Search Results

As a key component of in-vehicle intelligent voice technology, speech enhancement can extract clean speech signals contaminated by environmental noise to improve the perceptual quality and intelligibility of speech. It has extensive applications in the field of intelligent car cabins. Although some end-to-end speech enhancement methods based on time domain have been proposed, there is often limited consideration given to designing model architectures based on the characteristics of the speech signal. In this paper, we propose a new U-Net based speech enhancement framework that utilizes the temporal correlation of speech signals to reconstruct higher-quality and more intelligible clean speech.

In recent years, the burgeoning applications of hydrogen fuel cells have ignited a growing trend in their integration within the transportation sector, with a particular focus on their potential use in multi-rotor drones. The heightened mass-based energy density of fuel cells positions them as promising alternatives to current lithium battery-powered drones, especially as the demand for extended flight durations increases. This article undertakes a comprehensive exploration, comparing the performance of lithium batteries against air-cooled fuel cells, specifically within the context of multi-rotor drones with a 3.5kW power requirement. The study reveals that, for the specified power demand, air-cooled fuel cells outperform lithium batteries, establishing them as a more efficient solution.

The research and development of data-driven highly automated driving system components such as trajectory prediction, motion planning, driving test scenario generation, and safety validation all require large amounts of naturalistic vehicle trajectory data. Therefore, a variety of data collection methods have emerged to meet the growing demand. Among these, camera-equipped drones are gaining more and more attention because of their obvious advantages. Specifically, compared to others, drones have a wider field of bird's eye view, which is less likely to be blocked, and they could collect more complete and natural vehicle trajectory data. Besides, they are not easily observed by traffic participants and ensure that the human driver behavior data collected is realistic and natural. In this paper, we present a complete vehicle trajectory data extraction framework based on aerial videos. It consists of three parts: 1) objects detection, 2) data association, and 3) data cleaning.

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.

A comfortable thermal environment can alleviate fatigue, reduce irritability, and improve driving safety. However, it is rather a challenge to evaluate thermal comfort inside a vehicle due to multifarious geometric and environmental factors as well as human differences. This study conducted a series of field experiments both in summer and winter conditions, measuring the thermal environment parameters inside the compartment and the skin temperature of experimental personnel, and carrying out subjective thermal sensation and comfort questionnaires. The experimental results showed that head and trunk are the most relevant parts of all human body parts to the overall thermal sensation/comfort. For overall thermal sensation, the value of regression R2 referring to head/trunk is 0.691/0.721, while those corresponding to overall thermal comfort is 0.802/0.773.

Object detection is an important visual content of the autonomous vehicle, the traditional detecting methods usually cost a lot of computational memory and elapsed time. This paper proposes to use lightweight deep convolutional neural network (MobilenetV3-SSDLite) to carry out the object detection task of autonomous vehicles. Simulation analysis based on this method is implemented, the feature layer obtained after h-swish activation function in the first Conv of the 13th bottleneck module in MobilenetV3 is taken as the first effective feature layer, and the feature layer before pooling and convolution of the antepenultimate layer in MobilenetV3 is taken as the second effective feature layer, and these two feature layers are extracted from the MobilenetV3 network.

Environmental perception is a crucial subsystem in autonomous vehicles. In order to build safe and efficient traffic transportation, several researches have been proposed to build accurate, robust and real-time perception systems. Camera and LiDAR are widely equipped on autonomous self-driving cars and developed with many algorithms in recent years. The fusion system of camera and LiDAR provides state-of the-art methods for environmental perception due to the defects of single vehicular sensor. Extrinsic parameter calibration is able to align the coordinate systems of sensors and has been drawing enormous attention. However, differ from spatial alignment of two sensors’ data, joint calibration of multi-sensors (more than two sensors) should balance the degree of alignment between each two sensors.

The cab is an essential part of a light truck, and its fatigue durability performance plays an important role in the design and development stage. Accelerated fatigue bench test has been widely applied to product development of carmakers for its low cost and short development cycle. However, in reality, interference exists generally in torsional conditions for the light truck cab when tested on the 4-post vehicle road simulation system. To solve this problem and minimize the lateral force applied on the hydraulic cylinders, the direction and size combinations of displacement release about front and rear suspensions were discussed based on multi-body dynamics simulation and fixture design theory in this paper. Through comparative study, the optimum design and layout scheme of fixtures was determined to conduct the next test procedure. The weak positions of the light truck cab were firstly predicted by utilizing finite element method (FEM) and fatigue analysis theory.

