Adaptive remote maintenance of rolling stocks

摘要

Adaptive remote maintenance of rolling stocks is provided by machine-learning (28) of rules. Existing rules or models are automatically updated. Machine learning (28) is applied to establish a more efficient rule set. Rules may be replaced, generalized, or otherwise adapted based on interaction (26) by the dispatchers with the results of the current rules. The acceptance or discarding of an event by the dispatcher is used as a ground truth for supervised machine learning (28) of a new rule. The machine learning (28) uses user feedback to update the rule set.

主权项

1. A method for adaptive remote maintenance of rolling stocks, the method comprising:
receiving diagnostic information for rolling stock operation; identifying a plurality of events based on a plurality of current rules applied to the diagnostic information, the current rules and corresponding events being for maintenance incidents of the rolling stock; receiving, by a processor, dispensation information showing dispensation of the events relative to the respective current rules, the dispensation corresponding to event validation and event discarding; applying, by the processor, supervised learning to the diagnostic information with the event validation and event discard as ground truth information; and outputting a new rule from the applying of the supervised learning, the new rule being different than any of the current rules.