Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021059302 - METHOD AND SYSTEM FOR DIAGNOSING ANOMALY IN A MANUFACTURING PLANT

Publication Number WO/2021/059302
Publication Date 01.04.2021
International Application No. PCT/IN2020/050829
International Filing Date 26.09.2020
IPC
G16Z 99/00 2019.01
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
ZINFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
99Subject matter not provided for in other main groups of this subclass
CPC
G05B 23/024
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
23Testing or monitoring of control systems or parts thereof
02Electric testing or monitoring
0205by means of a monitoring system capable of detecting and responding to faults
0218characterised by the fault detection method dealing with either existing or incipient faults
0224Process history based detection method, e.g. whereby history implies the availability of large amounts of data
024Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
G05B 23/0283
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
23Testing or monitoring of control systems or parts thereof
02Electric testing or monitoring
0205by means of a monitoring system capable of detecting and responding to faults
0259characterized by the response to fault detection
0283Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
Applicants
  • TATA CONSULTANCY SERVICES LIMITED [IN]/[IN]
Inventors
  • BASAK, Arghya
  • RATHORE, Pradeep
  • NISTALA, Sri Harsha
  • RUNKANA, Venkatramana
Agents
  • GEHLOT, Aditi
  • GOYAL, Kamal Kant
Priority Data
20192103838327.09.2019IN
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD AND SYSTEM FOR DIAGNOSING ANOMALY IN A MANUFACTURING PLANT
(FR) PROCÉDÉ ET SYSTÈME POUR DIAGNOSTIQUER UNE ANOMALIE DANS UNE INSTALLATION DE FABRICATION
Abstract
(EN)
Industrial plants involve a large amount of equipment, which generate a large amount of data. By analyzing this data, the operator can diagnose anomaly in the plant. Analyzing this data is difficult and time taking task. A method and system for diagnosing anomaly in an industrial system in a time efficient and convenient manner has been provided. The system is configured to diagnose the anomaly by finding out one or more sensors responsible for the anomaly. The present disclosure treats the anomaly detection model as a score generating function. Whenever for a particular instance the score given by the anomaly detection model crosses a pre-determined threshold, anomaly is reported and the diagnosis algorithm is triggered. The system is configured to diagnose the anomaly predicted in case of time series as well as non-time series data.
(FR)
Les installations industrielles impliquent une grande quantité d'équipements, qui génèrent une grande quantité de données. En analysant ces données, l'opérateur peut diagnostiquer une anomalie dans l'installation. L'analyse de ces données est difficile et représente une tâche chronophage. L'invention concerne un procédé et un système pour diagnostiquer une anomalie dans un système industriel d'une manière efficace dans le temps et pratique. Le système est conçu pour diagnostiquer l'anomalie par la découverte d'un ou plusieurs capteurs responsables de l'anomalie. La présente invention traite le modèle de détection d'anomalie en tant que fonction de génération de score. Pour une instance particulière, à chaque fois que le score obtenu par le modèle de détection d'anomalie dépasse un seuil prédéfini, une anomalie est rapportée et l'algorithme de diagnostic est déclenché. Le système est conçu pour diagnostiquer l'anomalie prédite dans le cas de données de séries chronologiques ainsi que de séries non chronologiques.
Latest bibliographic data on file with the International Bureau