US 10,877,464 B2Granted

Discovery of relationships in a scalable industrial analytics platform

AssigneeRockwell Automation Technologies, Inc.

InventorsKevin Chao, Pradeep Kaushik, Richard W. Sze, John A. Genovesi

Life of this patent

Estimating the term…

Loading patent…

Abstract

A scalable industrial data ingestion and analysis architecture integrates and collects data from multiple diverse sources at one or more industrial facilities. Data sources can include plant-level industrial devices and higher-level business systems. The data can be integrated and collected from multiple sources at an on-premise edge or gateway device, which sends the data to event queues on the cloud platform. The data queues orchestrate and store the data on cloud storage, and an analytics layer performs business analytics or other types of analysis on the stored data to produce various outcomes. Similar analytic platforms can also be implemented at the device level, and analytic functions can be scaled between the device level and higher levels in accordance with the scope of a given analytic function.

Claims20

Dependent claims

A 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, from industrial devices and systems at one or more industrial facilities, data files of different file types, wherein
the data files comprise two or more of spreadsheet files, log files, database files, streaming data, power monitor data, image data from a camera or an optical scanner, energy matrix data, data files from an inventory system, maintenance schedule data, or purchase order data, and
the data files comprise metadata identifying names of data fields within which the data items are located;
a data queueing component configured to store the data files in one or more event queues of a cloud platform;
a discovery component configured to classify data items contained in the data files to yield classified data items, and to identify correlations between the classified data items based in part on identified correlations between subsets of the metadata;
a metadata generation component configured to generate relationship metadata identifying the correlations between the classified data items;
and
an analysis component configured to generate a model of normal operator behavior relative to an operator task based on a monitoring of a subset of the data items and relationship metadata relating to operator activities, and to identify incorrect operator behavior relative to the operator task based on a comparison of monitored operator behavior data with the model.

8 more elements

A method, comprising:

receiving, by a system comprising a processor, data files generated by industrial devices and industrial systems, wherein the data files are formatted according to different file types, and the receiving the data files comprises receiving at least two of spreadsheet files, log files, database files, streaming data, power monitor data, image data from a camera or an optical scanner, energy matrix data, data files from an inventory system, maintenance schedule data, or purchase order data;
storing, by the system, the data files in one or more event queues of a cloud platform;
classifying, by the system, data items contained in the data files to yield classified data items;
identifying, by the system, correlations between the classified data items, wherein the identifying comprises:
identifying names of data fields within which the data items are located within the data files, and
identifying the correlations based on identified correlations between the names of the data fields;
generating, by the system, relationship metadata identifying the correlations between the classified data items;
generating, by the system, a model of normal operator behavior relative to an operator task based on a monitoring of a subset of the data items and relationship metadata relating to operator activities;
and
identifying, by the system, incorrect operator behavior relative to the operator task based on a comparison of monitored operator behavior data with the model.

7 more elements

A non-transitory computer-readable medium having stored thereon executable components that, in response to execution, cause a system comprising a processor to perform operations, the operations comprising:

receiving data files generated by industrial devices and industrial systems, wherein the data files accord to respective different file types, and the data files comprise at least two of spreadsheet files, log files, database files, streaming data, power monitor data, image data from a camera or and optical scanner, energy matrix data, data files from an inventory system, maintenance schedule data, or purchase order data;
storing the data files in one or more event queues of a cloud platform;
classifying data items contained in the data files to yield classified data items;
identifying correlations between the classified data items;
generating relationship metadata identifying the correlations between the classified data items;
generating, based on a monitoring of a subset of the data items and relationship metadata, a model of normal operator behavior relative to an operator task;
and
identifying incorrect operator behavior relative to the operator task based on a comparison of monitored operator behavior data with the model.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/936,835Filed 27 Mar 2018 · us provisional application
Priority: 8 Jun 2017
Published: US 2018/0357334 A113 Dec 2018
Granted: 29 Dec 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification18 codes

G05B 19/41835
Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible…:…
G05B 19/406
Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to…
G05B 19/408
Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to…
G05B 19/4185
Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible…:…