Search Results

Fuel cell electric vehicles (FCEVs) require multiple components to operate properly, and the fuel cell stack—the source of power—is one of the most important components. While the number of enterprises manufacturing and selling fuel cell stacks is increasing globaly year after year, the residual challenges of core components and technologies still need to be resolved in order to keep pace with the development of lithium-ion batteries (i.e., its primary competitor). Additionally, many production and distribution standards are seen as unsettled. These barriers make large-scale commercialization an issue. Use of Proton-exchange Membrane Fuel Cells in Ground Vehicles explores the opportunities and challenges within the PEMFC industry. With the help of expert contributors, a critical overview of fuel cells and the FCEV industry is presented, and core technology, applications, costs, and trends are 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.

As the connectivity of vehicles increases rapidly, more vehicles have the capability to communicate with each other. Because Vehicular Ad-hoc NETworks (VANETs) have the characteristics of solid mobility and decentralization, traditional security strategies such as authentication, firewall, and access control are difficult to play an influential role. As a soft security method, trust management can ensure the security attributes of VANETs. However, the rapid growth of newly encountered nodes of the trust management system also increases the requirements for trust establishing mechanisms. Without a proper trust establishment mechanism, the trust value of the newly encountered nodes will deviate significantly from its actual performance, and the trust management system will suffer from newcomer attacks.

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.

Aiming at the test safety problems in the early stage of self-driving cars development, firstly the virtual vehicle on-board CAN data acquisition module of the present project was designed based on virtual LabVIEW. Then a wireless remote control system for the self-driving car was constructed, which integrated the built virtual vehicle on-board CAN data acquisition system, the remote real-time image monitoring module and the remote upper computer control module based on ZigBee wireless transmission. It can execute the environmental awareness training and continuous and complex motion manipulation testing of the vehicle without relying on the driver, which can solve the safety problems in the tests of initial development of self-driving cars. Finally, the four-wheel independent steering electric vehicle was used as the self-driving test vehicle, and the wireless remote control system was tested on the double lane change type path and S-type path.

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.

The separation and analysis of the torque of the permanent magnet synchronous motor is of great significance for optimizing the torque output of the motor. Based on the frozen permeability method, the virtual work principle (VWP) or the Maxwell stress tensor method (MSTM) is often used to separate the torque for torque analysis. However, considering the influence of non-ideal factors such as motor saturation, cross-coupling and flux harmonics, there are differences in torque separation between the VWP and the MSTM, which has been researched and analyzed in this paper. Based on this, for the assisted airspace barrier design of a surface-inserted permanent magnet synchronous motor, to conduct theoretical research on the torque optimization design, this paper uses the VWP to separate the average torque and the MSTM to separate the torque ripple.

As the international community strengthens the control of carbon dioxide emissions, electric vehicles have gradually become a substitute for internal combustion engine vehicles. The battery pack is one of the most important components of electric vehicles. The strength and fatigue performance of the battery support plate not only affect the performance of the vehicle but also concern the safety of the driver. In the present study, the finite element model of a battery pack for fatigue analysis is completely established. The random vibration stress response analysis and acceleration power spectral density response analysis of the support plate for the battery pack are carried out, and the accuracy of the finite element model is verified by a random vibration test.

This study investigated the plastic deformation behavior of 304 stainless steel thin-walled tubes under axial compression by means of numerical calculation and theoretical analysis. It was found that the plastic deformation length of thin-walled tube determined the formability of folds and the work done in the whole axial compression process. To reveal the relation between the range of plastic deformation length and tube geometry parameters, regression equations were established using the quadratic regression orthogonal design method. Experiments were conducted to validate the equations. The process windows for forming a single fold and tube joining at ends had been printed ultimately. The results showed that the regression equations can accurately predict the range of plastic deformation length for forming a single fold.

The diesel engine is the core in the field of engineering machine power plants. While both at home and abroad for the cold start of diesel engine, the transient emission characteristics below 0 °C and above 2000m is almost a blank. Therefore, aimed at high altitude and low-temperature environment emission characteristics of cold start, this article has carried on the systematic analysis and research. In this paper, a simulation test system for the cold start of the diesel engine at low temperature at high altitude is established. The cold start experiments of a heavy diesel engine at different ambient temperatures (10°C, 0°C, -10°C and -20°C) and different altitudes (0m, 3000m, and 4000m) is carried out. In this paper, the gas emission of the diesel engine during the speed-up period of cold start is studied.

Diesel engine is vital in the industry for its characteristics of low fuel consumption, high-torque, reliability, and durability. Existing diesel engine technology has reached the upper limit. It is difficult to break through the fuel consumption and emission of diesel engines. VVA (Variable Valve Actuation) is a new technology in the field of the diesel engines. In this paper, GT-Suite and ANN (artificial neural network) model are established based on engine experimental data and DoE simulation results. By inputting Intake Valve Opening crake angle (IVO), Intake Valve Angle Multiplier (IVAM) and Exhaust Valve Angle Multiplier (EVAM) into the ANN Model, and by using SA (simulated annealing algorithm), the optimized results of intake and exhaust valve lift under the target conditions are obtained.

With the degradation of lithium-ion batteries, the battery safety performance changes, which further influences the safe working window. In this paper, the pouch ternary lithium-ion battery whose rated capacity is 4.2 Ah is used as the research object to investigate the impact of the high-temperature calendar and cyclic aging on tolerance performance. The overcharge-to-thermal-runaway test is performed on the fresh cell and aged cell (90% SOH). The inflection point of voltage for aged cells appears earlier than that of the fresh cell, while the voltage corresponding to the inflection point is the same for them, which means that the voltage at which lithium plating occurs is the same. However, the voltage plateau and the crest voltage before thermal runaway of aged cell are significantly higher than that of the fresh cell. Besides, ohmic heat, reversible heat, and side reaction heat make contribution to the thermal runaway triggering.

To improve the durability of Proton-exchange membrane fuel cell (PEMFC) in actual transportation application scenario, the research on fault diagnosis of PEMFC is receiving extensive attention. With the development of artificial intelligence, performing fault diagnosis with the massive sampling data of the fuel cell system has become a popular research topic. But few people have successfully verified the diagnosis performance of these artificial intelligence algorithms on a real high power on-board PEMFC system. Therefore, we intend to make a step forward with these data-driven artificial intelligence algorithms. We applied four data-driven artificial intelligence algorithms to diagnose three common faults of PEMFC (each fault type has two severity levels, slight and severe). AVL CRUISE M was firstly applied for generation of simulation fault dataset to speed up the algorithm screening process. Based on the dataset, these algorithms are trained and optimized.

Proton exchange membrane fuel cell (PEMFC) system is considered as one of the most popular power sources because of its high energy density, fast dynamic response and zero pollution. However, the start-up at low temperature (e.g. - 30 °C) is still a major challenge for its wide application due to water freezing in Membrane Electrode Assembly (MEA). In this paper, a cold start test process in an environment cabin with auxiliary heat was carried out for a full power automotive PEMFC system, including normal operation, shutdown purge and cold start processes analysis from -30°C. Rated power of this stack is 100kW at the current density of 1.4A/cm2 and relevant maximum output power can reach to 120kW. In order to reduce the damage of high potential to MEA, on-load purge with a current of 30A is conducted to removing extra water in stack for improving cold start ability. Based on corresponding control strategy, cold start was realized successfully within 110s.

Diesel engine starts stably under extreme conditions of high altitude and low ambient temperature, which is of great significance to national economic development, national defense force and user safety. However, there are few studies on cold start performance and transient emission of diesel engines with ambient temperature below 0°C and altitude above 2000m. A simulation test system for high altitude and low temperature cold start of diesel engine is established in this paper. The cold start-up of a high-pressure common rail turbocharged heavy diesel engine discharged from the fifth stage in China at altitudes of 0m, 3000m and 4000m at 10°C, 0°C, -10°C and -20°C is studied. The ignition mechanism of diesel engine at high altitude and low temperature is put forward. The combustion characteristics of diesel engine at variable altitude and ambient temperature were studied.

High-nickel lithium-ion batteries extend the driving mileage of electric vehicles (EVs) to 600km without much cost increment. However, thermal accidents commonly occur due to their poor thermal stability, such as thermal runaway. To address the issue, a comprehensive analysis of the thermal runaway behavior of high-nickel lithium-ion batteries with different specifications is conducted. The thermal runaway process is divided into five stages based on self-heating generation, voltage drop, safety valve rupture, and thermal runaway triggering for the three tested cells. The three tested cells demonstrate similar behaviors during each stage of the thermal runaway process. However, there are still apparent differences between their characteristics. This study analyses the thermal runaway features from the following aspects: (i) characteristic temperature; (ii) the relationship between sudden voltage drop and characteristic temperatures; (iii) temperature recovery; (iv) thermodynamics.

With the strict requirements of harmful emission regulations, carbon peaking and neutralization goal, the internal combustion engine (ICE) industry is facing great challenges. Compared with pure ICE powertrain, hybrid powertrain has the advantages on fuel consumption and harmful emissions, which is more suitable for the market today. In series hybrid powertrain, because of the direct mechanical connection between ICE and motor, the motor can be used as an assistant in optimizing the performance of ICE. In order to realize the cycle-based or crank angle-based control of ICE, a high-frequency motor control system need to be built. Field Programmable Gate Array (FPGA) has the characteristics of high calculation frequency and high reliability to meet the demand. At the same time, the ICE control based on LabVIEW and FPGA has been realized.