Search Results

Low-frequency vibration caused by road roughness while driving is transmitted to the human body through tires, suspension, and seats. Prolonged exposure of the human body to the vibratory environment will have an impact on ride comfort or even health issues. In order to investigate the vibration response of various segments of occupants while driving, a 15-DOF multi-body dynamic model depicting the shanks with feet, thighs, pelvis, torso with arms, and the head of occupants is established in the two-dimensional sagittal plane, which considers the contact between the occupant and the cushion, backrest headrest, and the vehicle floor simultaneously. The biodynamic parameters are obtained by fitting the published vibration experimental data based on an optimization algorithm. The previously proposed half-car model is incorporated into the human model to construct an integrated vehicle-human model for further ride comfort analysis.

Electric centrifugal air compressor is one of the most important auxiliary components for the fuel cell engine, which has great impacts on the system efficiency, cost and compactness. However, the centrifugal compressor works at an ultra-high speed for a long time, which poses a great challenge to the lives of motor, bearing and seal. Therefore, reducing the rotating speed of the impeller and maintaining high pressure ratio and high efficiency are important issues for aerodynamic design of the compressor. In this paper, a centrifugal compressor rotor for a 100kW fuel cell system is designed. Aiming at reducing the rotating speed, the influences of three key structural parameters including inlet blade angle, outlet blade angle and blade outlet radius on performance are investigated. The aerodynamic performance of the compressor is predicted using the Reynolds-averaged Navier-Stokes (RANS) equations with computational fluid dynamic (CFD) tools.

The roof sensor system is an indispensable part of intelligent vehicles to observe the environment, however, it deteriorates the aerodynamic and noise performance of the vehicle. In this paper, large eddy simulation and the acoustic perturbation equation are combined to simulate the flow and sound fields of the intelligent vehicle. Firstly, test and simulation differences of aerodynamic drag and pressure coefficients on the roof and rear of the intelligent vehicle without roof sensor system are discussed. It is found that the difference in aerodynamic drag coefficient is 5.5%, and the pressure coefficients’ differences at 21 out of 24 measurement points are less than 0.05. On this basis, under the influence of the sensor system, the aerodynamic drag coefficient of the intelligent vehicle is increased by 23.4%.

The temperature management of the proton exchange membrane fuel cell cooling system is very important to the stability and life of the engine. The size and cycle switching of the cooling system and the rapid temperature rise of the system are inseparable from the thermostat. In this paper, a simulation model of the fuel cell cooling system is built for a 30KW fuel cell system, and its accuracy is verified by experiments. The temperature fluctuation of the system in the confluence mode is mainly studied, and the error is about 0.9 °C. The influence of the converging mode of the thermostat on the temperature of the cooling system is researched through the simulation platform. Based on the simulation model, the influence of thermostats with different external environments and opening degrees on the size cycle switching of cooling system is predicted, which provides optimization and guidance for the system control strategy.

The diesel particulate filter (DPF) is an effective device for reducing particulate emissions from diesel engines, while its durability and reliability after long-term use are causes for concern. Usually, particulates are considered to be uniformly deposited in DPF channels to form a cake or end plug, however, recent studies have found that a “middle channel deposit” phenomenon of particulates can form a bridge near the middle of the DPF channel. This phenomenon has serious adverse effects on the durability and reliability of the DPF, including abnormally increased pressure drop and frequent regeneration. Since the width of the DPF channel is only about 1-2 millimeters, conventional methods cannot observe the particulate deposition process inside the DPF.

Visual sensors are widely used in autonomous vehicles (AVs) for object detection due to the advantages of abundant information and low-cost. But the performance of visual sensors is highly affected by low light conditions when AVs driving at nighttime and in the tunnel. The low light conditions decrease the image quality and the performance of object detection, and may cause safety of the intended functionality (SOTIF) problems. Therefore, to analyze the performance limitations of visual sensors in low light conditions, a controlled light experiment on a proving ground is designed. The influences of low light conditions on the two-stage algorithm and the single-stage algorithm are compared and analyzed quantificationally by constructing an evaluation index set from three aspects of missing detection, classification, and positioning accuracy.

A formal gesture recognition based on optics has limitations, but millimeter-wave (MMW) radar has shown significant advantages in gesture recognition. Therefore, the MMW radar has become the most promising human-computer interaction equipment, which can be used for human-computer interaction of vehicle personnel. This paper proposes a multi-branch network based on a residual neural network (ResNet) to solve the problems of insufficient feature extraction and fusion of the MMW radar and immense algorithm complexity. By constructing the gesture sample library of six gestures, the MMW radar signal is processed and coupled to establish the relationship between the motion parameters of the distance, speed, and angle of the gesture information and time, and the depth features are extracted. Then the three depth features are fused. Finally, the classification and recognition of MMW radar gesture signals are realized through the full connection layer.

Recent researches in autonomous driving mainly consider the uncertainty in perception and prediction modules for safety enhancement. However, obstacles which block the field-of-view (FOV) of sensors could generate blind areas and leaves environmental uncertainty a remaining challenge for autonomous vehicles. Current solutions mainly rely on passive obstacles avoidance in path planning instead of active perception to deal with unexplored high-risky areas. In view of the problem, this paper introduces the concept of information entropy, which quantifies uncertain information in the blind area, into the motion planning module of autonomous vehicles. Based on model predictive control (MPC) scheme, the proposed algorithm can plan collision-free trajectories while actively explore unknown areas to minimize environmental uncertainty. Simulation results under various challenging scenarios demonstrate the improvement in safety and comfort with the proposed perception-aware planning scheme.

Multi-Target tracking is a central aspect of modeling the surrounding environment of autonomous vehicles. Automotive millimeter-wave radar is a necessary component in the autonomous driving system. One of the biggest advantages of radar is it measures the velocity directly. Another big advantage is that the radar is less influenced by environmental conditions. It can work day and night, in rainy or snowy conditions. In the expressway scenario, the forward-looking radar can generate multiple objects, to properly track the leading vehicle or neighbor-lane vehicle, a multi-target tracking algorithm is required. How to associate the track and the measurement or data association is an important question in a multi-target tracking system. This paper applies the nearest-neighbor method to solve the data association problem and uses an extended Kalman filter to update the state of the track.

Proton exchange membrane fuel cells (PEMFC) are considered an environment-friendly alternative vehicle power in the future owing to their high power density and zero-carbon emission. To research the performance of the air supplied by the PEMFC air system, the PEMFC air system bench composed of an air compressor, cooler, emulated stack, back-pressure valve, and sensors was built. Then, a PEMFC system test bench composed of a hydrogen supply subsystem, stack, air supply subsystem, electronic control subsystem, and cooling subsystem was established. The fuel cell system control parameters and control method are complex due to the coupling and nonlinearity of the air supply system. The strategy composed of a feedforward table and piecewise proportional integral (PI) feedback control strategy was employed to regulate the pressure and flow rate of the air supply system.

As a newly designed hybrid transmission, DHT (Dedicated Hybrid Transmission) owns the advantages of compact structure, multi-modes and excellent comprehensive performance. Compared with the traditional add-on hybrid transmission with one single motor, DHT uses one independent generator for engine starting and speed adjusting which can be largely improve the driving performance in the mode changing process. Based on the series-parallel DHT with wet clutch for power coupling, this paper firstly analyses the power coupling clutch device functionalities from the power flow viewpoint under normal and limp home condition. And for the changing process from series to parallel mode, a clutch coordination control strategy is designed by combining generator fast speed adjusting with clutch accurately pressure controlling to fulfill the fast driver intension response and clutch protection.

The driving conditions of commercial logistics vehicles have the characteristics of combined urban and suburban roads with relatively fixed mileage and cargo load alteration, which affect the vehicular fuel economy. To this end, an adaptive equivalent consumption minimization strategy (A-ECMS) with vehicle speed and weight recognition is proposed to improve the fuel economy for a range-extender electric van for logistics in this work. The driving conditions are divided into nine representative groups with different vehicle speed and weight statuses, and the driving patterns are recognized with the use of the bagged trees algorithm through vehicle simulations. In order to generate the reference SOC near the optimal values, the optimal SOC trajectories under the typical driving cycles with different loads are solved by the shooting method and the optimal slopes for these nine patterns are obtained.

Numerical analysis of thermal efficiency improvement up to 45% of an 1.8-liter turbocharged direct-injection (DI) gasoline engine was conducted in this study in response to the need of improving vehicle fuel economy. 1D thermodynamics simulations and 3D computational fluid dynamics (CFD) modeling were carried out to investigate the technical approaches for improving engine thermal efficiency. Effects of various technologies on the improvement in the engine performance were evaluated, and then the technical routes to achieve 41% and 45% brake thermal efficiency were summarized, respectively. It is concluded that 41% thermal efficiency can be reached under stoichiometric combustion conditions, while it is expected lean burn technology is needed for the target of 45% thermal efficiency. The effects of high tumble intake flow on accelerating burning speed and of high compression ratio on intensifying knocking were analyzed.

