Travel experience matters: Expected personal mobility impacts after simulated L3/L4 automated driving

Automated vehicles (AVs) are expected to change personal mobility in the near future. Most studies on the mobility impacts of AVs focus on fully automated (SAE L5) vehicles, but the gradual development of the technology will probably bring AVs with more limited capabilities to begin with. This stated-preference study focused on the potential mobility impacts of conditionally automated (L3) and highly automated cars (L4). We investigated personal mobility impacts among 59 participants who experienced automated driving repeatedly in a driving simulator. Half of them drove with an L3 and half with an L4 motorway function. After the first and final drive they answered questions on their travel experience and how automated vehicles could change their mobility. After the drives, participants in both groups were willing to accept 30–50% longer travel times for a 30 min trip if they did not need to drive the whole trip themselves. This translates into savings of around 30% for the perceived value of travel time on routes where automation is available. There were no statistically significant differences between L3 and L4 in the accepted travel times. Most participants did not expect to make more trips with automated cars, but around half of them anticipated making longer trips. The amount of car travel may increase more with L4 than with L3 automation, possibly due somewhat to changes in the experienced travel quality. The results suggest that the mobility impacts of automated driving may increase with a higher level of automation.

Search for rational ratio of maximum speed and minimum fuel consumption of the vehicle

The gear ratio of the final drive and the distribution of the vehicle mass along the axles has a great influence on the technical and operational parameters of the vehicle. The article discusses the use of mathematical modelling in the MATLAB Simulink and the planning of the experiment to identify the optimal values of the final drive ratio and the mass distribution along the axles when driving a vehicle on a horizontal reference surface. A computational model for determining the moment of resistance on the wheels is developed when the vehicle moves along a supporting surface without slopes. The roughness and unevenness of the surface were not taken into account in the above model. The response function is obtained by studying the dependence of change in two parameters: the speed and fuel consumption of the car from two factors of variation: the final drive ratio and the mass distribution along the axles. The steep ascent method is used to determine the optimal parameters of the vehicle design, which allow achieving maximum speed with minimum fuel consumption when the vehicle is moving on a horizontal supporting surface.

MODELING THE TRANSMISSION OF A MOBILE MEANS ON TIRES OF EXTRA LOW PRESSURE TAKING INTO ACCOUNT THE INFLUENCE OF ROAD UNEQUALITIES

The work is devoted to the problem of negative dynamic effects on the transmission and the engine of a mobile vehicle on ultra-low pressure tires. When using this propulsion device on technological means, the load on wheel reducers (final drives), half shafts, differential, final drive, on the shaft and cardan drive hinges, spline connection, transfer case, elastic transmission clutch, transmission drive and driven shafts sharply increases with gears, clutch driving and driven parts, engine crankshaft. When the load on these elements is excessive, their service life is reduced, and excessive loading can even lead to a sudden failure. Since each of these nodes is somehow fixed on the frame of the vehicle, to which vibrations from the unevenness of the rolling surfaces perceived by the propulsion are transmitted, they also have an additional effect. For a comprehensive assessment of the dynamic loading of the transmission and the engine of a mobile vehicle equipped with ultra-low pressure tires, taking into account the influence of road irregularities, a mobile vehicle model was compiled. The model will allow a more accurate calculation of the basic characteristics of technological equipment transmissions on ultra-low pressure tires.

A Deep Learning Model for Fault Diagnosis with a Deep Neural Network and Feature Fusion on Multi-Channel Sensory Signals

Collecting multi-channel sensory signals is a feasible way to enhance performance in the diagnosis of mechanical equipment. In this article, a deep learning method combined with feature fusion on multi-channel sensory signals is proposed. First, a deep neural network (DNN) made up of auto-encoders is adopted to adaptively learn representative features from sensory signal and approximate non-linear relation between symptoms and fault modes. Then, Locality Preserving Projection (LPP) is utilized in the fusion of features extracted from multi-channel sensory signals. Finally, a novel diagnostic model based on multiple DNNs (MDNNs) and softmax is constructed with the input of fused deep features. The proposed method is verified in intelligent failure recognition for automobile final drive to evaluate its performance. A set of contrastive analyses of several intelligent models based on the Back-Propagation Neural Network (BPNN), Support Vector Machine (SVM) and the proposed deep architecture with single sensory signal and multi-channel sensory signals is implemented. The proposed deep architecture of feature extraction and feature fusion on multi-channel sensory signals can effectively recognize the fault patterns of final drive with the best diagnostic accuracy of 95.84%. The results confirm that the proposed method is more robust and effective than other comparative methods in the contrastive experiments.