Search Results

In order to solve the environmental pollution and energy crisis, Electric Vehicles (EVs) have been developed rapidly. Lithium-ion (Li-ion) battery is the key power supply equipment for EVs, and the scientific and accurate prediction of its Remaining Useful Life (RUL) has become a hot topic in the field of new energy research. The internal resistance and capacity are often used to characterize the Li-ion battery State of Health (SOH) from which RUL is obtained. However, in practical applications, it is difficult to obtain internal resistance and capacity information by using the non-intrusive measurement method. Therefore, it is necessary to extract the measurable parameters to characterize the degradation of Li-ion battery. At present, the methods of extracting health indicators based on measurable parameters have gained preliminary results, but most of them are derived from the Li-ion battery discharging data.

Intelligent sweeper vehicle is gradually applied to human life, in which the accuracy of garbage identification and classification can improve cleaning efficiency and save labor cost. Although Deep Learning has made significant progress in computer vision and the application of semantic network segmentation can improve waste identification rate and classification accuracy. Due to the loss of some spatial information during the convolution process, coupled with the lack of specific datasets for garbage identification, the training of the network and the improvement of recognition and classification accuracy are affected. Based on the Unet algorithm, in this paper we adjust the number of input and output channels in the convolutional layer to improve the speed during the feature extraction part. In addition, manually generated datasets are used to greatly improve the robustness of the model.

A flow divider valve is a device which allows a single stream of fluid to be split into two paths according to a predetermined ratio and independent of variations or differences in the load pressures. A flow combiner valve combines two paths of fluid into one stream such that the ratio of the flow rates coming into the valve remains independent of any variation or difference between the inlet pressures. This paper describes the design, operation and performance of an integrated flow divider/combiner valve. This design maintains the small flow dividing/combining error of high precision valves (less than 1.5% at rated flow) but incorporates the shuttle valve into the main spool system. This new design reduces the weight of the valve by 20% reducing the cost by approximately 10%. The new structure simplifies the construction of high precision valves and reduces a source of flow dividing/combining error (leakage).

The development of high precision flow divider/combiner valves has received considerable attention by the authors over the past decade. Several different valve designs for division and combination of flow have been designed which display small flow dividing/combining error (1-2%) when compared to conventional designs (2-10%). Recent studies have improved upon the design in order to reduce cost, weight and complexity of the valve. This paper will present the latest of the authors research into the development of a high precision, autoregulated flow divider/combiner valve with an integral shuttle valve. The autoregulator extends the operating range of the integrated flow divider/combiner valve (for errors less than 2 %) to 10-50 lpm compared to 30-50 lpm for the unregulated valve.

On-road testing of driving performance of the urban bus was carried out, and a representative urban bus driving cycle was developed after on-road testing, according to the test results. Then, the vehicle simulation software AVL CRUISE was used to simulate the dynamic behavior of the urban bus. It involves the simulation of complete drive train system and the driver behavior. The model is validated by comparing the results of the simulation to the results of the field test. Then the developed driving cycle is evaluated by fuel consumption resulted from the simulation and engine bench test on fuel economy.

Road traffic accidents resulting from alcohol-impaired driving are increasing globally despite several measures, currently in place, to curb the trend. For this reason, recent research aims at integrating alcohol early-detection systems and driving simulator experiments to identify intoxicated drivers. However, driving simulator experiments on drunk driving have focused mostly on male participants than female drivers whose characteristics have scarcely been explored. Hence in this paper, vehicle dynamic control inputs on steering, braking, and acceleration performance of 75 licensed female drivers with an upshot of alcohol at four different blood alcohol concentration (BAC) levels (0%, 0.03%, 0.05%, and 0.08%) were investigated. The participants completed simulated driving in a fixed-based simulator experiment coupled with real-time ecological scenarios to extract discrete responses.

In the process of designing the aerodynamic kit for Formula SAE racing cars, there is a lot of repetitive work and low efficiency in optimizing parameters such as wing angle of attack and chord length. Moreover, the optimization of these parameters in past designs heavily relied on design experience and it's difficult to achieve the optimal solution through theoretical calculations. By establishing a parametric model in CAD software and integrating it with CFD software, we can automatically modify model parameters, run a large number of simulations, and analyze the simulation results using statistical methods. After multiple iterations, we achieve fully automatic parameter optimization and obtain higher negative lift. At the same time, the simulation process is optimized, and simulations are run based on GPUs, resulting in a significant increase in simulation speed compared to the original.

