Search Results

In this research, the interior noise of a passenger car was measured, and the sound quality metrics including sound pressure level, loudness, sharpness, and roughness were calculated. An artificial neural network was designed to successfully apply on automotive interior noise as well as numerous different fields of technology which aim to overcome difficulties of experimentations and save cost, time and workforce. Sound pressure level, loudness, sharpness, and roughness were estimated by using the artificial neural network designed by using the experiment values. The predicted values and experiment results are compared. The comparison results show that the realized artificial intelligence model is an appropriate model to estimate the sound quality of the automotive interior noise. The reliability value is calculated as 0.9995 by using statistical analysis.

Artificial intelligence systems are highly accepted as a technology to offer an alternative way to tackle complex and non-linear problems. They can learn from data, and they are able to handle noisy and incomplete data. Once trained, they can perform prediction and generalization at high speed. The aim of the present study is to propose a novel approach utilizing the adaptive neuro-fuzzy inference system (ANFIS) and the fuzzy clustering method for automotive ride performance estimation. This study investigated the relationship between the automotive ride performance and relative parameters including speed, spring stiffness, damper coefficients, ratios of sprung and unsprung mass. A Takagi-Sugeno fuzzy inference system associated with artificial neuro network was employed. The C-mean fuzzy clustering method was used for grouping the data and identifying membership functions.

To reduce the interference and conflict of human-machine cooperative control, lighten the operation workload of drivers, and improve the friendliness and acceptability of intelligent vehicles, a personalized human-machine cooperative lane-change trajectory tracking control method was proposed. First, a lane-changing driving data acquisition test was carried out to collect different driving behaviors of different drivers and form the data pool for the machine learning method. Two typical driving behaviors from an aggressive driver and a moderate driver are selected to be studied. Then, a control structure combined by feedforward and feedback control based on Long Short Term Memory (LSTM) and model-based optimum control was introduced. LSTM is a machine learning method that has the ability of memory. It is used to capture the lane-changing behaviors of each driver to achieve personalization. For each driver, a specific personalized controller is trained using his driving data.

In this paper, a shock absorber physical model is developed. Firstly, a rebound valve model which is based on its structure parameters is built through using the large deflection theory. The von Karman equations are introduced to discover the physical relationships between the load and the deflection of valve discs. An analytical solution of the von Karman equations is then deducted via perturbation method. Secondly, the flow equations and the pressure equations of the shock absorber operating are investigated. The relationship between fluid flow rate and pressure drop of rebound valve is analyzed based on the analytical solution of valve discs deflection. Thirdly, an inter-iterative process of flow rate and pressure drop is employed in order to adequately consider the influence of fluid flow on damping force. Finally, the physical model is validated by comparing the experimental data with the simulation output.

A novel non-destroy repeatable-use impact theory based total cylinder sampling system has been established. This system is mainly composed of a knocking body and a sampling valve. The knocking body impacts the sampling valve with certain velocity resulting in huge force to open the sampling valve and most of the in-cylinder gas has been dumped to one sampling bag for after-treatment. The feasibility and sampling response characteristics of this impact theory based total cylinder sampling system were investigated by engine bench testing. Within 0 to 35°CA ATDC (Crank Angle After Top Dead Center) sample timing 50 percent to 80 percent of in-cylinder mass would be sampled, which was a little less compared with the traditional system. The half decay period of pressure drop was 10 to 20 degrees crank angle within 0 to 60°CA ATDC sample timing, which was about 2-3 times of the traditional system.

In the intelligent airbag system, the detection accuracy of occupant position is the precondition and plays a vital role to control airbag detonation time and inflated strength during the crash. Through accurately analyzing the seat surface pressure distributions of different occupant sitting position and types, an occupant position recognition approach which purely uses occupant pressure distribution information measured by seat pressure sensors is presented with the method of Support Vector Machine. In the end, the distribution samples with different occupant sitting position and types are used to train and test the recognition approach, and the good validity and accuracy are shown in the experiments.

This paper presents an integrated method for rapid modeling, simulation and virtual evaluation of the interface pressure between driver human body and seat. For simulation of the body-seat interaction and for calculation of the interface pressure, besides body dimensions and material characteristics an important aspect is the posture and position of the driver body with respect to seat. In addition, to ensure accommodation of the results to the target population usually several individuals are simulated, whose body anthropometries cover the scope of the whole population. The multivariate distribution of the body anthropometry and the sampling techniques are usually adopted to generate the individuals and to predict the detailed body dimensions. In biomechanical modeling of human body and seat, the correct element type, the rational settings of the contacts between different parts, the correct exertion of the loads to the calculation field, etc., are also crucial.

