Invention Grant
- Patent Title: Anomaly detection in multidimensional sensor data
-
Application No.: US17003088Application Date: 2020-08-26
-
Publication No.: US11893004B2Publication Date: 2024-02-06
- Inventor: Gaurav Pandey , Brian George Buss , Dimitar Petrov Filev
- Applicant: Ford Global Technologies, LLC
- Applicant Address: US MI Dearborn
- Assignee: Ford Global Technologies, LLC
- Current Assignee: Ford Global Technologies, LLC
- Current Assignee Address: US MI Dearborn
- Agency: Bejin Bieneman PLC
- Agent Frank A. MacKenzie
- Main IPC: G06F16/23
- IPC: G06F16/23 ; G06F17/16 ; G05D1/02 ; G05D1/00 ; G01D3/032

Abstract:
A computer includes a processor and a memory storing instructions executable by the processor to receive a time series of vectors from a sensor, determine a weighted moving mean of the vectors, determine an inverse covariance matrix of the vectors, receive a current vector from the sensor, determine a squared Mahalanobis distance between the current vector and the weighted moving mean, and output an indicator of an anomaly with the sensor in response to the squared Mahalanobis distance exceeding a threshold. The squared Mahalanobis distance is determined by using the inverse covariance matrix.
Public/Granted literature
- US20220067020A1 ANOMALY DETECTION IN MULTIDIMENSIONAL SENSOR DATA Public/Granted day:2022-03-03
Information query