Industrial Plant Machine Learning System

Patent metadata

Field	Value
Publication number	US-2023019201-A1
Application number	US-202217956076-A
Country	US
Kind code	A1
Filing date	Sep 29, 2022
Priority date	Mar 31, 2020
Publication date	Jan 19, 2023
Grant date	—

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.

First claim

What is claimed is:

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

2 . The system of claim 1 , wherein the abstraction layer is configured to enrich the received plant data with context data, and wherein the context data comprises plant states.

3 . The system of claim 2 , wherein the industrial plant comprises a distributed control system (DCS), and wherein the abstraction layer is configured to determine the context data by analyzing a code of the DCS to automatically generate a finite state machine for auto-generating the plant states.

4 . The system of claim 3 , wherein the abstraction layer is configured to use a code expression tree analysis for analyzing the code of the DCS.

5 . The system of claim 2 , wherein the machine learning model is configured to use the plant states as labels for training the machine learning model.

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

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

8 . The system of claim 7 , wherein the platform-independent communication technology comprises one of: OPC Unified Architecture (OPC UA) or Message Queuing Telemetry Transport (MQTT).

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

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

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

12 . The system of claim 11 , wherein the API comprises an access control unit providing access control for a user to the industrial plant data and the machine learning data.

13 . 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, standardized communication between the machine learning model and the industrial plant using a machine learning markup language.

14 . The method of claim 13 , wherein the abstraction layer is configured to enrich the received plant data with context data, and wherein the context data comprises plant states.

15 . The method of claim 14 , wherein the industrial plant comprises a distributed control system (DCS), and wherein the method further comprises using the abstraction layer to determine the context data by analyzing a code of the DCS to automatically generate a finite state machine for auto-generating the plant states.

16 . The method of claim 15 , further comprises causing the abstraction layer to use a code expression tree analysis for analyzing the code of the DCS.

17 . The method of claim 14 , further comprising using the plant states as labels for training the machine learning model in the machine learning model.

18 . The method of claim 13 , further comprising using the abstraction layer to abstract the machine learning data and the plant data.

19 . The method of claim 18 , wherein abstracting the plant data comprises standardizing and abstracting vendor specific parts and industrial plant specific parts using the machine learning markup language.

20 . The method of claim 13 , wherein the abstraction layer is located in an edge device located near the industrial plant.

Assignees

• Abb Schweiz Ag

Inventors

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

Classifications

• Y02P90/80

  Management or planning · CPC title

• G06N3/082 Primary

  modifying the architecture, e.g. adding, deleting or silencing nodes or connections · CPC title

• G05B2219/32352

  Modular modeling, decompose large system in smaller systems to simulate · CPC title

• G05B13/0265 Primary

  the criterion being a learning criterion · CPC title

• G05B19/41885

  characterised by modeling, simulation of the manufacturing system · CPC title