公开(公告)号：US10606251B2

公开(公告)日：2020-03-31

申请号：US15545722

申请日：2016-01-22

Applicant: ABB Schweiz AG

Inventor： Jinendra Gugaliya ,  Naveen Bhutani ,  Nandkishor Kubal ,  Kaushik Ghosh ,  Moncef Chioua

IPC: G05B17/02 ,  G05B19/418 ,  G05B19/042 ,  G05B19/05 ,  G05B23/02

Abstract: The present invention discloses a method for controlling a process in a process plant using a controller. The method comprises receivable associated with the process, determining a first value of at least one key performance indicator associated with the transition from the process data of the first process variable between the first steady state and the second steady state, comparing the determined first value of the at least one key performance indicator against a threshold value of the at least one key performance indicator; and determining a correction factor for modifying a set point of the process variable based on the comparison, for controlling the process.

公开(公告)号：US20240102242A1

公开(公告)日：2024-03-28

申请号：US17993924

申请日：2022-11-24

Applicant: ABB Schweiz AG

Inventor： Vadthyavath Ramu ,  Dinesh Patil ,  Nandkishor Kubal

IPC: D21F7/04 ,  D21G9/00 ,  G06F30/27

CPC classification number: D21F7/04 ,  D21G9/0054 ,  G06F30/27

Abstract: A system and method for labelling normal and abnormal regions in data related to a paper machine for web break prediction and labelling individual parameters for root cause analysis, using machine learning models, includes using the machine learning models in real-time to predict breaks in the paper web, analyzing root cause for the breaks in the paper web, and estimating a time to break. An auto-data-labeling framework helps in adaptive learning for autonomous model improvement of the deployed model, transfer learning, shortlisting parameters and automating feasibility study.

公开(公告)号：US10429823B2

公开(公告)日：2019-10-01

申请号：US15539653

申请日：2015-12-29

Applicant: ABB Schweiz AG

Inventor： Jinendra Gugaliya ,  Naveen Bhutani ,  Kaushik Ghosh ,  Nandkishor Kubal ,  Vinay Kariwala ,  Wilhelm Wiese

IPC: G05B19/4063 ,  G05B19/418 ,  G05B23/02 ,  G10L15/26

Abstract: The invention provides a method for identifying a sequence of events associated with a condition in a process plant using a control system. The method comprises recording process data, which is timestamped, and recording audio input from each personnel of a plurality of personnel of the process plant. The audio input is synchronized according to time with the process data. A keyword is identified from the temporally synchronized content of each audio input, and compared with the process information of one or more of an event and an equipment, for identifying at least one of a new process information and a supplementary process information related to the condition. One or more of the new process information and the supplementary process information identified for each keyword, and the plurality of events identified from the process data, are used for identifying the sequence of events associated with the condition.