Pub Date : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9776795
Naragoni Saidulu, K. A. Monsley, K. Yadav, R. Laskar
Recognition of handwritten characters is one of the difficult and challenging task because of the variation of characters in size, style and pattern. The complexity increased further with dictionary (alphabets, numerals, special characters), more individuals, age groups, and also with working environment. The exploration of open-source pre-trained networks for the classification of characters was minimal. This motivated us to explore the pre-trained deep convolutional networks (Alexnet, VGG-16, Resnet-50), and fine-tune them to recognize the handwritten characters using transfer learning. The experimentation results of widely used database EMNIST using pre-trained networks are in-par with the results of the state-of-art customized networks,which is specific to database and language. The classification accuracy of Resnet-50 for EMNIST (By-class: 87.24%, By-merge: 90.64%, Balanced: 89.18%, Letters: 94.90%, Digits: 99.57%).
{"title":"Exploration of Deep Convolutional Neural Networks(Via Transfer Learning) for Handwritten Character Recognition","authors":"Naragoni Saidulu, K. A. Monsley, K. Yadav, R. Laskar","doi":"10.1109/ICPC2T53885.2022.9776795","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776795","url":null,"abstract":"Recognition of handwritten characters is one of the difficult and challenging task because of the variation of characters in size, style and pattern. The complexity increased further with dictionary (alphabets, numerals, special characters), more individuals, age groups, and also with working environment. The exploration of open-source pre-trained networks for the classification of characters was minimal. This motivated us to explore the pre-trained deep convolutional networks (Alexnet, VGG-16, Resnet-50), and fine-tune them to recognize the handwritten characters using transfer learning. The experimentation results of widely used database EMNIST using pre-trained networks are in-par with the results of the state-of-art customized networks,which is specific to database and language. The classification accuracy of Resnet-50 for EMNIST (By-class: 87.24%, By-merge: 90.64%, Balanced: 89.18%, Letters: 94.90%, Digits: 99.57%).","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127342690","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}
Growing electricity demands combined with drastic environmental changes have led to the penetration of renewable distributed generations (DGs) close to the load via the adoption of microgrids. However, the intermittent nature of solar based DGs complicates the protection of hybrid microgrid system. Integrating the microgrid system with battery energy storage system (BESS) ensures the reliability of power supply during dual operating modes. The role of BESS during the maximum and minimum demand scenarios has been discussed for grid-connected mode. Further, a reliable fault detection classification scheme using Discrete Wavelet Transform (DWT) and Linear Discriminant Analysis (LDA) approach has been proposed for hybrid microgrid network integrated with BESS. The proposed scheme has been validated for fault and no-fault cases and found effective for varying fault locations, fault inception angles, and fault resistances in both the microgrid operating modes.
{"title":"A Reliable Protection Scheme for Hybrid Microgrid Network with Battery Energy Storage System","authors":"Awagan Goyal Rameshrao, Ebha Koley, Subhojit Ghosh","doi":"10.1109/ICPC2T53885.2022.9776872","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776872","url":null,"abstract":"Growing electricity demands combined with drastic environmental changes have led to the penetration of renewable distributed generations (DGs) close to the load via the adoption of microgrids. However, the intermittent nature of solar based DGs complicates the protection of hybrid microgrid system. Integrating the microgrid system with battery energy storage system (BESS) ensures the reliability of power supply during dual operating modes. The role of BESS during the maximum and minimum demand scenarios has been discussed for grid-connected mode. Further, a reliable fault detection classification scheme using Discrete Wavelet Transform (DWT) and Linear Discriminant Analysis (LDA) approach has been proposed for hybrid microgrid network integrated with BESS. The proposed scheme has been validated for fault and no-fault cases and found effective for varying fault locations, fault inception angles, and fault resistances in both the microgrid operating modes.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126979859","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9776841
A. Anand, Nisha Kumari, Pulakraj Aryan, G. Raja
Due to the availability of an extra dimension in the membership functions, type-2 fuzzy logic controllers are more efficient in handling uncertainties and nonlinearities associated with load frequency control (LFC) of multi-area power systems. This work explores the novel type-2 fuzzy integral-derivative plus proportional (T2FIDPP) controller for LFC of a two-area hybrid power system with multiple generation units under deregulation. Generating units considered for this work are thermal with reheat turbine, gas unit and distributed generation (DG) which include solar photovoltaic (PV) & wind turbine system. Physical nonlinearities such as governor dead band (GDB), boiler dynamics (BD) and generation rate constraint (GRC) are considered in simulation for thermal units. The investigated system is subjected to step load disturbance to investigate the effectiveness of the proposed controller. Finally, the equilibrium optimizer (EO) is applied to obtain the optimal settings of the suggested controller. The comparison of prevalent optimization techniques and controllers is also illustrated. Along with this, a robust stability analysis of the controlled system is presented. Simulation studies establish the efficacy of the suggested control scheme.
