Search Results

The active engine mount (AEM) is developed in automotive industry to improve overall NVH performance. The AEM is designed to reduce major-order signals of engine vibration over a broad frequency range, therefore it is of vital importance to extract major-order signals from vibration before the actuator of the AEM works. This work focuses on a method of real-time extraction of the major-order acceleration signals at the passive side of the AEM. Firstly, the transient engine speed is tracked and calculated, from which the FFT method with a constant sampling rate is used to identify the time-related frequencies as the fundamental frequencies. Then the major-order signals in frequency domain are computed according to the certain multiple relation of the fundamental frequencies. After that, the major-order signals can be reconstructed in time domain, which are proved accurate through offline simulation, compared with the given signals.

The backlash between engaging components in a driveline is unavoidable, especially when the gear runs freely and collides with the backlash, the impact torque generated increases the vibration amplitude. The power-split hybrid electric vehicle generates output torque only from the traction motor during the launching process. The nonlinear backlash can greatly influence the driveability of the driveline due to the rapid response of the traction motor and the lack of the traditional clutches and torsional shock absorbers in the powertrain. This paper focuses on the launch vibration of the power-split hybrid electric vehicle, establishes a nonlinear driveline model considering gear backlash, including an engine, two motors, a Ravigneaux planetary gear set, a reducer, a differential, a backlash assembly, half shafts, and wheels.

Manufacturers have been encouraged to accommodate advanced downsizing technologies such as the Variable Displacement Engine (VDE) to satisfy commercial demands of comfort and stringent fuel economy. Particularly, Active control engine mounts (ACMs) notably contribute to ensuring superior effectiveness in vibration attenuation. This paper incorporates a PID controller into the active control engine mount system to attenuate the transmitted force to the body. Furthermore, integrated time absolute error (ITAE) of the transmitted force is introduced to serve as the control goal for searching better PID parameters. Then the particle swarm optimization (PSO) algorithm is adopted for the first time to optimize the PID parameters in the ACM system. Simulation results are presented for searching optimal PID parameters. In the end, experimental validation is conducted to verify the optimized PID controller.

The turbocharger air intake noise during transient conditions like wide open throttle and tip-in/out affects the passenger ride comfort. This paper aims to study an optimized design of multi-chamber perforated resonators to attenuate this noise. The noise produced by a turbocharger in a test vehicle has been measured to find out the noise spectral characteristics which can be used to design the acoustic targets including the amplitude and frequency range of transmission loss (TL). The structural parameters of the resonators are optimized based on genetic algorithm (GA) and two-dimensional prediction theory of the resonator TL. The optimized resonators are installed on the test vehicle to verify the actual noise reduction effect. The results suggest that the broadband noise has been eliminated, and subjective feelings are greatly improved.

Active engine mount (AEM) is an effective approach which can optimize the noise, vibration and harshness (NVH) performance of vehicles. The filtered-x-least-mean-squares (FxLMS) algorithm is widely applicated for vibration attenuation in AEMs. However, the performance of FxLMS algorithm can be deteriorated without an accurate secondary path estimation. First, this paper models the secondary path using finite impulse response (FIR) model, infinite impulse response (IIR) model and back propagation (BP) neural network model and the model errors of which are compared to determine the most accurate and robust modeling method. After that, the influence of operation frequency on accuracy of the secondary path model is analyzed through simulation approach. Then, the impact of reference signal mismatch on the control effect is demonstrated to study the robustness of FxLMS algorithm.

This paper focuses on lane-changing trajectory planning and trajectory tracking control in autonomous vehicle technology. Aiming at the lane-changing behavior of autonomous vehicles, this paper proposes a new lane-changing trajectory planning method based on particle swarm optimization (PSO) improved third-order Bezier curve path planning and polynomial curve speed planning. The position of Bezier curve control points is optimized by the particle swarm optimization algorithm, and the lane-changing trajectory is optimized to improve the comfort of lane changing process. Under the constraints of no-collision and vehicle dynamics, the proposed method can ensure that the optimal lane-changing trajectory can be found in different lane-changing scenarios. To verify the feasibility of the above planning algorithm, this paper designs the lateral and longitudinal controllers for trajectory tracking control based on the vehicle dynamic tracking error model.

The plug-in hybrid electric vehicles with dual-motor and multi-gear structure can realize multiple operation modes such as series, parallel, hybrid, etc. The traditional rule-based energy management strategy mostly selects some of the modes (such as series and parallel) to construct the energy management strategy. Although this method is simple and reliable, it can’t fully exert the full potential of this structure considering both economy and driving performance. Therefore, it is very important to study the algorithm which can exert the maximum potential of the multi-degree-of-freedom structure. In this paper, a new RL-PMP algorithm is proposed, which does not divide the operation modes, and explores the optimal energy allocation strategy to the maximum extent according to the economic and drivability criteria within the allowable range of the characteristics of the power system components.

Object detection is an important visual content of the autonomous vehicle, the traditional detecting methods usually cost a lot of computational memory and elapsed time. This paper proposes to use lightweight deep convolutional neural network (MobilenetV3-SSDLite) to carry out the object detection task of autonomous vehicles. Simulation analysis based on this method is implemented, the feature layer obtained after h-swish activation function in the first Conv of the 13th bottleneck module in MobilenetV3 is taken as the first effective feature layer, and the feature layer before pooling and convolution of the antepenultimate layer in MobilenetV3 is taken as the second effective feature layer, and these two feature layers are extracted from the MobilenetV3 network.

Motivated by applying artificial intelligence technology to the automobile industry, reinforcement learning is becoming more and more popular in the community of intelligent driving research. The reward function is one of the critical factors which affecting reinforcement learning. Its design principle is highly dependent on the features of the agent. The agent studied in this paper can do perception, decision-making, and motion-control, which aims to be the assistant or substitute for human driving in the latest future. Therefore, this paper analyzes the characteristics of excellent human driving behavior based on the six-layer model of driving scenarios and constructs it into a human knowledge graph. Furthermore, for highway pilot driving, the expert demo data is created, and the reward function is self-learned via inverse reinforcement learning. The reward function design method proposed in this paper has been verified in the Unity ML-Agent environment.