Distributed big data in a process control system

• US 10,311,015 B2
• Filed: 03/14/2014
• Issued: 06/04/2019
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Original Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Inventors: Nixon, Mark J., Muston, Paul Richard, Blevins, Terrence L., Wojsznis, Wilhelm K.
• Primary Examiner(s): Ali, Mohammad
• Assistant Examiner(s): Booker, Kelvin
• Application Number:
  US14/212,493
• Publication Number:
  US 20140277604A1
• Time in Patent Office: 1,908 Days
• Field of Search: None
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 19/4185 characterised by the network communication
• CPC Class Codes: G05B 2219/31211 Communicate diagnostic data from intelligent field device controller to central
• CPC Class Codes: G05B 2219/31324 Distributed real time knowledge, database
• CPC Class Codes: G06F 15/173 using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
• CPC Class Codes: G06F 15/17331 Distributed shared memory [DSM], e.g. remote direct memory access [RDMA]
• CPC Class Codes: G06F 2212/2515 being configurable for different purposes, e.g. as cache or non-cache memory
• CPC Class Codes: G06F 9/54 Interprogram communication
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A distributed big data device in a process plant includes an embedded big data appliance configured to locally stream and store, as big data, data that is generated, received, or observed by the device, and to perform one or more learning analyzes on at least a portion of the stored data. The embedded big data appliance generates or creates learned knowledge based on a result of the learning analysis, which the device may use to modify its operation to control a process in real-time in the process plant, and/or which the device may transmit to other devices in the process plant. The distributed big data device may be a field device, a controller, an input/output device, or other process plant device, and may utilize learned knowledge created by other devices when performing its learning analysis.

Claims

1. A first process control device for supporting distributed big data in a process plant, the first process control device being a field device that performs a physical function to control at least a pre-determined portion of a process in the process plant, and the field device including:

(i) a device processor;

(ii) one or more device tangible, non-transitory, computer-readable storage media having stored thereon a set of computer-executable instructions that, when executed by the device processor, cause the field device to at least one of;

(i) perform the physical function, generate process data corresponding to the performed physical function, and transmit, via a communication network within the process plant, the generated process data to a second process control device operating to control the process in real-time, or

(ii) receive process data from the second process control device via the communication network within the process plant, and perform the physical function based on the received process data;

(iii) a first interface via which the field device is connected to an input/output (I/O) device, the I/O device disposed between the field device and a controller and communicatively connecting the field device to the communication network, the generated process data transmitted via the first interface, and the received process data received via the first interface; and

(iv) an embedded big data apparatus having embedded data storage and embedded computer-executable instructions stored on one or more embedded tangible, non-transitory, computer-readable storage media that, when executed by one or more processors, cause the embedded big data apparatus to;

locally store, in the embedded big data storage, the generated process data and the received process data;

perform a learning analysis on at least a part of the locally stored process data;

create learned knowledge based on a result of the learning analysis, the learned knowledge including at least one of a time relationship or a causal relationship between process variables having values included in the locally stored process data;

locally store the created learned knowledge in the embedded big data storage of the embedded big data apparatus included in the field device; and

cause at least a portion of the locally stored learned knowledge to be distributed, via a second interface included in the field device and communicatively connecting the field device with a process control big data network different than the communication network, to the second process control device in the process plant to thereby modify, based upon the distributed learned knowledge, an operation of the second process control device, the second process control device including a respective embedded big data apparatus and operating in real-time to control the process.

2. The first process control device of claim 1, wherein the locally stored process data includes multiple types of data, and a set of types of the locally stored process data includes continuous data, event data, measurement data, batch data, calculated data, and configuration data corresponding to controlling the process executed by the process plant.

3. The first process control device of claim 1, wherein the embedded computer-executable instructions of the embedded big data apparatus are further executable to cause the embedded big data apparatus to determine the learning analysis based on the locally stored process data, wherein the determination of the learning analysis is at least one of a selection or a derivation of the learning analysis.

4. The first process control device of claim 1, wherein the learning analysis includes at least one of a partial least square regression analysis, a random forest, a pattern recognition, a predictive analysis, a correlation analysis, a principle component analysis, data mining, or data discovery.

5. The first process control device of claim 1, wherein the learning analysis is a first data analysis algorithm, and the embedded computer-executable instructions of the embedded big data apparatus are further executable to cause the embedded big data apparatus to receive another data analysis algorithm from another big data device via the process control big data network and to execute the another data analysis algorithm.

6. The first process control device of claim 5, wherein at least one of:

the another big data device is one of another distributed data device or a centralized big data device of the process plant;

or

the another data analysis algorithm includes at least one of an R script, a Python script, or a Matlab®

script.

