Brushless direct current (BLDC) motor aims to obtain high efficiency when compared to conventional DC motors due to several reasons. But when it comes to the control then its control is much more complicated due to the requirement of a phase supply switching circuit. Usually, the conventional and classical proportional integral derivative (PID) controller is used but it is quite cumbersome to tune its fixed gains. APID controller is used where PID fails to fulfill the objectives in varying situations. So, the adaptive proportional integral derivative (APID) controller is utilized to enhance the results. An artificial neural network (ANN) controller is one of the recent control methods, which gives accurate and precise results and utilizes ANN to give more accurate results. But it lacks fuzzy logic, that is, human tendency, and finally, the artificial neuro-fuzzy inference system (ANFIS) controller is concluded as the best controller to limit the speed of the BLDC motor. ANFIS includes all the advantages of controllers and provides the most accurate results. The mathematical model of all the controllers is discussed and its performance is simulated in MATLAB/Simulink. ANFIS includes all the advantages of controllers and provides the most accurate results.
{"title":"Design and Implementation of Adaptive and Artificial Intelligence Controller for Brushless Motor Drive Electric Vehicle","authors":"Aditi Saxena, Amit Gupta, Nitesh Tiwari","doi":"10.4271/14-13-01-0003","DOIUrl":"https://doi.org/10.4271/14-13-01-0003","url":null,"abstract":"Brushless direct current (BLDC) motor aims to obtain high efficiency when compared to conventional DC motors due to several reasons. But when it comes to the control then its control is much more complicated due to the requirement of a phase supply switching circuit. Usually, the conventional and classical proportional integral derivative (PID) controller is used but it is quite cumbersome to tune its fixed gains. APID controller is used where PID fails to fulfill the objectives in varying situations. So, the adaptive proportional integral derivative (APID) controller is utilized to enhance the results. An artificial neural network (ANN) controller is one of the recent control methods, which gives accurate and precise results and utilizes ANN to give more accurate results. But it lacks fuzzy logic, that is, human tendency, and finally, the artificial neuro-fuzzy inference system (ANFIS) controller is concluded as the best controller to limit the speed of the BLDC motor. ANFIS includes all the advantages of controllers and provides the most accurate results. The mathematical model of all the controllers is discussed and its performance is simulated in MATLAB/Simulink. ANFIS includes all the advantages of controllers and provides the most accurate results.","PeriodicalId":36261,"journal":{"name":"SAE International Journal of Electrified Vehicles","volume":"13 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87634174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The transport sector is one of the major parties responsible for carbon dioxide (CO2) and pollutants emissions in Europe. For this reason, one of the main commitments of the European Commission is its decarbonization by 2035/2040. To achieve this target, during the last decades, different propulsion technologies were developed such as hybrid electric vehicles (HEVs), plug-in electric vehicles (PHEVs), and battery electric vehicles (BEV). The first two proposals can be considered as bridging technology between the internal combustion engine (ICE) and the BEV because they offer at the same time comparable performance as conventional powertrains and improved efficiency. However, both technologies are struggling with the tightening of pollutants and CO2 limits. On the other hand, the BEV can offer zero emissions at the tailpipe, but it suffers from limited range capabilities and the lack of fast-charging infrastructures. Within this context, the fuel cell vehicle (FCV) appears as an interesting opportunity because it offers zero tailpipe emissions and equivalent refuelling time of the ICE. This article evaluates through mathematical simulations the performance of two fuel cell electric buses (FCEBs), which are supposed to work respectively in urban and highway driving conditions. The urban bus is equipped with a single fuel cell (FC) module of 85 kW-Net and an electric motor (EM) of 225 kW. The intercity bus is equipped with two FC modules with a total power of 170 kW-Net and two EMs of 225 kW each. A sensitivity to the battery capacity from 20 kWh to 40 kWh was performed for both FECBs. The power split between the FC module and the high-voltage battery was optimized with the Equivalent Consumption Minimization Strategy (ECMS). The two FCEBs were tested considering different portfolios of cycles: in the case of the urban bus in Braunschweig and the Standardized On-Road Test Cycles SORT1 and SORT2 were assumed as a reference, while cycles like the Highway Fuel Economy Test (HWFET), European Transient Cycle (ETC), and cruising at 100 km/h were assumed as reference for the intercity. Simulation results highlighted that the increase of battery capacity in the case of the urban bus from 20 kWh to 30 kWh reduces hydrogen (H2) consumption by 11% along the Braunschweig cycle. On the other hand, in the case of the intercity bus, the fuel consumption is less affected by the increase of capacity in the same range. In this case a reduction of 4.7% is estimated for the HWFET cycle, and it is less than 1% in the case of cruising conditions.
