Automatic signal processing-based learning in a process plant

Patent metadata

Field	Value
Publication number	US-10282676-B2
Application number	US-201414507252-A
Country	US
Kind code	B2
Filing date	Oct 6, 2014
Priority date	Oct 6, 2014
Publication date	May 7, 2019
Grant date	May 7, 2019

Abstract

Techniques for automatically or autonomously performing signal processing-based learning in a process plant are disclosed. Generally, said techniques automatically or autonomously perform signal processing on a real-time signal that is generated based on the process plant controlling a process. Typically, the signal corresponds to a parameter value that varies over time, and the signal is processed as it is generated in real-time during on-line plant operations. Results of the signal processing may indicate characteristics of the signal, and one or more analytics functions may determine the sources of the characteristics, which may include a process element or device, a piece of equipment, and/or an asset of the process plant that is upstream, within the process, of the source of the signal. An autonomous signal processor may be integrated with or included in a process control device and/or a big data node of the process plant.

First claim

What is claimed:

1. A system for providing big data based learning in a process plant controlling a process, the system comprising:
a process control device that is one of a controller, a field device performing a physical function to control at least the portion of the process, or an input/output (I/O) device communicatively connecting the controller and the field device;
a signal processing module that is integral with the process control device, the integrated process control device and signal processing module including at least one memory and at least one processor, and the signal processing module including:
an input to receive a signal generated by a signal source associated with the process plant as the signal source generates the signal in real-time, the signal indicative of parameter value that varies over time based on the process plant controlling the process by using at least one field device that performs a respective physical function, and the process control device being the signal source;
an output to provide, to one or more respective recipient applications, an indication of at least one characteristic of the signal; and
computer-executable instructions that are stored in the at least one memory and that, when executed by the at least one processor, cause the signal processing module to perform real-time signal processing on the signal as the process control device generates the signal in real-time to determine the at least one characteristic of the signal, the real-time signal processing including at least one of: magnitude or amplitude analysis, power analysis, intensity analysis, phase analysis, frequency analysis, spectrum or spectral analysis, correlation analysis, convolution, smoothing, Hilbert transformation, level detection, linear signal processing, or non-linear signal processing; and

an analytics module including:
an input to receive the indication of the at least one characteristic of the signal from the signal processing module; and
an output to provide an indication of a source of the at least one characteristic of the signal to the one or more respective recipient applications, the one or more respective recipient applications including at least one of a user interface application or another application; and

wherein:
the analytics module is configured to determine that at least one member of a set of upstream elements is the source of the at least one characteristic of the signal, the set of upstream elements being elements that are associated with the process plant and that are upstream, within the process, of the signal, and the determination that the at least one member is the source of the at least one characteristic of the signal is based on respective strengths of impact of members of the set of upstream elements on the at least one characteristic of the signal; and
the source of the at least one characteristic of the signal includes at least one of a process control device, a process variable, a piece of equipment, or an asset of the process plant that is upstream of the signal source.

2. The system of claim 1 , wherein:
the process control device is a first signal source, the signal generated by the first signal source is a first signal, and the signal processing module is a first signal processing module; and
the system further comprises a second signal processing module integral with a second signal source generating a second signal, the second signal processing module performing real-time signal processing on the second signal as the second signal is generated in real-time by the second signal source, the second signal source being one of: a second process control device controlling a respective at least a portion of the process, a big data node included in a process control big data network of the process plant, a piece of equipment within the process plant, or an asset of the process plant.

3. The system of claim 2 , wherein the second signal source is the big data node included in the process control big data network of the process plant, and wherein the big data node is one of: a local big data node, a regional big data node, a centralized big data node, or another big data node.

4. The system of claim 2 , wherein the system further comprises a third signal source and a third signal processing module performing real-time signal processing on a third signal generated by the third signal source as the third signal is being generated in real-time by the third signal source, the third signal source included in a first device, and the third signal processing module included in a second device coupled to the first device in which the third signal source is included.

5. The system of claim 4 , wherein:
the third signal source is a third process control device controlling a respective at least a portion of the process, the third process control device being one of a third controller, a third field, or a third input/output (I/O).

6. The system of claim 2 , wherein the signal generated by the second signal source is indicative of a parameter value that is indicative of a value of one of an output signal of the second process control device, a process variable, a measurement, a balance of energy, a balance of mass, or an output of an analytics module.

7. The system of claim 1 , wherein:
the system further comprises a presentation module, the presentation module including:
an input to receive learned output from the analytics module; and
an output to provide the learned output to the one or more respective recipient applications; and

the learned output includes at least one of the indication of the source of the at least one characteristic of the signal, or other information learned by the analytics module.

8. The system of claim 7 , wherein the presentation module is configured to determine the one or more respective recipient applications.

9. The system of claim 1 , wherein the analytics module is a first analytics module, and the one or more respective recipient applications include the another application included in a second analytics module.

10. The system of claim 1 , wherein the analytics module is a first analytics module, and the first analytics module determines the source of the at least one characteristic of the signal based on (i) the respective strengths of impact of the members of the set of upstream elements on the at least one characteristic of the signal, and (ii) information provided by a second analytics module.

11. The system of claim 10 , wherein the second analytics module comprises a process element alignment module.

12. The system of claim 1 , wherein the analytics module is integral with the process control device and the signal processing module, and the process control device is a single big data node that is communicatively connected to a process control big data network of the process plant.

13. The system of claim 1 , wherein the integrated process control device and signal processing module is included in a first node corresponding to the process plant, the analytics module is included in a second node corresponding to the process plant, and the second node is communicatively connected to the first node.

14. The system of claim 13 , the second node is a big data node included in a process control big data network of the process plant.

15. The system of claim 1 , wherein the variations over time of the parameter value comprise one or more oscillations.

16. The system of claim 1 , wherein the at least one characteristic of the signal comprises at least one of: a dominant frequency, an n-th order frequency wherein n

Assignees

• Fisher Rosemount Systems Inc

Inventors

• Nixon Mark J
• Zornio Peter
• Wojsznis Wilhelm K
• Lucas J Michael
• Muston Paul R
• Rotvold Eric D
• Blevins Terrence L

Classifications

• G06N99/005 Primary

  Physics · mapped topic

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G05B13/028 Primary

  using expert systems only · CPC title

• G06N20/00

  Machine learning · CPC title

• G05B2219/14097

  Display of error messages · CPC title