Non-road equipment is one of the key contributing sources to air pollution.Thus,an accurate development of emission inventory from non-road equipment is imperative for air quality management,especially for equipment w...Non-road equipment is one of the key contributing sources to air pollution.Thus,an accurate development of emission inventory from non-road equipment is imperative for air quality management,especially for equipment with a large population such as diesel-fueled forklifts.The objective of this paper is to characterize duty-cycle based emissions from diesel-fueled forklifts using a portable emission measurement system(PEMS).Three dutycycles were defined in this study,including idling,moving,and working(active duty operation)and used to characterize in-use emissions for diesel-fueled forklifts.A total of twelve diesel-fueled forklifts were selected for real-world emission measurements.Results showed that fuel-based emission factors appear to have smaller variability compared to time-based ones.For example,the time-based emission factors for CO,HC,NO,and PM 2.5 for forklifts were estimated to be 16.6-43.9,5.3-15.1,26.2-49.9,5.5-11.1 g/hr with the fuel-based emission factors being 12.1-20.3,4.1-8.3,19.1-32.4,3.5-6.5 g/kg-fuel,respectively.NO emissions appear to be the biggest concern for emissions control.Furthermore,most of the emissions factors estimated from this study are significantly different from those in both National Guideline for Emission Inventory Development for Non-Road Equipment in China and welldeveloped emission factor models such as NONROAD by US EPA.This implies that localized,preferably fuel-based emission factors should be adjusted based on real-world emission measurements in order to develop a representative emission inventory for non-road equipment.展开更多
State of health(SOH)estimation of e-mobilities operated in real and dynamic conditions is essential and challenging.Most of existing estimations are based on a fixed constant current charging and discharging aging pro...State of health(SOH)estimation of e-mobilities operated in real and dynamic conditions is essential and challenging.Most of existing estimations are based on a fixed constant current charging and discharging aging profiles,which overlooked the fact that the charging and discharging profiles are random and not complete in real application.This work investigates the influence of feature engineering on the accuracy of different machine learning(ML)-based SOH estimations acting on different recharging sub-profiles where a realistic battery mission profile is considered.Fifteen features were extracted from the battery partial recharging profiles,considering different factors such as starting voltage values,charge amount,and charging sliding windows.Then,features were selected based on a feature selection pipeline consisting of filtering and supervised ML-based subset selection.Multiple linear regression(MLR),Gaussian process regression(GPR),and support vector regression(SVR)were applied to estimate SOH,and root mean square error(RMSE)was used to evaluate and compare the estimation performance.The results showed that the feature selection pipeline can improve SOH estimation accuracy by 55.05%,2.57%,and 2.82%for MLR,GPR and SVR respectively.It was demonstrated that the estimation based on partial charging profiles with lower starting voltage,large charge,and large sliding window size is more likely to achieve higher accuracy.This work hopes to give some insights into the supervised ML-based feature engineering acting on random partial recharges on SOH estimation performance and tries to fill the gap of effective SOH estimation between theoretical study and real dynamic application.展开更多
文摘Non-road equipment is one of the key contributing sources to air pollution.Thus,an accurate development of emission inventory from non-road equipment is imperative for air quality management,especially for equipment with a large population such as diesel-fueled forklifts.The objective of this paper is to characterize duty-cycle based emissions from diesel-fueled forklifts using a portable emission measurement system(PEMS).Three dutycycles were defined in this study,including idling,moving,and working(active duty operation)and used to characterize in-use emissions for diesel-fueled forklifts.A total of twelve diesel-fueled forklifts were selected for real-world emission measurements.Results showed that fuel-based emission factors appear to have smaller variability compared to time-based ones.For example,the time-based emission factors for CO,HC,NO,and PM 2.5 for forklifts were estimated to be 16.6-43.9,5.3-15.1,26.2-49.9,5.5-11.1 g/hr with the fuel-based emission factors being 12.1-20.3,4.1-8.3,19.1-32.4,3.5-6.5 g/kg-fuel,respectively.NO emissions appear to be the biggest concern for emissions control.Furthermore,most of the emissions factors estimated from this study are significantly different from those in both National Guideline for Emission Inventory Development for Non-Road Equipment in China and welldeveloped emission factor models such as NONROAD by US EPA.This implies that localized,preferably fuel-based emission factors should be adjusted based on real-world emission measurements in order to develop a representative emission inventory for non-road equipment.
基金funded by China Scholarship Council.The fund number is 202108320111 and 202208320055。
文摘State of health(SOH)estimation of e-mobilities operated in real and dynamic conditions is essential and challenging.Most of existing estimations are based on a fixed constant current charging and discharging aging profiles,which overlooked the fact that the charging and discharging profiles are random and not complete in real application.This work investigates the influence of feature engineering on the accuracy of different machine learning(ML)-based SOH estimations acting on different recharging sub-profiles where a realistic battery mission profile is considered.Fifteen features were extracted from the battery partial recharging profiles,considering different factors such as starting voltage values,charge amount,and charging sliding windows.Then,features were selected based on a feature selection pipeline consisting of filtering and supervised ML-based subset selection.Multiple linear regression(MLR),Gaussian process regression(GPR),and support vector regression(SVR)were applied to estimate SOH,and root mean square error(RMSE)was used to evaluate and compare the estimation performance.The results showed that the feature selection pipeline can improve SOH estimation accuracy by 55.05%,2.57%,and 2.82%for MLR,GPR and SVR respectively.It was demonstrated that the estimation based on partial charging profiles with lower starting voltage,large charge,and large sliding window size is more likely to achieve higher accuracy.This work hopes to give some insights into the supervised ML-based feature engineering acting on random partial recharges on SOH estimation performance and tries to fill the gap of effective SOH estimation between theoretical study and real dynamic application.