Siemens Aktiengesellschaft

Ekkehard Toensing

Frank Popp

Thomas Mueller

Dirk Punstein

Erhard Fischer

Christian Schulze

Mathaeus Dejori

Ciprian Dan Raileanu

A method and a system for diagnosing the operating state of one or more railroad components of a railroad network for rail transport. The railroad components each have at least a first measuring device for measuring first measurement values of at least one measurement variable for describing the operating state of the railroad component. The novel method includes the following steps: measuring the first measurement values by way of the first measuring device; measuring additional, second measurement values, which are independent of the operating state of the railroad components, by way of at least one additional, second measuring device; transmitting the measurement values to a control center situated along the tracks; evaluating the measurement values in the control center by way of a predefined algorithm, and providing at least one result of the evaluation as an output.

Method for diagnosing railroad components of a railroad network for rail transport

A method and a system for diagnosing one or more rail vehicles, each of which has at least one measuring device for measuring measurement values of at least one measurement variable. The method includes the following steps: measuring measurement values by way of at least one measuring device of at least one rail vehicle; transmitting the measurement values from the rail vehicle to a control center situated along the track; evaluating the measurement values in the control center by means of a predefined algorithm, and providing a result of the evaluation as an output.

Diagnostic method for rail vehicles

Adaptive remote maintenance of rolling stocks is provided by machine-learning () of rules. Existing rules or models are automatically updated. Machine learning () is applied to establish a more efficient rule set. Rules may be replaced, generalized, or otherwise adapted based on interaction () 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 () of a new rule. The machine learning () uses user feedback to update the rule set.

Adaptive remote maintenance of rolling stocks

Growing community of inventors

Hausen, Germany

Ekkehard Toensing