Multibody models built in commercial software packages, e.g., ADAMS, can be used for accurate vehicle dynamics, but computational efficiency and numerical stability are very challenging in complex driving environments. These issues can be addressed by using data-driven models, owing to their robust generalization and computational speed. In this study, we develop a deep neural network (DNN) based model to predict longitudinal-lateral dynamics of an autonomous vehicle. Dynamic simulations of the autonomous vehicle are performed based on a semirecursive multibody method for data acquisition. The data are used to train and test the DNN model. The DNN inputs include the torque applied on wheels and the vehicle’s initial speed that imitates a double lane change maneuver. The DNN outputs include the longitudinal driving distance, the lateral driving distance, the final longitudinal velocities, the final lateral velocities, and the yaw angle. The predicted vehicle states based on the DNN model are compared with the multibody model results. The accuracy of the DNN model is investigated in detail in terms of error functions. The DNN model is verified within the framework of a commercial software package CarSim. The results demonstrate that the DNN model predicts accurate vehicle states in real time. It can be used for real-time simulation and preview control in autonomous vehicles for enhanced transportation safety.

Time history testing using a shaking table is one of the most widely used methods for assessing the dynamic response of structures. In shaking-table experiments and on-site monitoring, acceleration sensors are facing problems of missing data due to the fact of measurement point failures, affecting the validity and accuracy of assessing the structural dynamic response. The original measured signals are decomposed by ensemble empirical mode decomposition (EEMD), and the widely used deep neural networks (DNNs), gated recurrent units (GRUs), and long short-term memory networks (LSTMs) are used to predict the subseries of the decomposed original measured signal data to help model and recover the irregular, periodic variations in the measured signal data. The raw acceleration data of a liquefied natural gas (LNG) storage tank in shaking-table experiments were used as an example to compare and discuss the method’s performance for the complementation of missing measured signal data. The results of the measured signal data recovery showed that the hybrid method (EEMD based) proposed in this paper had a higher complementary performance compared with the traditional deep learning methods, while the EEMD-LSTM exhibited the best missing data complementary accuracy among all models. In addition, the effect of the number of prediction steps on the prediction accuracy of the EEMD-LSTM model is also discussed. This study not only provides a method to fuse EEMD and deep learning models to predict measured signal’ missing data but also provides suggestions for the use of EEMD-LSTM models under different conditions.

The shape of a bluff body section is of high importance to its aerostatic performance. Obtaining the aerostatic performance of a specific shape based on wind tunnel tests and CFD simulations takes a lot of time, which affects evaluation efficiency. This paper proposes a novel fully convolutional neural network model that enables rapid prediction from shape to aerostatic performance. Its main innovations are: (1) The proposal of a new shape description method in which the shape is described by the combination of the wall distance field and the space coordinate field, which can efficiently express the influencing factors of the shape on the aerostatic performance. (2) A step-by-step strategy in which the pressure field is used as the model output and then the calculation of the aerostatic coefficient is proposed. Compared with the simple direct prediction of the aerostatic coefficient, the logical connection between input and output can be enhanced and the prediction accuracy can be improved. It is found that the model proposed in this paper has good prediction accuracy, and its average relative error is 9.42% compared with the CFD calculation results. Compared with the direct use of the shape as the model input, the accuracy is improved by 13.25%; compared with the direct use of the drag coefficient as the model output, the accuracy is improved by 10%. Compared with traditional CFD calculations and wind tunnel experiments, this method can be used as a fast auxiliary screening method for the optimization of the aerodynamic shapes of bluff body sections.

Based on passive heat and mass transfer enhancement technology, a control method combining a cylindrical obstacle and a flexible beam was proposed to improve heat transfer performance in a microchannel. The optimal layout of a flexible beam was investigated under varying inclination angles of the beam and its spacing distances to the cylindrical obstacle through two-dimensional simulations of heat transfer, fluid and solid interaction. The control mechanism of the flexible beam was qualitatively analyzed from views of flow pattern and structural vibration. It was found that the pressure loss and heat flux should be considered simultaneously, to achieve the best performance of the heat transfer. Results showed that optimal performance occurred when the inclination angle of the beam and its spacing distance to the cylinder took specific values. In such circumstances, the flexible beam’s vibration was amplified by the periodic vortex shedding from the upstream cylinder, without introducing too large a blocking effect. The appropriate control strategy of fluid-structure interaction can enhance the disturbance of the thermal boundary layer and result in the largest thermal enhancement factor.