Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND SYSTEM FOR INDUSTRIAL ANOMALY DETECTION
Document Type and Number:
WIPO Patent Application WO/2020/250247
Kind Code:
A3
Abstract:
The disclosure relates to anomaly detection in an industrial environment including multiple industrial units and systems, generating huge volume of data. The conventional methods rely only on sensor data alone. The techniques of handling missing data plays a crucial role in determining the performance of industrial anomaly detection system. Further, imputation of missing data could cause error in computation, thus affecting the accuracy of the industrial anomaly detection system. The present disclosure addresses the problems associated with missing data by utilizing a masking technique. Further, the present disclosure utilizes quantitative and qualitative metadata associated with industrial system along with the sensor data to improve anomaly detection performance. Furthermore, the present disclosure includes a model recommendation system which provides transfer learning based utilization of existing models for similar industrial systems.

Inventors:
RATHORE PRADEEP (IN)
BASAK ARGHYA (IN)
NISTALA SRI HARSHA (IN)
RUNKANA VENKATARAMANA (IN)
Application Number:
PCT/IN2020/050521
Publication Date:
May 06, 2021
Filing Date:
June 12, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
TATA CONSULTANCY SERVICES LTD (IN)
International Classes:
G05B11/01; G06F11/34; H04L12/26
Attorney, Agent or Firm:
GEHLOT, Aditi et al. (IN)
Download PDF: