The operation management of electric Taxi fleets requires cooperative optimization of Charging and Dispatching. The challenge is to make real-time decisions about which is the optimal charging station or passenger for each vehicle in the fleet. With the rapid advancement of Vehicle Internet of Things (VIOT) technologies, the aforementioned challenge can be readily addressed by leveraging big data analytics and machine learning algorithms, thereby contributing to smarter transportation systems. This study focuses on optimizing real-time decision-making for charging and dispatching in large-scale electric taxi fleets to improve their long-term benefits. To achieve this goal, a spatiotemporal decision framework using Bi-level optimization is proposed. Initially, a deep reinforcement learning-based model is built to estimate the value of charging and order dispatching under uncertainty.
Brake judder affects vehicle safety and comfort, making it a key area of research in brake NVH. Transfer path analysis is effective for analyzing and reducing brake judder. However, current studies mainly focus on passenger cars, with limited investigation into commercial vehicles. The complex chassis structures of commercial vehicles involve multiple transfer paths, resulting in extensive data and testing challenges. This hinders the analysis and suppression of brake judder using transfer path analysis. In this study, we propose a simulation-based method to investigate brake judder transfer paths in commercial vehicles. Firstly, road tests were conducted to investigate the brake judder of commercial vehicles. Time-domain analysis, order characteristics analysis, and transfer function analysis between components were performed.
Lightweight design is a key factor in general engineering design practice, however, it often conflicts with fatigue durability. This paper presents a way for improving the effectiveness of fatigue performance dominated optimization, demonstrated through a case study on suspension brackets for heavy-duty vehicles. This case study is based on random load data collected from fatigue durability tests in proving grounds, and fatigue failures of the heavy-duty vehicle suspension brackets were observed and recorded during the tests. Multi-objective fatigue optimization was introduced by employing multiaxial time-domain fatigue analysis under random loads combined with the non-dominated sorting genetic algorithm II with archives.
Speech enhancement can extract clean speech from noise interference, enhancing its perceptual quality and intelligibility. This technology has significant applications in in-car intelligent voice interaction. However, the complex noise environment inside the vehicle, especially the human voice interference is very prominent, which brings great challenges to the vehicle speech interaction system. In this paper, we propose a speech enhancement method based on target speech features, which can better extract clean speech and improve the perceptual quality and intelligibility of enhanced speech in the environment of human noise interference. To this end, we propose a design method for the middle layer of the U-Net architecture based on Long Short-Term Memory (LSTM), which can automatically extract the target speech features that are highly distinguishable from the noise signal and human voice interference features in noisy speech, and realize the targeted extraction of clean speech.
Accurate prediction temperature variation of electric drive transmission (EDT) can effectively monitor its abnormal temperature rise that may occur under high speed and heavy load working conditions, so as to ensure the vehicles’ safe operation. In this paper, combined with real temperature and input/output characteristic data collected from EDT test platform under different working conditions, a spatio-temporal relationship dynamic graph convolution neural network based on least square method (OLS-DRGCN) for temperature prediction is proposed. Firstly, OLS is used to estimate the EDT’s internal temperature based on partial sensor information as the input of OLS-DRGCN. Secondly, the spatial dependence relationship of each temperature node is dynamically learned through node embedding and the dynamic thermal network topology of EDT is constructed. Meanwhile, the timing rule of each temperature node is obtained through the gated recurrent unit.
In the field of vehicle aerodynamic simulation, Reynold Averaged Navier-Stokes (RANS) model is widely used due to its high efficiency. However, it has some limitations in capturing complex flow features and simulating large separated flows. In order to improve the computational accuracy within a suitable cost, the Field Inversion and Machine Learning (FIML) method, based on a data-driven approach, has received increasing attention in recent years. In this paper, the optimal coefficients of the Generalized k-ω (GEKO) model are firstly obtained by the discrete adjoint method of FIML, utilizing the results of wind tunnel experiments. Then, the mapping relationship between the flow field characteristics and the optimal coefficients is established by a neural network to augment the turbulence model.
