Search Results

The fusion of multi-modal perception in autonomous driving plays a pivotal role in vehicle behavior decision-making. However, much of the previous research has predominantly focused on the fusion of Lidar and cameras. Although Lidar offers an ample supply of point cloud data, its high cost and the substantial volume of point cloud data can lead to computational delays. Consequently, investigating perception fusion under the context of 4D millimeter-wave radar is of paramount importance for cost reduction and enhanced safety. Nevertheless, 4D millimeter-wave radar faces challenges including sparse point clouds, limited information content, and a lack of fusion strategies. In this paper, we introduce, for the first time, an approach that leverages Graph Neural Networks to assist in expressing features from 4D millimeter-wave radar point clouds. This approach effectively extracts unstructured point cloud features, addressing the loss of object detection due to sparsity.

To reduce the energy consumption level of electric vehicles, the working range of the regenerative braking system will gradually expand to the high state of charge of the battery. The time delay in the control signal transmission path of the high state of charge regenerative braking control process will affect the regenerative braking. At the same time, regenerative braking under a high state of charge puts forward higher requirements for the control accuracy of regenerative current. In the research of this paper, the motor model, battery model, and vehicle dynamics model are firstly established by using MATLAB/Simulink, and the dynamic relationship between regenerative current and regenerative braking torque is analyzed at the same time. Considering the system time delay, this paper proposes a high-charge regenerative braking control strategy (SPPC) that combines Smith prediction and prescribed performance control.

Electrification is the well-accepted solution to address carbon emissions and modernize vehicle controls. Batteries play a critical in the journey of electrification and modernization with battery voltage prediction as the foundation for safe and efficient operation. Due to its strong dependency on prior information, battery voltage was estimated with recurrent neural network methods in the recent literatures exploring a variety of deep learning techniques to estimate battery behaviors. In these studies, standard recurrent neural networks, gated recurrent units, and long-short term memory are popular neural network architectures under review. However, in most cases, each neural network architecture is individually assessed and therefore the knowledge about comparative study among three neural network architecture is limited. In addition, many literatures only studied either the dynamic voltage response or the voltage relaxation.

Due to the poor ability of millimeter wave radar in recognizing distant static objects, target loss and incomplete information will occur when it recognizes the static target in front, thus increasing the false alarm rate and missing alarm rate of the radar-dependent driving assistant system, which will reduce the driving safety and the acceptability of the assistant system. Aiming at the radar's poor ability to recognize static targets, this paper uses a model based on machine learning algorithm to recognize and track targets. The radar signals are collected and processed in different conditions, and the results show that the radar has a poor recognition effect when the distance is more than 100 meters and the speed is more than 19m/s.

HTL is a kind of biodiesel converted from wet biowaste via hydrothermal liquefaction (HTL), which has drawn increasing attention in recent years due to its wide range of raw materials (algae, swine manure, and food processing waste). However, from the previous experiments done in a constant volume chamber, it was observed that the presence of 20% of HTL in the blend produced as much soot as pure diesel at in chamber environment oxygen ratio of 21%, and even more soot at low oxygen ratios. It was also observed that n-butanol addition could reduce the soot emission of diesel significantly under all tested conditions. In this work, the spray and combustion characteristics of HTL and diesel blends with n-butanol added were investigated in a constant volume chamber. The in-chamber temperature and oxygen ranged from 800 to 1200 K and 21% to 13%, respectively, covering both conventional and low-temperature combustion (LTC) regimes.

Flash boiling has drawn much attention recently for its ability to enhance spray atomization and vaporization, while providing better fuel/air mixing for gasoline direct injection engines. However, the behaviors of flash boiling spray with multi-component fuels have not been fully discovered. In this study, isooctane, ethanol and the mixtures of the two with three blend ratios were chosen as the fuels. Measurements were performed with constant fuel temperature while ambient pressures were varied to adjust the superheated degree. Macroscopic and microscopic characteristics of flash boiling spray were investigated using Diffused Back-Illumination (DBI) imaging and Phase Doppler Anemometry (PDA). Comparisons between flash boiling sprays with single component and binary fuel mixtures were performed to study the effect of fuel properties on spray structure as well as atomization and vaporization processes.

The spray structure and vaporization processes of flash-boiling sprays in a constant volume chamber under a wide range of superheated conditions were experimentally investigated by a high speed imaging technique. The Engine Combustion Network’s Spray G injector was used. Four fuels including gasoline, ethanol, and gasoline-ethanol blends E30 and E50 were investigated. Spray penetration length and spray width were correlated to the degree of the superheated degree, which is the ratio of the ambient pressure to saturated vapor pressure (pa/ps). It is found that parameter pa/ps is critical in describing the spray transformation under flash-boiling conditions. Three distinct stages namely the slight flash-boiling, the transition flash-boiling, and the flare flash-boiling are identified to describe the transformation of spray structures.

