Invention Grant
- Patent Title: Method for detection and isolation of faulty sensors
-
Application No.: US15277814Application Date: 2016-09-27
-
Publication No.: US11940318B2Publication Date: 2024-03-26
- Inventor: Carlos Alberto Cavichioli Gonzaga , Luiz Felipe Willcox de Souza , Luiz Ricardo Douat , Rafael Horschutz Nemoto
- Applicant: GE Oil & Gas UK, Ltd.
- Applicant Address: GB Aberdeen
- Assignee: Baker Hughes Energy Technology UK Limited
- Current Assignee: Baker Hughes Energy Technology UK Limited
- Current Assignee Address: GB Bristol
- Agency: Hogan Lovells US LLP
- Main IPC: G06F11/30
- IPC: G06F11/30 ; G01F1/34 ; G01F1/68 ; G01F1/696 ; G01F25/00 ; G01F25/10 ; G05B23/02
Abstract:
Technical effects of the invention include use of a data-driven multivariate statistical method for the detection and isolation of sensor faults applied in a virtual flow metering context. In one implementation, the data-driven multivariate statistical method employs principal components analysis, weighted squared prediction error, and partial decomposition contribution plots.
Public/Granted literature
- US20180087954A1 METHOD FOR DETECTION AND ISOLATION OF FAULTY SENSORS Public/Granted day:2018-03-29
Information query
