Virtual sensors

• US 8,572,155 B2
• Filed: 02/12/2008
• Issued: 10/29/2013
• Est. Priority Date: 08/23/2007
• Status: Active Grant

• Current Assignee: Applied Materials Incorporated
• Original Assignee: Applied Materials Incorporated
• Inventors: Yanovich, Aleksey, Kril, Thorsten, Kroupnova, Natalia
• Primary Examiner(s): TAYLOR, NICHOLAS R
• Application Number:
  US12/069,879
• Publication Number:
  US 20090055126A1
• Time in Patent Office: 2,086 Days
• Field of Search: 709/201, 709/217, 709/224
• US Class Current: 709/201
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 23/00 Testing or monitoring of control systems or parts thereof monitoring of programme-control systems G05B19/048, G05B19/406
• CPC Class Codes: G05B 23/021 adopting a different treatment of each operating region or a different mode of the monitored system, e.g. transient modes; different operating configurations of monitored system
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A method and apparatus for providing a virtual sensor in real-time have been described. In one embodiment, a method to provide a virtual sensor in real-time includes identifying data indicating desired functionality. The method further includes executing the virtual sensor in real-time based on the identified data to generate an output of the virtual sensor with the output being used by at least one data analysis module in real-time for statistical process monitoring.

Claims

1. A method to provide a virtual sensor in real-time, comprising:

identifying data indicating desired functionality;

creating a first virtual sensor in real-time during data collection by determining an algorithm to perform calculations including logic functions on the identified data to obtain the desired functionality, wherein creating the first virtual sensor further includes storing the algorithm, which is a programming language script, in a format of an extensible markup language (xml) file and copying the xml file into a file directory of a virtual sensor manager;

executing the first virtual sensor in real-time during data collection based on the identified data to generate an output of the first virtual sensor with the output including an artificial parameter that is being used by at least one data analysis module in real-time for statistical process monitoring of at least one machine tool in a manufacturing facility; and

creating, in real-time, a data collection plan for the first virtual sensor based on an analysis performed by the at least one data analysis module.

2. The method of claim 1, further comprising:

acquiring, with the first virtual sensor, the identified data from a physical sensor and a second virtual sensor that includes another algorithm to perform calculations on selected data.

3. The method of claim 1, further comprising:

acquiring the identified data from at least one of a database, the at least one machine tool, and a real sensor attached to the machine tool, wherein the artificial parameter can not be measured by a physical sensor.

4. The method of claim 1, wherein the identified data used by the first virtual sensor is formed from a combination of data sources comprising at least two of the following:

a database, a machine tool of the at least one machine tool, a real sensor attached to the machine tool, an external physical sensor associated with the machine tool, a second virtual sensor, and a third virtual sensor.

5. The method of claim 1, further comprising:

analyzing the output of the first virtual sensor in real-time; and

generating an error notification in real-time based on the data analysis module analyzing the output of the first virtual sensor in real-time.

6. The method of claim 5, further comprising:

stopping a machine tool in real-time in response to the data analysis module analyzing the output of the first virtual sensor in real-time and determining a fault condition.

7. The method of claim 1, wherein accessing and executing the first virtual sensor in real-time occurs without having to restart a data analysis software application that performs functionality associated with the data analysis module.

22. The method of claim 1, further comprising:

acquiring the identified data from a data source associated with the manufacturing facility, the manufacturing facility comprising a machine tool.

8. A non-transitory machine-accessible medium including data that, when accessed by a machine, cause the machine to perform a method comprising:

identifying data indicating desired functionality;

creating a first virtual sensor in real-time during data collection by determining an algorithm to perform calculations including logic functions on the identified data to obtain the desired functionality, wherein creating the first virtual sensor further includes storing the algorithm, which is a programming language script, in a format of an extensible markup language (xml) file and copying the xml file into a file directory of a virtual sensor manager;

executing the first virtual sensor in real-time during data collection based on the identified data to generate an output of the first virtual sensor with the output including an artificial parameter that is being used by at least one data analysis module in real-time for statistical process monitoring of at least one machine tool in a manufacturing facility; and

creating, in real-time, a data collection plan for the first virtual sensor based on an analysis performed by the at least one data analysis module.

9. The machine-accessible medium of claim 8, the method further comprising:

acquiring, with the first virtual sensor, identified data from a physical sensor and a second virtual sensor that includes another algorithm to perform calculations on selected data.

10. The machine-accessible medium of claim 8, the method further comprising:

acquiring the identified data from at least one of a database, the at least one machine tool, and a real sensor attached to the machine tool, wherein the artificial parameter can not be measured by a physical sensor.

11. The machine-accessible medium of claim 8, wherein the identified data used by the first virtual sensor is formed from a combination of data sources comprising at least two of the following:

a database, a machine tool of the at least one machine tool, a real sensor attached to the machine tool, an external physical sensor associated with the machine tool, a second virtual sensor, and a third virtual sensor.

12. The machine-accessible medium of claim 8, the method further comprising:

analyzing the output of the first virtual sensor in real-time; and

generating an error notification in real-time based on the data analysis module analyzing the output of the first virtual sensor in real-time.

13. The machine-accessible medium of claim 12, the method further comprising:

stopping a machine tool in real-time in response to the data analysis module analyzing the output of the first virtual sensor in real-time and determining a fault condition.

14. The machine-accessible medium of claim 8, wherein accessing and executing the first virtual sensor in real-time occurs without having to restart a data analysis software application that performs functionality associated with the data analysis module.

15. A process monitoring apparatus, comprising:

a processor coupled to a memory;

a database to store raw data received from at least one manufacturing machine of a manufacturing facility and to store analyzed data; and

a calculated data tag manager communicatively coupled to the database, the calculated data tag manager having at least one calculated data tag that is created in real-time during data collection, wherein the calculated data tag manager executes the at least one calculated data tag in real-time during data collection by performing the calculations on the selected data to generate an output of the at least one calculated data tag with the output including an artificial parameter that is being used by a statistical process control module in real-time for statistical process monitoring, wherein the calculated data tag manager selects data to be used for performing calculations based on an algorithm associated with the at least one calculated data tag being executed in real-time, and wherein the calculated data tag manager creates, in real-time, a data collection plan based on an analysis performed by the statistical process control module, wherein creating the at least one calculated data tag further includes storing the algorithm, which is a programming language script, in a format of an extensible markup language (xml) file and copying the xml file into a file directory of the calculated data tag manager.

16. The process monitoring apparatus of claim 15, wherein the calculated data tag manager receives the selected data from at least one of an external physical sensor associated with a machine tool, a second calculated data tag, the database, the machine tool, and a real sensor attached to the machine tool.

17. The process monitoring apparatus of claim 15, wherein the calculated data tag manager further comprises a set of classes that perform operations necessary for generating data using one or more calculated data tags.

18. The process monitoring apparatus of claim 15, wherein the statistical process control module to analyze the output of the at least one calculated data tag in real-time and to generate an error notification in real-time based on analyzing the output of the at least one calculated data tag in real-time.

19. The process monitoring apparatus of claim 18, wherein the statistical process control module to stop a manufacturing machine in real-time in response to analyzing the output of the at least one calculated data tag in real-time and determining a fault condition.

20. The process monitoring apparatus of claim 19, wherein creating and executing the at least one calculated data tag in real-time occurs without having to restart or reinstall a data analysis software application that performs functionality associated with the statistical process control module.

21. The process monitoring apparatus of claim 15, further comprising a statistical process control module to analyze data and to send the analyzed data to the database.