Recently, several datasets have become available for occupant monitoring algorithm development, including real and synthetic datasets. However, real data acquisition is expensive and labeling is complex, while virtual data may not accurately reflect actual human physiology. To address these issues and obtain high-fidelity data for training intelligent driving monitoring systems, we have constructed a hybrid dataset that combines real driving image data with corresponding virtual data generated from 3D driving scenarios. We have also taken into account individual anthropometric measures and driving postures. Our approach not only greatly enriches the dataset by using virtual data to augment the sample size, but it also saves the need for extensive annotation efforts. Besides, we can enhance the authenticity of the virtual data by applying ergonomics techniques based on RAMSIS, which is crucial in dataset construction.
The software installed in Electronic Control Units (ECUs) has witnessed a significant scale expansion as the functionality of Intelligent Connected Vehicles (ICVs) has become more sophisticated. To seek convenient long-term functional maintenance, stakeholders want to access ECUs data or update software from anywhere via diagnostic. Accordingly, as one of the external interfaces, Diagnostics over Internet Protocol (DoIP) is inevitably prone to malicious attacks. It is essential to note that cybersecurity threats not only arise from inherent protocol defects but also consider software implementation vulnerabilities. When implementing a specification, developers have considerable freedom to decide how to proceed. Differences between protocol specifications and implementations are often unavoidable, which can result in security vulnerabilities and potential attacks exploiting them.
In the process of automobile industrialization, integrated electric drive systems turn to be the mainstream transmission system of electric vehicles gradually. The main sources of noise and vibration in the chassis are from the gear reducer and motor system, as a replacement of engine. For improving the electric vehicles NVH performance, effective identification and quantitative analysis of the main noise sources are a significant basis. Based on the rotating hub test platform in the semi-anechoic chamber, in this experiment, an electric vehicle equipped with a three-in-one electric drive system is taken as the research object. As well the noise and vibration signals in the interior vehicle and the near field of the electric drive system are collected under the operating conditions of uniform speed, acceleration speed, and coasting with gears under different loads, and the test results are processed and analyzed by using the spectral analysis and order analysis theories.
Hydrogen energy is a kind of secondary energy with an abundant source, wide application, green, and is low-carbon, which is important for building a clean, low-carbon, safe, and efficient energy system and achieving the goal of carbon peaking and being carbon neutral. In this paper, the effect of nozzle position, hydrogen injection timing, and ignition timing on the in-cylinder combustion characteristics is investigated separately with the 13E hydrogen engine as the simulation object. The test results show that when the nozzle position is set in the middle of the intake and exhaust tracts (L2 and L3), the peak in-cylinder pressure is slightly higher than that of L1, but when the nozzle position is L2, the cylinder pressure curve is the smoothest, the peak exothermic rate is the lowest, and the peak cylinder temperature is the lowest.
To improve the prediction accuracy of the remaining useful life (RUL) of the proton exchange membrane fuel cell (PEMFC), an integrated health index (IHI) including electrical and non-electrical parameters of PEMFC is established, and the RUL prediction is conducted based on the above index. Firstly, several operating conditions including the PEMFC degradation information are selected according to the information theory method. Moreover, the IHI is established by the sequential quadratic programming method. Secondly, RUL predictions based on the power and IHI are conducted by the adaptive neuro fuzzy inference system (ANFIS), respectively. Finally, different results comparisons including power and IHI differences, differences between experimental and training/predicting results, amounts of different differences in training and predicting phases, and RUL prediction results are presented in detail.
With the increase of motor speed and the deterioration of operating environment, it is more difficult to predict the transient temperature field (TTF). Meanwhile, it is difficult to obtain the temperature test dataset of key nodes under various complete road conditions, so the cost of bench test or real vehicle test is high. Therefore, it is of great significance to establish a high fidelity, lightweight temperature prediction model which can be applied to real vehicle thermal management for ensuring the safe and stable operation of motor. In this paper, a physical model simulating electromagnetic-heat-flow multi-physical coupling of permanent magnet synchronous motor (PMSM) in electric drive gearbox (EDG) is established, and the correctness of the model is verified by the actual EDG bench test.
In this paper, an equivalent conversion method is proposed to apply the six-dimensional force road spectrum of the four-axle vehicle on the same platform to the three-axle through the axle load comparison. Further, the feasibility of the devolved equivalent conversion method is verified, and the fatigue performance improvement of the wishbone support structure of a commercial vehicle is finally achieved. Specifically, firstly, the load spectrum at each attachment point of the suspension for the three-axle vehicle is obtained through the iteration of the multi-body dynamic model. Furthermore, the finite element model of the suspension for the three-axle vehicle is established; the analysis of fatigue life for the suspension structure is performed by extracting stress amplitude through the multi-axis cyclic counting method and calculating equivalent force amplitude through McDiarmid’s criterion, combined with the SN curve of the material.
