Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ADAPTIVE-LEARNING, AUTO-LABELING METHOD AND SYSTEM FOR PREDICTING AND DIAGNOSING WEB BREAKS IN PAPER MACHINE
Document Type and Number:
WIPO Patent Application WO/2021/240257
Kind Code:
A3
Abstract:
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.

Inventors:
RAMU VADTHYAVATH (IN)
PATIL DINESH (IN)
KUBAL NANDKISHOR (IN)
Application Number:
PCT/IB2021/053173
Publication Date:
January 06, 2022
Filing Date:
April 16, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ABB SCHWEIZ AG (CH)
International Classes:
D21F7/04; D21G9/00; G01N33/34; G06V30/194
Foreign References:
US5942689A1999-08-24
US6405140B12002-06-11
US6466877B12002-10-15
JP2005299028A2005-10-27
Other References:
CHUNSHENG YANG ET AL: "Learning to predict train wheel failures", PROCEEDINGS OF THE 11TH. ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING. KDD-2005, CHICAGO, IL, AUG. 21 - 24, 2005, ACM, NEW YORK, NY , US, 21 August 2005 (2005-08-21), pages 516 - 525, XP058100236, ISBN: 978-1-59593-135-1, DOI: 10.1145/1081870.1081929
Download PDF: