Using soft-sensors in a programmable logic controller
A method of operating an intelligent programmable logic controller over a plurality of scan cycles includes the intelligent programmable logic controller selecting one or more soft-sensors available in a control program corresponding to a production unit, each soft-sensor comprising a local parameter or variable used by the control program. The intelligent programmable logic controller determines updated soft-sensor values corresponding to the one or more soft-sensors during each scan cycle and stores those values during each scan cycle on a non-volatile computer-readable storage medium operably coupled to the intelligent programmable logic controller. Additionally, the intelligent programmable logic controller annotates the updated soft-sensor values with automation system context information to generate contextualized data.
1. A method of operating a programmable logic controller in a control layer of n multi-layered automation system over a plurality of scan cycles, the method comprising:
selecting, by the programmable logic controller, one or more soft-sensors available in a control program corresponding to a production process, each soft-sensor comprising a hidden parameter or variable derived internally by the control program and not exposed to at least one layer of the automation system other than the control layer, wherein the selected soft-sensors are determined to be useful for data analytics based on a particular set of observed conditions during execution of the control program;
historizing, by the programmable logic controller during each scan cycle, the hidden parameter or variable for the selected soft-sensor to produce a historical soft-sensor value by storing the historical soft-sensor value during each scan cycle on a non-volatile computer-readable storage medium operably coupled to the programmable logic controller;
retrieving, by the programmable logic controller, one or more historical soft-sensor values from the non-volatile computer-readable storage medium; and
executing, by the programmable logic controller, one or more data analytics algorithms on the one or more historical soft-sensor values to yield analytics data for analyzing the production process.
2. The method of claim 1 , wherein the selecting further comprises:
identifying, automatically by the programmable logic controller, the hidden variable or parameter for the soft-sensor using a soft-sensor symbol table generated during compilation of the control program.
3. The method of claim 1 , further comprising:
annotating, by the programmable logic controller, the historical soft-sensor values with automation system context information to generate contextualized data;
applying, by the programmable logic controller, the one or more data analytics algorithms to at least one of the contextualized data and the historical soft-sensor values to yield calculated data; and
adjusting one or more data generation parameters of the production unit based on the calculated data.
4. The method of claim 3 , further comprising:
compressing, by the programmable logic controller, the contextualized data to yield compressed contextualized data; and
storing, by the programmable logic controller, the compressed contextualized data on the non-volatile computer-readable storage medium operably coupled to the programmable logic controller.
5. The method of claim 3 , wherein the automation system context information comprises one or more of an indication of a device that generated data associated with the historical soft-sensor values, a structural description of an automation system comprising the programmable logic controller, a system working mode indicator, and information about a product that was produced while the historical soft-sensor value was determined.
6. The method of claim 3 , wherein the automation system context information comprises one or more of a description of automation software utilized by the programmable logic controller or a status indictor indicative of a status of the automation software while the historical soft-sensor value was determined.
7. The method of claim 1 , further comprising:
compressing, by the programmable logic controller, the historical soft-sensor values during each scan cycle prior to storing the historical soft-sensor values on the non-volatile computer-readable storage medium.
8. A programmable logic controller operating in a control layer of a multi-layered automation system, the programmable logic controller comprising:
a processor configured to execute according to a scan cycle;
a volatile computer-readable storage medium comprising a process image area;
a non-volatile computer-readable storage medium; and
a plurality of controller components executed by the processor, the plurality of controller components comprising:
a soft-sensor selection component configured to automatically select one or more available soft-sensors available in a control program corresponding to a production process in response to a set of one or more observed conditions, each soft-sensor comprising a hidden parameter or variable derived by the control program and not exposed to at least one layer of the automation system other than the control layer,
a historian component configured to historize the hidden parameter or variable for the selected soft-sensor during each scan cycle to produce a historical soft-sensor value by storing the historical soft-sensor value on the non-volatile computer-readable storage medium, and
a data analytics component configured to apply one or more data analytics algorithms to the historical soft-sensor values to analyze execution of the control program and yield analytics data for analyzing the production process.
9. The programmable logic controller of claim 8 , wherein the plurality of controller components further comprise:
a contextualization component configured to generate contextualized data by annotating the historical soft-sensor values with automation system context information, and
a data connector component configured to transmit the contextualized data to one or more external components for distributed analytics of the production process.
10. The programmable logic controller of claim 9 , wherein the historian component is further configured to adjust one or more data generation parameters of a production unit associated with the production process based on the analytics data.
11. The programmable logic controller of claim 10 , wherein the one or more data generation parameters comprise a sampling rate value.
12. The programmable logic controller of claim 8 , wherein the historian component is further configured to:
compress the values associated with the one or more soft-sensors during each scan cycle prior to storing the contents on the non-volatile computer-readable storage medium.
13. The programmable logic controller of claim 8 , wherein the plurality of controller components further comprises:
a networking functionality configured to communicate with a wireless device for sending soft-sensor values, analytics and contextualization information to the wireless device and for receiving from the wireless device a soft-sensor configuration to change soft-sensors that are to be monitored or to create conditional alarms based on the soft-sensors.
14. The programmable logic controller of claim 8 , wherein the soft-sensors include one of derived variables that have links to physical sensors, or variables that are generated as part of analytics functions.
15. The programmable logic controller of claim 8 , wherein the a data analytics component is further configured to perform a correlation study between the historical soft-sensor values and data of a physical sensor to yield a forecasted probability for error.
16. An article of manufacture for operating a programmable logic controller in a control layer of a multi-layered automation system over a plurality of scan cycles, the article of manufacture comprising a non-transitory, tangible computer-readable medium holding computer-executable instructions for performing a method comprising:
selecting one or more soft-sensors available in a control program corresponding to a production process, each soft-sensor comprising a hidden parameter or variable derived internally by the control program and not exposed to at least one layer of the automation system other than the control layer, wherein the selected soft-sensors are determined to be useful for data analytics based on a particular set of observed conditions during execution of the control program;
historizing during each scan cycle, the hidden parameter or variable for the selected soft-sensor to produce a historical soft-sensor value by storing the historical soft-sensor value during each scan cycle on a non-volatile computer-readable storage medium operably coupled to the programmable logic controller;
retrieving one or more historical soft-sensor values from the non-volatile computer-readable storage medium; and
executing one or more data analytics algorithms on the one or more historical soft-sensor values to yield analytics data for analyzing the production process.
17. The article of manufacture of claim 16 , wherein the selecting further comprises:
identifying, automatically, the hidden variable or parameter for the soft-sensor using a soft-sensor symbol table generated during compilation of the control program.
18. The article of manufacture of claim 17 , wherein the method further comprises:
annotating, by the programmable logic controller, the historical soft-sensor values with automation system context information to generate contextualized data;
applying the one or more data analytics algorithms to at least one of the contextualized data and the historical soft-sensor values to yield calculated data; and
adjusting one or more data generation parameters of the production unit based on the calculated data.
19. The article of manufacture of claim 16 , wherein the method further comprises
compressing the updated soft-sensor values during each scan cycle prior to storing the updated soft-sensor values on the non-volatile computer-readable storage medium.