response the system frequency, resulting in poorer frequency characteristics of the system after wind power is connected to the grid. Therefore, this paper proposes a coordinated control method for wind farms. At the wind farm level, a method for grouping control of wind turbines under different wind speeds is proposed. Different WTGs use different load reduction coefficients, which improves the stability of wind turbines and avoids the second drop in frequency. At the level of WTGs, the equivalent inertial time constant of the wind turbine is calculated, which provides a theoretical basis for the control method. A controller based on adaptive fuzzy control is designed, which dynamically changes the control coefficient in different stages of frequency response, improves the active output of wind turbines participating in the inertial frequency modulation stage, and reduces the static error of primary frequency modulation. The simulation model of the proposed control strategy was applied to simulate different frequency fluctuations. The results show that the frequency response of the WTG after grid connection is significantly improved, proving the effectiveness and robustness of the proposed method.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"5 1","pages":"5157-5162"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87153961","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9255269
G. Berardi, S. Nategh, N. Bianchi, Yves Thioliere
This paper presents a comparative study on traction motors built using random and hairpin winding. Advantages and disadvantages of each winding configuration are reported and challenges of using hairpin winding are detailed. The paper focus is placed on winding copper loss, which is the main root of performance differences in motor equipped by random and hairpin windings. A motor is designed using both winding types. Differences in losses and their effect on motor efficiency is studied. Considering the higher slot fill factor of hairpin winding, DC component of copper losses in hairpin winding has less contribution on the motor efficiency, however, higher AC copper loss is seen in hairpin windings. Thus, motors designed and manufactured using hairpin winding have higher efficiency in comparison to the equivalent random wound motors, especially at high load and low speed.
{"title":"A Comparison Between Random and Hairpin Winding in E-mobility Applications","authors":"G. Berardi, S. Nategh, N. Bianchi, Yves Thioliere","doi":"10.1109/IECON43393.2020.9255269","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9255269","url":null,"abstract":"This paper presents a comparative study on traction motors built using random and hairpin winding. Advantages and disadvantages of each winding configuration are reported and challenges of using hairpin winding are detailed. The paper focus is placed on winding copper loss, which is the main root of performance differences in motor equipped by random and hairpin windings. A motor is designed using both winding types. Differences in losses and their effect on motor efficiency is studied. Considering the higher slot fill factor of hairpin winding, DC component of copper losses in hairpin winding has less contribution on the motor efficiency, however, higher AC copper loss is seen in hairpin windings. Thus, motors designed and manufactured using hairpin winding have higher efficiency in comparison to the equivalent random wound motors, especially at high load and low speed.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"42 1","pages":"815-820"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88075063","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254736
A. Muzumdar, Chirag N. Modi, C. Vyjayanthi
The conventional grid has experienced a transition towards smart grid with the advancements in metering infrastructure and increasing usage of renewable energy sources. In smart grid, the energy management system relies heavily on an accurate short-term load forecasting at regional level for an efficient planning and operations of grid.In this paper, we propose an efficient model for regional short-term load forecasting using machine learning techniques in parallel. This model uses feasible machine learning techniques such as support vector regressor (SVR) and random forest (RF) as base predictors. The forecasting results of RF and SVR are averaged to derive final outcome. The performance of the proposed model is validated using load data collected from different regions such as Goa, Maharashtra and Mumbai in India.
{"title":"An Efficient Regional Short-Term Load Forecasting Model for Smart Grid Energy Management","authors":"A. Muzumdar, Chirag N. Modi, C. Vyjayanthi","doi":"10.1109/IECON43393.2020.9254736","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254736","url":null,"abstract":"The conventional grid has experienced a transition towards smart grid with the advancements in metering infrastructure and increasing usage of renewable energy sources. In smart grid, the energy management system relies heavily on an accurate short-term load forecasting at regional level for an efficient planning and operations of grid.In this paper, we propose an efficient model for regional short-term load forecasting using machine learning techniques in parallel. This model uses feasible machine learning techniques such as support vector regressor (SVR) and random forest (RF) as base predictors. The forecasting results of RF and SVR are averaged to derive final outcome. The performance of the proposed model is validated using load data collected from different regions such as Goa, Maharashtra and Mumbai in India.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"1 1","pages":"2089-2094"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88226515","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254741
Vaibhav Shah, S. Payami
Most of the direct and indirect torque control schemes proposed for switched reluctance motors (SRMs) consider equal rotor and stator pole arc. Leading to a linear non-saturating inductance profile. However, actually, in SRM, the rotor pole arc is kept higher than the stator pole arc. Leading to a non-linear saturating inductance profile. And not considering this in control leads to underutilization of the maximum torque producing capacity during the constant torque region. In the proposed novel direct torque control (DTC) scheme, firstly, the rotor pole arc and saturation effect are incorporated by considering it in the sector formation for every electrical cycle. Second, the flux control loop is removed, and sectors are classified based on the actual inductance profile, which is rotor position-dependent. Also, the voltage vector selection rule is modified for torque control. And the proposed voltage vector concerning the sector, allows multiple phases to conduct simultaneously. Wherein each phase conducts according to its actual inductance profile. This also ensures complete energization of incoming phase current while the outgoing phase is maintained at a constant current level. Leading to a reduction in torque ripples during commutation. The proposed DTC scheme incorporating the rotor pole arc and saturation effect improves the operating range for effectively reducing the torque ripples and facilitates a higher torque/ampere ratio.
{"title":"A Novel Direct Torque Control for 4-Phase Switched Reluctance Motor Considering the Actual Rotor Pole Arc with High Torque/Ampere Ratio","authors":"Vaibhav Shah, S. Payami","doi":"10.1109/IECON43393.2020.9254741","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254741","url":null,"abstract":"Most of the direct and indirect torque control schemes proposed for switched reluctance motors (SRMs) consider equal rotor and stator pole arc. Leading to a linear non-saturating inductance profile. However, actually, in SRM, the rotor pole arc is kept higher than the stator pole arc. Leading to a non-linear saturating inductance profile. And not considering this in control leads to underutilization of the maximum torque producing capacity during the constant torque region. In the proposed novel direct torque control (DTC) scheme, firstly, the rotor pole arc and saturation effect are incorporated by considering it in the sector formation for every electrical cycle. Second, the flux control loop is removed, and sectors are classified based on the actual inductance profile, which is rotor position-dependent. Also, the voltage vector selection rule is modified for torque control. And the proposed voltage vector concerning the sector, allows multiple phases to conduct simultaneously. Wherein each phase conducts according to its actual inductance profile. This also ensures complete energization of incoming phase current while the outgoing phase is maintained at a constant current level. Leading to a reduction in torque ripples during commutation. The proposed DTC scheme incorporating the rotor pole arc and saturation effect improves the operating range for effectively reducing the torque ripples and facilitates a higher torque/ampere ratio.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"54 1","pages":"826-831"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88425856","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：