Search Results

In recent years, due to its strong plasticity and excellent future potential, the development of automated vehicles in the mining environment is extraordinarily rapid. The application of lidar in automated vehicles has also become more and more popular, and algorithms for point cloud object detection have emerged endlessly. However, due to rough road and dusk-to-dawn operations in the mining scenario and the large size of the truck, traditional detection algorithms fail to meet the requirements of real-time updates. Due to the high precision and efficiency of the deep learning network, its application could break through the limitations of traditional algorithms. In this paper, the algorithm called PointPillars is adapted for object detection in the mining scenario. After converting the point cloud to a sparse pseudo-image and extracting features by a two-dimensional convolutional neural network (2D CNN), the time consumption of the entire algorithm becomes much less.

Collision avoidance technology is one of the key areas in the longitudinal safety research of intelligent vehicles. For the research of collision avoidance system, the existing methods usually use the evaluation index based on time interval or braking process to carry out risk assessment. In order to overcome the shortcomings of the formulas for describing the longitudinal hazard degree established in most studies, such as great differences, inconsistent standards and weak normalization, a comprehensive evaluation method for the longitudinal hazard in front-impact scenarios is established. This method takes into account both the analysis of time interval and braking process, and considers the non-linear variation of the longitudinal hazard degree with the real-time distance and speed of two vehicles. It can describe the longitudinal hazard degree of vehicles in dangerous traffic scenarios.

High-speed rotating gears are generally lubricated by spray lubrication. Lubricating oil is driven by high-speed rotating gear, and some lubricating oil will be excited into oil mist, so that the gears are in the gas-liquid mixed environment. In this paper, the computational fluid dynamics model of the spray lubrication cooling process is established based on the gear heat transfer behavior under the spray lubrication condition. The influence of different spray parameters on the liquid-solid two-phase convective heat transfer coefficient is obtained. On this basis, the accurate boundary conditions of gear temperature field calculation are analyzed by studying the heat transfer behavior of high speed gear spray lubrication. The calculation model of gear temperature based on spray lubrication is established, and the temperature field distribution of gear is obtained.

When automobiles are at the threat of collisions, steering usually needs shorter longitudinal distance than braking for collision avoidance, especially under the condition of high speed or low adhesion. Thus, more collision accidents can be avoided in the same situation. The steering assistance is in need since the operation is hard for drivers. And considering the dynamic characteristics of vehicles in those maneuvers, the real-time and the accuracy of the assisted algorithms is essential. In view of the above problems, this paper first takes lateral acceleration of the vehicle as the constraint, aiming at the collision avoidance situation of the straight lane and the stable driving inside the curve, and trajectory of the collision avoidance is derived by a quintic polynomial.

The fracture of the retainer leads to the failure of the needle rolling bearings in a planetary gear train of a planetary gearbox. In order to solve this engineering problem, the kinematics and kinetics of the failed needle rolling bearings is analyzed with the analytical model and the numerical model. A simple mathematical model is pointed out to analyze the dynamic load of a needle rolling element in the failed bearings. The assembling position of the small sun gear is also found to influence the performance of the needle rolling bearings significantly and therefore a best scheme for modifying the structure of the planetary gearbox is pointed out based on the multi-object optimization theory to reduce the bearing load heavily. Based on the calculated work, a systematic method of choosing the proper bearings for planetary gearbox can be concluded.

Recognizing road conditions using onboard sensors is significant for the performance of intelligent vehicles, and the road profile is a widely accepted representation both in the temporal and frequency domains, greatly influencing driving quality. In this paper, a recurrent neural network embedded with attention mechanisms is proposed to reconstruct the road profile sequence. Firstly, the road and vehicle sensor signals are obtained in a simulated environment by modeling the road, tire, and vehicle dynamic system. After that, the models under different working conditions are trained and tested using the collected data, and the attention weights of the trained model are then visualized to optimize the input channels. Finally, field experiments on the real vehicle are conducted to collect real road profile data, combined with vehicle system simulation, to verify the performance of the proposed method.

The main objective of this work is to investigate, by means of numerical simulations, the performance of the engine nacelle ventilation cooling system of a helicopter under hover and forward flight conditions, and to propose a simplified method of evaluating the performance based on rotor downwash flow by taking the synthetical effect of engine nacelle, exhaust ejector and external flow of a helicopter into account. For the engine nacelle of a helicopter, an integrated model of the nacelle and exhaust ejector was set up including the domain of external flow. The unstructured grid and finite volume method were applied for domains and control equations discreteness, and the standard k-ε model was applied for solving turbulent control equations. Using the business CFD software, the flow field and the temperature field in the nacelle were calculated for single inlet scheme and double inlets scheme, total up to 9 schemes. The performance of the exhaust ejector was computed.