Optimization design of hard point parameters for hinge mechanism has been paid more attention in recent years, attributable to their significant improvement in dynamic performance. In this paper, the experimental analysis and dynamic optimization design of hinge mechanism is performed. The acceleration measurement experiments are carried out at different arrangement points and under different working conditions. Furthermore, the accuracy of established multi-body dynamics model is verified by three-axis accelerometer measurement experiment. In addition, sensitivity analysis for electric strut and gas strut coordinates is performed and shows that the Y coordinate of the lower end point of the electric strut is the design variable that has the greatest impact on the responses.
Aiming at the laborious process in motor structure modeling for acoustic noise calculation, an improved stator structure modeling scheme is proposed, which includes stator structure simplification and equivalent material parameters identification. The stator assembly is modeled as a homogeneous solid with the same size as the stator core, and the influence of model simplification is compensated by orthotropic equivalent material parameters. The equivalent material parameters are acquired through an optimization algorithm by minimizing the error between FEM calculated modal frequencies and the modal tested results. With the stator assembly model, the motor assembly model is built, and the constrained modal characteristics of the motor assembly are verified by comparing the modal frequencies to the resonance bands in the vibration acceleration spectrum. Finally, the motor structure model is used to calculate the electromagnetic noise of an induction motor.
In this paper, the principles, advantages and disadvantages of the main technology of variable strength design of automobile B-pillar Based on the finite element simulation technology, the local stress variable strength design effect of Automobile B-pillar structure is simulated, compared and evaluated. The simulation results show that with the same mechanical properties, the overall lightweight degree of B-pillar structure with variable strength design can be reduced by about 8.9%. With the expansion of the strengthening area of variable strength design of parts, the degree of lightweight of parts can be further improved. It can be seen that the local stress variable strength design method provides a new technical option for the lightweight design of automobile parts.
Air foil bearings are gradually applied in air compressors in fuel cell vehicles for the advantages of high speed, oil-free and non-contact. Advanced air foil bearings with different structures are used to improve the performance of air compressor. Accurate modeling of the complex structures in air foil bearings has become a research hotspot in recent years. This paper presents a theoretical model for a double-top-foil air foil journal bearing (DAFJB) for centrifugal air compressors used in fuel cell vehicles. The foil structure is modeled by finite element method (FEM) using shell elements. Coulomb law and penalty function method are applied to model the tangential and normal behavior of the contact areas. The local contact between the middle top foil and the bump foil, the bump foil and the bearing sleeve are modeled using node-to-segment contact method. The large-area contact behavior between two layers of top foils is modeled by simplified surface-to-surface contact scheme.
Intrusion Detection Systems (IDS), technically speaking, is to monitor the network, system, and operation status according to certain security policies, and try to find various attack attempts, attacks or attack results to ensure the confidentiality, integrity and availability of network system resources. Automotive intrusion detection systems can identify and alert by analyzing in-vehicle traffic and log when software applications or devices with malicious activity exist, or the in-vehicle network is tampered and injected. But unfortunately, automotive cybersecurity researchers hardly produce a comprehensive detection method due to the confidential nature of Controller Area Network (CAN) DBC format files, which is a standard long maintained by car manufacturers. In this paper, an enhanced intrusion detection method is proposed based on the double-decision-tree to classify different attack models for in-vehicle CAN network without the need to obtain complete DBC files.
Image corruptions due to noise, blur, contrast change, etc., could lead to a significant performance decline of Deep Neural Networks (DNN), which poses a potential threat to DNN-based autonomous vehicles. Previous works attempted to explain corruption from a Fourier perspective. By comparing the absolute Fourier spectrum difference between corrupted images and clean images in the RGB color space, they regard the noise from some corruptions (Gaussian noise, defocus blur, etc.) as concentrating on the high-frequency components while others (contrast, fog, etc.) concentrate on the low-frequency components. In this work, we present a new perspective that unifies corruptions as noise from high frequency and thus propose an image augmentation algorithm to achieve a more robust performance against common corruptions. First, we notice the 1/fα statistical rule of the natural image's spectrum and the channels-wise differential sensitivity on the YCbCr color space of the Human Visual System.