{"title":"EO Optimized Novel Type-2 Fuzzy ID-P Controller for LFC of Deregulated Multi-area Power System with Robust Stability Analysis","authors":"A. Anand, Nisha Kumari, Pulakraj Aryan, G. Raja","doi":"10.1109/ICPC2T53885.2022.9776841","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776841","url":null,"abstract":"Due to the availability of an extra dimension in the membership functions, type-2 fuzzy logic controllers are more efficient in handling uncertainties and nonlinearities associated with load frequency control (LFC) of multi-area power systems. This work explores the novel type-2 fuzzy integral-derivative plus proportional (T2FIDPP) controller for LFC of a two-area hybrid power system with multiple generation units under deregulation. Generating units considered for this work are thermal with reheat turbine, gas unit and distributed generation (DG) which include solar photovoltaic (PV) & wind turbine system. Physical nonlinearities such as governor dead band (GDB), boiler dynamics (BD) and generation rate constraint (GRC) are considered in simulation for thermal units. The investigated system is subjected to step load disturbance to investigate the effectiveness of the proposed controller. Finally, the equilibrium optimizer (EO) is applied to obtain the optimal settings of the suggested controller. The comparison of prevalent optimization techniques and controllers is also illustrated. Along with this, a robust stability analysis of the controlled system is presented. Simulation studies establish the efficacy of the suggested control scheme.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131208615","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9776804
Nadya Aditama, R. Munir
Indonesian people need to know about the calorie information of the street food. One of effective ways to get that is using image-based calorie estimation technologies. However, there are two limitations. First, the problem of occluded food and second is the low R Squared value in measurement using linear regression model with area feature. This research proposed the Mask R-CNN model for amodal instance segmentation task to get the complete object shape and multiple linear regression model with area, perimeter, length, and width to predict the food weight. This research proposed Indonesian street food dataset that has six classes. There are 1646 images of the dataset and total instance of each food are 644 bakwan, 812 bolu, 918 cireng, 679 serabi, 711 tahu, and 766 tempe. The number of data point in multiple linear regression model is 230 bakwan, 200 bolu, 250 cireng, 240 serabi, 230 tahu, and 230 tempe. The proposed multiple linear regression model has the highest R Squared score in all classes with the average R Squared 0.80425. Mask R-CNN ResNeXt-101-FPN in amodal instance segmentation task reaches the best F1 Score. In occluded scenario this model gets F1 Score 0.821 in IoU threshold 0.85. In non-occluded scenario the model gets F1 Score 0.994 in IoU threshold 0.9. Even though the F1 Score is high, there are some false detections and the bad segmentation quality. In calorie prediction, the proposed model is not reducing MAE score in some classes due to the segmentation quality and food characteristic.
