Geo-defect repair modeling with location uncertainty is provided. A method includes logically dividing a railroad network into segments each of a specified length. The method also includes identifying, via a computer processor, geo-defects and approximated locations of the geo-defects occurring at each inspection run for each of the segments. The method also includes calculating, via the computer processor, a rate of increase in amplitude of each of the geo-defects for each of the segments between inspection runs, determining a correlation of the geo-defects between the inspection runs as a function of the approximated locations, and predicting a deterioration rate for each of the geo-defects based on the calculating.

A method for carrying out a test process relating to a rail vehicle achieves a fast-working, flexible, and in the event of a misdetection, precise monitoring environment, in particular without complex system or architectural adjustments to the rail vehicle. A stationary control unit and a simulation unit are provided on the land side. A data connection is established between the stationary control unit and the rail vehicle. A data connection is established between the stationary control unit and the simulation unit. The test process includes providing data traffic between the stationary control unit and the rail vehicle and the simulation unit. A device for carrying out a test process relating to a rail vehicle is also provided.

A method (600) for generating schedules for railroad vehicles travelling within a railroad network using a genetic algorithm (GA) (100), through operation of at least one processor (82), includes providing an initial population (200) of initial schedules (220), each schedule (220) having first information of a railroad track network and second information of railroad vehicles travelling in the railroad track network for a specific time instance, selecting multiple schedules of the initial schedules (220), and generating a final population (480) of final schedules (420) utilizing crossover operation (400) between selected initial schedules (220), wherein the second information of the railroad vehicles travelling in the railroad track network are exchanged between the selected initial schedules (220).

A method and an apparatus for a train control system are disclosed, and are based on virtualization of train control logic and the use of cloud computing resources. A train control system is configured into two main parts. The first part includes physical elements of the train control system, and the second part includes a virtual train control system that provides the computing resources for the required train control application platforms. The disclosed architecture can be used with various train control technologies, including communications based train control, cab-signaling and fixed block, wayside signal technology. Further, the disclosure describes methodologies to convert cab-signaling and manual operations into distance to go operation.

A method of controlling one or more locomotives in a train includes using a machine learning engine and a virtual system modeling engine to model and classify sections of track along which the train is traveling according to the tractive power needs for the train traversing each section of track as a function of an effective weight profile for the train in the section and an effective friction profile for the train in the section of track. The method includes using the results of the effective weight profile, the effective friction profile, and an effective power availability profile to train the virtual system modeling engine using the machine learning engine to model designated areas of the track where the total tractive effort force or dynamic braking force applied by all of the locomotives in the train is less than a tractive effort force or dynamic braking force, respectively, that can be provided by a subset of the available locomotives in the train.

A method of controlling one or more locomotives in a train includes using a machine learning engine and a virtual system modeling engine to model and classify sections of track along which the train is traveling according to the tractive power needs for the train traversing each section of track as a function of an effective weight profile for the train in the section and an effective friction profile for the train in the section of track. The method includes using the results of the effective weight profile, the effective friction profile, and an effective power availability profile to train the virtual system modeling engine using the machine learning engine to model designated areas of the track where the total tractive effort force or dynamic braking force applied by all of the locomotives in the train is less than a tractive effort force or dynamic braking force, respectively, that can be provided by a subset of the available locomotives in the train.

A train control system minimizes in-train forces in a train with a hybrid consist including a diesel-electric locomotive and a battery electric locomotive. The train control system includes a virtual in-train forces modeling engine configured to simulate in-train forces and train operational characteristics using physics-based equations, kinematic or dynamic modeling of behavior of the train or components of the train when the train is accelerating, and inputs derived from stored historical contextual data characteristic of the train, and a virtual in-train forces model database configured to store in-train forces models. Each of the in-train forces models includes a mapping between combinations of the stored historical contextual data and corresponding simulated in-train forces and train operational characteristics that occur when the consist is changing speed. An energy management system determines an easing function of tractive effort vs. time that will minimize the in-train forces created by changes in tractive effort responsive to power notch changes in a diesel-electric locomotive, and commands execution of the easing function by a battery electric locomotive based at least in part on an in-train forces model with simulated in-train forces and train operational characteristics that fall within a predetermined acceptable range of values.

A train control system minimizes in-train forces in a train with a hybrid consist including a diesel-electric locomotive and a battery electric locomotive. The train control system includes a virtual in-train forces modeling engine configured to simulate in-train forces and train operational characteristics using physics-based equations, kinematic or dynamic modeling of behavior of the train or components of the train when the train is accelerating, and inputs derived from stored historical contextual data characteristic of the train, and a virtual in-train forces model database configured to store in-train forces models. Each of the in-train forces models includes a mapping between combinations of the stored historical contextual data and corresponding simulated in-train forces and train operational characteristics that occur when the consist is changing speed. An energy management system determines an easing function of tractive effort vs. time that will minimize the in-train forces created by changes in tractive effort responsive to power notch changes in a diesel-electric locomotive, and commands execution of the easing function by a battery electric locomotive based at least in part on an in-train forces model with simulated in-train forces and train operational characteristics that fall within a predetermined acceptable range of values.

A simulator device uses, among passenger action ratios linked to selection conditions, a passenger action ratio that is linked to a selection condition matching the type of moving body stopping in a simulation for a traffic system to calculate the number of people alighting from the moving body and/or the number of people boarding the moving body.

A simulator device uses, among passenger action ratios linked to selection conditions, a passenger action ratio that is linked to a selection condition matching the type of moving body stopping in a simulation for a traffic system to calculate the number of people alighting from the moving body and/or the number of people boarding the moving body.