Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 9:00 AM CET
Settings

Settings

Goto Application

1. WO2021240257 - ADAPTIVE-LEARNING, AUTO-LABELING METHOD AND SYSTEM FOR PREDICTING AND DIAGNOSING WEB BREAKS IN PAPER MACHINE

Publication Number WO/2021/240257
Publication Date 02.12.2021
International Application No. PCT/IB2021/053173
International Filing Date 16.04.2021
IPC
D21F 7/04 2006.1
DTEXTILES; PAPER
21PAPER-MAKING; PRODUCTION OF CELLULOSE
FPAPER-MAKING MACHINES; METHODS OF PRODUCING PAPER THEREON
7Other details of machines for making continuous webs of paper
04Paper-break control devices
D21G 9/00 2006.1
DTEXTILES; PAPER
21PAPER-MAKING; PRODUCTION OF CELLULOSE
GCALENDERS; ACCESSORIES FOR PAPER-MAKING MACHINES
9Other accessories for paper-making machines
G01N 33/34 2006.1
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
33Investigating or analysing materials by specific methods not covered by groups G01N1/-G01N31/131
34Paper
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
D21F 7/04
DTEXTILES; PAPER
21PAPER-MAKING; PRODUCTION OF CELLULOSE
FPAPER-MAKING MACHINES; METHODS OF PRODUCING PAPER THEREON
7Other details of machines for making continuous webs of paper
04Paper-break control devices
D21G 9/0009
DTEXTILES; PAPER
21PAPER-MAKING; PRODUCTION OF CELLULOSE
GCALENDERS; ACCESSORIES FOR PAPER-MAKING MACHINES
9Other accessories for paper-making machines
0009Paper-making control systems
D21G 9/0054
DTEXTILES; PAPER
21PAPER-MAKING; PRODUCTION OF CELLULOSE
GCALENDERS; ACCESSORIES FOR PAPER-MAKING MACHINES
9Other accessories for paper-making machines
0009Paper-making control systems
0054details of algorithms or programs
G06K 9/6257
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
6257characterised by the organisation or the structure of the process, e.g. boosting cascade
G06K 9/6264
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6262Validation, performance evaluation or active pattern learning techniques
6263based on the feedback of a supervisor
6264the supervisor being an automated "intelligent" module, e.g. "intelligent oracle"
G06V 30/194
Applicants
  • ABB SCHWEIZ AG [CH]/[CH]
Inventors
  • RAMU, Vadthyavath
  • PATIL, Dinesh
  • KUBAL, Nandkishor
Priority Data
20204102195926.05.2020IN
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) ADAPTIVE-LEARNING, AUTO-LABELING METHOD AND SYSTEM FOR PREDICTING AND DIAGNOSING WEB BREAKS IN PAPER MACHINE
(FR) PROCÉDÉ ET SYSTÈME D'APPRENTISSAGE ADAPTATIF ET D'AUTO-ÉTIQUETAGE POUR PRÉDIRE ET DIAGNOSTIQUER DES RUPTURES DE BANDE DANS UNE MACHINE À PAPIER
Abstract
(EN) Embodiments of the present invention discloses methods and a system (103) for labelling normal and abnormal regions in the data related to a paper machine (101) tor web break prediction and labelling individual parameters for root cause analysis, using machine learning models. Further, the present invention relates to training machine learning models to predict web breaks and root, causes for the web breaks using the labels generated. Thereafter, the present invention comprises using the machine learning models in real-time to predict breaks in the paper web, analyse root cause for the breaks in the paper web and estimate a time to break. Proposed auto-data-labe!ing framework helps in adaptive learning for autonomous model improvement of the deployed model, transfer learning, shortlisting parameters and automates feasibility study.
(FR) Des modes de réalisation de la présente invention concernent des procédés et un système (103) pour étiqueter des régions normales et anormales dans les données relatives à une machine à papier (101) pour la prédiction de rupture de bande et pour étiqueter des paramètres individuels pour une analyse des causes profondes, à l'aide de modèles d'apprentissage automatique. En outre, la présente invention concerne des modèles d'apprentissage automatique d'entraînement pour prédire les ruptures de bande et les causes profondes des ruptures de bande à l'aide des étiquettes générées. Par la suite, la présente invention consiste à utiliser les modèles d'apprentissage automatique en temps réel pour prédire des ruptures de la bande de papier, analyser les causes profondes des ruptures de la bande de papier et estimer un temps de rupture. Le cadre d'auto-étiquetage de données proposé aide à l'apprentissage adaptatif pour l'amélioration de modèle autonome du modèle déployé, l'apprentissage par transfert, les paramètres de présélection et automatise l'étude de faisabilité.
Latest bibliographic data on file with the International Bureau