Deep neural network models have been widely used for environment perception of intelligent vehicles. However, due to models’ innate probabilistic property, the lack of transparency, and sensitivity to data, perception results have inevitable uncertainties. To compensate for the weakness of probabilistic models, many pieces of research have been proposed to analyze and quantify such uncertainties. For safety-critical intelligent vehicles, the uncertainty analysis of data and models for environment perception is especially important. Uncertainty estimation can be a way to quantify the risk of environment perception. In this regard, it is essential to deliver a comprehensive survey. This work presents a comprehensive overview of uncertainty estimation in deep neural networks for environment perception of intelligent vehicles.

The parameter setting has a great influence on the noise reduction performance of the road noise active control (RNC) system. This paper analyzes and optimizes the parameters of the RNC system. Firstly, the model of the RNC system is established based on the FxLMS algorithm. Based on this model, taking the maximum noise reduction as the evaluation index, the sensitivity analysis of convergence coefficient, filter order, and reference signal gain was carried out using the Sobol method with the data measured by a real vehicle on asphalt pavement at 40km/h. The results show that there is no significant interaction between the three parameters. Then, using the idea of orthogonal experiment, the simulation results of the control model are analyzed by taking the maximum noise reduction as the evaluation index. It is found that the convergence coefficient has the greatest effect on the maximum noise reduction, followed by the filter order, and the reference signal gain has the least effect.

For high levels autonomous driving functions, the Decision Layer often takes on more responsibility due to the requirement of facing more diverse and even rare conditions. It is very difficult to accurately find a safe and efficient lane change timing when autonomous vehicles encounter complex traffic flow and need to change lanes. The traditional method based on rules and experiences has the limitation that it is difficult to be taken into account all possible conditions. Therefore, this paper designs a lane-changing decision algorithm based on data-driven and machine learning, and uses the DQN (Deep Q Network) algorithm in Reinforcement Learning to determine the appropriate lane-changing timing and target lane. Firstly, the scene characteristics of the highway are analyzed, the input and output of the decision-making model are designated and the data from the Perception Layer are processed.

The past decade has witnessed the rapid development of autonomous parking technology, since it has promising capacity to improve traffic efficiency and reduce the burden on drivers. However, it is prone to the trap of self-centeredness when each vehicle is automated parking in isolation. And it is easy to cause traffic congestion and even chaos when multiple autonomous vehicles require of parking into the same lot. In order to address the multiple vehicle parking problem, we propose a parking planning method with genetic algorithm. Firstly, an optimal mathematic model is established to describe the multiple autonomous vehicle parking problem. Secondly, a genetic algorithm is designed to solve the optimization problem. Thirdly, illustrative examples are developed to verify the parking planner. The performance of the present method indicates its competence in addressing parking multiple autonomous vehicles problem.

In recent years, intelligent driving technology is being extensively studied. This paper proposes a path planning method for perpendicular parking based on vehicle kinematics model using MPC optimization, which aims to solve the perpendicular parking task. Firstly, in the case of any initial position and orientation of the vehicle, judging whether the vehicle can be parked at one step according to the location of the parking place and the width of the lane, and then calculating the starting position for parking, and use the Bezier curve to connect the initial position and the starting position. Secondly, reference parking path is calculated according to the collision constraints of the parking space. Finally, because the parking path based on the vehicle kinematics model is composed of circle arcs and straight lines, the curvature of the path is discontinuous. The reference parking path is optimized using Model Predictive Control (MPC).

Although autonomous valet parking technology can replace the driver to complete the parking operation, it is easy to cause traffic chaos in the case of lacking scheduling for multiple parking agents, especially when multiple cars compete for the same parking slot at the same time. Therefore, in order to ensure orderly traffic and parking safety, it is necessary to allocate parking slots reasonably for multiple autonomous valet parking vehicles. The parking slots allocation model is built as an optimal problem with constraints. Both parking mileage cost and parking difficult cost are considering at the objective function in the optimization problem. There are three types of constraints. The first is the capacity limit of a single parking slot, the second is the space limit occupied by a single vehicle, and the third is the total capacity limit of the parking lot. After establishing parking slots allocation model, the immune algorithm is coded to solve the problem.

An accurate finite element (FE) model is the basis for the numerical prediction of vibration and noise of permanent magnet synchronous motors (PMSMs). This paper provides an equivalent modeling method of PMSMs considering the orthotropic material parameters of the stator system. First, a theoretical analysis of the influence of orthotropic material parameters on modal characteristics is implemented. Subsequently, the influence of orthotropic material parameters on the modal frequency of the stator is analyzed through the FE method. Then, the modal parameters of the stator core and the stator assembly are obtained by modal tests. According to the equivalent FE model and modal parameters, the orthotropic material parameters of the stator system are acquired. Moreover, to save the calculation time and simplify the modal identification process, the influence of windings is taken into account through additional mass and additional stiffness during the modeling process.