Search Results

Precise trajectory prediction of surrounding vehicles is critical for decision-making of autonomous vehicles, and learning-based approaches are well recognized for the robustness. However, state-of-the-art learning-based methods ignore (1) the feasibility of the vehicle’s multimodal state information for prediction and (2) the mutually exclusive relationship between the global traffic scene receptive fields and the local position resolution when modeling vehicles’ interactions, which may influence prediction accuracy. Therefore, we propose a “vehicle descriptor”-based long short-term memory (LSTM) model with the dilated convolutional social pooling (VD+DCS-LSTM) to cope with the above issues.

Aiming at the high altitude operation problems for piston-type aero-engines and to improve the practical ceiling and high altitude dynamic performance, this thesis analyzes a controllable three-stage composite supercharging system, using a two-stage turbocharger coupled supercharger method. The GT-Power simulation model of a four-cylinder boxer engine was established, and the control strategy of variable flight height was obtained. The simulation research of engine performance from 0 to 20,000 meters above sea level has been carried out, which shows that the engine power is at the same level as the plain condition, and it could still maintain 85.28 percent of power even at the height of 20,000 meters, which meets the flight requirements of the aircraft.

With the development of economic globalization, the speed of development of container terminals is also very rapid. Under the pressure brought by the surge in throughput, the unmanned and intelligent terminals will become the future development direction of terminals. As the cornerstone of the unmanned terminal, the positioning technology provides the most basic position information for system scheduling, path planning, real-time correction, and loading and unloading. Therefore, this paper is aimed to design a low-cost, high-precision, and easy-to-maintain unmanned dock positioning system in order to better solve the problem of unmanned dock positioning. The main research content of this paper is to design a positioning algorithm for unmanned terminal Automated Guided Vehicle (AGV) based on single-line lidar, including point cloud data acquisition, background filtering, point cloud clustering, vehicle position extraction, and result optimization.

The proper formation of fuel-air mixture, which depends to a large extend on the complex in-cylinder air flow, is an important criterion to control the clean and reliable combustion process in spark-ignition direct-injection (SIDI) engines. The in-cylinder flow vorticity field presents highly transient complex characteristics, and the corresponding vorticity field also evolves in the entire engine cycle from intake to exhaust strokes. It is also widely recognized that the vorticity field plays a key role in the in-cylinder turbulent field because it influences the air-fuel mixing and flame development process. In this investigation, the in-cylinder vortex structure and vorticity field characteristics are analyzed using the phase-invariant proper orthogonal decomposition (POD) method.

Motor speed synchronization is important in gear shifting of emerging clutchless automated manual transmissions for battery electric vehicles (BEV) and other kinds of parallel shaft-based powertrains for hybrid electric vehicles (HEV). Difficulties of the problem mainly come from random delay induced by network communication and unknown load torques from air drag, oil drag, and friction torques, etc. To deal with these two factors, this paper proposes a robust speed synchronization controller based on act-and-wait control and disturbance observer. The former is a kind of periodical controller specially for regulating problems with feedback delay while the latter is a technique for active disturbance rejection. Firstly, the dynamic model of the motor shaft is formulated, and the system parameters are offline identified. The speed tracking problem is then transformed into a regulating one.

A novel magnetorheological fluid dual clutch (MRFDC) for electric vehicle transmission is proposed in this article. The structure was based on the MR fluid clutch and traditional dual clutch equipped on internal combustion engine vehicle. Therefore the MRFDC combines the advantages of MR fluid clutch and dual clutch transmission (DCT) to achieve high control accuracy and fast response. The structure of MRFDC was designed by Unigraphics (UG) three-dimensional (3D) modeling software. Then, finite element analysis (FEA) for magnetic field was conducted by ANSYS under different applied currents from 0.1A to 1A with 0.1A space to obtain the relation between the applied current and magnetic field. In this article, Herschel-Bulkley model is used to predict the MR fluid behavior because of the high shear rate of MR fluid.

