Search Results

The operation management of electric Taxi fleets requires cooperative optimization of Charging and Dispatching. The challenge is to make real-time decisions about which is the optimal charging station or passenger for each vehicle in the fleet. With the rapid advancement of Vehicle Internet of Things (VIOT) technologies, the aforementioned challenge can be readily addressed by leveraging big data analytics and machine learning algorithms, thereby contributing to smarter transportation systems. This study focuses on optimizing real-time decision-making for charging and dispatching in large-scale electric taxi fleets to improve their long-term benefits. To achieve this goal, a spatiotemporal decision framework using Bi-level optimization is proposed. Initially, a deep reinforcement learning-based model is built to estimate the value of charging and order dispatching under uncertainty.

Fuel cell vehicles have always garnered a lot of attention in terms of energy utilization and environmental protection. In the analysis of fuel cell performance, there are usually some outliers present in the raw experimental data that can significantly affect the data analysis results. Therefore, data cleaning work is necessary to remove these outliers. The polarization curve is a crucial tool for describing the basic characteristics of fuel cells, typically described by semi-empirical formulas. The parameters in these semi-empirical formulas are fitted using the raw experimental data, so how to quickly and effectively automatically identify and remove data outliers is a crucial step in the process of fitting polarization curve parameters. This article explores data-cleaning methods based on the Local Outlier Factor (LOF) algorithm and the Isolation Forest algorithm to remove data outliers.

SLAM (Simultaneous Localization and Mapping) plays a key role in autonomous driving. Recently, 4D Radar has attracted widespread attention because it breaks through the limitations of 3D millimeter wave radar and can simultaneously detect the distance, velocity, horizontal azimuth and elevation azimuth of the target with high resolution. However, there are few studies on 4D Radar in SLAM. In this paper, RI-FGO, a 4D Radar-Inertial SLAM method based on Factor Graph Optimization, is proposed. The RANSAC (Random Sample Consensus) method is used to eliminate the dynamic obstacle points from a single scan, and the ego-motion velocity is estimated from the static point cloud. A 4D Radar velocity factor is constructed in GTSAM to receive the estimated velocity in a single scan as a measurement and directly integrated into the factor graph. The 4D Radar point clouds of consecutive frames are matched as the odometry factor.

The current automotive industry has a growing demand for real-time transmission to support reliable communication and for key technologies. The Time-Sensitive Networking (TSN) working group introduced standards for reliable communication in time-critical systems, including shaping mechanisms for bounded transmission latency. Among these shaping mechanisms, Cyclic Queuing and Forwarding (CQF) and frame preemption provide deterministic guarantees for frame transmission. However, despite some current studies on the performance analysis of CQF and frame preemption, they also need to consider the potential effects of their combined usage on frame transmission. Furthermore, there is a need for more research that addresses the impact of parameter configuration on frame transmission under different situations and shaping mechanisms, especially in the case of mechanism combination.

The noise tests of electric motor systems serve as the foundation for studying their acoustic issues. However, there is currently a lack of corresponding method for identifying key noise characteristics, such as the noise frequency range that needs to be considered, the significant noise order, and the resonance band worth paying attention to, based on experimental test data under actual operating conditions. This article proposes a method for identifying the noise characteristics of an electric motor system based on tests conducted under distinct operating conditions, which consists of three parts: identifying the primary frequency range, the significant order, and the important resonance band. Firstly, in order to extract noise with the primary energy, the concept of noise contribution is introduced. The primary frequency range and the significant order under a specific operating condition can be obtained after extraction.

Brake judder affects vehicle safety and comfort, making it a key area of research in brake NVH. Transfer path analysis is effective for analyzing and reducing brake judder. However, current studies mainly focus on passenger cars, with limited investigation into commercial vehicles. The complex chassis structures of commercial vehicles involve multiple transfer paths, resulting in extensive data and testing challenges. This hinders the analysis and suppression of brake judder using transfer path analysis. In this study, we propose a simulation-based method to investigate brake judder transfer paths in commercial vehicles. Firstly, road tests were conducted to investigate the brake judder of commercial vehicles. Time-domain analysis, order characteristics analysis, and transfer function analysis between components were performed.

