Imperfections in the wheel-rail contact are one of the main sources of generation of railway vibrations. Consequently, it is essential to take expensive corrective maintenance measures, the results of which may be unk...Imperfections in the wheel-rail contact are one of the main sources of generation of railway vibrations. Consequently, it is essential to take expensive corrective maintenance measures, the results of which may be unknown. In order to assess the effectiveness of these measures, this paper develops a vehicle-track interaction model in the time domain of a curved track with presence of rail corrugation on the inner rail. To characterize the behavior of the track, a numerical finite element model is developed using ANSYS software, while the behavior of the vehicle is characterized by a unidirectional model of two masses developed with VAMPIRE PRO software. The overloads obtained with the dynamic model are applied to the numerical model and then, the vibrational response of the track is obtained. Results are validated with real data and used to assess the effectiveness of rail grinding in the reduction of wheel-rail forces and the vibration generation phenomenon.展开更多
Future unconstrained and science-driven missions to Mars will require advanced guidance algorithms that are able to adapt to more demanding mission requirements, e.g. landing on selected locales with pinpoint accuracy...Future unconstrained and science-driven missions to Mars will require advanced guidance algorithms that are able to adapt to more demanding mission requirements, e.g. landing on selected locales with pinpoint accuracy while autonomously flying fuel-efficient trajectories. In this paper, a novel guidance algorithm designed by applying the principles of reinforcement learning(RL) theory is presented. The goal is to devise an adaptive guidance algorithm that enables robust, fuel efficient,and accurate landing without the need for off line trajectory generation and real-time tracking. Results from a Monte Carlo simulation campaign show that the algorithm is capable of autonomously following trajectories that are close to the optimal minimum-fuel solutions with an accuracy that surpasses that of past and future Mars missions. The proposed RL-based guidance algorithm exhibits a high degree of flexibility and can easily accommodate autonomous retargeting while maintaining accuracy and fuel efficiency. Although reinforcement learning and other similar machine learning techniques have been previously applied to aerospace guidance and control problems(e.g., autonomous helicopter control), this appears, to the best of the authors knowledge, to be the first application of reinforcement learning to the problem of autonomous planetary landing.展开更多
文摘Imperfections in the wheel-rail contact are one of the main sources of generation of railway vibrations. Consequently, it is essential to take expensive corrective maintenance measures, the results of which may be unknown. In order to assess the effectiveness of these measures, this paper develops a vehicle-track interaction model in the time domain of a curved track with presence of rail corrugation on the inner rail. To characterize the behavior of the track, a numerical finite element model is developed using ANSYS software, while the behavior of the vehicle is characterized by a unidirectional model of two masses developed with VAMPIRE PRO software. The overloads obtained with the dynamic model are applied to the numerical model and then, the vibrational response of the track is obtained. Results are validated with real data and used to assess the effectiveness of rail grinding in the reduction of wheel-rail forces and the vibration generation phenomenon.
文摘Future unconstrained and science-driven missions to Mars will require advanced guidance algorithms that are able to adapt to more demanding mission requirements, e.g. landing on selected locales with pinpoint accuracy while autonomously flying fuel-efficient trajectories. In this paper, a novel guidance algorithm designed by applying the principles of reinforcement learning(RL) theory is presented. The goal is to devise an adaptive guidance algorithm that enables robust, fuel efficient,and accurate landing without the need for off line trajectory generation and real-time tracking. Results from a Monte Carlo simulation campaign show that the algorithm is capable of autonomously following trajectories that are close to the optimal minimum-fuel solutions with an accuracy that surpasses that of past and future Mars missions. The proposed RL-based guidance algorithm exhibits a high degree of flexibility and can easily accommodate autonomous retargeting while maintaining accuracy and fuel efficiency. Although reinforcement learning and other similar machine learning techniques have been previously applied to aerospace guidance and control problems(e.g., autonomous helicopter control), this appears, to the best of the authors knowledge, to be the first application of reinforcement learning to the problem of autonomous planetary landing.