The study of vehicle coupling state estimation accuracy especially in observer-based vehicle chassis control for improving road handling and ride comfort is a challenging task for vehicle industry under various driving conditions. Due to a large amount of life safety arising from vehicle roll behavior, how to precisely acquire vehicle roll state and rapidly provide for the vehicle control system are of great concern. Simultaneously, uncertainty is unavoidable for various aspects of a vehicle system, e.g., varying sprung mass, moment of inertia and position of the center of gravity. To deal with the above issues, a novel dual observer approach, which combines adaptive Unscented Kalman Filter (AUKF) and Takagi-Sugeno (T-S), is proposed in this paper. A full-car nonlinear model is first established to describe vehicle lateral and vertical coupling roll behavior under various road excitation.

Ignition location is one of the important factors that affect the thermal efficiency, exhaust emissions and knock sensitivity in premixed-charge ignition engines. However, the ignition initiation locations of pre-chamber generated turbulent jet ignition, which is a promising ignition enhancement method, are not clearly understood due to the complex physics behind it. Motivated by this, the ignition initiation location of a transient turbulent jet in a constant volume combustor is analyzed by the use of computational fluid dynamics (CFD) simulations. In the CFD simulations of this work, commercial codes KIVA-3 V release 2 and an in-house-developed chemical solver with a detailed mechanism for H2/air mixtures are used. Comparisons are performed between simulated and experimental ignition initiation locations, and they agree well with one another. A detailed parametric study of the influence of in-cylinder temperature on the ignition initiation location is also performed.

The electric vehicles and the intelligent vehicles put forward to new requirements for the brake system, such as the vacuum-independent braking, automatic or active braking, and regenerative braking, which are the key link for the vehicle’s safety and economy. However, the traditional vacuum brake booster is no longer able to meet these requirements. In this article, a novel integrated power-assisted actuator of brake system is proposed to satisfy the brake system requirements of the electric vehicles and intelligent vehicles. The electronic brake booster system is designed to achieve the function of boosting pedal force of driver, being independent on vacuum source, supplying autonomous or active braking. It is mainly composed of a permanent magnet synchronous motor (PMSM), a two-stage reduction transmission (gears and a ball screw), a servo body, and a reaction disk. The scheme design and power-assisted braking control are the key for the electronic actuator.

Considering the randomness and instability of the oil pressure in the lubrication system, a new approach for fault detection and diagnosis of diesel engine lubrication system based on support vector machine optimized by particle swarm optimization (PSO-SVM) model and centroid location algorithm has been proposed. Firstly, PSO algorithm is chosen to determine the optimum parameters of SVM, to avoid the blindness of choosing parameters. It can improve the prediction accuracy of the model. The results show that the classify accuracy of PSO-SVM is improved compared with SVM in which parameters are set according to experience. Then, the support vector machine classification interface is fitted to a curve, and the boundary conditions of fault diagnosis are obtained. Finally, diagnose algorithm is achieved through analyzing the centroid movement of features. According to Performance degradation data, degenerate trajectory model is established based on centroid location.

In this paper, a novel driver model is proposed to track vehicle speed in MIL (Model-in-the-Loop) test system, which has structural consistency with HIL (Hardware-in-the-Loop) test system. First, the MIL test system which contains models of driver, vehicle and test bench is established. Second, according to the connections of the established models in Matlab/Simulink environment, the vehicle speed is calculated in vehicle model. Emphatically, through the deviation between driving cycle speed and calculated vehicle speed, PI controller in driver model adjusts the vehicle speed to ideal point through sending the torque command to drive motor, the ILC (Iterative Learning Control) controller modifies and stores P value of PI controller. Then, in order to obtain the better modification of PI controller, iterative learning control algorithm is deeply researched in term of types and parameters.

Light-weighting of vehicles is one of the challenges for transportation industry due to the increasing pressure of demands in better fuel economy and environment protection. Advanced high strength steels (AHSS) are considered as prominent material of choice to realize lightweight auto body and structures at least in near term. Stamping of AHSS with conventional die materials and surface coatings, however, results in frequent die failures and undesired panel surface finish. A chromium nitride (CrN) coating with plasma nitriding case hardened layer on a die material (duplex treatment) is found to offer good wear and galling resistances. The coating failure initiates from fatigue cracking on the coating surface due to cyclic sliding frictions. In this work, cyclic inclined sliding wear test was used to imitate a stamping process for study on development of coating fatigue cracking, including crack length and spacing vs. sliding-cycles and sliding energy densities.