7. The first process control device of claim 1, wherein the first process control device is further configured to:

modify, based on the learned knowledge, an operation of the first process control device to control, in real-time, the process executed by the process plant, and

cause an indication of the modification to be transmitted to the second process control device or to a third process control device in conjunction with the learned knowledge.

8. The first process control device of claim 7, wherein the modification is an updated process model.

9. The first process control device of claim 1, wherein the communication network comprises at least one of a wired communications network or a wireless communications network.

10. The first process control device of claim 1, wherein the learned knowledge includes at least one of additional data that was previously unknown to the first process control device, an application, a service, a routine, or a function.

11. The first process control device of claim 1, wherein:

the learned knowledge is first learned knowledge and the learning analysis is a first learning analysis; and

the embedded computer-executable instructions of the embedded big data apparatus are further executable to cause the embedded big data apparatus to;

receive second learned knowledge created by the second process control device or by a third process control device, and

at least one of (i) modify, based on the received second learned knowledge, an operation of the first process control device to control, in real-time, the process, or (2) perform a second learning analysis on at least some of the locally stored process data and the received second learned knowledge.

12. A method of supporting distributed big data using a field device that is (i) communicatively coupled to a first communications network of a process plant, (ii) operating, based on control signals delivered via the first communications network, to control a process in real-time in the process plant, and (iii) configured to perform a physical function to control at least a pre-determined portion of the process in real-time, the method comprising, at the field device:

at least one of;

receiving, at the field device, data via the first communications network and using the received data to perform the physical function to control at least the pre-determined portion of the process in real-time, or

generating, by the field device, data as a result of performing the physical function and transmitting the generated data via the first communications network to control at least the pre-determined portion of the process in real-time;

collecting data at the field device, the data including at least one of;

(i) the data that is generated by the field device as a result of performing the physical function, (ii) data that is created by the field device, or (iii) the data that is received at the field device and used by the field device to perform the physical function;

locally storing, in an embedded big data apparatus included in the field device, the collected data;

performing, by the embedded big data apparatus included in the field device, a learning analysis on at least a portion of the locally stored data;

generating, by the embedded big data apparatus, learned knowledge indicative of a result of the learning analysis, the learned knowledge including at least one of a time relationship or a causal relationship between process variables having values included in the locally stored process data, and wherein the learned knowledge is included in the data that is created by the field device;

locally storing the generated learned knowledge in the embedded big data apparatus included in the field device;

modifying, based on a first at least a portion of the locally stored learned knowledge, an operation of the field device to control the process in real-time; and

distributing, via a process control big data network that is different than the first communications network, the first at least a portion of the locally stored learned knowledge or a second at least a portion of the learned knowledge to another device, the another device including a respective embedded big data apparatus.

13. The method of claim 12, wherein performing the learning analysis comprises performing at least one of a machine learning analysis, a predictive analysis, data mining, or data discovery.

14. The method of claim 12, wherein collecting the data at the field device comprises at least one of:

collecting all data that is generated by the field device, collecting all data that is created by the field device, or collecting all data that is received at the field device.

15. The method of claim 12, wherein collecting the data at the field device comprises at least one of:

collecting data that is generated by the field device at a rate of generation, collecting all data that is created by the field device at a rate of creation, or collecting all data that is received at the field device at a rate of reception.

16. The method of claim 12, wherein collecting the data at the field device comprises collecting, at the field device, at least one type of data included in a set of types of data that includes continuous data, event data, measurement data, batch data, calculated data, and configuration data.

17. The method of claim 12, wherein:

the field device is a first device, the learned knowledge is first learned knowledge, and the operation of the first device is a first operation; and

the method further comprises;

receiving, at the first device, second learned knowledge generated by a second device, the second learned knowledge determined by an embedded big data apparatus of the second device;

performing, by the embedded big data apparatus of the first device, a further learning analysis on the second learned knowledge and at least some of the stored data;

generating, by the embedded big data apparatus of the first device, further learned knowledge indicative of a result of the further learning analysis;

locally storing the further learned knowledge in the embedded big data apparatus included in the field device;

modifying the first operation or a second operation of the first device to control the process in real-time based on the locally stored, further learned knowledge.

18. The method of claim 17, wherein receiving the second learned knowledge generated by the second device comprises receiving the second learned knowledge generated by one of:

another field device, a controller, an I/O device, a user interface device, a gateway device, an access point, a routing device, a historian device, or a network management device.

19. The method of claim 12, further comprising causing one or more portions of the locally stored learned knowledge to be distributed to yet another device, wherein a device type of the yet another device is one of field device, controller, or I/O device.