A general principle scheme of IEHB (Integrated Electro-Hydraulic Brake system) is proposed, and the working principle of the system is simply introduced in this paper. Considering the structure characteristics of the hydraulic control unit of the system, a kind of time-sharing control strategy is adopted to realize the purpose of independent and precise hydraulic pressure regulation of each wheel brake cylinder in various brake conditions of a vehicle. Because of the strong nonlinear and time varying characteristics of the dynamic brake pressure regulation processes of IEHB, its comprehensive brake performance is mainly affected by temperature, humidity, load change, the structure and control parameters of IEHB, and so on.

Based on the research and analysis of the current brake systems, this paper presents a novel electro-hydraulic brake system, which can better meet the functional requirements. The system mainly contains a master cylinder, two brake hydraulic cylinders and drive motors, two transmission mechanisms, thirteen solenoid valves, pedal force simulator, etc. Since the proposed brake system uses a dual motor along with two brake hydraulic cylinders, it has advantages in providing fast pressure response, flexible working modes, high precision and strong fault tolerance. In order to facilitate the study of pressure control algorithm for the proposed brake system, a mathematical model of the brake system is firstly established, then a multiplexed time-division pressure control algorithm is proposed to realize the simultaneous or partially simultaneous pressure control, which ensures the high precision and short response time.

As bottom layer actuator for the AEB system, the active brake system and the brake force control of tractor-semitrailer have been the hot topics recently. In this paper, a set of active pneumatic brake system was designed based on the traditional brake system of tractor-semitrailer, which can realize the active brake of the vehicle under necessary conditions. Then, a precise mathematical model of the active pneumatic brake system was built by referring the flow characteristics of the solenoid valve, and some tests were implemented to verify the accuracy and validity of the active brake system model. Based on the model, an active pneumatic brake pressure control strategy combining the feedforward and feedback controlling modes was designed. By generating the PWM control signal, it can precisely control the desired wheel cylinder brake pressure of the active brake system. Finally, the brake pressure control strategy was validated both by simulation tests and bench tests.

In order to improve ride comfort and reduce interior noise of commercial vehicles, modal sensitivity analysis and optimization design of a commercial vehicle cab was carried out, which increased the first natural frequency of the optimized cab by 23.96%. The result of cab modal test verified the correctness of the finite element model and the effectiveness of the improving method. The structure-acoustic coupling model of the cab was established, and the acoustic response of the coupled sound field was predicted. The sound pressure level of the optimized cab was reduced. In comparison of the optimized cab with the original one, the optimization scheme was confirmed to be effective and reasonable.

Autonomous driving technology, as the product of the fifth stage of the information technology revolution, is of great significance for improving urban traffic and environmentally friendly sustainable development. Autonomous driving can be divided into three main modules. The input of the decision module is the perception information from the perception module and the output of the control strategy to the control module. The deep reinforcement learning method proposes an end-to-end decision-making system design scheme. This paper adopts the Deep Deterministic Policy Gradient Algorithm (DDPG) that incorporates the Priority Experience Playback (PER) method. The framework of the algorithm is based on the actor-critic network structure model. The model takes the continuously acquired perception information as input and the continuous control of the vehicle as output.

Accurate sensing of road conditions is one of the necessary technologies for safe driving of intelligent vehicles. Compared with the structured road, the unstructured road has complex road conditions, and the response characteristics of vehicles under different road conditions are also different. Therefore, accurately identifying the road categories in front of the vehicle in advance can effectively help the intelligent vehicle timely adjust relevant control strategies for different road conditions and improve the driving comfort and safety of the vehicle. However, traditional road identification methods based on vehicle kinematics or dynamics are difficult to accurately identify the road conditions ahead of the vehicle in advance. Therefore, this paper proposes an unstructured road region detection and road classification algorithm based on machine vision to obtain the road conditions ahead.

