Artificial intelligence channel for industrial automation

Patent metadata

Field	Value
Publication number	US-2021096551-A1
Application number	US-201916587187-A
Country	US
Kind code	A1
Filing date	Sep 30, 2019
Priority date	Sep 30, 2019
Publication date	Apr 1, 2021
Grant date	—

Abstract

An industrial data broker system receives contextualized industrial data from one or more industrial devices that support data modeling at the device level. The received industrial data is augmented with contextualization metadata that defines correlations between the data relevant to an analytical objective, and labels specifying analytic topics to which each data item is relevant. The broker system allows external systems, such as analytic systems, to subscribe to topics of interest, and streams a subset of contextualized device data relevant to the topic of interest to the external system for analysis.

First claim

What is claimed is:

1 . An industrial data broker system, comprising:
a memory that stores executable components; and a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:
a device interface component configured to receive industrial data from an industrial device, wherein respective data items of the industrial data are labeled with analytic topics to which the respective data items are relevant;
an analytic system interface component configured to receive subscription data from an external system requesting to subscribe to a topic of the analytic topics; and
a data stream publishing component configured to, in response to receipt of the subscription data, establish a data channel to the external system that streams a subset of the industrial data corresponding to the topic to the external system.

2 . The industrial data broker system of claim 1 , wherein the external system is an industrial analytics system.

3 . The industrial data broker system of claim 1 , wherein the analytic topics comprise at least one of product quality, product throughput, machine runtime, machine downtime, energy consumption, overall equipment effectiveness, or lifecycle management.

4 . The industrial data broker system of claim 1 , wherein the industrial data comprises time-series values of the respective data items of the industrial data and contextualization data defining relationships between data items of the industrial data relevant to a defined business objective.

5 . The industrial data broker system of claim 4 , wherein the defined business objective is at least one of maximization of product output, minimization of machine downtime, minimization of machine faults, optimization of energy consumption, prediction of machine downtime events, determination of a cause of a machine downtime, maximization of product quality, minimization of emissions, identification of factors that yield maximum product quality, identification of factors that yield maximum product output, or identification of factors that yield minimal machine downtime.

6 . The industrial data broker system of claim 4 , wherein the data channel streams, to the external system, a subset of the time-series values and a subset of the contextualization data corresponding to the subset of the industrial data.

7 . The industrial data broker system of claim 6 , wherein
the external system is an analytic system, and the contextualization data comprises at least metadata that defines a type of analytic problem to be solved by the analytics system via analysis of the subset of the industrial data corresponding to the topic.

8 . The industrial data broker system of claim 1 , further comprising a data labeling component configured to apply a label to an item of unlabeled industrial data received by the industrial device component, the label identifying an analytic topic to which the item of unlabeled data is relevant.

9 . The industrial data broker system of claim 8 , wherein the data labeling component is further configured to infer the label to be applied to the item of unlabeled industrial data based on at least one of a determination of a relationship of the item of unlabeled industrial data to other received data items, an analysis of a data model used to structure the industrial data, an analysis of contextual metadata received from other related items of the industrial data, or an identity of the industrial device from which the item of unlabeled industrial data was received.

10 . The industrial data broker system of claim 1 , wherein the device interface components, the analytic system interface component, and the data stream publishing component are implemented as cloud services on a cloud platform.

11 . A method, comprising:
receiving, by a system comprising a processor, industrial data from an industrial device, wherein respective data items of the industrial data comprise labels identifying analytic topics to which the respective data items are relevant; receiving, by the system, subscription data from an external system requesting to subscribe to a topic of the analytic topics; and in response to receiving the subscription data, initiating, by the system, a streaming of a subset of the industrial data corresponding to the topic to the external system.

12 . The method of claim 11 , wherein the receiving the subscription data comprises receiving the subscription data from an industrial analytic system configured to perform analytics on the subset of the industrial data to yield an insight relevant to the topic.

13 . The method of claim 11 , wherein the analytic topics comprise at least one of product quality, product throughput, machine runtime, machine downtime, energy consumption, emissions, overall equipment effectiveness, or lifecycle management.

14 . The method of claim 11 , wherein the initiating the streaming comprises streaming time-series values of the subset of the industrial data corresponding to the topic and contextualization metadata defining relationships between data items of the subset of the industrial data relevant to a defined business objective.

15 . The method of claim 14 , wherein
the external system is an analytic system, and the initiating the streaming comprises streaming, as a portion of the contextualization metadata, metadata that specifies a type of analytic problem to be solved by the analytics system via analysis of the subset of the industrial data corresponding to the topic.

16 . The method of claim 11 , further comprising:
receiving, by the system, unlabeled industrial data from another industrial device; and applying, by the system, a label to an item of the unlabeled industrial data, the label identifying an analytic topic to which the item of unlabeled data is relevant.

17 . The method of claim 16 , further comprising inferring, by the system, the label to be applied to the item of the unlabeled industrial data based on at least one of a determination of a relationship of the item to other received data items, an analysis of a data model used to structure the unlabeled industrial data, an analysis of contextual metadata received from other related items of the unlabeled industrial data, or an identity of the other industrial device from which the item of the unlabeled industrial data was received.

18 . A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause a system comprising a processor to perform operations, the operations comprising:
receiving industrial data from an industrial device, wherein respective data items of the industrial data comprise labels identifying analytic topics to which the respective data items are relevant; receiving subscription data from an external system requesting a subscription to a topic of the analytic topics; and in response to receiving the subscription data, establishing a data channel to the external system that streams a subset of the industrial data corresponding to the topic to the external system.

19 . The non-transitory computer-readable medium of claim 18 , wherein the receiving the subscription data comprises receiving the subscription data from an analytic system configured to perform analytics on the subset of the industrial data to yield an insight relevant to the topic.

20 . The non-transitory computer-readable medium of claim 19 , wherein the data channel streams, to the analytic system, time-series values

Assignees

• Rockwell Automation Tech Inc

Inventors

• Sayyarrodsari Bijan
• Pantaleano Michael
• Lin Ka H
• Weinhofer Juergen K
• Ellis Andrew J
• Crum Kyle
• Chand Sujeet
• Vasko David
• Govindaraj Subbian

Classifications

• H04L67/56

  Provisioning of proxy services (store-and-forward switching systems in data switching networks H04L12/54) · CPC title

• Y02P90/80

  Management or planning · CPC title

• Y02P90/30

  Computing systems specially adapted for manufacturing · CPC title

• G06Q10/0639

  Performance analysis of employees; Performance analysis of enterprise or organisation operations · CPC title

• G06F16/2458

  Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries · CPC title