作者:
Kai Gao;Hao Huang;Linhong Liu;Ronghua Du;Jinlai Zhang
期刊:
2023 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom),2023年:809-816
作者机构:
[Kai Gao; Hao Huang; Linhong Liu; Ronghua Du; Jinlai Zhang] College of Automotive and Mechanical Engineering, Changsha University of Science & Technology, Changsha, China
摘要:
The development of vehicular networking technology continuously enhances the internet connectivity of modern vehicles. However, for in-vehicle networks, constant communication with the outside world dramatically increases vehicle security risks, posing serious security threats to automotive systems and occupants. This paper proposes a CNN-BiLSTM vehicular network intrusion detection model based on multi-head attention by analyzing the information security vulnerabilities in the Controller Area Network (CAN) bus. By extracting only the communication features of CAN messages, including CAN ID and Data field, this paper conducted a multiclass classification study on the real-time traffic dataset CarHacking. The model achieved a detection accuracy of 99.992%. The reduction of features effectively simplifies the model and improves its computation efficiency.
作者机构:
[Li, Wang; Zheng, Ya-ya] Hunan Univ Humanities, Dept Mat Engn, Sci & Technol, Loudi 417000, Hunan, Peoples R China.;[Luo, Bing-hui] Cent South Univ, Coll Mat Sci & Engn, Changsha 410083, Peoples R China.;[Xie, Wei; Zheng, Ya-ya] Changsha Univ Sci & Technol, Key Lab Safety Design & Reliabil Technol Engn Vehi, Changsha 410114, Peoples R China.
通讯机构:
[Ya-ya Zheng] D;Department of Materials Engineering, Hunan University of Humanities, Science and Technology, Loudi, Hunan, China<&wdkj&>Key Laboratory of Safety Design and Reliability Technology for Engineering Vehicle, Changsha University of Science & Technology, Changsha, China
摘要:
The microstructure evolution and precipitation behavior of Al-Mg-Si alloy during initial aging were studied using hardness testing, conductivity testing, differential scanning calorimetry (DSC), and high resolution transmission electron microscopy (HRTEM). The results show that the precipitation sequence of the Al-Mg-Si alloy during initial aging can be represented as: supersaturated solid solution -> spherical Mg/Si clusters -> needle-like Guinier Preston (GP) zone -> beta ''. Clusters are completely coherent with the Al matrix. The GP zone with relatively complete independent lattice parameters that differ slightly from the Al matrix parameters, is oriented along the direction of < 111 > Al and lying on {111}(Al) plane. The strength of the Al-Mg-Si alloy is greatly enhanced by the threedimensional strain field that exists between the beta '' phase and the two {200}(Al) planes. After aging at 170 degrees C for 6 h, the hardness reaches the peak of 127 HV and remains for a long time. At this stage, the electrical conductivity keeps relatively stable due to the formation of coherent precipitates (Mg/Si clusters/GP zones) and the reduction in solute atom concentration in the Al matrix. The severe coarsening and decreased number density of the beta '' phase during the over-aging stage result in a significant decrease in the hardness.
期刊:
Transportation Safety and Environment,2023年5(4) ISSN:2631-4428
通讯作者:
Lin Hu
作者机构:
[Lin Hu] School of Automotive and Mechanical Engineering, Changsha University of Science and Technology , Changsha 410114 , Hunan, China;[Jing Huang; Wei Wei; Xiaoyan Peng] College of Mechanical and Vehicle Engineering, Hunan University , Changsha 410082 , Hunan, China;[Huiqin Chen] College of Mechanical Engineering, Hangzhou Dianzi University , Hangzhou 310018 , Zhejiang, China
通讯机构:
[Lin Hu] S;School of Automotive and Mechanical Engineering, Changsha University of Science and Technology , Changsha 410114 , Hunan, China
摘要:
Objective
At present, most research on driver mental load identification is based on a single driving scene. However, the driver mental load model established in a road traffic scene is difficult to adapt to the changes of the surrounding road environment during the actual driving process. We proposed a driver mental load identification model which adapts to urban road traffic scenarios.
Methods
The model includes a driving scene discrimination sub-model and driver load identification sub-model, in which the driving scene discrimination sub-model can quickly and accurately determine the road traffic scene. The driver load identification sub-model selects the best feature subset and the best model algorithm in the scene based on the judgement of the driving scene classification sub-model.
Results
The results show that the driving scene discrimination sub-model using five vehicle features as feature subsets has the best performance. The driver load identification sub-model based on the best feature subset reduces the feature noise, and the recognition effect is better than the feature set using a single source signal and all data. The best recognition algorithm in different scenarios tends to be consistent, and the support vector machine (SVM) algorithm is better than the K-nearest neighbors (KNN) algorithm.
Conclusion
The proposed driver mental load identification model can discriminate the driving scene quickly and accurately, and then identify the driver mental load. In this way, our model can be more suitable for actual driving and improve the effect of driver mental load identification.
