The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicti...The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.展开更多
To compensate for the shortcomings of the thermal and catalytic regeneration of the diesel particulate filter(DPF),a self-designed packed-bed dielectric barrier discharge(DBD)reactor for DPF regeneration was developed...To compensate for the shortcomings of the thermal and catalytic regeneration of the diesel particulate filter(DPF),a self-designed packed-bed dielectric barrier discharge(DBD)reactor for DPF regeneration was developed.The DBD reactor with the main active substance of nonthermal plasma(NTP)as the target parameter was optimized by adjusting the feed gas,packing particles(material or size),and cooling water temperature.Moreover,a set of optimal working parameters(gas source,O_2;packing particles,1.2–1.4 mm ZrO_(2);and cooling water temperature,20℃)was selected to evaluate the effect of different O_(3) concentrations on DPF regeneration.The research results showed that selecting packing particles with high dielectric constant and large particles,as well as reducing the cooling water temperature,with oxygen as the feed gas,contributed to an increase in O_(3) concentration.During DPF regeneration,the following changes were observed:the power of the NTP reactor decreased to lower than 100 W,the O_(3) concentration increased from 15 g m^(-3) to 45 g m^(-3),the CO and CO_2 volume fractions of the particulate matter decomposition products increased,and the peak regeneration temperature increased to 173.4℃.The peak temperature arrival time was 60 min earlier,indicating that the regeneration rate of DPF increased with the increase in O_(3) concentration.However,the O_(3) utilization rate(the amount of carbon deposit removed per unit volume O_(3))initially increased and then decreased;when the O_(3) concentration was set to 25 g m^(-3),the highest O_(3) utilization rate was reached.The packed-bed DBD technology contributed to the increase in the concentration of NTP active substances and the regeneration efficiency of DPF.It provides a theoretical and experimental basis for high-efficiency regeneration of DPF at low temperatures(<200℃).展开更多
Particulate matter(PM)capture tests were carried out on clean diesel particulate filters(DPFs)under different loads(25%,50%,75%and 100%).DPFs were regenerated by a non-thermal plasma(NTP)injection device.Raman spectro...Particulate matter(PM)capture tests were carried out on clean diesel particulate filters(DPFs)under different loads(25%,50%,75%and 100%).DPFs were regenerated by a non-thermal plasma(NTP)injection device.Raman spectroscopy and x-ray photoelectron spectroscopy were used to investigate changes in the microstructure and element occurrence state of the sediment in DPF channel before and after regeneration.The order of the PM samples decreased before NTP treatment as the load increased;the amorphous carbon content was high,and the oxidationactivity was higher.After NTP treatment,the carbon atoms at the edge of the microcrystalline structure in the ash-PM samples were oxidized,and the structure was reorganized;in addition,the amorphous carbon content decreased,and the structure was more diversified.Before NTP,the C element of PM samples was the main component,and the content of the O element was relatively low.The C element occurred in the form of C–C,C–OH,and O–C=O functional groups,and O atoms were mainly combined with C–O.After NTP,the content of Na,P,S,Ca,and other inorganic elements in ash-PM samples was prominent because C atoms were removed by NTP active substances.There were two forms of S element occurrence(SO42-and SO32-);the proportion of SO42-was approximately 40%,and the proportion of SO32-was approximately60%.Study of the microstructure and element occurrence of the residues in the DPF channels improved our understanding of the mechanism of the low-temperature regeneration of DPFfrom NTP.展开更多
Diesel engine alternative fuels, such as methanol and biodiesel, are beneficial to reduce diesel engine emission. In order to study the influence of methanol and biodiesel on the performance, economy and emission of s...Diesel engine alternative fuels, such as methanol and biodiesel, are beneficial to reduce diesel engine emission. In order to study the influence of methanol and biodiesel on the performance, economy and emission of small agricultural diesel engine, the physical-chemical properties(cetane number, lower heat value(LHV), viscosity, etc.) of methanol and biodiesel were analyzed. The methanol and biodiesel showed good complementary property to some extent. When a large proportion of methanol was added into biodiesel, the cetane number of the methanol/biodiesel blend will be greatly reduced. Since the cetane number of the blend fuel has great influence on the combustion process of diesel engine, after testing for blending ratio of methanol/biodiesel, the blend was prepared with 5%(BM5), 10%(BM10) and 15%(BM15) methanol, respectively. Di-Tert-Butyl Peroxide(DTBP) was chosen as a cetane number improver to be added into methanol/biodiesel blend. 0.25%, 0.50% and 0.75% of DTBP was added into BM15. The bench test was carried out on a 186 FA diesel engine to study the effect of methanol and DTBP on the engine performance and emissions. The results show that, at rated condition, compared with biodiesel, the NO;concentration of BM5, BM10 and BM15 is reduced by 5.02%, 33.85% and 21.24%, and smoke is reduced by 5.56%, 22.22% and 55.56%. However, the engine power is also reduced by 5.77%, 14.23% and 25.41%, and the brake specific energy consumption is increased by 3.31%, 7.78% and 6.37%. The addition of DTBP in methanol/biodiesel could recover the engine power to the level of diesel. DTBP shows good effect on the reduction of the brake specific energy consumption and NO_(x), CO, HC concentration, but a little increase of exhaust smoke.展开更多