20. The method of claim 12, wherein generating the learned knowledge comprises generating at least one of:

additional data that was previously unknown to the field device, a new or modified application, a new or modified function, a new or modified routine, or a new or modified service.

21. A system for supporting distributed big data in a process plant, the system comprising:

a process control big data network having a plurality of nodes, the plurality of nodes including a first node that is a field device configured to at least one of;

(i) perform a physical function to control at least a pre-determined portion of the process executing in the process plant, generate first real-time data corresponding to the performed physical function, and transmit, via a communications network within the process plant that is different than the process control big data network, the first real-time data to another process control device operating to control the at least the pre-determined portion of the process, or

(ii) receive second real-time data from the another process control device via the communications network, and perform the physical function based on the second real-time data; and

each of the plurality of nodes is configured to;

collect respective data generated in real-time resulting from control of a process executing in the process plant;

locally store the collected respective data at a respective embedded big data apparatus included in the each of the plurality of nodes; and

perform, by the respective embedded big data apparatus included in the each of the plurality of nodes, a respective learning analysis on at least a portion of the locally stored data, thereby generating respective learned knowledge;

locally store the generated respective learned knowledge at the respective embedded big data apparatus included in the each of the plurality of nodes; and

wherein the field device is further configured to cause at least a portion of the respective learned knowledge that is locally stored at the embedded big data apparatus included in the field device and that is indicative of a result of a performance of the respective learning analysis of the field device to be distributed, via the process control big data network, to a second node included in the plurality of nodes for use in the respective learning analysis of the second node or in another respective learning analysis of the second node, the at least the portion of the respective learned knowledge that is locally stored at the field device including at least one of a time relationship or a causal relationship between process variables having values included in the locally stored process data.

22. The system of claim 21, wherein the field device is a first field device, and the plurality of nodes further includes at least one of:

a controller configured to receive a set of inputs, determine, based on the set of inputs, a value of an output, and cause the output to be transmitted, via the communications network, to the first field device to control the process executed by the process plant, wherein the first field device is configured to perform the physical function based on the output of the controller to control the process;

a second field device;

an input/output (I/O) device having an interface to the controller and an interface to at least one of the first field device or the second field device;

a user interface device;

a gateway device;

an access point;

a routing device;

a historian device;

or

a network management device.

23. The system of claim 21, wherein:

the plurality of nodes further includes a controller that is configured to receive a set of inputs, determine, based on the set of inputs, a value of an output, and cause the output to be transmitted, via the communications network that is different than the process control big data network, to the field device to control the at least the pre-determined portion of the process executed by the process plant; and

the field device is configured to perform the physical function based on the output of the controller to control the at least the pre-determined portion of the process executed by the process plant.

24. The system of claim 23, wherein the controller includes a first interface to the communications network and a second interface to the process control big data network.

25. The system of claim 21, wherein the generated respective learned knowledge includes at least one of respective application, a respective function, a respective service, or a respective routine.

26. The system of claim 21, wherein the result of the performance of the respective learning analysis includes a prediction based on properties of the at least the portion of the locally stored data.

27. The system of claim 21, wherein the result of the performance of the respective learning analysis includes additional data that was previously unknown to the first node.

28. The system of claim 21, wherein the learned knowledge locally stored at the embedded big data apparatus of the first node is first learned knowledge, and wherein the second node is configured to:

receive the first learned knowledge from the first node;

perform, by the respective embedded big data apparatus included in the second node, the respective learning analysis of the second node or another respective learning analysis of the second node on the first learned knowledge and at least a portion of locally collected and stored data at the second node; and

at least one of;

store, at the respective embedded big data apparatus of the second node, second learned knowledge indicative of a result the performance of the respective learning analysis of the second node or the another respective learning analysis of the second node;

modify an operation of the second node to control the process based on the second learned knowledge;

or

cause the second learned knowledge to be distributed, via the process control big data network, to a third node of the plurality of nodes.

29. The system of claim 28, wherein the third node is configured to:

receive the second learned knowledge from the second node;

perform, by the respective embedded big data apparatus of the third node, the respective learning analysis of the third node or another respective learning analysis of the third node on the second learned knowledge and at least a portion of locally collected and stored data at the third node; and

at least one of;

store, at the respective embedded big data apparatus of the third node, third learned knowledge indicative of a result the performance of the respective learning analysis of the third node or the another respective learning analysis of the third node;

modify an operation of the third node to control the process based on the third learned knowledge;

or

cause the third learned knowledge to be distributed, via the process control big data network, to a fourth node of the plurality of nodes.