Current Issue : July-September Volume : 2024 Issue Number : 3 Articles : 5 Articles
Intelligent decisions for autonomous lane-changing in vehicles have consistently been a focal point of research in the industry. Traditional lane-changing algorithms, which rely on predefined rules, are ill-suited for the complexities and variabilities of real-world road conditions. In this study, we propose an algorithm that leverages the deep deterministic policy gradient (DDPG) reinforcement learning, integrated with a long short-term memory (LSTM) trajectory prediction model, termed as LSTM-DDPG. In the proposed LSTM-DDPG model, the LSTM state module transforms the observed values from the observation module into a state representation, which then serves as a direct input to the DDPG actor network. Meanwhile, the LSTM prediction module translates the historical trajectory coordinates of nearby vehicles into a word-embedding vector via a fully connected layer, thus providing predicted trajectory information for surrounding vehicles. This integrated LSTM approach considers the potential influence of nearby vehicles on the lane-changing decisions of the subject vehicle. Furthermore, our study emphasizes the safety, efficiency, and comfort of the lane-changing process. Accordingly, we designed a reward and penalty function for the LSTM-DDPG algorithm and determined the optimal network structure parameters. The algorithm was then tested on a simulation platform built with MATLAB/Simulink. Our findings indicate that the LSTM-DDPG model offers a more realistic representation of traffic scenarios involving vehicle interactions. When compared to the traditional DDPG algorithm, the LSTM-DDPG achieved a 7.4% increase in average single-step rewards after normalization, underscoring its superior performance in enhancing lane-changing safety and efficiency. This research provides new ideas for advanced lane-changing decisions in autonomous vehicles....
Further advances in hardware and software features are needed to optimize battery and thermal management systems to allow for the execution of longer trips in electric vehicles. This paper assesses the economic and environmental impacts of the following features: eco-charging, eco-driving, smart fast charging, predictive thermal powertrain and cabin conditioning, and an advanced heat pump system. A Total Cost of Ownership (TCO) and externalities calculation is carried out on two passenger cars and one light commercial vehicle (LCV). The energy consumption data from the vehicles are based on experiments. The analysis shows more benefits for the LCV, while the smart fast-charging feature on the car shows a slight increase in TCO. However, negative results did not contribute significantly compared to the ability to install a smaller battery capacity for similar use....
The steering knuckle is a critical component of the suspension and steering drive systems of electric vehicles. The electrification of last-mile vehicles presents a challenge in terms of cost, driving range and compensation of battery weight. This work presents a numerical methodology to evaluate 60XX series aluminum metal matrix composites (AMMCs) with reinforcement ceramic particles for steering knuckle components in medium heavy-duty last-mile cargo vehicles. The use of AMMCs provides lightweight knuckles with sufficient strength, stiffness and safety conditions for electrical vehicle cargo configurations. The numerical study includes three aluminum alloys, two AMMC alloys and an Al 6061-T6 alloy as reference materials. The medium-duty heavy vehicle class < 12 t, such as electrical vehicle cargo configurations, is considered for the numerical study (class 1–4). The maximum von Mises stress for class 4 AMMC alloys exceeds 350 MPa, limited by fracture toughness. The weight reduction is about 65% when compared with commercial cast iron. Moreover, Al 6061-T6 alloys exhibit stress values surpassing 300 MPa, constraining their suitability for heavier vehicles. The study proposes assessing the feasibility of implementing AMMC alloys in critical components like steering knuckles and suggests solutions to enhance conventional vehicle suspension systems and overcome associated challenges. It aims to serve as a lightweight design guide, offering insights into stress variations with differing load conditions across various cargo vehicles....
The Electric Bus DynamicWireless Charging (EB-DWC) system is a bus charging system that enables electric buses to receive power wirelessly from ground-based electromagnetic induction devices. In this system, how to optimally configure the charging infrastructures while considering the unpredictable nature of bus movement is a great challenge. This paper presents an optimization problem for an EB-DWC system in urban settings, addressing stochastic elements inherent in the vehicle speed, initial charging state, and dwell time at bus stops. We formulate a stochastic planning problem for the EB-DWC system by integrating these uncertainties and apply Monte Carlo sampling techniques to effectively solve this problem. The proposed method can improve the system’s robustness effectively....
The three-phase voltage type PulseWidth Modulation (PWM) rectifier is widely used in the front-end power factor of electric vehicle wireless charging systems due to its simple control structure and easy implementation. The system often adopts a double closed-loop PI control method based on voltage and current, which inevitably leads to a significant starting current surge and poses significant risks to the safe operation of the equipment. On the basis of establishing a mathematical model for PWM rectifiers, this article analyzes in detail the causes of starting over-current and designs a starting strategy with a voltage outer proportional and integral separated active current directly given. Simulation experiments show that this method can reduce the starting over-current of PWM rectifiers and the excessive DC voltage surge towards normal operation during the starting process....
Loading....