Heavy-duty diesel vehicles are important sources of urban nitrogen oxides(NOx)in actual applications for environmental compliance,emitting more than 80%of NOx and more than 90%of particulate matter(PM)in total vehicle...Heavy-duty diesel vehicles are important sources of urban nitrogen oxides(NOx)in actual applications for environmental compliance,emitting more than 80%of NOx and more than 90%of particulate matter(PM)in total vehicle emissions.The detection and control of heavy-duty diesel emissions are critical for protecting public health.Currently,vehicles on the road must be regularly tested,every six months or once a year,to filter out high-emission mobile sources at vehicle inspection stations.However,it is difficult to effectively screen high-emission vehicles in time with a long interval between annual inspections,and the fixed threshold cannot adapt to the dynamic changes of vehicle driving conditions.An on-board diagnostic device(OBD)is installed inside the vehicle and can record the vehicle’s emission data in real time.In this paper,we propose a temporal optimization long short-term memory(LSTM)and adaptive dynamic threshold approach to identify heavy-duty high-emitters by using OBD data,which can continuously track and record the emission status in real time.First,a temporal optimization LSTM emission prediction model is established to solve the attention bias discrepancy problem on time steps that is caused by the large number of OBD data streams in practice.Then,the concentration prediction error sequence is detected and distinguished from the anomalous emission contexts using flexible criteria,calculated by an adaptive dynamic threshold with changing driving conditions.Finally,a similarity metric strategy for the time series is introduced to correct some pseudo anomalous results.Experiments on three real OBD time-series emission datasets demonstrate that our method can achieve high accuracy anomalous emission identification.展开更多
A small fraction of high-emitting vehicles make disproportionally large contributions to total fleet emissions.Therefore identifying high emitters under real driving conditions is crucial.In this study,two portable se...A small fraction of high-emitting vehicles make disproportionally large contributions to total fleet emissions.Therefore identifying high emitters under real driving conditions is crucial.In this study,two portable sensor platforms for high-emitter identification were used for online roadside measurements of vehicle-emitted NO,particle number(PN),and CO_(2) concentrations in Tangshan and Chengdu,respectively.The measured mean concentrations of vehicle-emitted NO,PN,and CO_(2) in Tangshan and Chengdu were 27.7-32.9 ppb,5.4×10^(3)-8.2×10^(3)#/cm^(3),and 7.3-8.2 ppm,respectively.Based on more than one month of second-by-second measured pollutant concentrations and passed vehicle information,a scheme was developed to identify high emitters.Among the 217000 and 43000 vehicles that passed the roadside sensor platforms at Tangshan and Chengdu,approximately 60%and 73%of vehicle exhaust plumes were successfully detected using the sensor platform.The NO and PN emission factors(EFs)tended to have log-normal distributions with the median values of 14.3 g/kg-fuel and 1.3×10^(15)#/kg-fuel,respectively.In general,the percentages of high-emitters identified at the Tangshan and Chengdu sites were 8.7% and 12.2% of the total identified vehicles,respectively.Among these high-emitters,122 vehicles were randomly inspected on-site with the assistance of traffic officers,and the rate of correct identification was approximately 95%,which demonstrates that our methodology performs well in identifying real-world high-emitters.Overall,its low cost,good mobility,strong adaptability,and high correct identification rate make this roadside sensor platform a promising approach for real-world high-emitter identification.展开更多
基金Project supported by the National Natural Science Foundation of China (Nos.62033012 and 62103124)the Major Special Science and Technology Project of Anhui Province,China (No.202003a07020009)。
文摘Heavy-duty diesel vehicles are important sources of urban nitrogen oxides(NOx)in actual applications for environmental compliance,emitting more than 80%of NOx and more than 90%of particulate matter(PM)in total vehicle emissions.The detection and control of heavy-duty diesel emissions are critical for protecting public health.Currently,vehicles on the road must be regularly tested,every six months or once a year,to filter out high-emission mobile sources at vehicle inspection stations.However,it is difficult to effectively screen high-emission vehicles in time with a long interval between annual inspections,and the fixed threshold cannot adapt to the dynamic changes of vehicle driving conditions.An on-board diagnostic device(OBD)is installed inside the vehicle and can record the vehicle’s emission data in real time.In this paper,we propose a temporal optimization long short-term memory(LSTM)and adaptive dynamic threshold approach to identify heavy-duty high-emitters by using OBD data,which can continuously track and record the emission status in real time.First,a temporal optimization LSTM emission prediction model is established to solve the attention bias discrepancy problem on time steps that is caused by the large number of OBD data streams in practice.Then,the concentration prediction error sequence is detected and distinguished from the anomalous emission contexts using flexible criteria,calculated by an adaptive dynamic threshold with changing driving conditions.Finally,a similarity metric strategy for the time series is introduced to correct some pseudo anomalous results.Experiments on three real OBD time-series emission datasets demonstrate that our method can achieve high accuracy anomalous emission identification.
基金support from the National Key R&D Program of China(No.2023YFC370540203)the China Postdoctoral Fellowship Program of CPSF(No.GZC20231271).
文摘A small fraction of high-emitting vehicles make disproportionally large contributions to total fleet emissions.Therefore identifying high emitters under real driving conditions is crucial.In this study,two portable sensor platforms for high-emitter identification were used for online roadside measurements of vehicle-emitted NO,particle number(PN),and CO_(2) concentrations in Tangshan and Chengdu,respectively.The measured mean concentrations of vehicle-emitted NO,PN,and CO_(2) in Tangshan and Chengdu were 27.7-32.9 ppb,5.4×10^(3)-8.2×10^(3)#/cm^(3),and 7.3-8.2 ppm,respectively.Based on more than one month of second-by-second measured pollutant concentrations and passed vehicle information,a scheme was developed to identify high emitters.Among the 217000 and 43000 vehicles that passed the roadside sensor platforms at Tangshan and Chengdu,approximately 60%and 73%of vehicle exhaust plumes were successfully detected using the sensor platform.The NO and PN emission factors(EFs)tended to have log-normal distributions with the median values of 14.3 g/kg-fuel and 1.3×10^(15)#/kg-fuel,respectively.In general,the percentages of high-emitters identified at the Tangshan and Chengdu sites were 8.7% and 12.2% of the total identified vehicles,respectively.Among these high-emitters,122 vehicles were randomly inspected on-site with the assistance of traffic officers,and the rate of correct identification was approximately 95%,which demonstrates that our methodology performs well in identifying real-world high-emitters.Overall,its low cost,good mobility,strong adaptability,and high correct identification rate make this roadside sensor platform a promising approach for real-world high-emitter identification.