{"title":"Design of Two Fuel Cell Buses for Public Transport According to Two Different Operating Scenarios: Urban and Motorway","authors":"Claudio Cubito, A. Almondo, R. Ruotolo","doi":"10.4271/14-13-02-0007","DOIUrl":"https://doi.org/10.4271/14-13-02-0007","url":null,"abstract":"The transport sector is one of the major parties responsible for carbon dioxide (CO2) and pollutants emissions in Europe. For this reason, one of the main commitments of the European Commission is its decarbonization by 2035/2040. To achieve this target, during the last decades, different propulsion technologies were developed such as hybrid electric vehicles (HEVs), plug-in electric vehicles (PHEVs), and battery electric vehicles (BEV). The first two proposals can be considered as bridging technology between the internal combustion engine (ICE) and the BEV because they offer at the same time comparable performance as conventional powertrains and improved efficiency. However, both technologies are struggling with the tightening of pollutants and CO2 limits. On the other hand, the BEV can offer zero emissions at the tailpipe, but it suffers from limited range capabilities and the lack of fast-charging infrastructures. Within this context, the fuel cell vehicle (FCV) appears as an interesting opportunity because it offers zero tailpipe emissions and equivalent refuelling time of the ICE. This article evaluates through mathematical simulations the performance of two fuel cell electric buses (FCEBs), which are supposed to work respectively in urban and highway driving conditions. The urban bus is equipped with a single fuel cell (FC) module of 85 kW-Net and an electric motor (EM) of 225 kW. The intercity bus is equipped with two FC modules with a total power of 170 kW-Net and two EMs of 225 kW each. A sensitivity to the battery capacity from 20 kWh to 40 kWh was performed for both FECBs. The power split between the FC module and the high-voltage battery was optimized with the Equivalent Consumption Minimization Strategy (ECMS). The two FCEBs were tested considering different portfolios of cycles: in the case of the urban bus in Braunschweig and the Standardized On-Road Test Cycles SORT1 and SORT2 were assumed as a reference, while cycles like the Highway Fuel Economy Test (HWFET), European Transient Cycle (ETC), and cruising at 100 km/h were assumed as reference for the intercity. Simulation results highlighted that the increase of battery capacity in the case of the urban bus from 20 kWh to 30 kWh reduces hydrogen (H2) consumption by 11% along the Braunschweig cycle. On the other hand, in the case of the intercity bus, the fuel consumption is less affected by the increase of capacity in the same range. In this case a reduction of 4.7% is estimated for the HWFET cycle, and it is less than 1% in the case of cruising conditions.","PeriodicalId":36261,"journal":{"name":"SAE International Journal of Electrified Vehicles","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72412865","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}
Electric vehicles (EVs) suffer from long charging time and inconvenient charging due to limited charging stations, which are the main causes of drivers’ range anxiety. Real-time and accurate driving range prediction can help drivers plan journeys, alleviate range anxiety, and promote EV development. However, predicting the EV driving range is challenging due to different weather, road conditions, driver habits, and limited available data. To address this issue, this article proposes a novel digital twin-based driving range prediction method. First, a one-year real-world EV dataset in Beijing is utilized. Detailed feature selection is conducted for the dataset, and six key features are extracted: battery SOC, consumed battery SOC, battery total voltage, battery maximum cell voltage, battery minimum cell voltage, and mileage already driven. Then, a random forest method is used to train the EV driving range prediction model using the features described earlier. Four prediction models with different adopted features are trained, respectively. Finally, the sliding window algorithm is proposed for the input of random forest to investigate its impact on prediction accuracy in the four prediction models, and different window sizes are evaluated. Results show that the sliding window algorithm can significantly improve the prediction model with only SOC as input, while it can deteriorate other models with more features. The most accurate model taking all six features as inputs provides 89.8% data that has an accuracy of over 80%, while data proportion of the prediction model without past energy consumption is only 31.8%.