Nowadays more and more in-depth study and continuous investigation is being carried out in the continuously variable transmission (CVT) field. A good continuously variable ratio changing action would greatly improve the performance of the transmission and offer a high fuel economy. So it would save energy and protect environment, furthermore it would reduce the working intensity and demands of driving skill on the driver. Therefore, a high efficiency and good performance continuously variable transmission (CVT) is urgently needed. This paper presents a new Satellite Star Gear (SSG) Continuously Variable Transmission System. It was created based on the Pulse Stepless Transmission with some improvements on the overrunning clutch, stepless speed change device etc. This paper introduces the basic mechanical structure and kinematical principle of a double eccentricity stepless speed change device, overrunning clutch and the whole mechanism (SSG).

Unmanned Aerial Vehicles (UAVs) encounter various uncertainties, including unfamiliar environments, signal delays, limited control precision, and other disturbances during task execution. Such factors can significantly compromise flight safety in complex scenarios. In this paper, to enhance the safety of UAVs amidst these uncertainties, a control accuracy prediction model based on ensemble learning abnormal state detection is designed. By analyzing the historical state data, the trained model can be used to judge the current state and obtain the command tracking control accuracy of the UAV at that instant. Ensemble learning offers superior classification capabilities compared to weak learners, particularly for anomaly detection in flight data. The learning efficacy of support vector machine, random forest classifier is compared and achieving a peak accuracy of 95% for the prediction results using random forest combined with adaboost model .

Generally, noise will occur during steering with the hydraulic power steering system (hereinafter HPS). The noise producing in the rotary valve takes up a big proportion of the total one. To study the noise in the control valve, 2-D meshes of the flow field between the sleeve and the rotor were set up and a general CFD code-Fluent was used to analyze the flow inside the valve. The areas where the noise may be occurred were shown and some suggestions to silence the noise were given.

Lagrangian approach has been widely adopted in the droplet impingement analysis for aircraft icing simulation. Some improvements were proposed, including: 1) The heat and mass transfer consideration in droplet dynamics; 2) More efficient droplet localization method, which could and facilitated to find the initial cell in Eulerian grid; 3) New computation method of impingement efficiency, which uses the cover ratio to transform the impingement efficiency of arbitrary impinged region to that of the cell element of body surface and avoids the iterative computation to find the trajectories reaching the corner of the panel or cell element. A numerical solver was built and integrated with the capabilities to deal with super-cooled large droplet (SLD) conditions by considering the splashing and bouncing of SLD. The computational results were validated with the experiment data, which shown good agreements in the impingement limitations and tendency.

Most tractor-semitrailers are fitted with multi-axle trailers which cannot be actively steered, and such vehicles with an articulated configuration are inclined to exhibit instability such as trailer swing, jack-knifing, and rollover at high speed. Proposed in this paper is an optimal control of the yaw stability of tractor-semitrailers at high speed by applying an active trailer's steering angle. An optimal control algorithm is designed by employing a 3-DOF vehicle model in the yaw plane. The optimal linear quadratic regulator (LQR) approach is used with a cost function including sideslip angles, yaw rates of both tractor and trailer, and trailer's steering angle. The yaw stability at the high speed is also quantified by the dynamic performance measurements of lateral path deviation, hitch angle and rearward amplification (RA). The algorithm is evaluated by co-simulations using TruckSim and Matlab/Simulink softwares.

Ice protection is important for aero-engine induction system, such as the inlet vanes. For the ice protection of such parts manufactured with low thermal conductivity polymer-based composite material, the combined heating method using interior jet impingement and exterior ejection film has certain advantages. The simulation model coupling CFD with solid heat conduction was developed and solved with the anisotropic thermal conductivities model to investigate the heat transfer enhancement in the stagnation region of aero-engine inlet vanes due to ejection slot and anisotropic heat conduction, which is related to the curved geometry, ejection slots and anisotropic heat conduction. The temperature distribution and heat flux ratio between the stagnation region on outside surface and the impingement region inside were calculated and analyzed for the configuration with different ejection angle and different materials.

