| CPC G07C 5/006 (2013.01) [G06N 5/02 (2013.01); G07C 5/008 (2013.01); G07C 5/0808 (2013.01); G07C 5/0816 (2013.01)] | 21 Claims |
|
1. A method for a vehicle, the method including the following steps:
generating signals by a plurality of vehicle components of the vehicle during operation of the vehicle and the vehicle components, wherein a first knowledge graph contains information concerning the plurality of vehicle components of the vehicle; and
determining an operating state of a vehicle component from the plurality of vehicle components, the determining including the following steps:
selecting, using the first knowledge graph, a plurality of signals from the signals provided by the vehicle components and selecting one or more state parameters that are necessary for determining the operating state of the vehicle component;
for each respective one of the one of more state parameters that have been selected, calculating a respective value of the respective state parameter based on the selected plurality of signals; and
ascertaining the operating state of the vehicle component based on the calculated values of the one or more state parameters;
wherein the method includes at least one of the following features (I)-(II);
(I) the knowledge graph:
(i) includes: (a) a conceptual model that includes (1) a plurality of concepts, each of the concepts mapping a corresponding one of the vehicle components from the plurality of vehicle components, (2) attributes provided for the concepts, and (3) definitions of relationships of the plurality of concepts with one another; and (b) a plurality of data instances that include data points from the plurality of signals and/or from the respective values of the one or more state parameters, and that are associated with the respective concepts in the conceptual model; and
(ii) is configured to receive the selected signals and the values of the selected state parameters, and to transfer the received signals and the received state parameters into the conceptual model and/or into the data instances, thereby generating the data points of the plurality of data instances of the knowledge graph; and
(II) the method further includes classifying whether the operating state of the vehicle component is abnormal with a malfunction or is normal without the malfunction, based on the ascertained operating state of the vehicle component, and the method further includes at least one of the following features (i)-(iii):
(i) (a) the classifying includes calculating a deviation between the calculated values of the selected one or more state parameters and values of the selected one or more state parameters previously stored in the first knowledge graph, and (b) for each of the state parameters, the first knowledge graph contains an operating state indicator of the abnormal operating state of the vehicle component, as the result of which a plurality of operating state indicators is formed;
(ii) (a) the calculating of the values of the selected one or more state parameters is performed at certain points in time that are specified by a calculation frequency provided by the first knowledge graph and (b) the method further comprises updating, using the first knowledge graph, one or more values of the calculation frequency in response to a classification result obtained from the classifying of the operating state of the vehicle component; and
(iii) the method further comprises transmitting the classified operating state of the vehicle component and a respective one or more of the values of the state parameters that resulted in the operating state of the vehicle component being determined as abnormal with the malfunction, to a second knowledge graph.
|