Granted Patent B2

US 12,730,419 · App. 17/956,076 · Granted Sep 8, 2026

Inventors: Benedikt Schmidt (Heidelberg, DE); Ido Amihai (Heppenheim, DE); Arzam Muzaffar Kotriwala (Ladenburg, DE); Moncef Chioua (Montreal, CA); Dennis Janka (Heidelberg, DE); Felix Lenders (Darmstadt, DE); Jan Christoph Schlake (Darmstadt, DE); Martin Hollender (Dossenheim, DE); Hadil Abukwaik (Weinheim, DE); Benjamin Kloepper (Mannheim, DE)

Assignee: ABB Schweiz AG

G05B13/0265G05B19/41835G06N20/00G05B2219/32015

Abstract

Claims (28)

1 . An industrial plant machine learning system, comprising:

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 communication between the machine learning model and the industrial plant using a machine learning markup language;

wherein the industrial plant comprises a distributed control system (DCS), and wherein the abstraction layer is configured to determine plant states by analyzing a code of the DCS to automatically generate a finite state machine for auto-generating the plant states and to provide the plant states as abstracted plant data to the machine learning model;

wherein the machine learning model is configured to use the plant states as data labels for training and machine learning; and

wherein the machine learning model is trained using the plant states and the data labels and the trained machine learning model is used in a process control system or an automation system.

2 . The system of claim 1 , wherein the abstraction layer is configured to use a code expression tree analysis for analyzing the code of the DCS.

3 . The system of claim 1 , wherein the abstraction layer is configured to abstract the machine learning data and plant data.

4 . The system of claim 1 , wherein a connection between the abstraction layer and the industrial plant uses a platform-independent communication technology.

5 . The system of claim 4 , wherein the platform-independent communication technology comprises one of: OPC Unified Architecture (OPC UA) or Message Queuing Telemetry Transport (MQTT).

6 . The system of claim 3 , wherein abstracting the plant data comprises standardizing and abstracting vendor specific parts and industrial plant specific parts using the machine learning markup language.

7 . The system of claim 1 , wherein the abstraction layer is located in an edge device located near the industrial plant.

8 . The system of claim 1 , wherein the abstraction layer comprises an application programming interface (API) that provides standardized access to the plant data.

9 . The system of claim 8 , wherein the API comprises an access control unit providing access control for a user to the industrial plant data and the machine learning data.

10 . A method for industrial plant machine learning communication, comprising:

providing, by a machine learning model, machine learning data;

providing, by an industrial plant, plant data; and

providing, by an abstraction layer that connects the machine learning model and the industrial plant, communication between the machine learning model and the industrial plant using a machine learning markup language;

wherein the industrial plant comprises a distributed control system (DCS), and wherein the method further comprises using the abstraction layer to determine plant states by analyzing a code of the DCS to automatically generate a finite state machine for auto-generating the plant states;

providing the plant states as abstract data to the machine learning model;

using, by the machine learning model, the plant states as labels for training and machine learning;

wherein the trained machine learning model is used in a process control system or an automation system.

11 . The method of claim 10 , further comprises causing the abstraction layer to use a code expression tree analysis for analyzing the code of the DCS.

12 . The method of claim 10 , further comprising using the abstraction layer to abstract the machine learning data and plant data.

13 . The method of claim 12 , wherein abstracting the plant data comprises standardizing and abstracting vendor specific parts and industrial plant specific parts using the machine learning markup language.

14 . The method of claim 10 , wherein the abstraction layer is located in an edge device located near the industrial plant.

Assignments (1)

Continuity (3)

References Cited (87)