{"title":"Indonesian Street Food Calorie Estimation Using Mask R-CNN and Multiple Linear Regression","authors":"Nadya Aditama, R. Munir","doi":"10.1109/ICPC2T53885.2022.9776804","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776804","url":null,"abstract":"Indonesian people need to know about the calorie information of the street food. One of effective ways to get that is using image-based calorie estimation technologies. However, there are two limitations. First, the problem of occluded food and second is the low R Squared value in measurement using linear regression model with area feature. This research proposed the Mask R-CNN model for amodal instance segmentation task to get the complete object shape and multiple linear regression model with area, perimeter, length, and width to predict the food weight. This research proposed Indonesian street food dataset that has six classes. There are 1646 images of the dataset and total instance of each food are 644 bakwan, 812 bolu, 918 cireng, 679 serabi, 711 tahu, and 766 tempe. The number of data point in multiple linear regression model is 230 bakwan, 200 bolu, 250 cireng, 240 serabi, 230 tahu, and 230 tempe. The proposed multiple linear regression model has the highest R Squared score in all classes with the average R Squared 0.80425. Mask R-CNN ResNeXt-101-FPN in amodal instance segmentation task reaches the best F1 Score. In occluded scenario this model gets F1 Score 0.821 in IoU threshold 0.85. In non-occluded scenario the model gets F1 Score 0.994 in IoU threshold 0.9. Even though the F1 Score is high, there are some false detections and the bad segmentation quality. In calorie prediction, the proposed model is not reducing MAE score in some classes due to the segmentation quality and food characteristic.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"2021 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134213617","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9777079
Paramjeet Kaur, K. T. Chaturvedi
Despite growing concerns about biodiversity loss and the scarcity of fossil fuels, alternative energy sources are expected to take the lead in the world's energy landscape in the future. CHP systems (combined heat and power) combine electricity and heat energy into a single unit, increasing overall efficiency and lowering carbon emissions. CHPED (combined heat and power economic dispatch) problems are regarded as a difficult and nonlinear power system engineering challenge. Many solutions to this difficult problem have been proposed in recent years. In this article, the author proposes a new optimization algorithm. The Rao-I algorithm, which is metaphor-free and algorithm-specific, is used to solve the CHPED problem. The algorithm is tested on two different systems, and the results are compared to those of other well-known techniques to demonstrate that it is superior at dealing with real-time problems.
{"title":"An economic dispatch model for combined heat and power plant using Rao-I optimisation algorithm","authors":"Paramjeet Kaur, K. T. Chaturvedi","doi":"10.1109/ICPC2T53885.2022.9777079","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9777079","url":null,"abstract":"Despite growing concerns about biodiversity loss and the scarcity of fossil fuels, alternative energy sources are expected to take the lead in the world's energy landscape in the future. CHP systems (combined heat and power) combine electricity and heat energy into a single unit, increasing overall efficiency and lowering carbon emissions. CHPED (combined heat and power economic dispatch) problems are regarded as a difficult and nonlinear power system engineering challenge. Many solutions to this difficult problem have been proposed in recent years. In this article, the author proposes a new optimization algorithm. The Rao-I algorithm, which is metaphor-free and algorithm-specific, is used to solve the CHPED problem. The algorithm is tested on two different systems, and the results are compared to those of other well-known techniques to demonstrate that it is superior at dealing with real-time problems.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134296937","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9776988
Mitali Vijay Kondukwar, P. Dewangan
In this paper, Particle Swarm Optimization (PSO) technique has been discussed and reduction of the higher order model to a lower order model performed. The results are then compared to those produced using traditional methods. On the basis of step response specification, bode response specification, and performance indices, a comparison is made to demonstrate the superiority of the proposed model. The primary benefit of the proposed model is to offer reasonable accuracy in less time relative to other methods. Furthermore, the reduced model retains the time and frequency response characteristics of the original system.
{"title":"Implementation of Particle Swarm Optimization for Model Order Reduction","authors":"Mitali Vijay Kondukwar, P. Dewangan","doi":"10.1109/ICPC2T53885.2022.9776988","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776988","url":null,"abstract":"In this paper, Particle Swarm Optimization (PSO) technique has been discussed and reduction of the higher order model to a lower order model performed. The results are then compared to those produced using traditional methods. On the basis of step response specification, bode response specification, and performance indices, a comparison is made to demonstrate the superiority of the proposed model. The primary benefit of the proposed model is to offer reasonable accuracy in less time relative to other methods. Furthermore, the reduced model retains the time and frequency response characteristics of the original system.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128644763","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9776701
Shahzad Ali Rana, M. Jamil, Mumtaz Ahmad Khan, Mohammad Nair Aalam
In this article, a Mixed Norm based LMS control algorithm updated with s reweigh ted zero attraction parameter is implemented for power conversion in a two-stage solar photovoltaic (SPV) system interconnected with the three-phase grid. The boost converter extracts peak power from the SPV array by application of the incremental conductance (INC)-based maximum power point tracking (MPPT) technique. The Reweighted Zero Attraction Mixed Norm LMS (RZA-MNLMS) algorithm estimates the weight component relating to the load, used to estimate the total active weight required for generating gating signals for voltage source converter (VSC). The VSC provides compensation for varying solar insolation and unbalanced non-linear load conditions at the point of common connection, resulting in load-balancing and harmonics compensation along with unity power factor operation. The performance of the suggested control is studied by developing a simulation model in MATLAB Simulink. The simulated model shows satisfactory performance under several abnormal conditions.