The ever-growing number of interacting electronic vehicle control systems requires new control algorithms to manage the increasing system complexity. As a result, torque-based control architecture has been popular for its easy extension as the torque demand variable is the only interface between the engine control algorithms and other vehicle control systems. Under the torque-based control architecture, the engine and AT coordinated control for upshift process is investigated. Based on the dynamics analysis, quantitative relationship between the turbine torque of HTC and output shaft torque of AT has been obtained. Then the coordinated control strategy has been developed to smooth the torque trajectory of AT output shaft. The designed control strategy is tested on a powertrain simulation model in MATLAB/Simulink and a test bench. Through simulation, the shift time range in which the engine coordinated control strategy is effective is acquired.

Ultrasonic fatigue tests (testing frequency around 20 kHz) have been conducted on four different cast aluminum alloys each with a distinct composition, heat treatment, and microstructure. Tests were performed in dry air, laboratory air and submerged in water. For some alloys, the ultrasonic fatigue lives were dramatically affected by the environment humidity. The effects of different factors like material composition, yield strength, secondary dendrite arm spacing and porosity were investigated; it was concluded that the material strength may be the key factor influencing the environmental humidity effect in ultrasonic fatigue testing. Further investigation on the effect of chemical composition, especially copper content, is needed.

The cylinder-by-cylinder variations have many bad impacts on the engine performance, such as increasing the engine speed fluctuation, enlarging the torsional vibration and noise. To deal with this problem, the impact mechanism of cylinder-by-cylinder variations on low order torsional vibration has been studied in this paper, and subsequently a new individual cylinder control strategy was designed by processing the instantaneous crankshaft rotation speed signal, detecting the cylinder-by-cylinder variation and using feed-back control. The acceleration characteristics of each cylinder in each engine cycle were compared with each other to extract the variation index. The feed-back control algorithm was based on the regulation of the fuel injection according to the detected variation level.

Since their inception, the design of airbag sensing systems has continued to evolve. The evolution of air bag sensing system design has been rapid. Electromechanical sensors used in earlier front air bag applications have been replaced by multi-point electronic sensors used to discriminate collision mechanics for potential air bag deployment in front, side and rollover accidents. In addition to multipoint electronic sensors, advanced air bag systems incorporate a variety of state sensors such as seat belt use status, seat track location, and occupant size classification that are taken into consideration by air bag system algorithms and occupant protection deployment strategies. Electronic sensing systems have allowed for the advent of event data recorders (EDRs), which over the past decade, have provided increasingly more information related to air bag deployment events in the field.

The low cycle fatigue experiment is extensively used to test the reliability and durability of turbocharger. Low cycle fatigue test is mainly the switching between high and low speed. As the result of the experiment, the fatigue life is shorter as the difference between high and low speed becomes greater. In the traditional low cycle fatigue test, a large air compressor is needed to drive the turbocharger under different operating conditions, which consume large amounts of electric power. This paper presents a new experiment device which has double chambers and double turbochargers. This device can be self-circulating, without the large air compressor, to realize high and low speed switching on the premise of not exceeding the limitation of turbine entry temperature. First, a detailed model is established in GT-Power and self-circulation test data has been used to validate the model.

Accurate determination of the forming limit strain of aluminum sheet metal is an important topic which has not been fully solved by industry. Also, the effects of draw beads (enhanced forming limit behaviors), normally reported on steel sheet metals, on aluminum sheet metal is not fully understood. This paper introduces an experimental study on draw bead effects on aluminum sheet metals by measuring the forming limit strain zero (FLD0) of the sheet metal. Two kinds of aluminum, AL 6016-T4 and AL 5754-0, are used. Virgin material, 40% draw bead material and 60% draw bead material conditions are tested for each kind of aluminum. Marciniak punch tests were performed to create a plane strain condition. A dual camera Digital Image Correlation (DIC) system was used to record and measure the deformation distribution history during the punch test. The on-set necking timing is determined directly from surface shape change. The FLD0 of each test situation is reported in this article.

High silicon molybdenum (HiSiMo) ductile cast iron (DCI) is commonly used for high temperature engine components, such as exhaust manifolds, which are also subjected to severe thermal cycles during vehicle operation. It is imperative to understand the thermomechanical fatigue (TMF) behavior of HiSiMo DCI to accurately predict the durability of high temperature engine components. In this paper, the effect of the minimum temperature of a TMF cycle on TMF life and failure behavior is investigated. Tensile and low cycle fatigue data are first presented for temperatures up to 800°C. Next, TMF data are presented for maximum temperatures of 800°C and minimum cycle temperatures ranging from 300 to 600°C. The data show that decreasing the minimum temperature has a detrimental effect on TMF life. The Smith-Watson-Topper parameter applied at the maximum temperature of the TMF cycle is found to correlate well with out-of-phase (OP) TMF life for all tested minimum temperatures.