Accurate and fast positioning of large aircraft component is of great importance for Automated Alignment System. The Ball joint is a widely-used mechanical device connecting the aircraft component and positioners. However, there are some shortcomings for the device in man-machine engineering, such as the entry state of the ball-head still needs to be confirmed by the workers and then switched to the locking state manually. To solve above problems, a new positioning mechanism is present in this paper, which consists of a ball-head and a ball-socket. The new device is equipped with a monocular vision system, in which a calibrated industrial camera is used to collect the images of the ball-head. And then, the 3-D coordinate of the ball-head center is calculated by a designed algorithm, guiding the positioner to capture the ball-head. Once the ball-head gets into the ball-socket, the pneumatic system will drive the pistons to move to the specified location.

Excellent energy consumption performance of a plug-in hybrid electric vehicle (PHEV) is usually attributed to its hybrid drive mode. However, the factors including vehicle performance, driver behavior and traffic status have been shown to cause unsatisfactory performance. This phenomenon leads to a necessity of study on energy consumption control strategies under real-world driving conditions. This paper proposes a new approach for energy management optimization of plug-in hybrid electric vehicles based on real-world driving data for two purposes. One is for improving the energy consumption of PHEV under real-world driving conditions and the other is for reducing the computational complexity of optimization methods in simulation models. In this process, the paper collected real-world driving record data from 180 drivers within 6 months. Then the principal component analysis (PCA) was employed to extract and define the hidden factors from the initial real-world driving data.

The electricity energy consumption for passenger cabin heating can drastically shorten the driving range for electric vehicles in cold climates. Mobile heat pump system is considered as an effective method to improve heating efficiency. This study investigates the system characteristics of mobile heat pump systems for electrical vehicle application. Based on KULI thermal management software, simulation models including HFC-R134a direct heat pump (DHP) and secondary loop heat pump (SLHP) were developed. The secondary loop employed in the SLHP includes a coolant pump, an indoor heater core and a plate heat exchanger, instead of an indoor condenser in the DHP. The use of a secondary loop has advantages to improve air outlet temperature uniformity. The simulation models were verified by measured data obtained from calorimeter experiments. By adopting simulation models, the effects of indoor and outdoor temperatures on system performance and cycle characteristics were discussed.

In partially automated and conditionally automated vehicles, a part of the work of human drivers is replaced by the system, and the main source of safety risks is no longer system failures, but non-failure risks caused by insufficient system function design. The absence of unreasonable risk due to hazards resulting from functional insufficiencies of the intended functionality or by reasonably foreseeable misuse by persons, is referred to as the Safety Of The Intended Functionality. Drivers have the responsibility to supervise the automated driving system. When they don't agree with the operation behavior of the system, they will interfere with the instructions. However, this may lead to potential risks.

Gluing is an essential fastening step in the field of aircraft assembly except for riveting and bolting. Generally, the robotic programs of gluing are generated in CAM environment. Due to the positioning errors and deformation of the workpiece to be glued in the fixture, the nominal pose and the actual pose of the workpiece are no longer consistent with each other. The Robot trajectory of dispensing glue is adjusted manually according to the actual pose of the workpiece by robot teaching. In this paper, an on-line gluing path correction method is developed by 2D laser profile measurement. A pose calibration method for 2D laser profiler integrated into a gluing robot by measuring a fixed center point of a standard ball is proposed to identify the position and orientation of the laser sensor, which enables the accurate transforming coordinates between the robot frame and the sensor frame.

Visual Place Recognition (VPR) excels at providing a good location prior for autonomous vehicles to initialize the map-based visual SLAM system, especially when the environment changes after a long term. Condition change and viewpoint change, which influences features extracted from images, are two of the major challenges in recognizing a visited place. Existing VPR methods focus on developing the robustness of global feature to address them but ignore the benefits that local feature can auxiliarily offer. Therefore, we introduce a novel hierarchical place recognition method with both global and local features deriving from homologous VLAD to improve the VPR performance. Our model is weak supervised by GPS label and we design a fine-tuning strategy with a coupled triplet loss to make the model more suitable for extracting local features.

Ammonia has attracted the attention of a growing number of researchers in recent years. However, some properties of ammonia (e.g., low laminar burning velocity, high ignition energy, etc.) inhibit its direct application in engines. Several routes have been proposed to overcome these problems, such as oxygen enrichment, partial fuel cracking strategy and co-combustion with more reactive fuels. Improving the reactivity of ammonia from the oxidizer side is also practical. Ozone is a highly reactive oxidizer which can be easily and rapidly generated through electrical plasma and is an effective promoter applicable for a variety of fuels. The dissociation reaction of ozone increases the concentration of reactive radicals and promotes chain-propagating reactions. Thus, obtaining accurate rate constants of reactions related to ozone is necessary, especially at elevated to high pressure range which is closer to engine-relevant conditions.

