Granted Patent B2

US 12,461,509 · App. 17/870,352 · Granted Nov 4, 2025

Inventors: Timothy C. Mirth (Hudson, OH); Taryl J. Jasper (Concord Township, OH); Terence S. Tenorio (Solon, OH); Thaddeus A. Palus (Denver, CO)

Assignee: Rockwell Automation Technologies, Inc.

G05B19/4185

Abstract

Claims (74)

1 . A non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:

receiving data from one or more industrial automation systems, wherein the data comprises design artifacts of the one or more industrial automation systems, run time data collected from the one or more industrial automation systems, or both;

inputting the data to a machine learning-based security policy development engine to generate a set of recommended security policies for the one or more industrial automation systems based on the data, wherein the machine learning-based security policy development engine is configured to compare the data to one or more models and generate probabilities of the presence or likelihood of one or more conditions;

receiving the set of recommended security policies for the one or more industrial automation systems output by the security policy development engine;

transmitting the set of recommended security policies to the one or more industrial automation systems for implementation, wherein the one or more industrial automation systems are configured to implement the set of recommended security policies by controlling one or more industrial automation devices to automatically perform one or more remedial actions in response to an event based on the probabilities exceeding one or more threshold values;

anonymizing the data;

transmitting the anonymized data to a service provider;

in response, receiving, from the service provider, training data for the security policy development engine; and

retraining the security policy development engine based on the training data.

2 . The non-transitory computer readable medium of claim 1 , wherein the data is received from one or more industrial automation systems at an edge device, and wherein the set of recommended security policies are transmitted to the one or more industrial automation systems from the edge device.

3 . The non-transitory computer readable medium of claim 2 , wherein the security policy development engine is configured to run in a container on the edge device.

4 . The non-transitory computer readable medium of claim 3 , wherein the container is managed by a container orchestration system.

5 . The non-transitory computer readable medium of claim 1 , wherein the operations comprise:

receiving, from the service provider, an updated version of the security policy development engine; and

replacing the security policy development engine with the updated version of the security policy development engine.

6 . The non-transitory computer readable medium of claim 1 , wherein the operations comprise:

receiving additional data from the one or more industrial automation systems;

inputting the additional data to the machine learning-based security policy development engine to generate an additional set of recommended security policies for the one or more industrial automation systems;

receiving the additional set of recommended security policies for the one or more industrial automation systems output by the security policy development engine; and

transmitting the additional set of recommended security policies to the one or more industrial automation systems for implementation.

7 . The non-transitory computer readable medium of claim 1 , wherein the instructions are configured to be executed by the processor of a computing device of an enterprise control system configured to control industrial automation systems disposed at multiple facilities operated by an enterprise.

8 . The non-transitory computer readable medium of claim 1 , wherein the instructions are configured to be executed by the processor of a computing device of a plant management system configured to control industrial automation systems disposed in a facility operated by an enterprise.

9 . The non-transitory computer readable medium of claim 1 , wherein:

receiving the data from the one or more industrial automation systems comprises:

receiving first run time data from a first industrial automation system;

receiving second run time data from a second industrial automation system; and

receiving incident data from an operational technology network that includes the first industrial automation system and the second industrial automation system;

wherein the operations comprise aggregating the first run time data, the second run time data, and the incident data.

10 . The non-transitory computer readable medium of claim 1 , wherein the set of recommended security policies define access, use, or both, of industrial automation assets, including the one or more industrial automation systems, operated by an enterprise.

11 . The non-transitory computer readable medium of claim 1 , wherein anonymizing the data comprises:

identifying characteristic data elements associated with the one or more industrial automation systems within the data, wherein the characteristic data elements comprise employee information, network information, operating parameters, or a combination thereof associated with the one or more industrial automation systems; and

removing the characteristic data elements from the data.