It is considered that slow convergence speed and large calculation amount of commonly used adaptive algorithm in the active control system for vehicle interior noise yield noise reduction performance and hardware requirements problems. In this paper, a 4-channel active control of vehicle interior noise based on adaptive notch filter is established, and road test is carried out to test and analyze the performance of the control system. Firstly, the general mathematic model of the multi-channel active control system based on adaptive notch filter is established. The computational complexity of the algorithm is analyzed and compared with that of the FXLMS algorithm. Secondly, a hardware-in-the-loop test bench based on multi-channel adaptive notch filter is set up, to measure the noise reduction performance of ANC system under various working conditions.

Automotive security has become one of important topics in recent years under new automotive Electronic and Electrical Architecture (EEA). With the development of Intelligent Connected Vehicle (ICV), it has become possible to hack an automotive through in-vehicle networks. The introduction of Information Communications Technology (ICT) brings more risk threats to automotive. Researchers have shown that an attacker can easily tamper with many automotive functions via On-Board Diagnostic II (OBD-II) or In-Vehicle Infotainment (IVI). In order to protect automotive against malicious attacks, automotive security risks were analyzed and then security mechanisms based on network firewall were designed in this paper. Automotive network firewall is a security system that monitors and controls incoming and outgoing network traffics of automotive based on predetermined security rules. The main functions of network firewall include packet filter, anti-DoS and access control.

An online fault detection and isolation (FDI) method for several common sensor faults and even demagnetization of PMSM is proposed by combining model-based and signal analysis technology. To begin with, the field reconstruction method (FRM) of PMSM is employed to obtain the flux residuals which are used as the criterion of fault detection. Then, the flux residuals are transformed by multi sequence harmonic synchronous rotating transformation and inputted into low pass filters (LPFs) in order to obtain the DC components. Last, offset and gain faults of the two phase current sensors, offset fault of the rotor angle sensor and permanent magnet (PM) demagnetization can be isolated by comparing the DC components and preset thresholds. The detection and isolation strategy of PMSM is validated by motor controller hardware in motor bench tests.

The functional elements of decision making system are fuzzy, adaptive and self-learning for intelligent ground vehicles. As is well-known, operating environment of unmanned ground vehicles (UGVs) is complex, unknown and time-changing. And on the other hand, exact dynamic model of the vehicle is relatively difficult to gain. However, the changing of special dynamic parameters and the man-made driving laws of velocities and running direction are easily available. Therefore, this paper attempts to provide an approach based on fuzzy Q-learning algorithm for studying autonomous navigation and control system’s design, which aims to make unmanned vehicles adaptive and robust under complex and time-changing environment. The presented approach utilizes the drivers’ empirical knowledge for.

In this paper, an integrated electronic hydraulic brake(I-EHB) system is introduced, which is mainly composed of a motor, a worm gear, a worm, a gear, a rack etc. The friction leads the system to the creeping phenomenon and the dead zone. These phenomenon seriously affect the response speed and the hydraulic pressure control .In order to realize the accurate hydraulic pressure control of I-EHB system, a new friction compensation control method is proposed based on LuGre dynamic friction model. And the theoretical design of adaptive control method is designed based on the feedback of the master cylinder pressure and the operating state of the system. Then the stability of the control method is proved by Lyapunov theorem. A co-simulation model is built with Matlab/Simulink and AMESim, so as to prove the validity of the control method.

Two control strategies, safety preferred control and master cylinder oscillation control, were designed for anti-lock braking on a novel integrated-electro-hydraulic braking system (I-EHB) which has only four solenoid valves in its innovative hydraulic control unit (HCU) instead of eight in a traditional one. The main idea of safety preferred control is to reduce the hydraulic pressure provided by the motor in the master cylinder whenever a wheel tends to be locking even if some of the other wheels may need more braking torque. In contrast, regarding master cylinder oscillation control, a sinusoidal signal is given to the motor making the hydraulic pressure in the master cylinder oscillate in certain frequency and amplitude. Hardware-in-the-loop simulations were conducted to verify the effectiveness of the two control strategies mentioned above and to evaluate them.

