Refine Your Search

Topic

Search Results

Technical Paper

Evaluation Method of Harmony with Traffic Based on a Backpropagation Neural Network Optimized by Mean Impact Value

2021-06-02
2021-01-5060
With the development of autonomous driving, the penetration rate of autonomous vehicles on the road will continue to grow. As a result, the social cooperation ability of autonomous vehicles will have a great effect on the social acceptance of autonomous driving, which can be described as harmony with traffic. In order to research the evaluation method of the harmony with traffic, this paper proposes a subjective and objective mapping evaluation method based on the Mean Impact Value and Backpropagation (MIV-BP) Neural Network, with the merging vehicle on the expressway ramp as the research object. Firstly, by taking 16 original objective indexes obtained by theoretical analysis and the subjective evaluation results as input and output, respectively, the BP Neural Network model is constructed as a baseline model. Secondly, nine selected objective indexes are selected by the MIV method based on the baseline model.
Technical Paper

Multi-Modal Neural Feature Fusion for Pose Estimation and Scene Perception of Intelligent Vehicle

2021-04-06
2021-01-0188
The main challenge for future autonomous vehicles is to identify their location and body pose in real time during driving, that is, “where am I? and how will I go?”. We address the problems of pose estimation and scene perception from continuous visual frames in intelligent vehicle. Recent advanced technology in the domain of deep learning proposes to train some learning models for vehicle’s series detection tasks in a supervised or unsupervised manner, which has numerous advances over traditional approaches, mainly reflected in the absence of manual calibration and synchronization of the camera and IMU. In the paper, we propose a novel approach for pose estimation and scene recognition with a deep fusion of multi-modal neural features in the manner of unsupervised. Firstly, low-cost camera and IMU are used to extract original visual and inertial data, then the visual and inertial encoders are utilized to encoder the feature of the two modes.
Technical Paper

Comparison between Different Modelling Methods of Secondary Path to Maximize Control Effect for Active Engine Mounts

2021-04-06
2021-01-0668
Active engine mount (AEM) is an effective approach which can optimize the noise, vibration and harshness (NVH) performance of vehicles. The filtered-x-least-mean-squares (FxLMS) algorithm is widely applicated for vibration attenuation in AEMs. However, the performance of FxLMS algorithm can be deteriorated without an accurate secondary path estimation. First, this paper models the secondary path using finite impulse response (FIR) model, infinite impulse response (IIR) model and back propagation (BP) neural network model and the model errors of which are compared to determine the most accurate and robust modeling method. After that, the influence of operation frequency on accuracy of the secondary path model is analyzed through simulation approach. Then, the impact of reference signal mismatch on the control effect is demonstrated to study the robustness of FxLMS algorithm.
Technical Paper

A Data Driven Fuel Cell Life-Prediction Model for a Fuel Cell Electric City Bus

2021-04-06
2021-01-0739
Life prediction is a major focus for a commercial fuel cell stack, especially applied in fuel cell electric vehicles (FCEV). This paper proposes a data driven fuel cell lifetime prediction model using particle swarm optimized back-propagation neural network (PSO-BPNN). For the prediction model PSO-BP, PSO algorithm is used to determine the optimal hyper parameters of BP neural network. In this paper, total voltage of fuel cell stack is employed to represent the health index of fuel cell. Then the proposed prediction model is validated by the aging data from PEMFC stack in FCEV at the actual road condition. The experimental results indicate that PSO-BP model can predict the voltage degradation of PEMFC stack at actual road condition precisely and has a higher prediction accuracy than BP model.
Technical Paper

An Optimized Design of Multi-Chamber Perforated Resonators to Attenuate Turbocharged Intake System Noise

2021-04-06
2021-01-0669
The turbocharger air intake noise during transient conditions like wide open throttle and tip-in/out affects the passenger ride comfort. This paper aims to study an optimized design of multi-chamber perforated resonators to attenuate this noise. The noise produced by a turbocharger in a test vehicle has been measured to find out the noise spectral characteristics which can be used to design the acoustic targets including the amplitude and frequency range of transmission loss (TL). The structural parameters of the resonators are optimized based on genetic algorithm (GA) and two-dimensional prediction theory of the resonator TL. The optimized resonators are installed on the test vehicle to verify the actual noise reduction effect. The results suggest that the broadband noise has been eliminated, and subjective feelings are greatly improved.
Technical Paper

