Cloud-level industrial controller loop gain tuning based on industrial application type

Patent metadata

Field	Value
Publication number	US-9971317-B2
Application number	US-201414525149-A
Country	US
Kind code	B2
Filing date	Oct 27, 2014
Priority date	Mar 26, 2014
Publication date	May 15, 2018
Grant date	May 15, 2018

Abstract

A control loop tuning system executing on a cloud platform facilitate remote control system analysis and generation of suitable controller gains for a given closed-loop control application. The system leverages cloud-side analytics and a gain correlation model generated based on historical data collected from the industrial control system and maintained on cloud storage. The gain correlation model creates a virtual association between controller gains and process variables based on operational and configuration data collected from the industrial control system. The system then applies iterative analytics to the model to converge on a set of controller gains determined to satisfy an optimization criterion. The recommended controller gains are then provided to a client device for review and implementation in the real system controller.

First claim

What is claimed is:

1. A system for tuning controller gain values on a cloud platform, comprising:
a memory that stores executable components;
a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:
a system interface component configured to collect first industrial data from a first set of devices of a first industrial control system and store the first industrial data in a selected priority queue, of multiple priority queues, configured on a cloud platform;
a gain modeling component configured to discover a correlation between controller gain values and values of a process variable of the first industrial control system based on an analysis of the first industrial data and second industrial data collected from a second set of devices of a second industrial control system, and to generate a gain correlation model that defines the process variable as a function of controller gain values based on the correlation, wherein the gain modeling component selects the second industrial data for the analysis based on a determination that the second industrial control system executes a similar type of industrial application as an industrial application executed by the first industrial control system, and wherein the similar type of industrial application is at least one of a robot control application, a spinning load application, a conveyor control application, or a web tension control application;
a correlation analytics component configured to determine at least one controller gain value for the first industrial control system based on analysis of the gain correlation model; and

a cloud interface component configured to set the at least one controller gain value in an industrial controller of the first industrial control system to facilitate tuning the industrial controller, wherein tuning the industrial controller causes the industrial controller to execute the industrial application in accordance with the at least one controller gain value.

2. The system of claim 1 , further comprising a client interface component configured to send the at least one controller gain value to a client device communicatively connected to the cloud platform.

3. The system of claim 1 , wherein the gain modeling component is configured to generate the gain correlation model based on multi-enterprise industrial data collected from multiple industrial control systems, including the first industrial control system and the second industrial control system, associated with multiple industrial enterprises.

4. The system of claim 1 , wherein the correlation analytics component is configured to simulate, based on the gain correlation model, a process variable response using at least one test value of the at least one controller gain.

5. The system of claim 4 , wherein the correlation analytics component is configured to modify the at least one test value as a function of the process variable response based on one or more gain tuning rules to yield at least one modified test value, and to re-simulate the process variable response for the at least one modified test value to yield a new process variable response.

6. The system of claim 5 , wherein the correlation analytics component is configured to iteratively modify the at least one test value to yield the at least one modified test value and re-simulate the process variable response for the at least one modified test value, and to select, as the at least one controller gain value, the at least one modified test value in response to a determination that the new process variable response for the at least one modified test value satisfies a defined criterion.

7. The system of claim 1 , wherein the system interface component is configured to receive at least a portion of the first industrial data as a data packet from a cloud agent device associated with one or more of the first set of devices, and the data packet comprises header information identifying at least one of an owner of the first industrial control system, a site at which the first industrial control system is located, a priority of the portion of the first industrial data, a message type of the data packet, or a process identifier specifying a type of processing to be performed on the portion of the first industrial data.

8. The system of claim 1 , wherein the first industrial data comprises at least one of monitored process variable values for the first industrial control system, position data or velocity data for a motion device, configuration information for one or more of the first set of devices, device alarm data, system alarm data, machine cycle time data, a performance indicator for the first industrial control system, or firmware information for at least one of the first set of devices.

9. The system of claim 1 , further comprising a manifest assembly repository configured to maintain manifest data that defines, for respective priority queues of the multiple priority queues, customer-specific preferences relating to processing of data received at the cloud platform and assigned to the multiple priority queues,
wherein the manifest data is uploaded to the cloud platform via a cloud agent device at a plant facility, and wherein the customer-specific preferences define, for the selected priority queue, at least a processing priority for the first industrial data, an upload frequency for the first industrial data, and an indication of a storage location within the cloud storage for the first industrial data.

10. The system of claim 1 , wherein the process variable is at least one of a temperature, a pressure, a flow, a level, a motion device position, or a motion device velocity.

11. A method for tuning an industrial control loop, comprising:
receiving, at a cloud platform by a system comprising at least one processor, first industrial data from one or more first industrial devices of a first industrial control system;
storing, by the system, the first industrial data in a priority queue, of multiple priority queues, configured on the cloud platform;
selecting, by the system, second industrial data collected from one or more second industrial devices of a second industrial control system based on a determination that the second industrial control system implements a first industrial application having a similar type as a second industrial application executed by the first industrial control system, wherein the similar type is at least one of a robot control application, a spinning load application, a conveyor control application, or a web tension control application;
discovering, by the system, a correlation between controller gain values and process variable values of the first industrial control system based on a first analysis of the first industrial data and the second industrial data;
creating, by the system, a gain correlation model defining, based on the correlation, the process variable values as a function of the controller gain values, and storing the gain correlation model on cloud storage of the cloud platform, wherein the gain correlation model encodes the correlation between the controller gain values and the process variable values of the first industrial control system;
determining, by the system, at least one controller gain value for the first industrial control system based on a second analysis of the gain correlation model;
setting, by the system, the at least one controller gain value in an industrial controller to facilitate tuning the industrial controller; and
executing the industrial controller to control the industrial application in accordance with the at least one controller gain value.

12. The method o

Assignees

• Rockwell Automation Tech Inc

Inventors

• Maturana Francisco P
• Asenjo Juan L

Classifications

• G05B13/042 Primary

  in which a parameter or coefficient is automatically adjusted to optimise the performance · CPC title

• G06F9/5072

  Grid computing · CPC title

• Y02P90/80

  Management or planning · CPC title