In the process of automobile industrialization, integrated electric drive systems turn to be the mainstream transmission system of electric vehicles gradually. The main sources of noise and vibration in the chassis are from the gear reducer and motor system, as a replacement of engine. For improving the electric vehicles NVH performance, effective identification and quantitative analysis of the main noise sources are a significant basis. Based on the rotating hub test platform in the semi-anechoic chamber, in this experiment, an electric vehicle equipped with a three-in-one electric drive system is taken as the research object. As well the noise and vibration signals in the interior vehicle and the near field of the electric drive system are collected under the operating conditions of uniform speed, acceleration speed, and coasting with gears under different loads, and the test results are processed and analyzed by using the spectral analysis and order analysis theories.

In recent years, with the development of computing infrastructure and methods, the potential of numerical methods to reasonably predict aerodynamic noise in turbocharger compressors of heavy-duty diesel engines has increased. However, aerodynamic acoustic modeling of complex geometries and flow systems is currently immature, mainly due to the greater challenges in accurately characterizing turbulent viscous flows. Therefore, recent advances in aerodynamic noise calculations for automotive turbocharger compressors were reviewed and a quantitative study of the effects for turbulence models (Shear-Stress Transport (SST) and Detached Eddy Simulation (DES)) and time-steps (2° and 4°) in numerical simulations on the performance and acoustic prediction of a compressor under various conditions were investigated.

Tire forces and moments play an important role in vehicle dynamics and safety. X-by-wire chassis components including active suspension, electronic powered steering, by-wire braking, etc can take the tire forces as inputs to improve vehicle’s dynamic performance. In order to measure the accurate dynamic wheel load, most of the researches focused on the kinematic parameters such as body longitudinal and lateral acceleration, load transfer and etc. In this paper, the authors focus on the suspension system, avoiding the dependence on accurate mass and aerodynamics model of the whole vehicle. The geometry of the suspension is equated by the spatial parallel mechanism model (RSSR model), which improves the calculation speed while ensuring the accuracy. A suspension force observer is created, which contains parameters including spring damper compression length, push rod force, knuckle accelerations, etc., combing the kinematic and dynamic characteristic of the vehicle.

A DMS500 engine exhaust particle size spectrometer was employed to characterize the effects of injection strategies on particulate emissions from a turbocharged gasoline direct injection (GDI) engine. The effects of operating parameters (injection pressure, secondary injection ratio and secondary injection end time) on particle diameter distribution and particle number density of emission were investigated. The experimental result indicates that the split injection can suppress the knocking tendency at higher engine loads. The combustion is improved, and the fuel consumption is significantly reduced, avoiding the increase in fuel pump energy consumption caused by the 50 MPa fuel injection system, but the delayed injection increases particulate matter emissions.

In recent years, the burgeoning applications of hydrogen fuel cells have ignited a growing trend in their integration within the transportation sector, with a particular focus on their potential use in multi-rotor drones. The heightened mass-based energy density of fuel cells positions them as promising alternatives to current lithium battery-powered drones, especially as the demand for extended flight durations increases. This article undertakes a comprehensive exploration, comparing the performance of lithium batteries against air-cooled fuel cells, specifically within the context of multi-rotor drones with a 3.5kW power requirement. The study reveals that, for the specified power demand, air-cooled fuel cells outperform lithium batteries, establishing them as a more efficient solution.

It is recognized that the heavier vehicles, the more emissions, thus the more imperative to electrify. In this study, long haul heavy-duty trucks are referred as HDTs, which are recognized as one of the hard-to-electrify vehicle segments, though the automotive industry has gained trending advantages of electrifying both light-duty cars and SUVs. Since big rigs such as Class 8 HDTs have significant road-block challenges for electrification due to the demanding long-hour work cycles in all weathers, this study focuses on quantifying those electrification challenges by taking advantage of the public data of Class 8 tractors & trailers. Tesla Semi is the research target though its vehicle spec data is sorted out with fragmentary information in the public domain. The key task is to analyze the battery capacity requirements due to environmental temperature and inherent aging over the lifespan.

With the continuous popularization of electric vehicles (EVs), ensuring the best performance of EVs has become a significant concern, and lithium-ion power batteries are considered as the essential storage and conversion equipment for EVs. Therefore, it is of great significance to quickly evaluate the state of power batteries. This paper investigates a fast state estimation method of power batteries oriented to after-sales and maintenance. Based on the battery equivalent circuit model and heuristics optimization algorithm, the battery model parameters, including the internal ohmic and polarization resistance, can be identified using only 30 minutes of charging or discharging process data without full charge or discharge. At the same time, the proposed method can directly estimate the state of charge (SOC) and maximum available capacity of the battery without knowing initial SOC information.

