In Greece extended cracking of twin-block concrete sleepers （ties） and fouling of the ballast-bed were observed with implied problems of gauge widening and deterioration of track＇s geometry. This led to a ten-year ...In Greece extended cracking of twin-block concrete sleepers （ties） and fouling of the ballast-bed were observed with implied problems of gauge widening and deterioration of track＇s geometry. This led to a ten-year investigation program, during which a new method was developed for the estimation of actions on track panel as well as of the pressures / stresses that develop under the seating surface of the sleeper on the ballast-bed. Results from the tests performed on the ballast used in the Greek network are also presented, conducted in laboratories in France, Austria, and Greece. The influence of the actions -static and mainly dynamic- on the track response and the stress and strain of the ballast-bed are also discussed as derived from the tests and theoretical analysis.展开更多
Seasonally cold climate and resulting frost action set great demands to railway track substructure in order to maintain Irack geomelry. Chal- lenges culminate on high-speed lines, where the tolerances for roughness ar...Seasonally cold climate and resulting frost action set great demands to railway track substructure in order to maintain Irack geomelry. Chal- lenges culminate on high-speed lines, where the tolerances for roughness are the tightest. Problems may result in highly increased Irack maintenance and need for temporary speed reslrictions. The causes of frost action can be associated with subsoil, subballast or ballast. The major concern in frost protection is to avoid the freezing of frost susceptible subsoil by using sufficient thickness of subballast and relying on non-fi＇ost-susctible subballast material. This paper provides an overview of the main research findings on the role of ballast, subballast and subsoil in frost acedon. In new comlruclion the material specificalions, design procedures and construction methods have been developed to ensure adequate performance of Irack subscatt, but special challenges exist in managing existing Wacks that were not designed for modem requirements. In order to perform cost-effective and sustainable track maintenance, it is necessary to recognize the problem areas and define the root-causes of problems. For locating the problem sections and defining the causes of defects, a sophisticated analysis based on integration of track geometry and ground penetrating radar （GPR） data has been developed and is summarized in this paper,展开更多
The performance of the state-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient, and Soft Actor-Critic for generating a quadruped walking gai...The performance of the state-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient, and Soft Actor-Critic for generating a quadruped walking gait in a virtual environment was presented in previous research work titled “A Comparison of PPO, TD3, and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation”. We demonstrated that the Soft Actor-Critic Reinforcement algorithm had the best performance generating the walking gait for a quadruped in certain instances of sensor configurations in the virtual environment. In this work, we present the performance analysis of the state-of-the-art Deep Reinforcement algorithms above for quadruped walking gait generation in a physical environment. The performance is determined in the physical environment by transfer learning augmented by real-time reinforcement learning for gait generation on a physical quadruped. The performance is analyzed on a quadruped equipped with a range of sensors such as position tracking using a stereo camera, contact sensing of each of the robot legs through force resistive sensors, and proprioceptive information of the robot body and legs using nine inertial measurement units. The performance comparison is presented using the metrics associated with the walking gait: average forward velocity (m/s), average forward velocity variance, average lateral velocity (m/s), average lateral velocity variance, and quaternion root mean square deviation. The strengths and weaknesses of each algorithm for the given task on the physical quadruped are discussed.展开更多
文摘In Greece extended cracking of twin-block concrete sleepers （ties） and fouling of the ballast-bed were observed with implied problems of gauge widening and deterioration of track＇s geometry. This led to a ten-year investigation program, during which a new method was developed for the estimation of actions on track panel as well as of the pressures / stresses that develop under the seating surface of the sleeper on the ballast-bed. Results from the tests performed on the ballast used in the Greek network are also presented, conducted in laboratories in France, Austria, and Greece. The influence of the actions -static and mainly dynamic- on the track response and the stress and strain of the ballast-bed are also discussed as derived from the tests and theoretical analysis.
基金Finnish Transport Agency for enabling the research
文摘Seasonally cold climate and resulting frost action set great demands to railway track substructure in order to maintain Irack geomelry. Chal- lenges culminate on high-speed lines, where the tolerances for roughness are the tightest. Problems may result in highly increased Irack maintenance and need for temporary speed reslrictions. The causes of frost action can be associated with subsoil, subballast or ballast. The major concern in frost protection is to avoid the freezing of frost susceptible subsoil by using sufficient thickness of subballast and relying on non-fi＇ost-susctible subballast material. This paper provides an overview of the main research findings on the role of ballast, subballast and subsoil in frost acedon. In new comlruclion the material specificalions, design procedures and construction methods have been developed to ensure adequate performance of Irack subscatt, but special challenges exist in managing existing Wacks that were not designed for modem requirements. In order to perform cost-effective and sustainable track maintenance, it is necessary to recognize the problem areas and define the root-causes of problems. For locating the problem sections and defining the causes of defects, a sophisticated analysis based on integration of track geometry and ground penetrating radar （GPR） data has been developed and is summarized in this paper,
文摘The performance of the state-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient, and Soft Actor-Critic for generating a quadruped walking gait in a virtual environment was presented in previous research work titled “A Comparison of PPO, TD3, and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation”. We demonstrated that the Soft Actor-Critic Reinforcement algorithm had the best performance generating the walking gait for a quadruped in certain instances of sensor configurations in the virtual environment. In this work, we present the performance analysis of the state-of-the-art Deep Reinforcement algorithms above for quadruped walking gait generation in a physical environment. The performance is determined in the physical environment by transfer learning augmented by real-time reinforcement learning for gait generation on a physical quadruped. The performance is analyzed on a quadruped equipped with a range of sensors such as position tracking using a stereo camera, contact sensing of each of the robot legs through force resistive sensors, and proprioceptive information of the robot body and legs using nine inertial measurement units. The performance comparison is presented using the metrics associated with the walking gait: average forward velocity (m/s), average forward velocity variance, average lateral velocity (m/s), average lateral velocity variance, and quaternion root mean square deviation. The strengths and weaknesses of each algorithm for the given task on the physical quadruped are discussed.
