The present disclosure provides a method and system for controlling a heavy-haul train based on reinforcement learning. The method includes: obtaining operation state information of a heavy-haul train at a current time point; obtaining a heavy-haul train action of a next time point according to the operation state information of the heavy-haul train at the current time point and a heavy-haul train virtual controller, and sending the heavy-haul train action of the next time point to a heavy-haul train control unit to control operation of the heavy-haul train. The heavy-haul train virtual controller is obtained by training a reinforcement learning network according to operation state data of the heavy-haul train and an expert strategy network; the reinforcement learning network includes one actor network and two critic networks; the reinforcement learning network is constructed according to a soft actor-critic (SAC) reinforcement learning algorithm.

A speed control device that controls a speed of a train using a tacho-generator includes a calculating unit that calculates, when a pulse count signal obtained by conversion from an AC voltage signal that is outputted from the tacho-generator and corresponds to a rotating speed of a wheel of the train cannot be detected, a first speed using notch information, route data, and car characteristic data and calculates, when the pulse count signal can be detected, a second speed using the pulse count signal. The speed control device includes a position calculating unit that calculates a position of the train using the speed calculated by the calculating unit.

A speed control device that controls a speed of a train using a tacho-generator includes a calculating unit that calculates, when a pulse count signal obtained by conversion from an AC voltage signal that is outputted from the tacho-generator and corresponds to a rotating speed of a wheel of the train cannot be detected, a first speed using notch information, route data, and car characteristic data and calculates, when the pulse count signal can be detected, a second speed using the pulse count signal. The speed control device includes a position calculating unit that calculates a position of the train using the speed calculated by the calculating unit.

An anti-collision system for railcars and locomotives provides a distance ranging and worker coupling protection system utilizing remote-sensing radar techniques for use with a locomotive and railcar. The anti-collision system may include an object detector device attached to a railcar or a locomotive that detects objects in a path of the railcar and the locomotive and a train display device electrically connected to the object detector device. The anti-collision system may also include an emergency action device which enables a crew member to stop the railcar or locomotive without communication to a locomotive operator when a hazard is recognized. The object detector device may include a remote sensor, a radio, and a microprocessor programmed to include data-logging to record and log all data from the anti-collision system.

An anti-collision system for railcars and locomotives provides a distance ranging and worker coupling protection system utilizing remote-sensing radar techniques for use with a locomotive and railcar. The anti-collision system may include an object detector device attached to a railcar or a locomotive that detects objects in a path of the railcar and the locomotive and a train display device electrically connected to the object detector device. The anti-collision system may also include an emergency action device which enables a crew member to stop the railcar or locomotive without communication to a locomotive operator when a hazard is recognized. The object detector device may include a remote sensor, a radio, and a microprocessor programmed to include data-logging to record and log all data from the anti-collision system.

An examining system includes one or more application devices onboard a vehicle system. The application devices may electrically conduct an examination signal into one or more conductive bodies extending along a route and may include a catenary, a third rail, and/or a cable. The examining system may include one or more detection units that may be disposed onboard the vehicle system and that may monitor one or more electrical characteristics of the one or more conductive bodies in response to the examination signal being conducted into the one or more conductive bodies. The examining system may include an identification unit that may examine the one or more electrical characteristics of the one or more conductive bodies monitored by the one or more detection units to identify a compromised or damaged section of the one or more conductive bodies.

An examining system includes one or more application devices onboard a vehicle system. The application devices may electrically conduct an examination signal into one or more conductive bodies extending along a route and may include a catenary, a third rail, and/or a cable. The examining system may include one or more detection units that may be disposed onboard the vehicle system and that may monitor one or more electrical characteristics of the one or more conductive bodies in response to the examination signal being conducted into the one or more conductive bodies. The examining system may include an identification unit that may examine the one or more electrical characteristics of the one or more conductive bodies monitored by the one or more detection units to identify a compromised or damaged section of the one or more conductive bodies.

A train control system uses sensory inputs related to operational parameters of a train for automatically scoring or classifying particular train driving strategies implemented by a machine learning model for a particular train operating on a predefined route or route segment. The train control system includes one or more predefined rules related to one or more of a first set of the operational parameters, wherein each of the rules defines a Boolean, true or false classification based on whether a particular train driving strategy results in one or more of the first set of operational parameters complying with the rule. One or more comparative key performance indicators are related to one or more of a second set of operational parameters, and are used to rank the particular train driving strategy for the predefined route or route segment relative to a different train driving strategy for the same or comparable route or route segment.

A train control system uses sensory inputs related to operational parameters of a train for automatically scoring or classifying particular train driving strategies implemented by a machine learning model for a particular train operating on a predefined route or route segment. The train control system includes one or more predefined rules related to one or more of a first set of the operational parameters, wherein each of the rules defines a Boolean, true or false classification based on whether a particular train driving strategy results in one or more of the first set of operational parameters complying with the rule. One or more comparative key performance indicators are related to one or more of a second set of operational parameters, and are used to rank the particular train driving strategy for the predefined route or route segment relative to a different train driving strategy for the same or comparable route or route segment.

A method for operating a train comprising two or more locomotives, the method comprising the steps of: a) Setting one or more locomotive control levels and choosing a selected route of travel; b) Calculating a target train speed profile and a target in-train force profile over at least a portion of the selected route; c) Measuring one or more operating parameters related to the operation of the train; d) Calculating a future train speed profile and a future in-train force profile for a future period based on at least one of the one or more operating parameters, at least one of the one or more locomotive control levels and one or more pieces of information relating to the selected route; e) Calculating adjusted locomotive speed control levels relating to the one or more operating parameters based on a difference between the target train speed profile and the future train speed profile, the adjusted locomotive control levels being adapted to maintain the target train speed profile over the future period; f) Calculating adjusted in-train force control levels relating to the one or more operating parameters based on a difference between the target in-train force profile and the future in-train force profile, the adjusted in-train force control levels being adapted to maintain the target in-train force profile below a target level over the future period; g) Dividing the adjusted locomotive control levels and the adjusted in-train force control levels between the two or more locomotives to form locomotive-specific locomotive control levels for each of the two or more locomotives, the locomotive-specific locomotive control levels being at least partially adapted to control and/or balance in-train force levels below the target level h) Provide locomotive-specific locomotive control levels for communication to each of the two or more locomotives; and i) Operating each of the two or more locomotives according to the locomotive-specific locomotive control levels.