{"title":"Reweighted Zero Attraction Mixed Norm LMS (RZA-MNLMS) based Control for Grid Integrated SPV System","authors":"Shahzad Ali Rana, M. Jamil, Mumtaz Ahmad Khan, Mohammad Nair Aalam","doi":"10.1109/ICPC2T53885.2022.9776701","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776701","url":null,"abstract":"In this article, a Mixed Norm based LMS control algorithm updated with s reweigh ted zero attraction parameter is implemented for power conversion in a two-stage solar photovoltaic (SPV) system interconnected with the three-phase grid. The boost converter extracts peak power from the SPV array by application of the incremental conductance (INC)-based maximum power point tracking (MPPT) technique. The Reweighted Zero Attraction Mixed Norm LMS (RZA-MNLMS) algorithm estimates the weight component relating to the load, used to estimate the total active weight required for generating gating signals for voltage source converter (VSC). The VSC provides compensation for varying solar insolation and unbalanced non-linear load conditions at the point of common connection, resulting in load-balancing and harmonics compensation along with unity power factor operation. The performance of the suggested control is studied by developing a simulation model in MATLAB Simulink. The simulated model shows satisfactory performance under several abnormal conditions.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127786418","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9777001
A. A. Hussein
As the need for accurate readings from the usual digital meter is increased in undeveloped countries the importance to involve modern technologies in this kind of meter also increased. Therefore, a power line energy meter PLEM is proposed in this paper which describes the design and implementation of this project. PLEM depends on its idea on different parts (microcontroller/ Arduino, Ethernet shield, adapters, and simple SCADA system) to give the efficient reading for the power consumption that can be consumed from different buildings and send these readings over the transmission lines using power line adapters to the main building where controlling and examination of the data will be easier to make as an example to the ministry of electricity.
{"title":"Energy Consumption Reading System Design based on Microcontroller with TL-PA2010KIT Adapter","authors":"A. A. Hussein","doi":"10.1109/ICPC2T53885.2022.9777001","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9777001","url":null,"abstract":"As the need for accurate readings from the usual digital meter is increased in undeveloped countries the importance to involve modern technologies in this kind of meter also increased. Therefore, a power line energy meter PLEM is proposed in this paper which describes the design and implementation of this project. PLEM depends on its idea on different parts (microcontroller/ Arduino, Ethernet shield, adapters, and simple SCADA system) to give the efficient reading for the power consumption that can be consumed from different buildings and send these readings over the transmission lines using power line adapters to the main building where controlling and examination of the data will be easier to make as an example to the ministry of electricity.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134057073","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9776689
Vaibhav Shah, Kumawat Gautam, S. Payami
The article presents the design and implementation of an integrated power converter (IPC) for a switched reluctance motor (SRM) drive based electric vehicle (EV) application. The IPC proposed integrates driving and battery energy storage (BES) charging/discharging functionality. During BES charging mode, i.e., grid-to-vehicle (G2V) charging, the proposed IPC is reutilized as a bridgeless boost power factor correction circuit (PFCC) in cascade with a bidirectional DC-DC converter (BDDC). Similarly, during BES discharging mode, i.e., vehicle-to-grid (V2G) charging, the proposed IPC is reutilized as a BDDC in cascade with a single-phase voltage source inverter. Thus, with the proposed IPC, the BES can be charged/discharged at AC grid voltage. The proposed IPC also supports DC fast/vehicle-to-vehicle (V2V) charging wherein the host EV via the integrated BDDC can charge/discharge a receiver EV of higher or lower BES voltage rating than the host EV. In addition, during G2V, V2G and V2V charging, the charging current flowing in phase winding/s when reconfigured as charging inductor/s results in a zero-torque production. Detailed theoretical analysis and experimental verification on a prototype 4-phase SRM are presented to evaluate the proposed IPC's driving and BES charging features.