12 . A method, comprising:

receiving, from an enterprise network, data associated with one or more industrial automation systems operated by an enterprise, wherein the data comprises design artifacts of the one or more industrial automation systems, run time data collected from the one or more industrial automation systems, or both;

inputting the data to a machine learning-based security policy development engine to generate a set of recommended security policies for the enterprise based on the data, wherein the machine learning-based security policy development engine is configured to compare the data to one or more models and generate probabilities of the presence or likelihood of one or more conditions;

receiving the set of recommended security policies for the one or more industrial automation systems output by the security policy development engine, wherein the set of recommended security policies define access, use, or both, of the one or more industrial automation systems operated by the enterprise;

transmitting the set of recommended security policies to the enterprise, wherein the enterprise is configured to implement the set of recommended security policies by controlling one or more industrial automation devices of the one or more industrial automation systems to automatically perform one or more remedial actions based on the probabilities exceeding one or more threshold values;

anonymizing the data;

transmitting the anonymized data to a service provider;

in response, receiving, from the service provider, training data for the security policy development engine; and

retraining the security policy development engine based on the training data.

13 . The method of claim 12 , wherein the data comprises help ticket data, incident data, vulnerability data, data received from a service provider, data received from a customer, data received from a partner organization, data received from a supplier, or any combination thereof.

14 . The method of claim 12 , comprising:

receiving, from the enterprise network, additional data from the one or more industrial automation systems;

inputting the additional data to the machine learning-based security policy development engine to generate an additional set of recommended security policies for the one or more industrial automation systems;

receiving the additional set of recommended security policies for the one or more industrial automation systems output by the security policy development engine; and

transmitting the additional set of recommended security policies to the enterprise.

15 . The method of claim 12 , wherein anonymizing the data comprises:

identifying characteristic data elements associated with the one or more industrial automation systems within the data, wherein the characteristic data elements comprise employee information, network information, operating parameters, or a combination thereof associated with the one or more industrial automation systems; and

editing the characteristic data elements, wherein editing the characteristic data elements comprises generalizing, pseudonymizing, or masking the characteristic data elements.

16 . An industrial automation system, comprising:

a processor; and

a memory, accessible by the processor, and storing instructions that, when executed by the processor, cause the processor to perform operations comprising:

collecting data from one or more connected industrial automation devices, wherein the data comprises design artifacts of the one or more industrial automation devices, run time data collected from the one or more industrial automation devices, incident data for an operational technology network on which the one or more industrial automation devices operate, or any combination thereof;

transmitting the data to an enterprise control system of an enterprise that operates the one or more industrial automation devices;

receiving, from the enterprise control system, a set of recommended security policies, wherein the set of recommended security policies define access, use, or both, of industrial automation assets, including the one or more industrial automation devices, operated by the enterprise, wherein the enterprise control system is configured to execute a machine learning-based security policy development engine to generate the set of recommended security polices, and the machine learning-based policy development engine is configured to compare the data to one or more models and generate probabilities of the presence or likelihood of one or more conditions;

implementing one or more of the set of recommended security policies on the one or more industrial automation devices, wherein implementing one or more of the set of recommended security policies on the one or more industrial automation devices comprises controlling the one or more industrial automation devices to automatically perform one or more remedial actions in response to an event based on the probabilities exceeding one or more threshold values;

anonymizing the data; and

transmitting the anonymized data to a service provider.

17 . The industrial automation system of claim 16 , wherein the operations comprise:

collecting additional data from the one or more industrial automation devices;

transmitting the additional data to the enterprise control system;

receiving, from the enterprise control system, an additional set of recommended security policies for the one or more industrial automation devices; and

implementing one or more of the additional set of recommended security policies on the one or more industrial automation devices.

18 . The industrial automation system of claim 16 , wherein the operations comprise:

causing one or more security policies of the set of recommended security policies to be displayed on a user interface for review;

receiving an input approving the displayed one or more security policies of the set of recommended security policies; and

implementing the approved one or more security policies of the set of recommended security policies.

19 . The industrial automation system of claim 16 , wherein collecting data from the one or more industrial automation devices comprises:

receiving first run time data from a first industrial automation device;

receiving second run time data from a second industrial automation device; and

receiving incident data from an operational technology network that includes the first industrial automation device and the second industrial automation device;

wherein the operations comprise aggregating the first run time data, the second run time data, and the incident data.

20 . The industrial automation system of claim 16 , wherein controlling the one or more industrial automation devices comprises adjusting one or more communication permissions associated with sending data to or receiving data from the one or more industrial automation devices, adjusting data usage associated with the one or more industrial automation devices, or a combination thereof.

Assignments (1)

Continuity (1)

References Cited (23)