IP Library Granted Patent US 7,167,812
Granted Patent B1
US 7,167,812 · App. 10/903,160 · Granted Jan 23, 2007

Method and apparatus for high-sensitivity detection of anomalous signals in systems with low-resolution sensors

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,167,812
App. No.
10/903,160
Granted
Jan 23, 2007
Kind
B1
Abstract

A system that facilitates high-sensitivity detection of anomalous signals in systems with low-resolution sensors. During system operation, a low-resolution sensor monitors a signal within the system. The system periodically polls the low-resolution sensor in a burst mode to obtain a plurality of measurements of the signal within a specified short time interval, wherein the measurements are spread across multiple quantizing bins. The system then determines a mean value for the plurality of measurements. The system repeats the steps of polling the low-resolution sensor and determining the mean value to create a time-series of mean values. This time-series of mean values is subsequently analyzed to determine whether the signal is anomalous.

Claims (36)

1. A method for high-sensitivity detection of anomalous signals using low-resolution sensors, comprising:

using a low-resolution sensor to monitor a signal within a system;

polling the low-resolution sensor in a burst mode to obtain a plurality of measurements of the signal within a specified short time interval, wherein the measurements are spread across multiple quantizing bins;

determining a mean value for the plurality of measurements, wherein determining the mean value involves computing a simple average of the plurality of measurements;

repeating the steps of polling the low-resolution sensor and determining the mean value to create a time-series of mean values; and

analyzing the time-series of mean values to determine whether the signal is anomalous, wherein an anomalous signal indicates an incipient hardware failure.

2. The method of claim 1 , wherein determining whether the signal is anomalous involves identifying a trend by calculating a slope for the time-series of mean values.

3. The method of claim 2 , wherein calculating the slope for the time-series of mean values involves using Sen's slope technique.

4. The method of claim 2 , wherein slope values departing from zero indicate an anomaly within the system.

5. The method of claim 1 , wherein monitoring the signal with the low-resolution sensor involves monitoring the signal at a site where a noise level accompanying the signal is maximized so as to ensure that measurements are spread out across multiple quantizing bins.

6. The method of claim 1 , wherein repeating the steps of polling the low-resolution sensor and determining the mean value involves waiting a specified interval prior to performing each repetition.

7. The method of claim 1 , wherein the plurality of measurements includes at least one-hundred measurements.

8. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for high-sensitivity detection of anomalous signals using low-resolution sensors, the method comprising:

using a low-resolution sensor to monitor a signal within a system;

polling the low-resolution sensor in a burst mode to obtain a plurality of measurements of the signal within a specified short time interval, wherein the measurements are spread across multiple quantizing bins;

determining a mean value for the plurality of measurements, wherein determining the mean value involves computing a simple average of the plurality of measurements;

repeating the steps of polling the low-resolution sensor and determining the mean value to create a time-series of mean values; and

analyzing the time-series of mean values to determine whether the signal is anomalous, wherein an anomalous signal indicates an incipient hardware failure.

9. The computer-readable storage medium of claim 8 , wherein determining whether the signal is anomalous involves identifying a trend by calculating a slope for the time-series of mean values.

10. The computer-readable storage medium of claim 9 , wherein calculating the slope for the time-series of mean values involves using Sen's slope technique.

11. The computer-readable storage medium of claim 9 , wherein slope values departing from zero indicate an anomaly within the system.

12. The computer-readable storage medium of claim 8 , wherein monitoring the signal with the low-resolution sensor involves monitoring the signal at a site where a noise level accompanying the signal is maximized so as to ensure that measurements are spread out across multiple quantizing bins.

13. The computer-readable storage medium of claim 8 , wherein repeating the steps of polling the low-resolution sensor and determining the mean value involves waiting a specified interval prior to performing each repetition.

14. The computer-readable storage medium of claim 8 , wherein the plurality of measurements includes at least one-hundred measurements.

15. An apparatus for high-sensitivity detection of anomalous signals using low-resolution sensors, comprising:

a low-resolution sensor configured to monitor a signal within a system;

a polling mechanism configured to polling the low-resolution sensor in a burst mode to obtain a plurality of measurements of the signal within a specified short time interval, wherein the measurements are spread across multiple quantizing bins;

a mean determining mechanism configured to determine a mean value for the plurality of measurements, wherein determining the mean value involves computing a simple average of the plurality of measurements;

a repeating mechanism configured to repeat the steps of polling the low-resolution sensor and determining the mean value to create a time-series of mean values; and

and an analyzing mechanism configured to analyze the time-series of mean values to determine whether the signal is anomalous.

16. The apparatus of claim 15 , wherein determining whether the signal is anomalous involves identifying a trend by calculating a slope for the time-series of mean values.

17. The apparatus of claim 16 , wherein calculating the slope for the time-series of mean values involves using Sen's slope technique.

18. The apparatus of claim 16 , wherein slope values departing from zero indicate an anomaly within the system.

19. The apparatus of claim 15 , wherein monitoring the signal with the low-resolution sensor involves monitoring the signal at a site where a noise level accompanying the signal is maximized so as to ensure that measurements are spread out across multiple quantizing bins.

20. The apparatus of claim 15 , wherein repeating the steps of polling the low-resolution sensor and determining the mean value involves waiting a specified interval prior to performing each repetition.

21. The apparatus of claim 15 , wherein the plurality of measurements includes at least one-hundred measurements.

Assignments (2)
MERGER AND CHANGE OF NAME Recorded Dec 16, 2015
From: ORACLE USA, INC.; SUN MICROSYSTEMS, INC.; ORACLE AMERICA, INC.
To: ORACLE AMERICA, INC.
Reel/Frame 037302/0683 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 29, 2004
From: URMANOV, ALEKSEY M.; VAIDYANATHAN, KALYANARAMAN; GROSS, KENNY C.
To: SUN MICROSYSTEMS, INC.
Reel/Frame 015643/0566 →