公开(公告)号：US20240305572A1

公开(公告)日：2024-09-12

申请号：US18589535

申请日：2024-02-28

Applicant: ABB Schweiz AG

Inventor： Jan Christoph Schlake ,  Santonu Sarkar ,  Marie Christin Platenius-Mohr ,  Madapu Amarlingam ,  Reuben Borrison

IPC: H04L47/2441 ,  H04L67/1097 ,  H04L67/12

CPC classification number: H04L47/2441 ,  H04L67/1097 ,  H04L67/12

Abstract: A method for providing an efficient communication in a hierarchical network of distributed devices includes collecting first data from a first client device sent by a sensor via a second communication interface; storing the first data in a data storage; determining metadata of the first data; receiving a requirement information of the first data; generating classification information of the first data according to the metadata and the requirement information; providing the classification information to a master device and/or to a second client device according to a rule; and updating the classification information when the first data is changed.

公开(公告)号：US20230023896A1

公开(公告)日：2023-01-26

申请号：US17957592

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: G05B19/418 ,  G06N20/00

Abstract: A method of transfer learning for a specific production process of an industrial plant includes providing data templates defining expected data for a production process, and providing plant data, wherein the data templates define groupings for the expected data according to their relation in the industrial plant; determining a process instance and defining a mapping with the plant data; determining historic process data; determining training data using the determined process instance and the determined historic process data, wherein the training data comprises a structured data matrix, wherein columns of the data matrix represent the sensor data that are grouped in accordance with the data template and wherein rows of the data matrix represent timestamps of obtaining the sensor data; providing a pre-trained machine learning model using the determined process instance; and training a new machine learning model using the provided pre-trained model and the determined training data.

公开(公告)号：US20230016668A1

公开(公告)日：2023-01-19

申请号：US17954485

申请日：2022-09-28

Applicant: ABB Schweiz AG

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

IPC: G05B13/02 ,  G06N3/08

Abstract: A method includes training a first control model by utilizing a first set of input data as first input, resulting in a trained first control model; copying the trained first control model to a second control model, wherein, after copying, the second input layer and the plurality of second hidden layers is identical to the plurality of first hidden layers, and the first output layer is replaced by the second output layer; freezing the plurality of second hidden layers; training the second control model by utilizing the first set of input data as second input, resulting in a trained second control model; and running the trained second control model by utilizing a second set of input data as second input, wherein the second output outputs the quality measure of the first control model.

公开(公告)号：US20210349453A1

公开(公告)日：2021-11-11

申请号：US17382387

申请日：2021-07-22

Applicant: ABB Schweiz AG

Inventor： Jan Christoph Schlake ,  Mario Hoernicke ,  Dirk Schulz

IPC: G05B19/418

Abstract: A method for generating a dynamic model of an industrial plant having: a plurality of physical processes that are dependent such that an outcome of at least one first process is fed into at least one second process; a plurality of low-level controllers, each controller acting upon at least one physical process such that at least one process variable of the at least one physical process is controlled to match a set-point of the low-level controller; and a plurality of sensors, each sensor measuring at least one process variable of one of the physical processes, and/or of the plant as a whole, the set-points of the low-level controllers and current values of the process variables measured by the sensors being the inputs of the model, and predicted future values of the process variables that are likely to result from applying the set-points to the low-level controllers being the outputs.

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.

公开(公告)号：US12298751B2

公开(公告)日：2025-05-13

申请号：US17382387

申请日：2021-07-22

Applicant: ABB Schweiz AG

Inventor： Jan Christoph Schlake ,  Mario Hoernicke ,  Dirk Schulz

IPC: G05B19/418 ,  G05B13/04

Abstract: A method for generating a dynamic model of an industrial plant having: a plurality of physical processes that are dependent such that an outcome of at least one first process is fed into at least one second process; a plurality of low-level controllers, each controller acting upon at least one physical process such that at least one process variable of the at least one physical process is controlled to match a set-point of the low-level controller; and a plurality of sensors, each sensor measuring at least one process variable of one of the physical processes, and/or of the plant as a whole, the set-points of the low-level controllers and current values of the process variables measured by the sensors being the inputs of the model, and predicted future values of the process variables that are likely to result from applying the set-points to the low-level controllers being the outputs.

公开(公告)号：US20240303131A1

公开(公告)日：2024-09-12

申请号：US18598379

申请日：2024-03-07

Applicant: ABB Schweiz AG

Inventor： Santonu Sarkar ,  Marie Christin Platenius-Mohr ,  Jan Christoph Schlake ,  Madapu Amarlingam ,  Nafise Eskandani ,  Reuben Borrison

IPC: G06F9/50

CPC classification number: G06F9/505

Abstract: A computer-implemented method for orchestrating execution of workloads on nodes includes determining a set of requirements for resources needed for execution of the workload; determining for each compute node an availability of the resources required; establishing multiple candidate configurations having an assignment of each compute workload to at least one pair of a compute node and a working class, wherein different working classes differ at least in the degree of retention of the compute workload in memory and/or in at least one cache of the compute node after execution; computing for each candidate configuration at least one figure of merit with respect to at least one given optimization goal; and determining a candidate configuration with the best figure of merit as the optimal configuration.

公开(公告)号：US20230019201A1

公开(公告)日：2023-01-19

申请号：US17956076

申请日：2022-09-29

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: G05B13/02

Abstract: An industrial plant machine learning system includes a machine learning model, providing machine learning data, an industrial plant providing plant data and an abstraction layer, connecting the machine learning model and the industrial plant, wherein the abstraction layer is configured to provide standardized communication between the machine learning model and the industrial plant, using a machine learning markup language.

公开(公告)号：US20240303208A1

公开(公告)日：2024-09-12

申请号：US18598067

申请日：2024-03-07

Applicant: ABB Schweiz AG

Inventor： Santonu Sarkar ,  Marie Christin Platenius-Mohr ,  Madapu Amarlingam ,  Jan Christoph Schlake ,  Reuben Borrison

IPC: G06F13/362

CPC classification number: G06F13/362

Abstract: A system and method for enabling an efficient data processing in a distributed network of devices includes collecting first data from at least one client device sent by at least one plant device via a first communication interface; storing the first data in a data storage; profiling the first data to obtain characteristic information of the collected first data; determining a data processing strategy upon a result of the characteristic information of the first data; processing the first data according to the data processing strategy and deciding which data of the first data need to be sent to the master device via a second communication interface.