Method and apparatus for remotely controlling sensor processing algorithms to expert sensor diagnoses

• US 5,122,976 A
• Filed: 03/12/1990
• Issued: 06/16/1992
• Est. Priority Date: 03/12/1990
• Status: Expired due to Fees

• Current Assignee: Siemens Westinghouse Power Corporation
• Original Assignee: Westinghouse Electric Corporation (Paramount Global (f/k/a ViacomCBS Inc.))
• Inventors: Bellows, James C., Fridsma, Daniel E.
• Primary Examiner(s): Black, Thomas G.
• Application Number:
  US07/491,926
• Time in Patent Office: 827 Days
• Field of Search: 364/550, 364/551.01, 364/513, 364/131, 364/138, 364/571.01, 364/572, 364/574, 364/580
• US Class Current: 702/185
• CPC Class Codes: G05B 2223/06 Remote monitoring
• 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 23/0229 knowledge based, e.g. expert systems; genetic algorithms
• CPC Class Codes: Y10S 706/906 Process plant

Abstract

A system is disclosed including a data center computer for data collection and process control of a complex processing plant. The data center computer collects raw sensor data. The raw data is sent, by a conventional communicator routine, to a remote expert system for sensor diagnosis of faulty sensors. The diagnostic results, which include a calculation control value, are returned to the data center computer where the results are used to control sensor processing routines used to either control the plant based on the collected raw sensor data or to further process the sensor data. The further processed sensor data can then be used for high level system diagnoses.

Claims

1. An apparatus, comprising:

control means for sampling sensor data and performing sensor data processing; and

diagnostic means for diagnosing a sensor malfunction using the sensor data, and said control means performing the sensor data processing responsive to the diagnosis.

2. An apparatus as recited in claim 1, wherein said diagnostic means transmits a control parameter controlling sensor data processing by said control means.

3. An apparatus as recited in claim 1, wherein said diagnostic means comprises an expert system.

4. An apparatus as recited in claim 1, wherein said diagnostic means is located remotely with respect to said control means.

5. An apparatus as recited in claim 1, wherein a confidence factor in the diagnosis determines the sensor data processing performed by said control means.

6. An apparatus as recited in claim 1, wherein said diagnostic means communicates the results of the diagnoses to said control means using a message including a routine destination name and a control value indicating a type of sensor data processing to be performed by the destination routine.

7. An apparatus for controlling sensor data calculations comprising:

a process control computer for sampling sensor data and performing sensor data processing responsive to a diagnostic message;

a communication link coupled to said process control computer for transmitting the sensor data and the diagnostic message;

an expert system diagnostic computer coupled to said communications link for producing the diagnostic message by diagnosing malfunctioning sensors based on the transmitted sensor data.

8. A method of controlling sensor data calculations, comprising the steps of:

(a) sampling sensors to obtain raw sensor data;

(b) performing an expert system diagnoses on the raw sensor data to produce a sensor diagnosis; and

(c) selectively performing sensor data processing responsive to the diagnoses.

9. A method as recited in claim 8, further comprising communicating the diagnosis via a message that designates a destination routine and contains a processing routine control value.

10. A system that controls sensor data calculations responsive to a sensor diagnosis, comprising:

control means for sampling sensor data and performing sensor data processing; and

diagnostic means for diagnosing a sensor malfunction using the sensor data, and said control means performing the sensor data processing responsive to the diagnosis and said diagnostic means including a data

structure for communicating the sensor diagnosis and comprising a message node including a confidence factor in the diagnosis, a destination routine indicator and a calculation control value.