{"title":"Digital Twin-Based Remaining Driving Range Prediction for Connected Electric Vehicles","authors":"Shilong Zhuo, Heng Li, Muazz Bin Kaleem, Hui Peng, Yue Wu","doi":"10.4271/14-13-01-0004","DOIUrl":"https://doi.org/10.4271/14-13-01-0004","url":null,"abstract":"Electric vehicles (EVs) suffer from long charging time and inconvenient charging due to limited charging stations, which are the main causes of drivers’ range anxiety. Real-time and accurate driving range prediction can help drivers plan journeys, alleviate range anxiety, and promote EV development. However, predicting the EV driving range is challenging due to different weather, road conditions, driver habits, and limited available data. To address this issue, this article proposes a novel digital twin-based driving range prediction method. First, a one-year real-world EV dataset in Beijing is utilized. Detailed feature selection is conducted for the dataset, and six key features are extracted: battery SOC, consumed battery SOC, battery total voltage, battery maximum cell voltage, battery minimum cell voltage, and mileage already driven. Then, a random forest method is used to train the EV driving range prediction model using the features described earlier. Four prediction models with different adopted features are trained, respectively. Finally, the sliding window algorithm is proposed for the input of random forest to investigate its impact on prediction accuracy in the four prediction models, and different window sizes are evaluated. Results show that the sliding window algorithm can significantly improve the prediction model with only SOC as input, while it can deteriorate other models with more features. The most accurate model taking all six features as inputs provides 89.8% data that has an accuracy of over 80%, while data proportion of the prediction model without past energy consumption is only 31.8%.","PeriodicalId":36261,"journal":{"name":"SAE International Journal of Electrified Vehicles","volume":"12 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86744493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The development of predictive maintenance has become one of the most important drivers of innovation, not only in the maritime industry. The proliferation of on-board and remote sensing and diagnostic systems is creating many new opportunities to reduce maintenance costs and increase operational stability. By predicting impending system faults and failures, proactive maintenance can be initiated to prevent loss of seaworthiness or operability. The motivation of this study is to optimize predictive maintenance in the maritime industry by determining the minimum useful remaining lead-acid battery capacity measurement frequency required to achieve cost-efficiency and desired prognostic performance in a remaining battery capacity indication system. The research seeks to balance operational stability and cost-effectiveness, providing valuable insight into the practical considerations and potential benefits of predictive maintenance. The methodology employed in this study includes outlining the theoretical development of a fully automated condition monitoring system and describing data cleansing steps to account for environmental effects on system performance. A Monte Carlo simulation is used to evaluate the sensitivity of the remaining useful life prediction to varying measurement frequencies, prediction models, and parameter settings, leading to an estimate of the optimal measurement frequency for the system. The results show that a certain minimum measurement frequency is required to achieve the target prediction accuracy while balancing cost-efficiency and operational stability. Reliable failure prediction with negligible changes in prognostic accuracy can be achieved by performing useful remaining lead-acid battery capacity measurements twice a day or every 5 ship voyage cycles with the underlying utilization.
{"title":"Reliable Ship Emergency Power Source: A Monte Carlo Simulation Approach to Optimize Remaining Capacity Measurement Frequency for Lead-Acid Battery Maintenance","authors":"A. Golovan, I. Gritsuk, Iryna Honcharuk","doi":"10.4271/14-13-02-0009","DOIUrl":"https://doi.org/10.4271/14-13-02-0009","url":null,"abstract":"The development of predictive maintenance has become one of the most important drivers of innovation, not only in the maritime industry. The proliferation of on-board and remote sensing and diagnostic systems is creating many new opportunities to reduce maintenance costs and increase operational stability. By predicting impending system faults and failures, proactive maintenance can be initiated to prevent loss of seaworthiness or operability. The motivation of this study is to optimize predictive maintenance in the maritime industry by determining the minimum useful remaining lead-acid battery capacity measurement frequency required to achieve cost-efficiency and desired prognostic performance in a remaining battery capacity indication system. The research seeks to balance operational stability and cost-effectiveness, providing valuable insight into the practical considerations and potential benefits of predictive maintenance. The methodology employed in this study includes outlining the theoretical development of a fully automated condition monitoring system and describing data cleansing steps to account for environmental effects on system performance. A Monte Carlo simulation is used to evaluate the sensitivity of the remaining useful life prediction to varying measurement frequencies, prediction models, and parameter settings, leading to an estimate of the optimal measurement frequency for the system. The results show that a certain minimum measurement frequency is required to achieve the target prediction accuracy while balancing cost-efficiency and operational stability. Reliable failure prediction with negligible changes in prognostic accuracy can be achieved by performing useful remaining lead-acid battery capacity measurements twice a day or every 5 ship voyage cycles with the underlying utilization.","PeriodicalId":36261,"journal":{"name":"SAE International Journal of Electrified Vehicles","volume":"9 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84860143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The current development of electric and hybrid electric vehicles has drawn more attention toward the development of electrical machines with high power densities. Though highly efficient, these machines heat up significantly during operation. By design, state-of-the-art water jacket cooling concepts remove the heat mainly through high internal thermal resistances of the electrical machine. The resulting maximum temperatures in the end winding region limit the achievable machine power output. In this study, alternative cooling concepts are presented, which efficiently use the existing heat conduction paths of an electric machine. For this purpose, two modeling methods for the stator windings were developed: a high-resolution approach that considers each individual wire and an abstract approach that uses zones of constant anisotropic thermal conductivity to specify the heat flow in the windings. Both models were used in conjugate heat transfer simulations of a long-term thermal test of the electrical machine integrated in the BMW i3. For both models the validation showed a very good agreement of simulated and measured temperatures. An evaluation of both methods showed the abstract approach to be more efficient than other simulation methods used in the current R&D. Its application for alternative cooling concepts revealed the necessary heat transfer coefficients at different fluid temperatures for a sole convective cooling of the end windings. However, it could be found that a homogeneous temperature distribution in the stator of the machine can only be achieved if a combination of water jacket cooling and convective end winding cooling is used.
