Building management system with fault analysis

Patent metadata

Field	Value
Publication number	US-9753455-B2
Application number	US-201113077508-A
Country	US
Kind code	B2
Filing date	Mar 31, 2011
Priority date	Jun 22, 2009
Publication date	Sep 5, 2017
Grant date	Sep 5, 2017

Abstract

A controller for a building management system is configured to analyze faults in the building management system. The controller detects a fault in the building management system by evaluating data of building management system using a system of rules. The controller determines a conditional probability for each of a plurality of possible fault causes given the detected fault. The controller determines the most likely fault cause by comparing the determined probabilities and electronically reports the most likely fault cause.

First claim

The invention claimed is:

1. A computerized method for analyzing faults in a building management system, the method comprising:
at a computer of the building management system, detecting a fault by evaluating data of the building management system using a system of rules;
determining a conditional probability for each of a plurality of possible fault causes of the detected fault, wherein determining the conditional probability for each of the plurality of possible fault causes of the detected fault comprises:
determining whether two or more faults having one or more overlapping causes have been detected, and
increasing a conditional probability for the one or more overlapping causes in response to a determination that two or more faults having one or more overlapping causes have been detected;

determining a most likely fault cause of the detected fault by comparing the determined probabilities; and
electronically reporting the most likely fault cause of the detected fault.

2. The method of claim 1 , wherein determining the conditional probability for each of the plurality of possible fault causes of the detected fault comprises:
accounting for a marginal probability of the occurrence of the fault and a marginal probability of the occurrence of the possible fault cause.

3. The method of claim 2 , wherein determining the conditional probability for each of the plurality of possible fault causes of the detected fault comprises:
updating prior and marginal probabilities associated with the fault and one or more possible fault causes; and
applying Bayes' theorem to at least one of the possible fault causes of the detected fault and the updated prior and marginal probabilities.

4. The method of claim 3 , wherein updating the prior and marginal probabilities comprises receiving feedback from a user input module regarding an accuracy of prior electronic reporting of most likely fault causes.

5. The method of claim 1 , wherein determining a conditional probability for each of a plurality of possible fault causes of the detected fault comprises:
recalling the conditional probability of the detected fault and for each possible fault cause from memory.

6. The method of claim 1 , wherein electronically reporting the most likely fault cause comprises at least one of:
(a) causing an indication of the most likely fault cause to be displayed on an electronic display in communication with the computer;
(b) causing an indication of the most likely fault cause to be transmitted to another device or remote source; and
(c) adding the most likely fault cause to a report for the detected fault.

7. The method of claim 1 , wherein evaluating data of the building management system using a system of rules comprises comparing current information of the building management system to historical information of the building management system.

8. The method of claim 1 , further comprising:
causing expanding data logging of the building management system.

9. The method of claim 8 , further comprising:
using data obtained by the expanded data logging to update at least one of prior and marginal probabilities associated with the fault and/or one or more possible fault causes;
applying Bayes' theorem to at least one of the possible fault causes given the detected fault and the updated prior probabilities or marginal probabilities.

10. A method for analyzing faults in a building management system, comprising:
at a supervisory controller of the building management system, detecting a fault by evaluating data of one or more remote devices in the building management system;
in response to detecting the fault and by the supervisory controller, acquiring and storing new data from the building management system, wherein the new data comprises variables that are not received and stored by the supervisory controller when the fault is not detected, and wherein the acquiring and storing of the new data occurs without human intervention; and
analyzing the detected fault using the new data.

11. The method of claim 10 , wherein analyzing the detected fault comprises conducting one or more calculations to estimate a source for the fault.

12. The method of claim 10 , wherein acquiring the new data comprises sending a request to the one or more remote devices of the building management system for the new data.

13. The method of claim 10 , wherein acquiring the new data comprises receiving and storing a data point normally broadcast by one or more devices of the building management system but not normally acquired or stored by the supervisory controller.

14. The method of claim 10 , wherein acquiring the new data comprises sending a command to the one or more remote devices of the building management system.

15. The method of claim 10 , wherein the remote device that generated the data used in detection of the fault is a different remote device than that which generates the new data for acquisition and storing.

16. The method of claim 10 , further comprising:
determining whether additional information is needed to analyze the detected fault,
wherein the acquiring and storing of the new data from the building management system is performed in response to a determination that additional information is needed.

17. The method of claim 16 , wherein determining whether additional information is needed comprises:
comparing a set of variables needed to analyze the detected fault with a set of available or subscribed variables of the building management system;
determining that additional information is needed if the set of needed variables includes one or more variables not in the set of available or subscribed variables; and
determining that additional information is not needed if the set of needed variables does not include any variables that are not in the set of available or subscribed variables.

18. A supervisory controller for a building management system, comprising:
a communications interface; and
a processing circuit configured to receive data from one or more remote devices in the building management system via the communications interface;
wherein the processing circuit is configured to detect a fault by evaluating the received data; and
wherein the processing circuit is configured to acquire and store new data from the building management system in response to detecting the fault and without human intervention, wherein the new data comprises variables that are not received and stored by the processing circuit when the fault is not detected.

19. Non-transitory computer-readable media with computer-executable instructions embodied thereon that when executed by a computer system perform a method for analyzing faults in a building management system, wherein the instructions comprise:
instructions for detecting a fault by evaluating data of the building management system using a system of rules;
instructions for determining a conditional probability for each of a plurality of possible fault causes given the detected fault, wherein determining the conditional probability for each of the plurality of possible fault causes of the detected fault comprises:
determining whether two or more faults having one or more overlapping causes have been detected, and
increasing a conditional probability for the one or more overlapping causes in response to a determination that two or more faults having one or more overlapping causes have been detected;

instructions for determining a most likely fault cause of the detected fault by comparing the determined probab

Assignees

• Drees Kirk H
• Johnson Controls Tech Co

Inventors

• Drees Kirk H

Classifications

• H02J2103/30

  Simulating, planning, modelling, reliability check or computer assisted design [CAD] of electric power networks · CPC title

• H02J13/1321

  using a wired telecommunication network or a data transmission bus · CPC title

• H02J13/10

  characterised by displaying of information or by user interaction, e.g. supervisory control and data acquisition [SCADA] systems · CPC title

• H02J13/14

  the power network being locally controlled, e.g. home energy management systems [HEMS] · CPC title

• H02J13/12

  Monitoring network conditions, e.g. electrical magnitudes or operational status · CPC title