公开(公告)号：US20190165989A1

公开(公告)日：2019-05-30

申请号：US15822784

申请日：2017-11-27

Applicant: ABB Schweiz AG

Inventor： Sam Ade Jacobs ,  Mithun P. Acharya ,  Veronika Domova ,  Marcel Dix ,  Aldo Dagnino ,  Jinendra K. Gugaliya ,  Kaushik Ghosh

IPC: H04L12/24 ,  G08B29/18 ,  G05B23/02

Abstract: Unique systems, methods, techniques and apparatuses of an alarm management system are disclosed herein. One exemplary embodiment is a method for monitoring an industrial plant comprising determining a sequence of alarm events for each of a plurality of time intervals including a first alarm event of a plurality of alarm events and a second alarm event of the plurality of alarm events; determining a count of the first alarm events and second alarm events; determining the alarm events exceed a support threshold value; determining a third count of a sub-sequence of the sequences of alarm events including the first alarm event followed by the second alarm event in response to determining the first count and the second count exceeds the support threshold value; determining a ratio using the first count, the second count, and the third count exceeds a display threshold value; and displaying the sub-sequence.

公开(公告)号：US20250086514A1

公开(公告)日：2025-03-13

申请号：US18929807

申请日：2024-10-29

Applicant: ABB Schweiz AG

Inventor： Benjamin Kloepper ,  Dawid Ziobro ,  Divyasheel Sharma ,  Benedikt Schmidt ,  Yemao Man ,  Gayathri Gopalakrishnan ,  Joakim Astrom ,  Marcel Dix ,  Arzam Muzaffar Kotriwala

IPC: G06N20/00

Abstract: A method for deciding on a machine learning model result quality based on the identification of distractive samples in the training data includes providing a first result of the model based on initial training data; determining a first performance of the first result of the model; logging input data; providing a second result of the model based on initial training data and the input data, determining a second performance of the second result of the model and thereon based identifying erroneous data within the input data and/or the training data.

公开(公告)号：US12235628B2

公开(公告)日：2025-02-25

申请号：US17535724

申请日：2021-11-26

Applicant: ABB Schweiz AG

Inventor： Marcel Dix ,  Katharina Stark ,  Roland Braun ,  Michael Vach ,  Sten Gruener ,  Mario Hoernicke ,  Nicolai Schoch

IPC: G05B19/418

Abstract: A computer-implemented resource management method for modular plants may include: receiving data identifying a required module type to be assembled into the modular plant as part of a module pipeline including one or more modules; and executing an optimization algorithm to select, from a plurality of modules having the required module type, a module for inclusion in the module pipeline on the basis of one or more predetermined optimization criteria.

公开(公告)号：US12140936B2

公开(公告)日：2024-11-12

申请号：US17520738

申请日：2021-11-08

Applicant: ABB Schweiz AG

Inventor： Mario Hoernicke ,  Katharina Stark ,  Roland Braun ,  Michael Vach ,  Sten Gruener ,  Nicolai Schoch ,  Marcel Dix

IPC: G05B19/418

Abstract: A method for configuring a modular industrial plant using an engineering tool includes using a plant engineering facility of the tool to create a representation of the modular industrial plant identifying modules to be orchestrated in the modular industrial plant. The modules include at least one function module that includes control software for the modular industrial plant. The method further includes using a module engineering facility of the tool to configure the function module for use in the modular industrial plant by editing a placeholder configuration file created by the tool for defining the configuration of the function module. Editing the configuration file causes a representation of the function module in the plant engineering facility to be automatically updated to reflect adaptations made to the function module using the module engineering facility. The method includes instructing the tool to assign the function modules so configured to the modular industrial plant.

公开(公告)号：US20240302831A1

公开(公告)日：2024-09-12

申请号：US18669696

申请日：2024-05-21

Applicant: ABB Schweiz AG

Inventor： Hadil Abukwaik ,  Divyasheel Sharma ,  Benjamin Kloepper ,  Arzam Muzaffar Kotriwala ,  Pablo Rodriguez ,  Benedikt Schmidt ,  Ruomu Tan ,  Chandrika K R ,  Reuben Borrison ,  Marcel Dix ,  Jens Doppelhamer

IPC: G05B23/02

CPC classification number: G05B23/024 ,  G05B23/0251

Abstract: A method for determining the state of health of an industrial process executed by at least one industrial plant comprising an arrangement of entities, and the state of each such entity, includes obtaining values of the entity state variables; providing the values to a model to obtain a prediction of the state of health; determining propagation paths for anomalies between said entities; determining importances of the states of health of the individual entities for the overall state of health of the process; and aggregating the individual states of health of the entities to obtain the overall state of health of the process.