Biomechanics and biodynamics are increasingly focused on the automotive industry to provide comfortable driving environment, reduce driver fatigue, and improve passenger safety. Man-centered conception is a growing emphasis on the open design of automobile. During the long-term driving, occupational drivers are easily exposed to the neck pain, so it is important to reduce the muscle force load and its fatigue, which are not usually considered quantitatively during traditional ergonomics design, so standards related are not well developed to guide the vehicle design; On the other hand, the head-neck models are always built based on the statics theory, these are not sufficient to predict the instantaneous variation of the muscle force. In this paper, a head-neck model with multi DOFs is created based on multibody dynamics. Firstly, a driver-vehicle-road model considering driver multi-rigid body model, vehicle subsystems, and different ranks of pavement is built.

Electric vehicle driving permanent magnet synchronous motor has a wide speed range and load changes, with abundant harmonic currents, and its eccentric form is complex, which all result in poor sound quality and abnormal noise problems becoming increasingly prominent. To make a systematic and thorough study of the centralized drive permanent magnet synchronous motor (PMSM) is significant to ameliorate the sound quality and solve noise problems. MATLAB-based modeling technology, SPSS software, and the establishment of sound quality evaluation model for the centralized drive PMSM has a crucial reference value on the research and development of the electric vehicle driving permanent magnet synchronous motor. As for the sound quality of centralized drive PMSM, firstly, in order to get objective parameter values, evaluation models of objective parameters based on psychological acoustics should be established after the collection of the sound samples.

Noise signals of the driver’s right ear include those of engine, environment, chassis dynamometer, loaded gears and unloaded gears when they are recorded in full vehicle on chassis dynamometer in semi-anechoic room. Gear rattle noise signals of the driver’s right ear caused by unloaded gear pairs can’t be identified or quantified directly. To solve the problems, relative approaches are used to identify and quantify the gear rattle noise signals. Firstly, the rattle noise signals of the driver’s right ear are filtered by human ear characteristic functions and steady noise signals are extracted by regression and smoothing processes. The noise signals are regressed at 200ms interval in the hearing critical frequency bands and smoothed in the flanking frequencies. Then, the noise relative approaches are obtained by subtracting the steady noise signals from the filtered noise signals, which are the transient noise signals of the unloaded gear pairs inducing the rattle noise.

Driving posture study is essential for the evaluation of the occupant packaging. This paper presents a method of reconstructing driver’s postures in a real vehicle using a 3D laser scanner and Human Builder (HB), the digital human modeling tool under CATIA. The scanning data was at first converted into the format readable by CATIA, and then a personalized HB manikin was generated mainly using stature, sitting height and weight. Its pelvis position and joint angles were manually adjusted so as to match the manikin with the scan envelop. If needed, a fine adjustment of some anthropometric dimensions was also preceded. Finally the personalized manikin was put in the vehicle coordinate system, and joint angels and joint positions were extracted for further analysis.

With the development of vehicle electrification, electronic hydraulic brake system is gradually applied. Many companies have introduced products related to integrated electronic hydraulic brake system (I-EHB). In this paper, an I-EHB system is introduced, which uses the motor to drive the reduction mechanism as a power source for braking. The reduction mechanism is composed of a turbine, a worm, a gear and a rack. A control method based on command feed-forward is proposed to improve the hydraulic pressure control of I-EHB. Based on previous research, we simplify the system to first order system, and the theoretical design of the command feed-forward compensator is carried out. The feed-forward controller is applied, including the velocity feed-forward and the acceleration feed-forward, to improve the response speed and tracking effect of the system.

X-in-the-loop (XiL) framework is a new validation concept for vehicle product development, which integrates different virtual and physical components to improve the development efficiency. With XiL platform the requirements of reproducible test, optimization and validation, in which hardware, equipment and test objects are located in different places, could be realized. In the view of different location and communication form of hardware, equipment and test objects, time delay problem exists in the XiL platform, which could have a negative impact on development and validation process. In this paper, a simulation system of time delay prediction and compensation is founded with the help of BP neural network and RBF neural network. With this simulation system the effect of time delay in a vehicle dynamic model as well as tests of geographically distributed vehicle powertrain system is improved during the validation process.