Adaptive control of industrial automation for mining flotation cells

Patent metadata

Field	Value
Publication number	US-11944984-B2
Application number	US-201916578742-A
Country	US
Kind code	B2
Filing date	Sep 23, 2019
Priority date	Sep 23, 2019
Publication date	Apr 2, 2024
Grant date	Apr 2, 2024

Abstract

Techniques to facilitate adaptive optimization and control of flotation cell processing are disclosed herein. In at least one implementation, a computing system receives a plurality of flotation cell process variables associated with a flotation cell process. The flotation cell process variables are fed into a machine learning model associated with the flotation cell process to determine improved settings for the flotation cell process. The improved settings for the flotation cell process are provided to an industrial controller that controls at least one aspect of the flotation cell process to improve the flotation cell process.

First claim

What is claimed is:

1. One or more non-transitory computer-readable storage media having program instructions stored thereon to facilitate adaptive optimization and control of flotation cell processing, wherein the program instructions, when executed by a computing system, direct the computing system to at least:
receive a plurality of flotation cell process variables associated with a flotation cell process;
receive a desired system output for the flotation cell process from an industrial controller that controls at least one aspect of the flotation cell process;
input the plurality of flotation cell process variables and the desired system output to a machine learning model, wherein the machine learning model is trained to:
process the plurality of flotation cell process variables to determine improved settings for the flotation cell process and a change in performance of at least one component of a plurality of components associated with the flotation cell process based on the input; and
responsively generate the improved settings for the flotation cell process wherein the improved settings comprise an adjustment to a performance curve for the at least one component based on the change in performance of the at least one component;

provide the improved settings for the flotation cell process to the industrial controller; and
in response to receiving the improved settings, applying, by the industrial controller, the improved settings, including the adjustment to the performance curve for the at least one component, to achieve the desired system output for the at least one aspect of the flotation cell process.

2. The one or more non-transitory computer-readable storage media of claim 1 wherein the program instructions direct the computing system to determine the improved settings for the flotation cell process by directing the computing system to determine the improved settings for individual components of the plurality of components associated with the flotation cell process.

3. The one or more non-transitory computer-readable storage media of claim 1 wherein the program instructions direct the computing system to determine the improved settings for the flotation cell process by directing the computing system to determine the improved settings for overall master control of the flotation cell process.

4. The one or more non-transitory computer-readable storage media of claim 1 wherein the improved settings for the flotation cell process comprise updated set points for one or more components of the plurality of components associated with the flotation cell process and an updated offset to a Proportional, Integral, and Derivative (PID) control device associated with the flotation cell process.

5. The one or more non-transitory computer-readable storage media of claim 1 wherein the improved settings for the flotation cell process comprise energy optimizations that minimize an amount of energy used by one or more components of the plurality of components associated with the flotation cell process.

6. The one or more non-transitory computer-readable storage media of claim 1 wherein the program instructions direct the computing system to provide updated process variables to the machine learning model that indicate a change in performance associated with the flotation cell process, and wherein the machine learning model is configured to automatically adjust the machine learning model to compensate for the change in performance.

7. The one or more non-transitory computer-readable storage media of claim 1 wherein the flotation cell process variables comprise flotation cell level, agitation rate, air injection rate, and reagent feed rate.

8. A method to facilitate adaptive optimization and control of flotation cell processing, the method comprising:
receiving a plurality of flotation cell process variables associated with a flotation cell process;
receiving a desired system output for the flotation cell process from an industrial controller that controls at least one aspect of the flotation cell process;
inputting the plurality of flotation cell process variables and the desired system output to a machine learning model, wherein the machine learning model is trained to:
process the plurality of flotation cell process variables to determine improved settings for the flotation cell process and a change in performance of at least one component of a plurality of components associated with the flotation cell process based on the input; and
responsively generate the improved settings for the flotation cell process wherein the improved settings comprise an adjustment to a performance curve for the at least one component based on the change in performance of the at least one component;

providing the improved settings for the flotation cell process to the industrial controller; and
in response to receiving the improved settings, implementing, by the industrial controller, the improved settings, including the adjustment to the performance curve for the at least one component, to achieve the desired system output for the at least one aspect of the flotation cell process.

9. The method of claim 8 wherein feeding the flotation cell process variables into the machine learning model to determine the improved settings for the flotation cell process comprises feeding the flotation cell process variables into the machine learning model to determine the improved settings for individual components of the plurality of components associated with the flotation cell process.

10. The method of claim 8 wherein feeding the flotation cell process variables into the machine learning model to determine the improved settings for the flotation cell process comprises feeding the flotation cell process variables into the machine learning model to determine the improved settings for overall master control of the flotation cell process.

11. The method of claim 8 wherein the improved settings for the flotation cell process comprise updated set points for one or more components of the plurality of components associated with the flotation cell process and an updated offset to a Proportional, Integral, and Derivative (PID) control device associated with the flotation cell process.

12. The method of claim 8 wherein the improved settings for the flotation cell process comprise energy optimizations that minimize an amount of energy used by one or more components of the plurality of components associated with the flotation cell process.

13. The method of claim 8 further comprising providing updated process variables to the machine learning model that indicate a change in performance associated with the flotation cell process, and wherein the machine learning model is configured to automatically adjust the machine learning model to compensate for the change in performance.

14. The method of claim 8 wherein the flotation cell process variables comprise flotation cell level, agitation rate, air injection rate, and reagent feed rate.

15. A system to facilitate adaptive optimization and control of flotation cell processing, the system comprising:
a computing device comprising a processing system, one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media that, when executed by the processing system, direct the processing system to at least:
receive a plurality of flotation cell process variables associated with a flotation cell process;
receive a desired system output for the flotation cell process from an industrial controller that controls at least one aspect of the flotation cell process;

Assignees

• Rockwell Automation Tech Inc

Inventors

• Bromfield Scotty
• Peterson Corey A
• Stanford Timothy L
• Mazur David C
• Clohessy Steven
• Wolmarans Pieter
• Entzminger Rob A

Classifications

• B03D1/028 Primary

  Control and monitoring of flotation processes; computer models therefor · CPC title

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G05B13/041

  in which a variable is automatically adjusted to optimise the performance · CPC title

• B03D2203/02

  Ores · CPC title

• B03D1/02

  Froth-flotation processes · CPC title