To overcome the problem that a single feature can not reflect the state of machinery in different stages,a method of vibration feature fusion based on self-organizing map(SOM) is presented.Minimum quantization error(M...To overcome the problem that a single feature can not reflect the state of machinery in different stages,a method of vibration feature fusion based on self-organizing map(SOM) is presented.Minimum quantization error(MQE) is obtained unsupervised based on SOM network.And trend information of the MQE curve is extracted by the wavelet packet to enhance state differentiating.Experimental flat is designed for bearing accelerating fatigue.And experimental results show that the method of vibration feature fusion based on SOM can reflect the state of machinery in different stages effectively.展开更多
Diesel soot subjected to high exhaust temperature suffers from thermal ageing,which is difficult to be removed by regeneration process.Based on the thermogravimetric(TG)analysis and images by high resolution transmiss...Diesel soot subjected to high exhaust temperature suffers from thermal ageing,which is difficult to be removed by regeneration process.Based on the thermogravimetric(TG)analysis and images by high resolution transmission electron microscope(HRTEM),effects of thermal ageing temperature,ageing time and oxygen concentration on oxidation characteristic of soot are investigated.The activation energy of soot increases with the increase of ageing temperature and oxygen concentration.The activation energy increases rapidly when the ageing time is less than 45 min,and then it keeps in a value of 157 kJ/mol when the ageing time is between 45 and 60 min.Compared to the soot without thermal ageing,the shape of ageing soot particles presents shorter diameter and more regular circle by observing soot nanostructure.With the increase of ageing temperature,ageing time and oxygen concentration,the more stable structure of“shell and core”is shown in the basic carbon.The soot has an increased fringe length,decreased tortuosity and separation distance after thermal ageing process,which leads to the deepening of the disorder degree of soot nanostructures and reduction of soot oxidation activity.Consequently,the thermal ageing process should be avoided in order to optimize the active regeneration strategy.展开更多
基金supported in part by the Science and Technology Department of Sichuan Province(No.2025ZNSFSC0427,No.2024ZDZX0035)the Open Project Fund of Vehicle Measurement,Control and Safety Key Laboratory of Sichuan Province(No.QCCK2024-004)the Industrial and Educational Integration Project of Yibin(No.YB-XHU-20240001)。
文摘The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.
基金supported by National Natural Science Foundation of China (No. 51806085)China Postdoctoral Science Foundation (No. 2018M642175)+2 种基金Jiangsu Planned Projects for Postdoctoral Research Fund (No. 2018K101C)Open Research Subject of Key Laboratory of Automotive Measurement, Control and Safety (Xihua University) (No. QCCK2021-007)the Graduate Student Innovation Fund Project of Jiangsu Province (No. KYCX21_3354)
文摘To compensate for the shortcomings of the thermal and catalytic regeneration of the diesel particulate filter(DPF),a self-designed packed-bed dielectric barrier discharge(DBD)reactor for DPF regeneration was developed.The DBD reactor with the main active substance of nonthermal plasma(NTP)as the target parameter was optimized by adjusting the feed gas,packing particles(material or size),and cooling water temperature.Moreover,a set of optimal working parameters(gas source,O_2;packing particles,1.2–1.4 mm ZrO_(2);and cooling water temperature,20℃)was selected to evaluate the effect of different O_(3) concentrations on DPF regeneration.The research results showed that selecting packing particles with high dielectric constant and large particles,as well as reducing the cooling water temperature,with oxygen as the feed gas,contributed to an increase in O_(3) concentration.During DPF regeneration,the following changes were observed:the power of the NTP reactor decreased to lower than 100 W,the O_(3) concentration increased from 15 g m^(-3) to 45 g m^(-3),the CO and CO_2 volume fractions of the particulate matter decomposition products increased,and the peak regeneration temperature increased to 173.4℃.The peak temperature arrival time was 60 min earlier,indicating that the regeneration rate of DPF increased with the increase in O_(3) concentration.However,the O_(3) utilization rate(the amount of carbon deposit removed per unit volume O_(3))initially increased and then decreased;when the O_(3) concentration was set to 25 g m^(-3),the highest O_(3) utilization rate was reached.The packed-bed DBD technology contributed to the increase in the concentration of NTP active substances and the regeneration efficiency of DPF.It provides a theoretical and experimental basis for high-efficiency regeneration of DPF at low temperatures(<200℃).