Water content estimation is a key problem for studying the PEM fuel cell. When several hundred fuel cells are connected in serial and their active surface area is enlarged for sufficient power, the difference between cells becomes significant with respect to voltage and water content. The voltage of each cell is measurable by the cell voltage monitor (CVM) while it is difficult to estimate water content of the individual. Resistance of the polymer electrolyte membrane is monotonically related to its water content, so that the new online high frequency resistance (HFR) measurement technique is investigated to identify the uniformity of water content between cells and analyze its sensitivity to operating conditions in this paper. Firstly, the accuracy of the proposed technique is experimentally validated to be comparable to that of a commercialized electrochemical impedance spectroscopy (EIS) measurement equipment.

The formation is a crucial step in the production process of lithium-ion batteries (LIBs), during which the solid electrolyte interphase (SEI) is formed on the surface of the anode particles to passivate the electrode. It determines the performance of the battery, including its capacity and lifetime. A meticulously designed formation protocol is essential to regulate and optimize the stability of the SEI, ultimately achieving the optimal performance of the battery. Current research on formation protocols in lithium-ion batteries primarily focuses on temperature, current, and voltage windows. However, there has been limited investigation into the influence of different initial pressures on the formation process, and the evolution of cell pressure during formation remains unclear. In this study, a pressure-assisted formation device for lithium-ion pouch cells is developed, equipped with pressure sensors.

Lightweight design is a key factor in general engineering design practice, however, it often conflicts with fatigue durability. This paper presents a way for improving the effectiveness of fatigue performance dominated optimization, demonstrated through a case study on suspension brackets for heavy-duty vehicles. This case study is based on random load data collected from fatigue durability tests in proving grounds, and fatigue failures of the heavy-duty vehicle suspension brackets were observed and recorded during the tests. Multi-objective fatigue optimization was introduced by employing multiaxial time-domain fatigue analysis under random loads combined with the non-dominated sorting genetic algorithm II with archives.

As a key component of in-vehicle intelligent voice technology, speech enhancement can extract clean speech signals contaminated by environmental noise to improve the perceptual quality and intelligibility of speech. It has extensive applications in the field of intelligent car cabins. Although some end-to-end speech enhancement methods based on time domain have been proposed, there is often limited consideration given to designing model architectures based on the characteristics of the speech signal. In this paper, we propose a new U-Net based speech enhancement framework that utilizes the temporal correlation of speech signals to reconstruct higher-quality and more intelligible clean speech.

Speech enhancement can extract clean speech from noise interference, enhancing its perceptual quality and intelligibility. This technology has significant applications in in-car intelligent voice interaction. However, the complex noise environment inside the vehicle, especially the human voice interference is very prominent, which brings great challenges to the vehicle speech interaction system. In this paper, we propose a speech enhancement method based on target speech features, which can better extract clean speech and improve the perceptual quality and intelligibility of enhanced speech in the environment of human noise interference. To this end, we propose a design method for the middle layer of the U-Net architecture based on Long Short-Term Memory (LSTM), which can automatically extract the target speech features that are highly distinguishable from the noise signal and human voice interference features in noisy speech, and realize the targeted extraction of clean speech.

Accurate prediction temperature variation of electric drive transmission (EDT) can effectively monitor its abnormal temperature rise that may occur under high speed and heavy load working conditions, so as to ensure the vehicles’ safe operation. In this paper, combined with real temperature and input/output characteristic data collected from EDT test platform under different working conditions, a spatio-temporal relationship dynamic graph convolution neural network based on least square method (OLS-DRGCN) for temperature prediction is proposed. Firstly, OLS is used to estimate the EDT’s internal temperature based on partial sensor information as the input of OLS-DRGCN. Secondly, the spatial dependence relationship of each temperature node is dynamically learned through node embedding and the dynamic thermal network topology of EDT is constructed. Meanwhile, the timing rule of each temperature node is obtained through the gated recurrent unit.

The optimization of speed holds critical significance for pure electric vehicles. In multi-intersection scenarios, the determination of terminal velocity plays a crucial role in addressing the complexities of the speed optimization problem. However, prevailing methodologies documented in the literature predominantly adhere to a fixed speed constraint derived from traffic light regulations, serving as the primary basis for the terminal velocity constraint. Nevertheless, this strategy can result in unnecessary acceleration and deceleration maneuvers, consequently leading to an undesirable escalation in energy consumption. To mitigate these issues and attain an optimal terminal velocity, this paper proposes an innovative speed optimization method that incorporates a terminal-velocity heuristic. Firstly, a traffic light state model is established to determine the speed range required to avoid coming to a stop at signalized intersections.