公开(公告)号：US11880192B2

公开(公告)日：2024-01-23

申请号：US17228730

申请日：2021-04-13

Applicant: ABB Schweiz AG

Inventor： Dennis Janka ,  Moncef Chioua ,  Pablo Rodriguez ,  Mario Hoernicke ,  Benedikt Schmidt ,  Benjamin Kloepper

IPC: G05B19/418 ,  G06F30/18 ,  H04L41/12 ,  H04L41/14

CPC classification number: G05B19/41865 ,  G05B19/4183 ,  G05B19/4185 ,  G05B19/41885 ,  G06F30/18 ,  H04L41/12 ,  H04L41/145

Abstract: A method for determining an interdependency between a plurality of elements in an industrial processing system includes: providing a process flow diagram (PFD) of a topology of the processing system; transforming the PFD into a directed graph, each element of the plurality of elements being transformed into a node and each relation between the plurality of elements being transformed into a directed edge; selecting one node of the plurality of nodes as a starting node; and constructing a subgraph, the subgraph including all the nodes that are forward-connected from the starting node so as to show at least one interdependency between the plurality of elements in the subgraph.

公开(公告)号：US20230029400A1

公开(公告)日：2023-01-26

申请号：US17957609

申请日：2022-09-30

Applicant: ABB Schweiz AG

Inventor： Benedikt Schmidt ,  Ido Amihai ,  Arzam Muzaffar Kotriwala ,  Moncef Chioua ,  Dennis Janka ,  Felix Lenders ,  Jan Christoph Schlake ,  Martin Hollender ,  Hadil Abukwaik ,  Benjamin Kloepper

IPC: G06N20/00

Abstract: A method of hierarchical machine learning includes receiving a topology model having information on hierarchical relations between components of the industrial plant, determining a representation hierarchy comprising a plurality of levels, wherein each representation on a higher level represents a group of representations on a lower level, wherein the representations comprise a machine learning model, and training an output machine learning model using the determined hierarchical representations.

公开(公告)号：US20230019404A1

公开(公告)日：2023-01-19

申请号：US17956117

申请日：2022-09-29

Applicant: ABB Schweiz AG

Inventor： Benjamin Kloepper ,  Benedikt Schmidt ,  Ido Amihai ,  Moncef Chioua ,  Jan Christoph Schlake ,  Arzam Muzaffar Kotriwala ,  Martin Hollender ,  Dennis Janka ,  Felix Lenders ,  Hadil Abukwaik

IPC: G06N20/20

Abstract: A computer-implemented method for automating the development of industrial machine learning applications includes one or more sub-methods that, depending on the industrial machine learning problem, may be executed iteratively. These sub-methods include at least one of a method to automate the data cleaning in training and later application of machine learning models, a method to label time series (in particular signal data) with help of other timestamp records, feature engineering with the help of process mining, and automated hyper-parameter tuning for data segmentation and classification.