A train control system (100) controls the ramp rate at which a train (102) accelerates after braking. A machine learning engine receives training data from a data acquisition hub (312), including a plurality of input conditions of the train (102) and a plurality of outputs associated with the input conditions. A virtual system modeling engine (324) simulates in-train forces and train (102) operational characteristics using physics-based equations, kinematic or dynamic modeling of behavior of the train or components of the train during operation of the train when the train is accelerating after braking, and inputs derived from stored historical contextual data related to the train. The machine learning engine trains a learning system using the training data to generate an output based on an input using a learning function including at least one learning parameter. The learning parameter is modified as needed to improve the accuracy of the learning function in generating the output.
Artificial intelligence based ramp rate control for a train
2022-09-29
Patent
Elektronische Ressource
Englisch
ARTIFICIAL INTELLIGENCE BASED RAMP RATE CONTROL FOR A TRAIN
Europäisches Patentamt | 2021
|ARTIFICIAL INTELLIGENCE BASED RAMP RATE CONTROL FOR A TRAIN
Europäisches Patentamt | 2021
|Train entry warning system by artificial intelligence
Europäisches Patentamt | 2021
|Control prompting system for limiting ramp starting of train
Europäisches Patentamt | 2021
|