Method for monitoring environmental condition using a mathematical model

• US 6,917,845 B2
• Filed: 03/09/2001
• Issued: 07/12/2005
• Est. Priority Date: 03/10/2000
• Status: Expired due to Term

• Current Assignee: Smiths Detection (Smiths Group International Holdings Ltd.)
• Original Assignee: Smiths Detection Incorporated
• Inventors: Steinthal, Michael Gregory, Hsiung, Chang-Meng B., Vicic, Michael Allen, Zhang, Shou-Hua, Sunshine, Steven A., Roy, Ajoy Kumar, Munoz, Bethsabeth
• Primary Examiner(s): Picard, Leo
• Assistant Examiner(s): KASENGE, CHARLES R
• Application Number:
  US09/802,519
• Publication Number:
  US 20020002414A1
• Time in Patent Office: 1,586 Days
• Field of Search: 700/28, 700/29, 700/30, 700/95, 700/31, 700/49, 700/91, 700/104, 700/108, 340/631, 340/632, 204/406, 706/45, 706/50
• US Class Current: 700/104
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/042 using digital processors G05B19/05 takes precedence
• CPC Class Codes: G05B 19/4093 characterised by part programming, e.g. entry of geometrical information as taken from a technical drawing, combining this with machining and material information to obtain control information, named part programme, for the NC machine
• CPC Class Codes: G05B 19/41855 by local area network [LAN], network structure
• CPC Class Codes: G05B 19/41865 characterised by job scheduling, process planning, material flow
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/31265 Control process by combining history and real time data
• CPC Class Codes: G05B 2219/31337 Failure information database
• CPC Class Codes: G05B 2219/31435 Paging support with display board, status monitoring and report compiling
• CPC Class Codes: G05B 2219/31457 Factory remote control, monitoring through internet
• CPC Class Codes: G05B 2219/32129 Select program for specified machine from library, file server
• CPC Class Codes: G05B 2219/32194 Quality prediction
• CPC Class Codes: G05B 2219/32196 Store audit, history of inspection, control and workpiece data into database
• CPC Class Codes: G05B 2219/32201 Build statistical model of past normal proces, compare with actual process
• CPC Class Codes: G05B 2219/32404 Scada supervisory control and data acquisition
• CPC Class Codes: G05B 2219/33209 Protocol, mailbox, email, mail system
• CPC Class Codes: G05B 2219/35095 Features library
• 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 23/0235 based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
• CPC Class Codes: G05B 23/0243 model based detection method, e.g. first-principles knowledge model
• 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: G05B 23/0286 : Modifications to the monitored process, e.g. stopping operation or adapting control
• CPC Class Codes: G05B 23/0294 : Optimizing process, e.g. process efficiency, product quality
• CPC Class Codes: Y02A 90/10 : Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
• CPC Class Codes: Y02P 90/02 : Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
• CPC Class Codes: Y02P 90/80 : Management or planning

Abstract

A method for controlling an industrial process. The method includes outputting a plurality of parameters from a process for manufacture of a substance. The method also uses each of the plurality of parameters in a computer aided process, which compares at least two of the plurality of parameters against a training set of parameters. The training set of parameters is generally predetermined. A step of determining if the at least two of the plurality of parameters are within a predetermined range of the training set of parameters also is included. Additionally, the method includes outputting a result based upon the determining step.

Claims

1. A method for monitoring an environmental condition, the method comprising:

storing a first model in a memory;

acquiring environmental data from a plurality of sensors selected from at least one of a chemical sensor, a biological sensor, and a radiation sensor;

applying the first model to the environmental data to identify a first predicted descriptor characteristic of a state of an environment; and

consulting a first knowledge based system to provide an output based upon the first predicted descriptor,

wherein the environmental data obtained from the plurality of sensors is acquired by way of a distributed network, and

wherein the environmental condition corresponds to at least one of a chemical, biological or radiation condition.