公开(公告)号：US20230393538A1

公开(公告)日：2023-12-07

申请号：US18452313

申请日：2023-08-18

Applicant: ABB Schweiz AG

Inventor： Dawid Ziobro ,  Jens Doppelhamer ,  Benedikt Schmidt ,  Simon Hallstadius Linge ,  Gayathri Gopalakrishnan ,  Pablo Rodriguez ,  Benjamin Kloepper ,  Reuben Borrison ,  Marcel Dix ,  Hadil Abukwaik ,  Arzam Muzaffar Kotriwala ,  Sylvia Maczey ,  Marco Gaertler ,  Divyasheel Sharma ,  Chandrika K R ,  Matthias Berning

IPC: G05B13/02 ,  G05B23/02

CPC classification number: G05B13/0265 ,  G05B23/0216 ,  G05B2223/02

Abstract: A method for providing a solution strategy for a current event in industrial process automation includes monitoring a process for events and recording manual user action data, upon occurrence of an event, acquiring the recorded data regarding manual user actions before, during, and after the occurrence of the event, learning a procedure for handling the event based on the acquired data, and applying the learnt procedure to a currently occurring event.

公开(公告)号：US20210264317A1

公开(公告)日：2021-08-26

申请号：US17317926

申请日：2021-05-12

Applicant: ABB Schweiz AG

Inventor： Pablo Rodriguez ,  Benjamin Kloepper ,  Arzam Muzaffar Kotriwala ,  Marcel Dix ,  Debora Clever ,  Fan Dai

IPC: G06N20/00 ,  G06F30/20 ,  B25J9/16

Abstract: A method for applying machine learning to an application includes: a) generating a candidate policy by a learner; b) executing a program in at least one simulated application based on a set of candidate parameters provided based on the candidate policy and a state of the at least one simulated application, execution of the program providing interim results of tested sets of candidate parameters based on a measured performance information of the execution of the program; c) collecting a predetermined number of interim results and providing an end result based on a combination of the candidate parameters and/or the state with the measured performances information by a trainer; and d) generating a new candidate policy by the learner based on the end result.

公开(公告)号：US11069356B2

公开(公告)日：2021-07-20

申请号：US16988732

申请日：2020-08-10

Applicant: ABB Schweiz AG

Inventor： Andrew Cohen ,  Benedikt Schmidt ,  Benjamin Kloepper ,  Marco Gaertler ,  Arzam Kotriwala ,  Marcel Dix ,  Sylvia Maczey

IPC: G10L15/22 ,  G10L15/30 ,  G05B19/042

Abstract: A computer system for controlling a dialogue between a user and the computer system, the computer system being communicatively coupled with an industrial control system controlling an industrial system, the computer system including: an interface for receiving intent inputs representing a respective desired interaction with the computer system; an intent determination module for determining the desired interactions of received intent inputs; a data storage for storing one or more directed graphs, each graph specifying an industrial control domain specific dialogue, a particular graph defining a dialogue state machine with a plurality of nodes representing states of the dialogue, and with edges representing transitions between the states, each state transition from a first state to a second state depending on at least one precondition, the desired interaction of a received intent input corresponding to a target node to be reached from a current node of the particular graph.

公开(公告)号：US20210166684A1

公开(公告)日：2021-06-03

申请号：US16988732

申请日：2020-08-10

Applicant: ABB Schweiz AG

Inventor： Andrew Cohen ,  Benedikt Schmidt ,  Benjamin Kloepper ,  Marco Gaertler ,  Arzam Kotriwala ,  Marcel Dix ,  Sylvia Maczey

IPC: G10L15/22 ,  G10L15/30 ,  G05B19/042

Abstract: A computer system for controlling a dialogue between a user and the computer system, the computer system being communicatively coupled with an industrial control system controlling an industrial system, the computer system including: an interface for receiving intent inputs representing a respective desired interaction with the computer system; an intent determination module for determining the desired interactions of received intent inputs; a data storage for storing one or more directed graphs, each graph specifying an industrial control domain specific dialogue, a particular graph defining a dialogue state machine with a plurality of nodes representing states of the dialogue, and with edges representing transitions between the states, each state transition from a first state to a second state depending on at least one precondition, the desired interaction of a received intent input corresponding to a target node to be reached from a current node of the particular graph.

公开(公告)号：US20250111767A1

公开(公告)日：2025-04-03

申请号：US18899108

申请日：2024-09-27

Applicant: ABB Schweiz AG

Inventor： Marcel Dix

IPC: G08B25/00 ,  G08B21/18

Abstract: A method for managing alarms in a distributed control system, wherein the method comprises the following steps: monitoring at least one process parameter, activating an alarm when the process parameter exceeds an alarm threshold, deactivating an alarm when the process parameter no longer exceeds the alarm threshold, and determining by an AI based alarm control system before the alarm is activated at least one predicted alarm information, which comprises information about whether the alarm threshold will be exceeded.