With the increase of car ownership and the complex and crowded parking environment, it is difficult for drivers to complete the parking operation quickly and accurately, which may cause traffic accidents such as vehicle collisions and road jams because of poor parking skills. The emergence of an automatic parking system can help drivers park safely and reduce the occurrence of safety accidents. In this paper, the neural network identifier on the control method of an adaptive integral derivative of a neural network is proposed for an automatic parallel parking system with front-wheel steering is studied by using MATLAB/Simulink environment, and the simulation is carried out. Firstly, according to vehicle parameters and obstacle avoidance constraints, the minimum parking space, and parking starting position are calculated. Meanwhile, the path planning of parallel parking spaces is carried out by quintic polynomial.

Deep Deterministic Policy Gradient (DDPG) is one of the Deep Reinforcement Learning algorithms. Because of the well perform in continuous motion control, DDPG algorithm is applied in the field of self-driving. Regarding the problems of the instability of DDPG algorithm during training and low training efficiency and slow convergence rate. An improved DDPG algorithm based on segmented experience replay is presented. On the basis of the DDPG algorithm, the segmented experience replay select the training experience by the importance according to the training progress to improve the training efficiency and stability of the training model. The algorithm was tested in an open source 3D car racing simulator called TORCS. The simulation results demonstrate the training stability is significantly improved compared with the DDPG algorithm and the DQN algorithm, and the average return is about 46% higher than the DDPG algorithm and about 55% higher than the DQN algorithm.

Discretionary lane changing is commonly seen in highway driving. Intelligent vehicles are expected to change lanes discretionarily for better driving experience and higher traffic efficiency. This study proposed to optimize the decision-making and trajectory-planning process so that intelligent vehicles made lane changes not only with driving safety taken into account, but also with the goal to improve driving comfort as well as to meet the driver’ s expectation. The mechanism of how various factors contribute to the driver’s intention to change lanes was studied by carrying out a series of driving simulation experiments, and a Lane-Changing Intention Generation (LCIG) model based on Bi-directional Long Short-Term Memory (Bi-LSTM) was proposed.

Lane detection is an important component in automatic pilot system and advanced driving assistance system (ADAS). The stability and precision of lane detection will directly determine precision of control and lane plan of vehicles. Traditional mechanical vision lane detection approaches in complicated environment have the deficiencies of low precision and feature semantic description disabilities. But the lane detection depending on deep learning, e.g. SCNN network, LaneNet network, ENet-SAD network have imbalance problems of splitting precision and storage usage. This paper proposes an approach of high-efficiency deep learning Segnet-LSTM semantic segmentation network. This network structure is composed with encoding network and corresponding decoding networks. First, convolution and maximum pooling. The proposal extracts texture details of five images and stores searching position of maximum pooling. Meanwhile, it will implement interpolate processing to the lost points.

Several factors including internal factors which are related to the structure and components of transmission and external factors which are related to the running condition influence transmission efficiency (TE) collectively. Selected one manual transmission as the research object, this paper mainly analyzes factors including gears and bearings power loss through theoretical calculation and the external factors, such as gears, temperature and torque. Firstly, with a methodology, the overall efficiency of the manual transmission is calculated based on factors. Then, this paper discusses efficiency through external factor. This transmission is experimented on transmission test bench. On the bench, the driving motor (DM) simulates the power input of engine and the load motor (LM) simulates the whole resistance of vehicle. The mechanical transmission is operating in different speeds, torques and work temperature, thus the corresponding data are obtained.

In summer, the relatively low temperature water condenses in the evaporator when the vehicle air-conditioning (AC) is running. At present, the vehicle AC condensate water without well utilization is directly wasted. The condenser’s thermal transfer performance has a great influence on the AC performance, and to increase the convective heat transfer coefficient (CHTC) is the key to its design. In this paper, a method of using atomized condensate water (CW) to enhance the condenser’s thermal transfer performance is proposed, which can make the most of the CW's cold energy. It achieves the reuse of CW and increases the condenser’s CHTC. First, the CW flow calculation model in the evaporator and the calculation model of the condenser enhanced thermal transfer using atomized CW are both set up. The influence of the evaporation degree of atomized CW particles in the air on the enhancement effect is comprehensively considered.

