-
公开(公告)号:US20220357206A1
公开(公告)日:2022-11-10
申请号:US17871064
申请日:2022-07-22
Applicant: ABB Schweiz AG
Inventor: Joerg Gebhardt , Stephan Wildermuth , Ralf Gitzel , Kai Koenig , Joerg Ostrowski , Patrik Reto Kaufmann , Boguslaw Samul
IPC: G01J5/00 , G06T7/00 , H04N5/247 , G01R31/327
Abstract: A system for monitoring a switchgear includes multiple infrared cameras with fields of view; a processing unit; and an output unit. The cameras acquire multiple image data of a plurality of phases of the switchgear, and the processing unit determines whether there is a phase imbalance in a specific phase comprising a determination from a plurality of image data that temperature information for a plurality of component parts and/or a plurality of connections for that specific phase has an overall enhanced temperature compared to the temperature information for the same plurality of component parts and/or the same plurality of connections for one or more other phases of the plurality of phases. The output unit is configured to output information that a fault or load imbalance has occurred in a phase.
-
公开(公告)号:US20210397837A1
公开(公告)日:2021-12-23
申请号:US17465882
申请日:2021-09-03
Applicant: ABB Schweiz AG
Inventor: Subanatarajan Subbiah , Ralf Gitzel , Benedikt Schmidt
Abstract: An apparatus for monitoring a switchgear includes: an input unit; a processing unit; and an output unit. The input unit is provides the processing unit with a monitor infra-red image of a switchgear. The processing unit implements a machine learning classifier algorithm to analyse the monitor infra-red image and determine if there is one or more anomalous hot spots in the switchgear. The machine learning classifier algorithm has been trained based on a plurality of different training images, the plurality of training images including a plurality of synthetic infra-red images generated by an image processing algorithm. The output unit outputs information relating to the one or more anomalous hot spots.
-