Object Detection Method of Autonomous Vehicle Based on Lightweight Deep Learning

2021-04-06
2021-01-0192
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.
Technical Paper

Vehicle Detection Based on Deep Neural Network Combined with Radar Attention Mechanism

2020-12-29
2020-01-5171
In the autonomous driving perception task, the accuracy of target detection is an essential evaluation, especially for small targets. In this work, we propose a multi-sensor fusion neural network that combines radar and image data to improve the confidence level of the camera when detecting targets and the accuracy of the prediction box regression. The fusion network is based on the basic structure of single-shot multi-box detection (SSD). Inspired by the attention mechanism in image processing, our work incorporates the a priori knowledge of radar detection in the convolutional block attention module (CBAM), which forms a new attention mechanism module called radar convolutional block attention module (RCBAM). We add the RCBAM into the SSD target detection network to build a deep neural network fusing millimeter-wave radar and camera.
Technical Paper

LiDAR-Based High-Accuracy Parking Slot Search, Detection, and Tracking

2020-12-29
2020-01-5168
The accuracy of parking slot detection is a challenge for the safety of the Automated Valet Parking (AVP), while traditional methods of range sensor-based parking slot detection have mostly focused on the detection rate in a scenario, where the ego-vehicle must pass by the slot. This paper uses three-dimensional Light Detection And Ranging (3D LiDAR) to efficiently search parking slots around without passing by them and highlights the accuracy of detecting and tracking. For this purpose, a universal process of 3D LiDAR-based high-accuracy slot perception is proposed in this paper. First, the method Minimum Spanning Tree (MST) is applied to sort obstacles, and Separating Axis Theorem (SAT) are applied to the bounding boxes of obstacles in the bird’s-eye view, to find a free space between two adjacent obstacles. These bounding boxes are obtained by using common point cloud processing methods.
Technical Paper

Prediction of Bus Passenger Flow Based on CEEMDAN-BP Model

2020-12-14
2020-01-5166
The prediction of passenger flow is of great significance to facilitate the decision-making processes for local authorities and transport operators to provide an effective bus scheduling. In this work, a backpropagation neural network (BPNN) was adopted to predict the bus passenger flow. To reduce the prediction error and improve the prediction accuracy, a combined model CEEMDAN-BP, which combines CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) method and BPNN, has been proposed. CEEMDAN is an improved method based on EEMD, which has been widely applied to signal smoothing and de-noising. Experimental results show that this combined model can exactly achieve an excellent prediction effect and improve the prediction accuracy of the network greatly.
Technical Paper

Optimization of Electric Vacuum Pump Mount to Improve Sound Quality of Electric Vehicle

2020-04-14
2020-01-1259
The noise and vibration of electric vacuum pump (EVP) become a major problem for electric vehicles when the vehicle is stationary. This paper aims at the EVP’s abnormal noise of an electric vehicle when stationary. Driver’s right ear (DRE) noise was tested and spectrogram analysis was carried out to identify the noise sources. In order to attenuate this kind of abnormal noise, a new EVP rubber mount with a segmented structure was introduced, which optimized the transfer path of vibration. Then dynamic stiffness and fatigue life of the EVP mount with different rubber hardness were calculated through finite element analysis (FEA) approach. Bench tests of fatigue life and DRE noise were performed to validate the FEA results. Test data of the sample mount shows that sound pressure level of DRE was dramatically attenuated and thus passengers’ ride comfort was enhanced.
Technical Paper

Active and Passive Control of Torsional Vibration in Vehicle Hybrid Powertrain System