基金supported by National Natural Science Foundation of China(No.51806085)China Postdoctoral Science Foundation(No.2018M642175)+2 种基金Jiangsu Planned Projects for Postdoctoral Research Fund(No.2018K101C)Open Research Subject of Key Laboratory of automotive measurement,control and safety(Xihua University)(No.QCCK2021-007)Graduate Student Innovation Fund Project of Jiangsu Province(No.KYCX213354)。
文摘Particulate matter(PM)capture tests were carried out on clean diesel particulate filters(DPFs)under different loads(25%,50%,75%and 100%).DPFs were regenerated by a non-thermal plasma(NTP)injection device.Raman spectroscopy and x-ray photoelectron spectroscopy were used to investigate changes in the microstructure and element occurrence state of the sediment in DPF channel before and after regeneration.The order of the PM samples decreased before NTP treatment as the load increased;the amorphous carbon content was high,and the oxidationactivity was higher.After NTP treatment,the carbon atoms at the edge of the microcrystalline structure in the ash-PM samples were oxidized,and the structure was reorganized;in addition,the amorphous carbon content decreased,and the structure was more diversified.Before NTP,the C element of PM samples was the main component,and the content of the O element was relatively low.The C element occurred in the form of C–C,C–OH,and O–C=O functional groups,and O atoms were mainly combined with C–O.After NTP,the content of Na,P,S,Ca,and other inorganic elements in ash-PM samples was prominent because C atoms were removed by NTP active substances.There were two forms of S element occurrence(SO42-and SO32-);the proportion of SO42-was approximately 40%,and the proportion of SO32-was approximately60%.Study of the microstructure and element occurrence of the residues in the DPF channels improved our understanding of the mechanism of the low-temperature regeneration of DPFfrom NTP.
基金Sponsored by the Open Project of State Key Laboratory of Internal Combustion Engine Combustion,Tianjin University(Grand No.K2020-12)the Project of Natural Science Foundation of Jiangsu Province(Grant No.BK20200910)+1 种基金the Natural Science Research Projects in Jiangsu Higher Education Institutions(Grant No.20KJB470015)the Provincial Engineering Research Center for New Energy Vehicle Intelligent Control and Simulation Test Technology of Sichuan(Grant No.XNYQ2021-003)。
文摘Diesel engine alternative fuels, such as methanol and biodiesel, are beneficial to reduce diesel engine emission. In order to study the influence of methanol and biodiesel on the performance, economy and emission of small agricultural diesel engine, the physical-chemical properties(cetane number, lower heat value(LHV), viscosity, etc.) of methanol and biodiesel were analyzed. The methanol and biodiesel showed good complementary property to some extent. When a large proportion of methanol was added into biodiesel, the cetane number of the methanol/biodiesel blend will be greatly reduced. Since the cetane number of the blend fuel has great influence on the combustion process of diesel engine, after testing for blending ratio of methanol/biodiesel, the blend was prepared with 5%(BM5), 10%(BM10) and 15%(BM15) methanol, respectively. Di-Tert-Butyl Peroxide(DTBP) was chosen as a cetane number improver to be added into methanol/biodiesel blend. 0.25%, 0.50% and 0.75% of DTBP was added into BM15. The bench test was carried out on a 186 FA diesel engine to study the effect of methanol and DTBP on the engine performance and emissions. The results show that, at rated condition, compared with biodiesel, the NO;concentration of BM5, BM10 and BM15 is reduced by 5.02%, 33.85% and 21.24%, and smoke is reduced by 5.56%, 22.22% and 55.56%. However, the engine power is also reduced by 5.77%, 14.23% and 25.41%, and the brake specific energy consumption is increased by 3.31%, 7.78% and 6.37%. The addition of DTBP in methanol/biodiesel could recover the engine power to the level of diesel. DTBP shows good effect on the reduction of the brake specific energy consumption and NO_(x), CO, HC concentration, but a little increase of exhaust smoke.
文摘To overcome the problem that a single feature can not reflect the state of machinery in different stages,a method of vibration feature fusion based on self-organizing map(SOM) is presented.Minimum quantization error(MQE) is obtained unsupervised based on SOM network.And trend information of the MQE curve is extracted by the wavelet packet to enhance state differentiating.Experimental flat is designed for bearing accelerating fatigue.And experimental results show that the method of vibration feature fusion based on SOM can reflect the state of machinery in different stages effectively.
基金Project(51676167)supported by the National Natural Science Foundation of ChinaProject(17TD0035)supported by the Sichuan Provincial Scientific Research Innovation Team Program,ChinaProjects(2017TD0026,2015TD0021)supported by Science&Technology Department of Sichuan Province,China。
文摘Diesel soot subjected to high exhaust temperature suffers from thermal ageing,which is difficult to be removed by regeneration process.Based on the thermogravimetric(TG)analysis and images by high resolution transmission electron microscope(HRTEM),effects of thermal ageing temperature,ageing time and oxygen concentration on oxidation characteristic of soot are investigated.The activation energy of soot increases with the increase of ageing temperature and oxygen concentration.The activation energy increases rapidly when the ageing time is less than 45 min,and then it keeps in a value of 157 kJ/mol when the ageing time is between 45 and 60 min.Compared to the soot without thermal ageing,the shape of ageing soot particles presents shorter diameter and more regular circle by observing soot nanostructure.With the increase of ageing temperature,ageing time and oxygen concentration,the more stable structure of“shell and core”is shown in the basic carbon.The soot has an increased fringe length,decreased tortuosity and separation distance after thermal ageing process,which leads to the deepening of the disorder degree of soot nanostructures and reduction of soot oxidation activity.Consequently,the thermal ageing process should be avoided in order to optimize the active regeneration strategy.