2. The method of claim 1 wherein the model is constructed from a mathematical equation describing a physical law.

3. The method of claim 1 further comprising preprocessing the data prior to applying the model.

4. The method of claim 1 wherein the output is communicated to a human operator to permit monitoring of the environment.

5. The method of claim 1 wherein the output is resident on a server and accessible to a user through a browser software program.

6. The method of claim 5 wherein the input is acquired from the process over a network of computers.

7. The method of claim 1 wherein the input is acquired from the process over a network of computers.

8. The method of claim 1 wherein the output is communicated over a network to an associated system, the associated system including at least one of a legacy system, an e-enterprise system, and a desktop application.

9. The method of claim 1 wherein the first knowledge based system is an expert system.

10. The method claim 1 further comprising receiving key preliminary information and communicating the key preliminary information downstream to the first model, such that the first predicted descriptor reflects the key preliminary information.

11. The method of claim 1 wherein the distributed network is linked to at least one external system.

12. The method of claim 11, wherein information from the at least one external system is combined with the environmental data obtained from the plurality of sensors, and wherein the combined data is provided to the first knowledge based system.

13. The method of claim 1 wherein information from the at least one external system is obtained by way of a server connected to the distributed network, and wherein information is provided to the external system by way of the server.

14. The method of claim 1, wherein the plurality of sensors include at least one chemical sensor and at least one biological sensor.

15. The method of claim 1, wherein the plurality of sensors include at least one chemical sensor and at least one radiation sensor.

16. The method of claim 1, wherein the plurality of sensors include at least one biological sensor and at least one radiation sensor.

17. The method of claim 1, further comprising:

obtaining visual information regarding the environmental condition from at least one visual sensor,

wherein the environmental data applied to the first model includes the visual information.

18. The method of claim 17, wherein the visual information includes at least one of still images and video images.

19. The method of claim 1, further comprising:

providing the output to a network, to thereby obtain the output at a location remote from the first knowledge based system.

20. A method for monitoring an environmental condition, the method comprising:

storing a first model in a memory;

acquiring environmental data from at least one of a chemical sensor, a biological sensor, and a radiation sensor;

applying the first model to the environmental data to identify a first predicted descriptor characteristic of a state of an environment; and

consulting a first knowledge based system to provide an output based upon the first predicted descriptor,

said method further comprising;

acquiring initial data from a source comprising the at least one of the chemical, biological, and a radiation sensor at a first time;

converting the initial data into electronic form;

loading the initial data into memory;

retrieving the initial data from memory;

acquiring subsequent data from the source at a second time;

assigning a first descriptor to the initial data and a second descriptor to the subsequent data;

constructing the model based upon the initial data, the subsequent data, the first descriptor, and the second descriptor; and

storing the model in memory.

21. The method of claim 20 wherein the model is constructed from one of a univariate statistical technique, a multivariate statistical technique, a neural-based approach, and a time series analysis.

22. The method of claim 20 wherein the model is constructed from one of a group of different algorithms stored in a library.

23. The method of claim 20 wherein the source is in communication with the environment, the initial data and the subsequent data reflecting a prior state of the environment.

24. The method of claim 20 wherein the source is in communication with a second environment, the initial data and the subsequent data reflecting a state of the second environment.

25. The method of claim 20 further comprising:

constructing a second model;

storing the second model in memory;

applying the second model to the environmental data to identify a second predicted descriptor characteristic of the environmental data; and

consulting the first knowledge based system to produce the output based upon the first predicted descriptor and the second predicted descriptor.

26. The method of claim 25 wherein the second model is constructed based upon the initial data, the subsequent data, the first descriptor, and the second descriptor, such that comparison of the first descriptor and the second descriptor represents a cross-validation.

27. The method of claim 25 wherein the second model is constructed from a state of a second similar environment, such that comparison of the first descriptor to the second descriptor represents an external validation.

28. The method of claim 25 wherein the knowledge based system is an expert system.

29. The method of claim 25 wherein a difference between the first predicted descriptor and the second predicted descriptor is resolved by a second expert system.