The closed cabin temperature is anticipated to be cooled down when it is a bit hot inside the driving car. The traditional air-condition lowers the cabin temperature by frequently switching the status of the compressor, which increases the engine’s parasitic power and shortens the compressor’s service-life. The semiconductor auxiliary cooling system with the properties of no moving parts, high control precision and quick response has the potential to assist the on-board air-condition in modulating the cabin temperature with relative small ranges. Little temperature differences between the cabin and the outside environment means that the system energy consumption to ensure the occupant comfort is relatively low and the inefficiency could be made up by the renewable energy source.

For intelligent vehicles, a robust perception system relies on training datasets with a large variety of scenes. The architecture of federated learning allows for efficient collaborative model iteration while ensuring privacy and security by leveraging data from multiple parties. However, the local data from different participants is often not independent and identically distributed, significantly affecting the training effectiveness of autonomous driving perception models in the context of federated learning. Unlike the well-studied issues of label distribution discrepancies in previous work, we focus on the challenges posed by scene heterogeneity in the context of federated learning for intelligent vehicles and the inadequacy of a single scene for training multi-task perception models. In this paper, we propose a federated learning-based perception model training system.

As a key component of airstream system equipped in the road sweeper, the structure of the suction nozzle determines its internal flow field distribution, which affects the dust-sucking efficiency to a great degree. This research is aiming to determine a better suction nozzle structure. Starting with an analysis of the one used in a certain type of road sweeper, the initial model of the suction nozzle is established, and the internal flow field is simulated with typical computational fluid dynamics (CFD) software named FLUENT. Based on the simulation results, the dust-sucking capability of the initial structure is evaluated from the aspects of pressure and velocity distribution. Furthermore, in order to explore the influence of different structural parameters on the flow field distribution within the suction nozzle, models with different cavity heights and shoulder angles are established, and Univariate Method is utilized to analyze the contrast models.

Accurate surrounding vehicle motion prediction is critical for enabling safe, high quality autonomous driving decision-making and motion planning. Aiming at the problem that the current deep learning-based trajectory prediction methods are not accurate and effective for extracting the interaction between vehicles and the road environment information, we design a target vehicle intention-aware dual attention network (IDAN), which establishes a multi-task learning framework combining intention network and trajectory prediction network, imposing dual constraints. The intention network generates an intention encoding representing the driver’s intention information. It inputs it into the attention module of the trajectory prediction network to assist the trajectory prediction network to achieve better prediction accuracy.

In vehicles with urea-SCR system, normal operation of the urea-SCR system and engine will be influenced if there are deposits appearing on exhaust pipe wall. In this paper, a commercial vehicle is employed to study the influence factors of deposits through the vehicle road test. The results show that, urea injection rate, temperature and flow field have impacts on the formation of deposits. When decreasing the urea injection rate of calibration status by 20%, the deposit yield would reduce by 32%. If the ambient temperature decreased from 36 °C to 26 °C, the deposit yield would increase by 95%. After optimizing the exhaust pipe downstream of the urea injector by removing the step surface, only a few flow marks of urea droplets are observed on the pipe wall, and no lumps of deposits existing.

In the racing world, speed is everything, and the Formula Student cars are no different. As one of the key means to improve the speed of the car, lightweight plays an important role in the racing world. The weight reduction of unsprung metal parts can not only improve the driving speed, but also effectively optimize the dynamic of the car, so the lightweight design of unsprung parts has attracted much attention. In the traditional Formula Student racing car, the hub and spoke are two independent parts, they are fixed by four hub bolts or a central locking nut, the material of these fasteners is usually steel, so it brings a lot of weight burden. In order to achieve unsprung lightweight, a new type of wheel part design of Formula Student racing car is proposed in this paper. The hub and spoke are designed as integrated aluminum alloy parts, effectively eliminating the mass of hub bolts or central locking nuts.

The hydraulic retarder, an important auxiliary brake, has been widely used in heavy vehicles. Under the non-braking working condition, the air resistance torque in the working chamber, which is formed by the rotor of hydraulic retarder's stirring the air, causes pumping loss. This research designs a new type of hydraulic retarder, whose helium is charged into working chamber through closed loop gas system under non-braking working condition, can reduce the parasitic power loss of transmission system. First, under non-braking working condition, the resistance characteristics are analyzed on the base of hydraulic retarder pumping model; then, considering some parameters, such as the volume of chambers and the initial gas pressure, the working chamber gas charge model is established, and the transient gas charge characteristics are also analyzed under non-braking working condition.