摘要:
Double-hat beam is a thin-walled structure with excellent crashworthiness. The current research on improving the crashworthiness of double-hat beam through the design and arrangement of ribs is not sufficient. In this work, the axial crashworthiness of double-hat beam with various ribs is systematically investigated. Four kinds of ribs and seven types of mixed ribs are proposed. The results show that vertical ribs help to enhance the impact performance of double-hat beam, the specific mean crushing force (SMCF) values of VR-3 and VR-5 are, respectively, 8.3% and 8.4% higher than that of double-hat beam. Transverse and diagonal ribs are beneficial to obtain stable crushing forces and deformation patterns. The SMCF value of MR-1 is 7.25% higher than that of TNRN-1 and 13.33% lower than that of VR-5. The performance of a mixed double-hat beam is always between the two original double-hat beams that make up it. The double-hat beams exhibit the deformation patterns of axial crushing, bending and torsion. In addition, the multi-objective optimizations of three typical double-hat beams are carried out. The thickness of double-hat beam's components is defined as variable, and the optimisation objectives are maximise mean crushing force and minimise structural mass. The SMCF value of the third solution of VRN-3 selected in this study increases by 24.42% compared with double-hat beam. In summary, the collision performance and deformation pattern of the double-hat beam can be controlled by the design of ribs.
摘要:
This study proposes a robust concurrent topology optimization method with considering dynamic load uncer-tainty for the design of structures composed of periodic microstructures based on the bi-directional evolutionary structural optimization (BESO) method. The objective function is formulated as the summation of the mean and standard deviation of the structural dynamic compliance modulus. The constraints are imposed on the macro-structure and material microstructure volumes, respectively. The hybrid dimension reduction method and Gauss integral (HDRG) method is proposed to quantify and propagate load uncertainty to estimate the objective function. By the HDRG method, robust topology optimization with uncertainty modeled by probabilistic methods can be handed uniformly. To reduce the computational burden, a decoupled sensitivity analysis method is proposed to calculate the sensitivities of objective function with respect to the microstructure design variables. Five numerical examples are used to validate the effectiveness of the proposed robust concurrent topology optimization method and demonstrate the influence of load uncertainty on the design results. Results illustrate that the proposed methods can obtain the clear topologies of macro and micro structures, and the dynamic load uncertainty has a significant impact on the design results.
摘要:
Constructing self-supported electrocatalysts is recognized as a practical implement to promote the electrocatalytic performance of water splitting. Herein, bimetallic phosphide CoNiP grown on a micro-sized porous nickel substrate (MP Ni) as electrocatalyst (CoNiP/MP Ni) has been developed to decrease the overpotentials of hydrogen evolution and oxygen evolution reaction. The micro-sized porous nickel substrate provides adequate specific surface area for loading active materials, and the hierarchically porous structure offers numerous interconnected channels, which together accelerates the mass transfer process in the electrocatalytic reaction. The CoNiP/MP Ni electrocatalyst achieves an ultra-low overpotentials of 37 mV at 10 mA center dot cm(-2) and 358 mV at 100 mA center dot cm(-2) for driving hydrogen evolution and oxygen evolution, respectively. The stable porous structure also enables the integrated CoNiP/MP Ni electrolyzer an excellent long-term operation stability. Meanwhile, first-principles calculations demonstrate that the CoNiP bimetallic phosphide possesses a low energy barrier and a strong interfacial bonding strength with micro-sized porous Ni from an atomic viewpoint. This work opens up a simple and new way of constructing low-cost, efficient and applicable self-supported electrocatalysts for water splitting.
摘要:
Cross-section optimization is an effective way to improve the mechanical performance of a vehicle body and reduce its structural mass. However, previous studies suffer from the deficiencies involving inaccurate cross-sectional model, insufficient consideration of manufacturability constraints and inefficient single-objective optimization. In this work, eight typical cross-sections of a body are optimized. A chain node-based parametric modeling is proposed to realize accurately cross-sectional discretization, and the geometric and manufacturability constraints as well as three optimization objectives are considered in the cross-sectional optimization models. To realize multi-objective optimization, a multi-objective intelligence adaptive optimization algorithm (MIAOA) is proposed. By classifying the non-dominated solutions and applying a reward-penalty strategy, the MIAOA realizes intelligent iteration. The experimental results on ZDT and DTLZ suites obtained by MIAOA are better than those of five typical algorithms in terms of convergence, stability, uniformity and extensiveness. Besides, the MIAOA is applied to improve the moments of inertia of the cross-sections and reduce their material areas. These optimized cross-sections are applied to the body, and the optimized body shows better mechanical performances involving torsional stiffness, bending stiffness, first-order mode and second-order mode, while reducing the total mass by 9.96 kg. In conclusion, the proposed methods can effectively realize lightweight automobiles.