Search

The frequent traffic accidents lead to a large number of casualties and large related financial losses every year; this serious state is owed to several factors; among those, driving behavior is one of the most imperative subjects to discuss. Driving behaviors mainly include behavior characteristics such as car-following, lane change, and risky driving behavior such as distraction, fatigue, or aggressive driving, which are of great help to various tasks in traffic engineering. An accurate and reliable method of driving behavior recognition is of great significance and guidance for vehicle driving safety. In this paper, the vehicle multisensor information, vehicle CAN bus data acquisition system, and typical feature extraction methods are summarized at first. And then, several driving behavior recognition models based on machine learning and deep learning are reviewed. Through a detailed analysis of the features of random forests, support vector machines, convolutional neural networks, and recurrent neural networks used to build driving behavior recognition models, the following findings are obtained: the driving behavior model constructed by traditional machine learning model is relatively mature but it is greatly affected by feature extraction, data scale, and model structure, which affects the accuracy of the final driving behavior recognition. Deep learning model based on a neural network has achieved high accuracy in identifying driving behavior, and it may gradually become the mainstream of constructing the driving behavior model with the development of big data, artificial intelligence technology, and computer hardware. Finally, this paper points out some content that needs to be further explored, to provide reference and inspiration for scholars in this field to continue to study the driving behavior recognition model in depth.

The helical planetary transmission system (HPTS) is widely used in wind power, hydropower, and shield machine, which operating conditions are extremely complicated, and the existence of component installation errors will result in response deviations to the theoretical design. A dynamic model for slice type bending-torsional-pendulum of the HPTS is established in the lumped parameter method considering the installation error of shaft (IEOS) for the 1st planet gear, helical meshing characteristics, and bearing support characteristics. The vibration response characteristics of the HPTS under the IEOS for the 1st planet gear are studied. The results have shown that the FFT amplitudes for the horizontal vibration acceleration of the sun gear increased by 8.3%, and the axial vibration acceleration of the ring gear increased by 11.5%, respectively. The maximum magnitude increase of FFT amplitude for the vibration acceleration under a positive 0.13 mm IEOS for the 1st planet gear is the axial direction of the ring gear. The results indicate that the IEOS needs to be thoroughly introduced into the HPTS to simulate the actual operating conditions of the system.

As the most important element in improving the service life of a mechanical system, surface coating materials are of key importance in the development of high-end equipment. To improve the comprehensive properties of the surface coating, the common core-shell structure/Ni60 coating was prepared on the surface of #45 steel by supersonic plasma spraying. The results show that the Ni60 has no layer structure, pores, cracks, and other defects on the surface of the coating. The nanohardness of the NNA(Ni60/Ni (Al) mixture powder), NNM(Ni60/Ni (MoS2) mixture powder), and NNC(Ni60/Ni (C) mixture powder) coatings is 6815 μN, 5750 μN, and 2000 μN. The results show that the wear resistance of the NNA coating is better. In the friction and wear test, the NNA coating mainly shows adhesive wear and abrasive wear, while the NNM and NNC coatings mainly show abrasive wear.

This paper presents microstructural topology optimization of viscoelastic materials for the plates with constrained layer damping (CLD) treatments. The design objective is to maximize modal loss factor of macrostructures, which is obtained by using the Modal Strain Energy (MSE) method. The microstructure of the viscoelastic damping layer is composed of 3D periodic unit cells. The effective elastic properties of the unit cell are obtained through the strain energy-based method. The density-based topology optimization is adopted to find optimal microstructures of viscoelastic materials. The design sensitivities of modal loss factor with respect to the design variables are analyzed and the design variables are updated by Method of Moving Asymptotes (MMA). Numerical examples are given to demonstrate the validity of the proposed optimization method. The effectiveness of the optimal design method is illustrated by comparing a solid and an optimized cellular viscoelastic material as applied to the plates with CLD treatments.

This paper deals with an optimal layout design of the constrained layer damping (CLD) treatment of vibrating structures subjected to stationary random excitation. The root mean square (RMS) of random response is defined as the objective function as it can be used to represent the vibration level in practice. To circumvent the computationally expensive sensitivity analysis, an efficient optimization procedure integrating the pseudoexcitation method (PEM) and the double complex modal superposition method is introduced into the dynamic topology optimization. The optimal layout of CLD treatment is obtained by using the method of moving asymptote (MMA). Numerical examples are given to demonstrate the validity of the proposed optimization procedure. The results show that the optimized CLD layouts can effectively reduce the vibration response of the structures subjected to stationary random excitation.