The heat pump with low global warming potential (GWP) refrigerants is imperative for the electric vehicle (EV) to slow down global warming and extend the driving range while meeting passengers' thermal comfort in low ambient temperatures. However, there are no appropriate refrigerants. To provide long-term and environmental-friendly refrigerants in the heat pump for EVs, herein, we reported newly developed low-GWP refrigerant mixtures, i.e., DL3B, whose GWP is lower than 140, the flammability (lower flammability limit and burning velocity), saturation pressure, lubricant miscibility, material compatibility were experimentally tested. A test bench that can investigate the performance of an R410A prototype was built. The drop-in tests of the DL refrigerant were carried out to evaluate the capacities and COPs for both cooling and heating modes in the EV heat pump system.

An EV prototype, with all the wheels respectively driven by 4 inwheel motors, is developed, and undergoes a series of practical measurements and road tests. Based on the obtained vehicle parameters, a multi-body dynamics model is built by using SolidWorks and Adams/Car, and then validated by track test data. The virtual prototype is served as the control plant in simulation. An adaptive fractional order PID (A-FO-PID) controller is designed to enhance the handling and stability performance of the EV. Considering the model uncertainties, e.g. the variation in body mass distribution and the consequent change in yaw moment of inertial, a Parameter Self-Adjusting Differential Evolution (PSA-DE) algorithm is adopted for tuning the controller parameters, i.e. KP, KI, KD, λ and μ. As a modification of traditional DE algorithm, the so-called Variance of Population’s Fitness is utilized to evaluate the diversity of the population.

In this paper an estimation method on location of peak pressure (LPP) employing flame ionization measurement, with the spark plug as a sensor, was discussed to achieve combustion parameters estimation at quick start of HEV engines. Through the cycle-based ion signal analysis, the location of peak pressure can be extracted in individual cylinder for the optimization of engine quick start control of HEV engine. A series of quick start processes with different cranking speed and engine coolant temperature are tested for establishing the relationship between the ion signals and the combustion parameters. An Artificial Neural Network (ANN) algorithm is used in this study for estimating these two combustion parameters. The experiment results show that the location of peak pressure can be well established by this method.

A new kind of integrated semi-track air-cushion pitch controller is proposed in this paper. The controller first compute the target working point based on a weighed function, which is the combination of optimal power consumption and pitch angle control demand. Then the sequential quadratic programming algorithm distributes the general target values to specific control values. The performance of the controller is verified through co-simulation between Matlab/Simulink and ADAMS/View. The simulation results show the effectiveness of the control algorithm and the correctness of the choice in physical configuration with two air cushions for vehicle body pitch control.

In order to meet increasingly stringent emission regulations, it is significance to establish a control- oriented transient NOx and PM emission prediction model and improve the accuracy and real-time performance. In this study, the prediction model of transient PM emissions based on Transformer is established. In terms of model accuracy and real-time performance, Transformer emission prediction model is compared with Multilayer perceptron (MLP) neural network and Long-Short Term Memory (LSTM) emission prediction model. The results show that the performance of Transformer transient emission prediction model is superior to other model structures, it can be used for real-time prediction.

The prediction of agents' future trajectory is a crucial task in supporting advanced driver-assistance systems (ADAS) and plays a vital role in ensuring safe decisions for autonomous driving (AD). Currently, prevailing trajectory prediction methods heavily rely on high-definition maps (HD maps) as a source of prior knowledge. While HD maps enhance the accuracy of trajectory prediction by providing information about the surrounding environment, their widespread use is limited due to their high cost and legal restrictions. Furthermore, due to object occlusion, limited field of view, and other factors, the historical trajectory of the target agent is often incomplete This limitation significantly reduces the accuracy of trajectory prediction. Therefore, this paper proposes ETSA-Pred, a mapless trajectory prediction model that incorporates enhanced temporal modeling and spatial self-attention.