Comparing with traditional braking systems of automobiles, the brake-by-wire (BBW) system has a faster dynamic response and is more suitable for applications that facilitate regenerative braking. As the two main categories of BBW systems, the well-known electro-hydraulic braking system and electro- mechanical braking system are not compact enough and their fail-safe function has always been a worrying aspect. A new BBW system called integrated braking system (IBS) by employing the hydraulic multiplex method was proposed in recent years. The IBS implements power-assisted braking and active braking by means of just an integrated unit. It can certainly be used for ABS, ASR and ESC systems for building up and reducing brake pressure. Presented in the paper is a new structure of IBS, which is mainly composed of a motor, ball screw, master cylinder and four 2/2-way valves.

Forward obstacles detection is one of the key tasks in the perception system of autonomous vehicles. The perception solution differs from the sensors and the detection algorithm, and the vision-based approaches are always popular. In this paper, an embedding fast obstacles detection algorithm is proposed to efficiently detect forward diverse obstacles from the image stream captured by the monocular camera. Specifically, our algorithm contains three components. The first component is an object detection method using convolution neural networks (CNN) for single image. We design a detection network based on shallow residual network, and an adaptive object aspect ratio setting method for training dataset is proposed to improve the accuracy of detection. The second component is a multiple object tracking method based on correlation filter for the adjacent images.

Hydraulic system is very important for the performance of AT. The dynamic characteristics of automatic transmission hydraulic system are studied in this paper. Because the valves in the hydraulic system are not standard parts, ITI-SimulationX, the multi-domain physics simulation software from ITI GmbH, is used to build the dynamic model of the hydraulic system based on the basic elements in the library of SimulationX. And then the dynamic characteristics of the system are simulated. The simulation results and the test results from the test bench are compared to confirm the simulation model. The results show that the simulation model can couple with the real system very well and the simulation model can be confirmed. Based on the confirmed simulation model, the effects of different parameters of the hydraulic system on the characteristics of the system are analyzed.

This paper proposes an intelligent car testing and evaluation method based on digital twins, which is crucial for ensuring the proper functioning of autonomous driving systems. This method utilizes digital twin testing technology to effectively map and integrate real vehicles in real-world testing scenarios with virtual test environments. By enriching the testing and validation environment for smart cars, this approach improves testing efficiency and reduces costs. This study connects real test vehicles with simulation software testing toolchains to build a digital twin autonomous driving testing platform. This platform facilitates the validation, testing, and evaluation of functional algorithms, and case study is conducted through testing and validation of an emergency collision avoidance system. By rapidly applying digital twin testing and evaluation techniques for intelligent cars, this approach accelerates the development and deployment of autonomous vehicles.

Aiming at the fault that the speed signal of the automatic transmission output shaft Hall-type speed sensor fluctuates abnormally due to the change of the air gap, the method of fault detection and diagnosis is proposed. Firstly, a limited low-pass filter module was designed according to the characteristics of the fault, and a good filter effect is achieved. Secondly, by comparing the signals before and after filtering, a residual generator is designed, and an adaptive dynamic threshold is designed by analyzing the causes and influencing factors of the residual, which can configure a reliable and effective threshold for the generated residual in real time, which improves the fault identification robustness and effectiveness. Then, a fault debounce method is designed to avoid frequent false alarms of occasional faults. Finally, simulation verification proves the effectiveness of the method.

As one of advanced driver assistance systems (ADAS), automatic parking system has great market prospect and application value. In this paper, based on an intelligent vehicle platform, an automatic parking system is designed by using multi-point preview theory. The vehicle kinematics model was established, based on Ackermann steering principle. By analyzing working conditions of parallel parking, complex constraint condition of parking trajectory is established and reference trajectory based on sine wave is proposed. In addition, combined with multi-point preview theory, the design of trajectory following controller for automatic parking is completed. The cost function is designed, which consider the trajectory following effect and the degree of easy handling. The optimization of trajectory following control is completed by using the cost function.

This paper investigates the path planning and formation control problem for connected automated vehicles (CAVs) in unstructured road scenarios. A hierarchical framework that integrates path planning and vehicle dynamics control is proposed for multiple CAVs to form specific formations without lane information of the road. In the path planning layer, a virtual leader is used to guide the position and direction of the formation and the decentralized path planning algorithm for multiple CAVs is developed based on the virtual leader's information through the communication network. A spatial and temporal graph (STG) is constructed based on the virtual leader's local path and the specific formation shape. The improved A* method based on the STG is proposed to generate the coarse path for the following vehicles. Then the path is smoothed by the B-spline method.