{"title":"Integrated Power Converter with G2V, V2G and Direct V2V Capabilities for SRM Drive Based Electric Vehicle Application","authors":"Vaibhav Shah, Kumawat Gautam, S. Payami","doi":"10.1109/ICPC2T53885.2022.9776689","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9776689","url":null,"abstract":"The article presents the design and implementation of an integrated power converter (IPC) for a switched reluctance motor (SRM) drive based electric vehicle (EV) application. The IPC proposed integrates driving and battery energy storage (BES) charging/discharging functionality. During BES charging mode, i.e., grid-to-vehicle (G2V) charging, the proposed IPC is reutilized as a bridgeless boost power factor correction circuit (PFCC) in cascade with a bidirectional DC-DC converter (BDDC). Similarly, during BES discharging mode, i.e., vehicle-to-grid (V2G) charging, the proposed IPC is reutilized as a BDDC in cascade with a single-phase voltage source inverter. Thus, with the proposed IPC, the BES can be charged/discharged at AC grid voltage. The proposed IPC also supports DC fast/vehicle-to-vehicle (V2V) charging wherein the host EV via the integrated BDDC can charge/discharge a receiver EV of higher or lower BES voltage rating than the host EV. In addition, during G2V, V2G and V2V charging, the charging current flowing in phase winding/s when reconfigured as charging inductor/s results in a zero-torque production. Detailed theoretical analysis and experimental verification on a prototype 4-phase SRM are presented to evaluate the proposed IPC's driving and BES charging features.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129594188","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 : 2022-03-01DOI: 10.1109/ICPC2T53885.2022.9777004
Debottam Mukherjee, Samrat Chakraborty
Recently, with the rapid adoption of electric vehicles (EVs) for modern transportation systems, an accurate forecasting of speed and torque is an utmost priority. As permanent magnet synchronous motors (PMSM) are an integral part of such EVs, hence this work has undertaken an effective forecasting of speed and torque of such motors. To showcase the efficacy of the proposed deep learning architecture for an effective speed and torque forecasting policy, this work adopts the dataset as formulated by University of Paderborn incorporating the effects of various factors like ambient temperature, coolant temperature, stator temperature etc. Gaussian copula based synthetic data generation have been used in this paper which effectively showcases an enhancement in model performance. This work shows a critical comparison between the proposed deep learning architecture along with some machine learning models, which further promotes the efficacy of the proposed forecasting policy.
{"title":"A Deep Learning Approach for an Effective Speed and Torque Forecasting Policy of PMS Motors in Electric Vehicles","authors":"Debottam Mukherjee, Samrat Chakraborty","doi":"10.1109/ICPC2T53885.2022.9777004","DOIUrl":"https://doi.org/10.1109/ICPC2T53885.2022.9777004","url":null,"abstract":"Recently, with the rapid adoption of electric vehicles (EVs) for modern transportation systems, an accurate forecasting of speed and torque is an utmost priority. As permanent magnet synchronous motors (PMSM) are an integral part of such EVs, hence this work has undertaken an effective forecasting of speed and torque of such motors. To showcase the efficacy of the proposed deep learning architecture for an effective speed and torque forecasting policy, this work adopts the dataset as formulated by University of Paderborn incorporating the effects of various factors like ambient temperature, coolant temperature, stator temperature etc. Gaussian copula based synthetic data generation have been used in this paper which effectively showcases an enhancement in model performance. This work shows a critical comparison between the proposed deep learning architecture along with some machine learning models, which further promotes the efficacy of the proposed forecasting policy.","PeriodicalId":283298,"journal":{"name":"2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132646052","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：