It is generally considered that the material properties of foam are the most important factors in vehicle seat, which affect the human-seat interface pressure. Therefore, only the role of foam is usually considered when the finite element method is used to simulate the human-seat interface pressure. In this paper, the mechanical properties and the modeling method of commonly used seat cover material were studied. The models of the seat with and without cover were established respectively according to the real-vehicle seat geometric data, and the human-seat interface pressure was simulated after the seat and human model consisting of bones, soft tissue and skin were assembled. The simulation result was compared with the actual measurement results from test, which verified the accuracy of the simulation and the role of seat cover in the human-seat interface pressure simulation.

The underbody diffusers are used widely in race cars to improve the flow field structure at the bottom of the car and provide enough downforce. In recent years, passenger cars have begun to use bottom diffuser to improve aerodynamic characteristics, so as to reduce drag and increase downforce. In this paper, the aerodynamic characteristics of the bus with different underbody diffuser angles and channel numbers are studied by numerical simulation analysis. Firstly, the aerodynamics of the bus under different diffuser inlet and outlet angles are studied, and then an optimal inlet and outlet angle is determined based on the simulation results. Then, using this angle as a constant, the 2, 3, and 4 channel numbers were chosen as the diffuser channel variables to study the influence of the multiple-channel diffusers on the aerodynamic drag of the vehicle.

The Electronic Stability Program (ESP), as a key actuator of traditional automobile braking system, plays an important role in the development of intelligent vehicles by accurately controlling the pressure of wheels. However, the ESP is a highly nonlinear controlled object due to the changing of the working temperature, humidity, and hydraulic load. In this paper, an accurate pressure control strategy of single wheel during active braking of ESP is proposed, which doesn’t rely on the specific parameters of the hydraulic system and ESP. First, the structure and working principle of ESP have been introduced. Then, we discuss the possibility of Pulse Width Modulation (PWM) control based on the mathematical model of the high-speed switching valve. Subsequently, the pressure building characteristics of the inlet and outlet valves are analyzed by the hardware in the Loop (HiL) experimental platform.

During the vehicle braking, the Regenerative braking system (RBS) transforms the kinetic energy into electric power, storing it in the power sources. To secure the baking process, it is required to use hydraulic braking pressure to coordinately compensate the regenerative braking pressure. The traditional hydraulic pressure control algorithm which is used in regenerative braking system coordinated control has obvious laddering effect in braking. Unit control cycle pressure deviations seriously affect the comfort and the braking feeling on the vehicle.

Driving style and skill classification are of great significance in human-oriented advanced driver-assistance system (ADAS) development. In this paper, we propose Fully-Connected Deep Neural Networks (FC-DNN) to classify drivers’ styles and skills with naturalistic driving data. Followed by the data collection and pre-processing, FC-DNN with a series of deep learning optimization algorithms are applied. In the experimental part, the proposed model is validated and compared with other commonly used supervised learning methods including the k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), and multilayer perceptron (MLP). The results show that the proposed model has a higher Macro F1 score than other methods. In addition, we discussed the effect of different time window sizes on experimental results. The results show that the driving information of 1s can improve the final evaluation score of the model.

It’s hard to achieve complete self-driving using hand-crafting generalized decision-making rules, while the end-to-end self-driving system is low in complexity, does not require hand-crafting rules, and can deal with complex situations. Modular-based self-driving systems require multi-task fusion and high-precision maps, resulting in high system complexity and increased costs. In end-to-end self-driving, we usually only use camera to obtain scene status information, so image processing is very important. Numerous deep learning applications benefit from multi-task learning, as the multi-task learning can accelerate model training and improve accuracy with combine all tasks into one model, which reduces the amount of calculation and allows these systems to run in real-time. Therefore, the approach of obtaining rich scene state information based on multi-task learning is very attractive. In this paper, we propose an approach to multi-task learning for semantics, geometry and motion.

With the development of intelligent and electric vehicles, higher requirements are put forward for the active braking and regenerative braking ability of the braking system. The traditional braking system equipped with vacuum booster has difficulty meeting the demand, therefore it has gradually been replaced by the integrated braking system. In this paper, a novel Integrated Braking System (IBS) is presented, which mainly contains a pedal feel simulator, a permanent magnet synchronous motor (PMSM), a series of transmission mechanisms, and the hydraulic control unit. As an integrative system of mechanics-electronics-hydraulics, the IBS has complex nonlinear characteristics, which challenge the accurate pressure control. Furthermore, it is a completely decoupled braking system, the pedal force doesn’t participate in pressure-building, so it is necessary to precisely identify driver’s braking intention.