{"title":"Precise Electrical Machine Stator Winding Modeling for Thermal Analysis of Efficient Cooling Concepts","authors":"Nicolas Brossardt, Thinh Nguyen-Xuan, M. Pfitzner","doi":"10.4271/14-13-02-0008","DOIUrl":"https://doi.org/10.4271/14-13-02-0008","url":null,"abstract":"The current development of electric and hybrid electric vehicles has drawn more attention toward the development of electrical machines with high power densities. Though highly efficient, these machines heat up significantly during operation. By design, state-of-the-art water jacket cooling concepts remove the heat mainly through high internal thermal resistances of the electrical machine. The resulting maximum temperatures in the end winding region limit the achievable machine power output. In this study, alternative cooling concepts are presented, which efficiently use the existing heat conduction paths of an electric machine. For this purpose, two modeling methods for the stator windings were developed: a high-resolution approach that considers each individual wire and an abstract approach that uses zones of constant anisotropic thermal conductivity to specify the heat flow in the windings. Both models were used in conjugate heat transfer simulations of a long-term thermal test of the electrical machine integrated in the BMW i3. For both models the validation showed a very good agreement of simulated and measured temperatures. An evaluation of both methods showed the abstract approach to be more efficient than other simulation methods used in the current R&D. Its application for alternative cooling concepts revealed the necessary heat transfer coefficients at different fluid temperatures for a sole convective cooling of the end windings. However, it could be found that a homogeneous temperature distribution in the stator of the machine can only be achieved if a combination of water jacket cooling and convective end winding cooling is used.","PeriodicalId":36261,"journal":{"name":"SAE International Journal of Electrified Vehicles","volume":"41 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75718406","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}
Yulin Zhang, Yue Wu, Weilong He, Yang Gao, Hui Peng, Heng Li
Eco-driving plays an increasingly important role in intelligent transportation systems, where the vehicle-following economy and safety are receiving increasing attention in recent years. In this context, this article proposes a novel deep deterministic policy gradient (DDPG)-based driving control strategy for connected electric vehicles (CEVs) under vehicle-following scenarios. Three original contributions make this article distinctive from existing studies. First, a multi-objective optimization problem including driving safety, passenger comfort, and the driving economy for the following vehicle is established, in which the battery capacity degradation cost is first considered in the vehicle-following problem. Second, a DDPG-based driving control strategy is proposed where a penalty is introduced into the multi-objective optimization reward function to accelerate the convergence process. Third, the coupling relationship of the three objectives is carefully studied. Different weighting factors are tested and analyzed to balance the three objectives. Detailed discussion and comparison under different driving cycles validate the superiority of the proposed method, e.g., a 16–31% reduction of battery capacity degradation cost with better safety and comfort, compared with existing vehicle-following strategies. This work makes a potential contribution to the artificial intelligence application of intelligent transportation systems.
{"title":"Multi-Objective Optimization of Vehicle-Following Control for Connected Electric Vehicles Based on Deep Deterministic Policy Gradient","authors":"Yulin Zhang, Yue Wu, Weilong He, Yang Gao, Hui Peng, Heng Li","doi":"10.4271/14-13-01-0005","DOIUrl":"https://doi.org/10.4271/14-13-01-0005","url":null,"abstract":"Eco-driving plays an increasingly important role in intelligent transportation systems, where the vehicle-following economy and safety are receiving increasing attention in recent years. In this context, this article proposes a novel deep deterministic policy gradient (DDPG)-based driving control strategy for connected electric vehicles (CEVs) under vehicle-following scenarios. Three original contributions make this article distinctive from existing studies. First, a multi-objective optimization problem including driving safety, passenger comfort, and the driving economy for the following vehicle is established, in which the battery capacity degradation cost is first considered in the vehicle-following problem. Second, a DDPG-based driving control strategy is proposed where a penalty is introduced into the multi-objective optimization reward function to accelerate the convergence process. Third, the coupling relationship of the three objectives is carefully studied. Different weighting factors are tested and analyzed to balance the three objectives. Detailed discussion and comparison under different driving cycles validate the superiority of the proposed method, e.g., a 16–31% reduction of battery capacity degradation cost with better safety and comfort, compared with existing vehicle-following strategies. This work makes a potential contribution to the artificial intelligence application of intelligent transportation systems.","PeriodicalId":36261,"journal":{"name":"SAE International Journal of Electrified Vehicles","volume":"68 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83865002","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：