By considering lane change maneuver as primarily a Partial Observed Markov Decision Process (POMDP) and motion planning problem, this paper presents an interactive model with a Recurrent Neural Network (RNN) approach to determine the adversarial or cooperative intention probability of following vehicle in target lane. To make proper and efficient lane change decision, Deep Q-value network (DQN) is applied to solve POMDP with expected global maximum reward. Then quintic polynomials-based motion planning algorithm is used to obtain both optimal lateral and longitudinal trajectory for autonomous vehicle to pursuit. Experimental results demonstrate the capability of the proposed model to execute lane change maneuver with comfortable and safety reference trajectory at an appropriate time instance and traffic gap in various highway traffic scenarios.

Horizontal wells, extended-reach wells, and multi-branch wells were often used to exploit subsea oil and gas efficiently. However, during the sand control screen completion of those wells, the sand control screen pipe was easily deformed. Failure occurred when passing through the bending section due to the large bending section in the wellbore trajectory. A parametric analysis model of the screen pipe was established based on ABAQUS and Python software under pure bending load first. Then, deformation patterns and mechanisms were identified and discussed. The effects of parameters on the screen pipe bending deformation patterns and the ultimate moment were analyzed. Finally, an empirical formula for calculating the ultimate moment of the screen pipe was established. The results showed that the deformation of the screen pipe was complex, and three deformation patterns were related to the hole parameters. Due to an increase in the diameter and number of circumferential and axial holes, the ultimate moment of the screen pipe gradually decreased, and the circumferential holes had a more significant effect on the ultimate moment than the axial holes. The established empirical formula could accurately calculate the ultimate moment of the screen pipe, and the average difference between the formula and numerical simulation results was 3.25%.