System and method providing early prediction and forecasting of false alarms by applying statistical inference models

• US 10,522,031 B2
• Filed: 09/01/2015
• Issued: 12/31/2019
• Est. Priority Date: 09/01/2015
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Nalukurthy, RajeshBabu, Sethi, Aatish, Naraharisetti, Kanaka Nagendra Prasad, Singam, Kiran Reddy
• Primary Examiner(s): Nilsson, Eric
• Application Number:
  US14/842,278
• Publication Number:
  US 20170061783A1
• Time in Patent Office: 1,582 Days
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G08B 13/19682 Graphic User Interface [GUI] presenting system data to the user, e.g. information on a screen helping a user interacting with an alarm system
• CPC Class Codes: G08B 17/10 Actuation by presence of smoke or gases , e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
• CPC Class Codes: G08B 21/16 Combustible gas alarms
• CPC Class Codes: G08B 25/008 Alarm setting and unsetting, i.e. arming or disarming of the security system
• CPC Class Codes: G08B 25/009 Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range
• CPC Class Codes: G08B 25/08 using communication transmission lines G08B13/19658, G08B21/0286, G08B25/016 take precedence
• CPC Class Codes: G08B 25/14 Central alarm receiver or annunciator arrangements
• CPC Class Codes: G08B 26/008 central annunciator means of the sensed conditions, e.g. displaying or registering
• CPC Class Codes: G08B 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
• CPC Class Codes: G08B 29/186 Fuzzy logic; neural networks
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Abstract

A diagnostics and prediction system including a cloud system that continuously collects operating parameters from each of a number of environmental sensors and provides access to this data by a plurality of processing applications including (1) a predictive modeling system including (a) a health prediction system, (b) a sensor false alarm prediction system, (c) a zone false alarm prediction system and (d) a reporting system, (2) a system that diagnoses and predicts environmental hazardous areas and clusters areas based upon concentrations of CO in the site or building; and (3) a battery prediction system that predicts a battery life for the sensor.

Claims

1. A system comprising:

a security system having a sensor that detects threats within a secured area;

a monitoring system, coupled to the security system, including memory with instructions that can be executed by a processor to collect operating parameters from the sensor, maintain a history of the operating parameters in a database, and provide access to the operating parameters by a plurality of processing applications, the plurality of processing applications comprising;

a predictive modeling application comprising;

a health prediction system that compares, via the processor, values of the operating parameters with one or more thresholds to classify the sensor as either good or bad;

a sensor false alarm prediction system that predicts false alarms in the secured area, wherein the sensor false alarm prediction system mines the operating parameters to find a rate of change of the operating parameters and changes in the operating parameters, in response to the rate of change of the operating parameters remaining constant, the predictive modeling application extrapolates the rate of change using linear regression over a time period, in response to the rate of change of the operating parameters being intermittent, the predictive modeling application extrapolates using a non-linear regression over the time period, and predicts a probability of the false alarms based upon the time period; and

a reporting system that generates, via the processor, a possible false alarm report including information from the health prediction system and the sensor false alarm prediction system and sends the possible false alarm report to an authorized human user.

2. The system as in claim 1 wherein the sensor comprises a fire sensor.

3. The system as in claim 1 wherein the sensor comprises an intrusion sensor.

4. The system as in claim 1 further comprising a mapping processor that generates a two dimensional map of battery failure based upon the time period.

5. The system as in claim 1 further comprising a mapping processor that generates a two dimensional map of hazardous areas within the secured area based upon concentration of CO.

6. A system comprising:

a security system that protects a secured geographic area;

a first sensor that detects environmental threats within the secured geographic area;

a memory that saves operating parameters from the first sensor; and

a processor that analyzes the operating parameters, generates a probability report of a false alarm within X days based upon determining a rate of change over a time period in the operating parameters and extrapolates the rate of change using linear regression over the X days in response to an environment of the first sensor remaining constant and the rate of change of the operating parameters remaining constant and extrapolates the rate of change using non-linear regression over the X days in response to the rate of change of the operating parameters being intermittent, and sends the probability report to an authorized human user of the security system.

7. The system as in claim 6 wherein the memory and the processor collect the operating parameters from the first sensor, maintain a history of the operating parameters in the memory, and provide access to the operating parameters.

8. The system as in claim 7 wherein the processor executes a predictive modeling system.

9. The system as in claim 8 wherein the predictive modeling system comprises a health prediction system that compares, via the processor, values of the operating parameters with one or more thresholds to classify the first sensor as either good or bad.

10. The system as in claim 8 wherein the predictive modeling system comprises a sensor false alarm prediction system that predicts the false alarm in the secured geographic area, wherein the sensor false alarm prediction system mines the operating parameters to find the rate of change over the time in the operating parameters and changes in the operating parameters, and predicts a probability of the false alarm based upon a time period.

11. The system as in claim 8 further comprising a second sensor, wherein the predictive modeling system further comprises a zone false alarm prediction system that clusters zones of the security system based upon collected data associated with the first sensor and the second sensor and predicts a probability of the false alarms per clustered zone.

12. The system as in claim 8 wherein the predictive modeling system further comprises a reporting system that generates, via the processor, a possible false alarm report including information from a health prediction system, a sensor false alarm prediction system, and a zone false alarm prediction system and sends the possible false alarm report to the authorized human sensor.

13. The system as in claim 7 wherein the first sensor includes a CO sensor, and wherein the processor mines CO data parameters from the CO sensor, including one or more of CO concentration, CO detection state of the CO sensor, and last maintenance date of the CO sensor over a period of time, and runs a statistical interference model for the CO sensor.

14. The system as in claim 7 wherein the processor mines a battery status for the first sensor over a period of time and a network status, including at least a node status of either a parent or child node in a mesh network to predict a battery life for the first sensor.

15. A system comprising:

a security system that protects a secured geographic area;

a first sensor that detects environmental threats within the secured geographic area; and

a monitoring system embodied as a set of steps executed on a processor, wherein the monitoring system is coupled to the security system, wherein the monitoring system collects operating parameters from the first sensor, maintains a history of the operating parameters in a database, and provide access to the operating parameters by a plurality of processing applications, and

wherein the plurality of processing applications analyze the operating parameters, generate a probability report of a false alarm within X days based upon determining a rate of change over a time period in the operating parameters and in response to an environment of the first sensor remaining constant and the rate of change remaining constant extrapolating the rate of change using linear regression over the X days and in response to the rate of change being intermittent, extrapolating the rate of change using a least square method, and send the probability report to a human user of the security system.

16. The system as in claim 15 wherein the processor executes a predictive modeling system including a health prediction system that compares, via the processor, values of the operating parameters with one or more thresholds to classify the first sensor as either good or bad.

17. The system as in claim 15 wherein the processor mines device data to determine the rate of change.

18. The system as in claim 15 further comprising a second sensor, wherein the processor executes a zone false alarm prediction system that clusters zones of the security system based upon collected data associated with the first sensor and the second sensor and predicts a probability of the false alarm per clustered zone.

19. The system as in claim 15 wherein the processor executes a reporting system that generates, via the processor, a possible false alarm report including information from a health prediction system, a sensor false alarm prediction system, and a zone false alarm prediction system for maintenance operations.

20. The system as in claim 15 wherein the first sensor includes a CO sensor, and wherein the processor mines CO data parameters from the CO sensor, including one or more of CO concentration, CO detection state of the sensor, and last maintenance date of the CO sensor over a period of time, and runs a statistical inference model for the CO sensor.