2020-04-14
2020-01-0408
The vibration characteristics of hybrid vehicles are very different from that of traditional fuel vehicles. In this paper, the active and passive control schemes are used to inhibit the vibration issues in vehicle hybrid powertrain system. Firstly the torsional vibration mechanical model including engine, motor and planetary gear subsystems is established. Then the transient vibration responses of typical working condition are analyzed through power control strategy. Consequently the active and passive control of torsional vibration in hybrid powertrain system is proposed. The active control of the motor and generator torque is designed and the vehicle longitudinal vibration is reduced. The vibration of the planetary gear system is ameliorated with passive control method by adding torsional vibration absorbers to power units. The vibration characteristics in vehicle hybrid powertrain system are effectively improved through the active and passive control.
Technical Paper

An FxLMS Controller for Active Control Engine Mount with Experimental Secondary Path Identification

2020-04-14
2020-01-0424
Active engine mounts (AEMs) notably contribute to ensuring superior performance of vehicle’s noise, vibration, and harshness. This paper incorporates a filtered-x-least-mean-squares (FxLMS) controller into the active control engine mount system to attenuate the transmitted force to the body. To avoid the error caused by substituting the load cell for acceleration transducer, the FIR model of the secondary path was obtained by experiment. Finally, a hardware-in-the-loop testing system is built to verify the performance of the active engine mount. It can be observed from the test results that the vibration is reduced notably after control, which demonstrates the effectiveness of the active engine mount and the controller in vibration attenuation.
Technical Paper

Analysis of Vibroacoustic Behaviors and Torque Ripple of SRMs with Different Phases and Poles

2020-04-14
2020-01-0467
In this study, the vibroacoustic characteristics and torque fluctuation of switched reluctance motors (SRMs) with different phases and poles have been analyzed in detail. Also, the common four SRMs, i.e., three-phase 6/4 SRM, four-phase 8/6 SRM, five-phase 10/8 SRM, and six-phase 12/10 SRM, have been selected. First, the spatial-temporal distribution characteristics of radial force in SRMs were revealed by virtue of the analytical derivation, which was validated by the 2D Fourier decomposition based on the finite-element results of radial force. Second, a multiphysics model, which was composed of an electromagnetic field, a mechanical field, and an acoustic field, was established to predict the noise behaviors of SRMs with different phases and poles. Third, the relationship between the torque fluctuation and the phases / poles of SRMs, and the relationship between the noise and the radial force / phases / poles are all analyzed.
Technical Paper

Crashworthiness Design of Hierarchical Honeycomb-Filled Structures under Multiple Loading Angles

2020-04-14
2020-01-0504
Thin-walled structures have been widely used in automobile body design because of its good lightweight and superior mechanical properties. For the energy-absorbing box of the automobile, it is necessary to consider its working conditions under the axial and oblique impact. In this paper, a novel hierarchical honeycomb is proposed and used as filler for thin-walled structures. Meanwhile, the crashworthiness performances of the conventional honeycomb-filled and the hierarchical honeycomb-filled thin-walled structures under different impact conditions are systematically studied. The results indicate the energy absorption of the hierarchical honeycomb-filled thin-walled structure is higher than that of the conventional honeycomb-filled thin-walled structure, and the impact angle has significant effects on the energy absorption performance of the hierarchical honeycomb-filled structure.
Technical Paper

Optimization of the Finite Hybrid Piezoelectric Phononic Crystal Beam for the Low-Frequency Vibration Attenuation

2020-04-14
2020-01-0913
This paper presents a theoretical study of a finite hybrid piezoelectric phononic crystal (PC) beam with shunting circuits. The vibration transmissibility method (TM) is developed for the finite system. The uniform and non-uniform configurations of the resonators, piezoelectric patches and shunting circuits are respectively considered. The properties of the vibration attenuation of the hybrid PC beam undergoing bending vibration are investigated and quantified. It is shown that the proper relaxation of the periodicity of the PC is conducive to forming a broad vibration attenuation region. The hybrid piezoelectric PC combines the purely mechanical PC with the piezoelectric PC and provides more tunable mechanisms for the target band-gap. Taking the structural and circuit parameters into account, the design of experiments (DOE) method and the multi-objective genetic optimization method are employed to improve the vibration attenuation and meet the lightweight demand of the attachments.
Journal Article

Acoustic Characteristics Prediction and Optimization of Wheel Resonators with Arbitrary Section

