Automated driving is poised to become a pivotal technology in the future automotive transportation.However,it is evident that the implementation of automated driving presents significant technical challenges.To accele...Automated driving is poised to become a pivotal technology in the future automotive transportation.However,it is evident that the implementation of automated driving presents significant technical challenges.To accelerate the development and deployment of automated driving the European Commission initiated the research project L3Pilot in 2017.With a budget of 65 million Euros and the involvement of 13 car manufacturers,L3Pilot stands as the largest European project on automated driving(AD).This paper serves as a comprehensive account of BMW’s main activities in the L3Pilot project that ended in 2021.The research questions addressed in this project are related to the following topics:what are the guidelines for the development of AD?How do potential customers interact with AD?And what is the safety impact assessment of AD?The paper presents the findings related to all three research questions to contribute to the further development of automated driving.For this purpose together with other partners the Code of Practice of AD was defined as a guideline for the development of future AD systems.Related to the second question,BMW conducted tests with AD systems on motorways and in parking scenarios,with over 100 test subjects experiencing AD.The studies provide input and considerations for future AD systems.Finally,in the safety impact assessment,BMW investigated with other project partners the potential safety benefits of AD through simulation.The results show a potential to improve road safety.In conclusion,the exploration of all three research questions has led to a deeper understanding of SAE Level 3 AD.展开更多
The battery thermal management of electric vehicles can be improved using neural networks predicting quantile sequences of the battery temperature.This work extends a method for the development of Quantile Convolution...The battery thermal management of electric vehicles can be improved using neural networks predicting quantile sequences of the battery temperature.This work extends a method for the development of Quantile Convolutional and Quantile Recurrent Neural Networks(namely Q*NN).Fleet data of 225629 drives are clustered and balanced,simulation data from 971 simulations are augmented before they are combined for training and testing.The Q*NN hyperparameters are optimized using an efficient Bayesian optimization,before the Q*NN models are compared with regression and quantile regression models for four horizons.The analysis of point-forecast and quantile-related metrics shows the superior performance of the novel Q*NN models.The median predictions of the best performing model achieve an average RMSE of 0.66°C and R^(2) of 0.84.The predicted 0.99 quantile covers 98.87%of the true values in the test data.In conclusion,this work proposes an extended development and comparison of Q*NN models for accurate battery temperature prediction.展开更多
While redox flow batteries carry a large potential for electricity storage,specifically for regenerative energies,the current technology-prone system-the all-vanadium redox flow battery-exhibits two major disadvantage...While redox flow batteries carry a large potential for electricity storage,specifically for regenerative energies,the current technology-prone system-the all-vanadium redox flow battery-exhibits two major disadvantages:low energy and low power densities.Polyoxometalates have the potential to mitigate both effects.In this publication,the operation of a polyoxometalate redox flow battery was demonstrated for the polyoxoanions[SiW_(12)O_(40)]^(4-)(SiW_(12))in the anolyte and[PV_(14)O_(42)]^(9-)(PV14)in the catholyte.Emphasis was laid on comparing to which extent an upscale from 25 to 1400 cm^(2) membrane area may impede efficiency and operational parameters.Results demonstrated that the operation of the large cell for close to 3 months did not diminish operation and the stability of polyoxometalates was unaltered.展开更多
Quality testing costs hinder the large-scale production of PEM fuel cell systems due to long testing times and high safety measures for hydrogen.While eliminating both issues,electrochemical impedance spectroscopy at ...Quality testing costs hinder the large-scale production of PEM fuel cell systems due to long testing times and high safety measures for hydrogen.While eliminating both issues,electrochemical impedance spectroscopy at low hydrogen concentrations can provide valuable insights into fuel cell processes.However,the influence of high anode stream dilutions on PEM fuel cell performance is not yet completely understood.This study presents a new equivalent circuit model to analyze impedance spectra at low hydrogen partial pressures.The proposed model accurately describes the impedance response and explains the performance decrease at low hydrogen concentrations.First,the reduced availability of hydrogen at the anode leads to rising reaction losses from the hydrogen side.Further,the resulting losses lead to potential changes also influencing the cathode processes.The findings indicate that impedance spectroscopy at low hydrogen partial pressure might provide a reliable fuel cell quality control tool,simplifying production processes,reducing costs,and mitigating risks in fuel cell production.展开更多
基金the European Union's Horizon 2020 research and innovation programme under grant agreement No 723051.
