Browsing by Author "Li, Jie"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Open Access Deep reinforcement learning-based eco-driving control for connected electric vehicles at signalized intersections considering traffic uncertainties(Elsevier, 2023-06-19) Li, Jie; Fotouhi, Abbas; Pan, Wenjun; Liu, Yonggang; Zhang, Yuanjian; Chen, ZhengEco-driving control poses great energy-saving potential at multiple signalized intersection scenarios. However, traffic uncertainties can often lead to errors in ecological velocity planning and result in increased energy consumption. This study proposes an eco-driving approach with a hierarchical framework to be leveraged at signalized intersections that considers the impact of traffic uncertainty. The proposed approach leverages a queue-based traffic model in the upper level to estimate the impact of traffic uncertainty and generate dynamic modified traffic light information. In the lower level, a deep reinforcement learning-based controller is constructed to optimize velocity subject to the constraints from the traffic lights and traffic uncertainty, thereby reducing energy consumption while ensuring driving safety. The effectiveness of the proposed control strategy is demonstrated through numerous simulation case studies. The simulation results show that the proposed method significantly improves energy economy and prevents unnecessary idling in uncertain traffic scenarios, as compared to other approaches that ignore traffic uncertainty. Furthermore, the proposed method is adaptable to different traffic scenarios and showcases energy efficiency.Item Open Access Preliminary aerodynamic design methodology for aero engine lean direct injection combustors(Cambridge University Press, 2017-06-21) Sun, Xiaoxiao; Liu, Yize; Sethi, Vishal; Li, JieThe Lean Direct Injection (LDI) combustor is one of the low-emissions combustors with great potential in aero-engine applications, especially those with high overall pressure ratio. A preliminary design tool providing basic combustor sizing information and qualitative assessment of performance and emission characteristics of the LDI combustor within a short period of time will be of great value to designers. In this research, the methodology of preliminary aerodynamic design for a second-generation LDI (LDI-2) combustor was explored. A computer code was developed based on this method covering the design of air distribution, combustor sizing, diffuser, dilution holes and swirlers. The NASA correlations for NOx emissions are also embedded in the program in order to estimate the NOx production of the designed LDI combustor. A case study was carried out through the design of an LDI-2 combustor named as CULDI2015 and the comparison with an existing rich-burn, quick-quench, lean-burn combustor operating at identical conditions. It is discovered that the LDI combustor could potentially achieve a reduction in liner length and NOx emissions by 18% and 67%, respectively. A sensitivity study on parameters such as equivalence ratio, dome and passage velocity and fuel staging is performed to investigate the effect of design uncertainties on both preliminary design results and NOx production. A summary on the variation of design parameters and their impact is presented. The developed tool is proved to be valuable to preliminarily evaluate the LDI combustor performance and NOx emission at the early design stage.Item Embargo Review on eco-driving control for connected and automated vehicles(Elsevier, 2023-11-11) Li, Jie; Fotouhi, Abbas; Liu, Yonggang; Zhang, Yuanjian; Chen, ZhengWith the development of communication and automation technologies, the great energy-saving potential of connected and automated vehicles (CAVs) has gradually been highlighted. By means of interactions with surrounding vehicles and infrastructure, CAVs can automatically plan ecological driving behaviours to significantly reduce energy consumption, which is normally defined as eco-driving. Currently, eco-driving is recognised as an effective method to improve the energy economy of individual CAVs and promote the overall energy economy of transportation without requiring significant hardware investment. After reviewing the scattered eco-driving literature, this study systematically summarizes the state-of-the-art in this field for promoting its future development. The basic principles of eco-driving and energy management systems are firstly discussed to figure out the relationship between eco-driving and powertrain control. Then, related eco-driving studies are classified into three categories according to their applications in terms of single-vehicle scenario, car-following operation, and multi-vehicle co-operation. The key characteristics of various eco-driving studies are in-depth addressed, and the energy-saving potential for cooperative eco-driving is emphasized. Finally, the potential development trends are provided, thereby contributing to the development of eco-driving techniques.Item Open Access Selection and aggregation of low-cost particle sensors for outdoor particulate matter measurement(IEEE, 2024-06-28) Li, Jie; Nasar, Zaheer; Ferracci, Valerio; Harris, Neil; Xu, ZhengjiaA growing number of low-cost sensors (LCS) have been used to monitor air pollution in outdoor air. The benefit of utilizing LCS lies in its ability to offer increased spatial coverage, which provides real-time measurements at a reduced cost. The selection and combination of low-cost sensors represent the primary challenge in conducting observations using such sensors. This paper employs a sensor quality ranking strategy, utilizing random forest (RF) for aggregating the selected LCS combination, followed by evaluating the correction results using various model evaluation metrics. The LCS used in this study, regardless of their quality grades, achieves a coefficient of determination of 0.93 or higher after model calibration, indicating the effectiveness of employing RF for aggregation. It is found that using a pair of top and averaged LCS can significantly enhance the measurement quality by 25% in RMSE. Using RF to calibrate a single LCS increases the measurement performance at least two times in terms of MSE, RMSE, and MAE. Using paired LCS with RF aggregation for measuring PM2.5, the aggregated observation significantly approximates the reference measurement with R2=0.986.