| CPC G01R 31/62 (2020.01) | 19 Claims |
|
19. A system, comprising:
a power transformer comprising multiple transformer components;
a measurement system for the power transformer, the measurement system comprising: multiple sensors that are each designed to record a physical and/or chemical property of the power transformer, and are each coupled to at least one of the transformer components of the power transformer by way of a respective related direct or indirect connection, the physical and/or chemical property of the power transformer configured to be recorded by the respective sensor being influenced by at least one of the transformer components; and
a measurement device comprising:
a signal input interface directly or indirectly coupled to the measurement system;
a processor unit; and
a storage unit,
wherein the signal input interface is configured to receive a status signal of the measurement system, the status signal representing multiple, different status variables, each status variable being associated with at least one of the sensors,
wherein each status variable is in a functional relationship with at least one of the transformer components, each status variable representing a status state of the property of the power transformer recorded by the at least one associated sensor as a normal state or as an abnormal state;
wherein a dataset is stored by the storage unit, the dataset having a related first probability value for each status variable relating to a likelihood that the respective status variable represents an incorrect state, the dataset having a related second probability value for each transformer component relating to a likelihood that an error has occurred in the respective transformer component, the dataset having a related third probability value for each of the functional relationships from one of the transformer components to one of the status variables relating to a likelihood that an error causes an abnormal state of the respective status variable in the respective transformer component, and
wherein the processor unit is configured to determine a related error probability value for each transformer component, relating to the likelihood that an error has occurred in the respective transformer component, on the basis of a Bayesian network, which represents a directional graph from the transformer components to the status variables based on the first, second and third probability values, and on the basis of the status states represented by the status variables.
|