文摘Automated driving is poised to become a pivotal technology in the future automotive transportation.However,it is evident that the implementation of automated driving presents significant technical challenges.To accelerate the development and deployment of automated driving the European Commission initiated the research project L3Pilot in 2017.With a budget of 65 million Euros and the involvement of 13 car manufacturers,L3Pilot stands as the largest European project on automated driving(AD).This paper serves as a comprehensive account of BMW’s main activities in the L3Pilot project that ended in 2021.The research questions addressed in this project are related to the following topics:what are the guidelines for the development of AD?How do potential customers interact with AD?And what is the safety impact assessment of AD?The paper presents the findings related to all three research questions to contribute to the further development of automated driving.For this purpose together with other partners the Code of Practice of AD was defined as a guideline for the development of future AD systems.Related to the second question,BMW conducted tests with AD systems on motorways and in parking scenarios,with over 100 test subjects experiencing AD.The studies provide input and considerations for future AD systems.Finally,in the safety impact assessment,BMW investigated with other project partners the potential safety benefits of AD through simulation.The results show a potential to improve road safety.In conclusion,the exploration of all three research questions has led to a deeper understanding of SAE Level 3 AD.
基金support by the KIT-Publication Fund of the Karlsruhe Institute of Technology.
文摘The battery thermal management of electric vehicles can be improved using neural networks predicting quantile sequences of the battery temperature.This work extends a method for the development of Quantile Convolutional and Quantile Recurrent Neural Networks(namely Q*NN).Fleet data of 225629 drives are clustered and balanced,simulation data from 971 simulations are augmented before they are combined for training and testing.The Q*NN hyperparameters are optimized using an efficient Bayesian optimization,before the Q*NN models are compared with regression and quantile regression models for four horizons.The analysis of point-forecast and quantile-related metrics shows the superior performance of the novel Q*NN models.The median predictions of the best performing model achieve an average RMSE of 0.66°C and R^(2) of 0.84.The predicted 0.99 quantile covers 98.87%of the true values in the test data.In conclusion,this work proposes an extended development and comparison of Q*NN models for accurate battery temperature prediction.
文摘While redox flow batteries carry a large potential for electricity storage,specifically for regenerative energies,the current technology-prone system-the all-vanadium redox flow battery-exhibits two major disadvantages:low energy and low power densities.Polyoxometalates have the potential to mitigate both effects.In this publication,the operation of a polyoxometalate redox flow battery was demonstrated for the polyoxoanions[SiW_(12)O_(40)]^(4-)(SiW_(12))in the anolyte and[PV_(14)O_(42)]^(9-)(PV14)in the catholyte.Emphasis was laid on comparing to which extent an upscale from 25 to 1400 cm^(2) membrane area may impede efficiency and operational parameters.Results demonstrated that the operation of the large cell for close to 3 months did not diminish operation and the stability of polyoxometalates was unaltered.
文摘Quality testing costs hinder the large-scale production of PEM fuel cell systems due to long testing times and high safety measures for hydrogen.While eliminating both issues,electrochemical impedance spectroscopy at low hydrogen concentrations can provide valuable insights into fuel cell processes.However,the influence of high anode stream dilutions on PEM fuel cell performance is not yet completely understood.This study presents a new equivalent circuit model to analyze impedance spectra at low hydrogen partial pressures.The proposed model accurately describes the impedance response and explains the performance decrease at low hydrogen concentrations.First,the reduced availability of hydrogen at the anode leads to rising reaction losses from the hydrogen side.Further,the resulting losses lead to potential changes also influencing the cathode processes.The findings indicate that impedance spectroscopy at low hydrogen partial pressure might provide a reliable fuel cell quality control tool,simplifying production processes,reducing costs,and mitigating risks in fuel cell production.
