The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Oct. 03, 2017

Filed:

Jan. 15, 2014
Applicant:

Hitachi, Ltd., Chiyoda-ku, Tokyo, JP;

Inventors:

Hisae Shibuya, Tokyo, JP;

Shunji Maeda, Tokyo, JP;

Assignee:

Hitachi, Ltd., Tokyo, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 11/20 (2006.01); G06T 7/00 (2017.01); G05B 23/02 (2006.01); F01D 25/00 (2006.01); G01M 15/14 (2006.01); G06K 9/46 (2006.01); G06K 9/52 (2006.01); G06K 9/62 (2006.01); F01D 21/00 (2006.01); F01D 21/14 (2006.01);
U.S. Cl.
CPC ...
G06T 7/001 (2013.01); F01D 21/003 (2013.01); F01D 21/14 (2013.01); F01D 25/00 (2013.01); G01M 15/14 (2013.01); G05B 23/0235 (2013.01); G06K 9/46 (2013.01); G06K 9/52 (2013.01); G06K 9/627 (2013.01); G06K 9/6215 (2013.01); G06K 9/6267 (2013.01); G06K 9/6272 (2013.01); G06T 11/206 (2013.01); F05D 2260/80 (2013.01); F05D 2270/708 (2013.01); G06K 2009/4666 (2013.01); Y02T 50/671 (2013.01);
Abstract

To sensing an anomaly on the basis of a multi-dimensional time series sensor signal, in order to determine the next action for a countermeasure, survey, or the like, the present invention is configured such that a multi-dimensional feature vector for each time is extracted on the basis of a sensor signal, a reference feature vector for each time is extracted on the basis of a set of characteristic vectors for a predetermined learning period and the characteristic vector of each time, an anomaly measure is calculated on the basis of the difference between the feature vectors for the times and the reference feature vectors, an anomaly is detected by comparing the anomaly measure and a predetermined threshold value, and the anomaly-related sensor for the time the anomaly is detected is identified on the basis of a 2-dimensional distribution density of feature values.


Find Patent Forward Citations

Loading…