Method and apparatus for diagnosing and monitoring vehicles, vehicle components and routes
A method and apparatus for diagnosing and monitoring vehicles, vehicle components, routes and route components, wherein at least one first sensor is used to perform measurements and at least one computing unit is used to effect signal processing, where the at least one computing unit is supplied with at least measured first signals, at least one first characteristic value is formed from the at least first signals, the at least one first characteristic value or at least one first characteristic value combination is classified via at least one first statistical model, or a prediction is performed, and where at least one technical first condition indicator for at least one first vehicle component or at least one route component is determined, such that safe detection of faults, damage, excess wear, etc., and effective, condition-oriented maintenance of vehicles and infrastructures are achieved.
1 . A method for diagnosing and monitoring vehicles, vehicle components, routes and route components via an apparatus including at least one first sensor arranged on a bogie of the vehicle, at least one second sensor, at least one third sensor, and including at least one computer provided within the vehicle and connected to the at least one first, second and third sensors, the at least one computer including a plurality of statistical models, the at least one first sensor performing measurements during operation of the vehicle, and the at least one computer performing signal processing during operation of the vehicle, the method comprising:
operating the vehicle and supplying at least measured first, second and third signals to the at least one computer;
forming, by the at least one computer during operation of the vehicle, at least one first, at least one second and at least one third characteristic value from the at least measured first, second and third signals, the at least one first, at least one second and at least one third characteristic value being inserted into the plurality of statistical models, a first statistical model of the plurality of statistical models being trained from first and second reference characteristic values and a second statistical model of the plurality of statistical models being trained from first and third reference characteristic values;
classifying, continuously by the at least one computer during operation of the vehicle, the at least one first, at least one second and at least one third characteristic value or at least one combination of the at least one first characteristic value via a prediction based on one of the at least one first, at least one second and at least one third characteristic value and the combination of the at least one first, at least one second and at least one third characteristic value;
determining, by the at least one computer during operation of the vehicle, one of (i) at least one technical first state indicator for at least one first vehicle component and (ii) at least one route component from one of at least one classification result and at least one prediction result during operation of the vehicle to reduce risks associated with false alarms;
transmitting data including the at least one technical first state indicator from at least one of said forming, classifying and determining to an infrastructure-based device comprising a service platform and evaluating the transmitted data including the at least one technical first state indicator at the infrastructure-based device; and
performing state-oriented servicing or maintenance of vehicles or infrastructure at the service platform based on the at least one technical first state indicator.
2 . The method as claimed in claim 1 , wherein the at least one technical first state indicator is determined from a frequency distribution for one of classification results and prediction results.
3 . The method as claimed in claim 2 , wherein the at least one first characteristic value is formed as a statistical characteristic value referenced to one of a route section and a time period.
4 . The method as claimed in claim 1 , wherein the at least one first characteristic value is formed as a statistical characteristic value referenced to one of a route section and a time period.
5 . The method as claimed in claim 1 , wherein the at least one first statistical model is formed via a machine learning method.
6 . The method as claimed in claim 5 , wherein the at least one first characteristic value or the at least one first characteristic value combination is classified via a support vector machine method.
7 . The method as claimed in claim 6 , wherein reference characteristic values are formed as learning data from reference signals processed chronologically before the at least measured first signals.
8 . The method as claimed in claim 5 , wherein reference characteristic values are formed as learning data from reference signals processed chronologically before the at least measured first signals.
9 . The method as claimed in claim 1 , wherein the at least one first statistical model is formed based on an equalization calculation.
10 . The method as claimed in claim 9 , wherein the at least one first characteristic value is inserted into a regression function.
11 . The method as claimed in claim 1 , wherein the at least one first state indicator is assigned a first probability value for an occurrence of a technical state which is indicated by at least one of (i) the at least one classification result and (ii) the at least one prediction result.
12 . The method according to claim 11 , wherein the first probability value is formed from a frequency of a specific classification result referenced to a total number of classification results.
13 . The method as claimed in claim 1 , wherein one to n3 state indicators having one to n4 probability values are formed from signals from one to n1 signal categories and one to n2 characteristic values ascertained therefrom; and wherein each of the one to n3 state indicators is assigned one of the one to n4 probability values and a combination state indicator having an assigned combination probability value is formed from the one to n4 probability values.
14 . The method as claimed in claim 13 , wherein each of the one to n4 probability values is formed from a frequency of a specific classification result referenced to a total number of classification results.
15 . The method as claimed in claim 14 , wherein the combination probability value (P K ) is formed as a conditional probability from the one to n4 probability values.
16 . The method as claimed in claim 14 , wherein the combination state indicator is formed via a probabilistic graphical model.
17 . The method as claimed in claim 13 , wherein the combination probability value is formed as a conditional probability from the one to n4 probability values.
18 . The method as claimed in claim 17 , wherein the combination state indicator is formed via a probabilistic graphical model.
19 . The method as claimed in claim 13 , wherein the combination state indicator is formed via a probabilistic graphical model.
20 . The method as claimed in claim 19 , wherein the probabilistic graphical model is formed based on a machine learning method.
21 . The method as claimed in claim 1 , wherein at least one second characteristic value and a technical second state indicator for the at least one first vehicle component are formed from second signals.
22 . The method as claimed in claim 1 , wherein at least one second characteristic value and a technical second state indicator for a second vehicle component are formed from second signals.
23 . The method as claimed in claim 1 , wherein data from at least one method step are utilized in an on-board diagnoser and/or monitor of a vehicle.
24 . The method as claimed in claim 1 , wherein said monitoring and diagnosing of the vehicles, vehicle components, routes and route components are performed for rail vehicles and infrastructures of rail vehicles.
25 . An apparatus comprising:
at least one first sensor arranged on a bogie of a vehicle;
at least one second sensor;
at least one third sensor; and
at least one computer provided within the vehicle and connected to the at least one first, second and third sensors, the at least one computer including a plurality of statistical models;
wherein the at least one computer is configured to:
receive at least measured first, second and third signals during operation of the vehicle;
form, during operation of the vehicle, at least one first, at least one second and at least one third characteristic value from the at least measured first, second and third signals, the at least one first, at least one second and at least one third characteristic value being inserted into the plurality of statistical models, a first statistical model of the plurality of statistical models being trained from first and second reference characteristic values and a second statistical model of the plurality of statistical models being trained from first and third reference characteristic values;
classify, continuously during operation of the vehicle, the at least one first, at least one second and at least one third characteristic value or at least one combination of the at least one first, at least one second and at least one third characteristic value via a prediction based on one of the at least one first, at least one second and at least one third characteristic value and the combination of the at least one first, at least one second, and at least one third characteristic value; and
determine one of (i) at least one technical first state indicator for at least one first vehicle component and (ii) at least one route component from one of at least one classification result and at least one prediction result during operation of the vehicle to reduce risks associated with false alarms;
wherein data including the at least one technical first state indicator from at least one of said formation, classification and determination is transmitted to an infrastructure-based device comprising a service platform and the transmitted data including the at least one technical first state indicator is evaluated at the infrastructure-based device; and
wherein the at least one technical first state indicator is utilized for state-oriented servicing or maintenance of vehicles or infrastructure at the service platform.
26 . The apparatus as claimed in claim 25 , wherein the at least one computer is provided in a coach body of the vehicle.
27 . The apparatus as claimed in claim 26 , further comprising:
at least one data transmitter provided within or on the vehicle and connected to the at least one computer for providing data transmission.
28 . The apparatus as claimed in claim 25 , further comprising:
at least one data transmitter provided within or on the vehicle and connected to the at least one computer for providing data transmission.