2020-04-14
2020-01-0917
Tire cavity noise of pure electric vehicles is particularly prominent due to the absence of engine noise, which are usually eliminated by adding Helmholtz resonators with arbitrary transversal section to the wheel rims. This paper provides theoretical basis for accurately predicting and effectively improving acoustic performance of wheel resonators. A hybrid finite element method is developed to extract the transversal wavenumbers and eigenvectors, and the mode-matching scheme is employed to determine the transmission loss of the Helmholtz resonator. Based on the accuracy validation of this method, the matching design of the wheel resonators and the optimization method of tire cavity noise are studied. The identification method of the tire cavity resonance frequency is developed through the acoustic modal test. A scientific transmission loss target curve and fitness function are defined according to the noise characteristics.
Technical Paper

Study on Robust Motion Planning Method for Automatic Parking Assist System Based on Neural Network and Tree Search

2019-11-04
2019-01-5059
Automatic Parking Assist System (APAS) is an important part of Advanced Driver Assistance System (ADAS). It frees drivers from the burden of maneuvering a vehicle into a narrow parking space. This paper deals with the motion planning, a key issue of APAS, for vehicles in automatic parking. Planning module should guarantee the robustness to various initial postures and ensure that the vehicle is parked symmetrically in the center of the parking slot. However, current planning methods can’t meet both requirements well. To meet the aforementioned requirements, a method combining neural network and Monte-Carlo Tree Search (MCTS) is adopted in this work. From a driver’s perspective, different initial postures imply different parking strategies. In order to achieve the robustness to diverse initial postures, a natural idea is to train a model that can learn various strategies.
Technical Paper

Towards High Accuracy Parking Slot Detection for Automated Valet Parking System

2019-11-04
2019-01-5061
Highly accurate parking slot detection methods are crucial for Automated Valet Parking (AVP) systems, to meet their demanding safety and functional requirements. While previous efforts have mostly focused on the algorithms’ capabilities to detect different types of slots under varying conditions, i.e. the detection rate, their accuracy has received little attention at this time. This paper highlights the importance of trustworthy slot detection methods, which address both the detection rate and the detection accuracy. To achieve this goal, an accurate slot detection method and a reliable ground-truth slot measurement method have been proposed in this paper. First, based on a 2D laser range finder, datapoints of obstacle vehicles on both sides of a slot have been collected and preprocessed. Second, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm has been improved to efficiently cluster these unevenly-distributed datapoints.
Technical Paper

Virtual Co-Simulation Platform for Test and Validation of ADAS and Autonomous Driving

2019-11-04
2019-01-5040
Vehicles equipped with one or several functions of Advanced Driver Assistant System (ADAS) and autonomous driving (AD) technology are more mature and prevalent nowadays. Vehicles being smarter and driving being easier is an unstoppable trend. In the near future, intelligent vehicles will be mass produced and running on the road. However, before the mass-production of intelligent vehicles, a lot of experimental tests and validations need to be carried out to insure the safety and reliability of ADAS and AD technology. Although the road test of real vehicles is the most reliable and accurate test method, it cannot meet the need of rapid development of technology research due to high time and financial cost. Therefore, a high-efficient design and evaluation methodology for ADAS and AD development and test is a must. In this paper, a virtual co-simulation platform based on MATLAB/Simulink, OpenModelica and Unity 3D game engine (MOMU) is proposed.
Technical Paper

Improved Kmeans Algorithm for Detection in Traffic Scenarios

2019-06-17
2019-01-5067
In the Kmeans cluster segmentation used in traffic scenes, there are often zone optimization and over-segmentation problems caused by the algorithm randomly assigning the initial cluster center. In order to improve the target extraction effect in traffic road scenes, this article proposes an improved Kmeans (IM-Kmeans) method. Firstly, search for the histogram peaks of the whole pixels based on hue, saturation, value (HSV) image, and find the initial cluster centers’ positions and number. Secondly, the noise points which are far away from the center pixel are removed, and then the pixels are classified into the nearest cluster center according to its value. Finally, after the clustering model reaches convergence, the area-clustering method is used for another classification to solve the over-segmentation problem. The simulation and experimental comparisons show that the IM-Kmeans algorithm has higher clustering accuracy than the traditional Kmeans algorithm.
X