APPARATUS AND METHOD FOR SELECTION OF FAULT DETECTION ALGORITHMS FOR A BUILDING MANAGEMENT SYSTEM

• US 20140325291A1
• Filed: 01/24/2014
• Published: 10/30/2014
• Est. Priority Date: 04/29/2013
• Status: Abandoned Application

• Current Assignee: Enernoc
• Original Assignee: Enernoc
• Inventors: Spivey, Edward C., Spivey, Lindsay K.
• Application Number:
  US14/162,820
• Publication Number:
  US 20140325291A1
• Time in Patent Office: Days
• US Class Current: 714/48
• CPC Class Codes: G01M 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/24033 Failure, fault detection and isolation
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G05B 2219/37537 Virtual sensor
• CPC Class Codes: G05B 23/0213 Modular or universal configuration of the monitoring system, e.g. monitoring system having modules that may be combined to build monitoring program; monitoring system that can be applied to legacy systems; adaptable monitoring system; using different communication protocols
• CPC Class Codes: G05B 23/0218 characterised by the fault detection method dealing with either existing or incipient faults
• 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 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: G06F 11/0751 Error or fault detection not based on redundancy power supply failures G06F1/30; network fault management H04L41/06

Abstract

An apparatus for detecting component faults monitored by a building management system (BMS), including an automatic fault detection (AFD) element, coupled to the BMS, that monitors samples generated by the BMS indicating operative states of the components, and that employs the data samples to determine if one or more of the components are faulty. The AFD element includes a run time modeling element and a fault detection algorithm element. The modeling element employs the samples as inputs to execute one or more fault algorithms retrieved from a system model, and generates outputs that indicate if the one or more of the components are faulty. The algorithm element is coupled to the system model, and employs normalized/standardized datapoints representing the samples to select the one or more fault algorithms for storage in the system model, where the one or more fault algorithms are selected from a standard fault algorithm data base.

Claims

1. An apparatus for detecting faults of components monitored by a building management system (BMS), the apparatus comprising:

an automatic fault detection (AFD) element, coupled to the BMS, configured to monitor, in real time, data samples generated by the BMS indicating operative states of the components, and configured to employ said data samples to determine if one or more of the components are faulty, said AFD element comprising;

a run time modeling element, configured employ said data samples as inputs to execute one or more fault algorithms retrieved from a system configuration model, and configured to generate outputs to said one or more fault algorithms that indicate if said one or more of the components are faulty; and

a fault detection algorithm element, coupled to said system configuration model, configured to employ normalized and standardized datapoints representing said data samples to automatically select said one or more fault algorithms for storage in said system configuration model, wherein said one or more fault algorithms are selected from a standard fault algorithm data base.

2. The apparatus as recited in claim 1, wherein said AFD element is also coupled to one or more energy consumption meters, and wherein said run time modeling element additionally employs energy consumption data generated by said one or more energy consumption meters as inputs to said one or more fault algorithms.

3. The apparatus as recited in claim 2, wherein said AFD element is coupled to an analytics server, and wherein said analytics server is configured to provide additional data for use by said fault detection algorithm element in selection of said one or more fault algorithms.

4. The apparatus as recited in claim 3, wherein said additional data comprises meteorological data, a building plan, a site survey, or installer notes.

5. The apparatus as recited in claim 1, wherein said system configuration model comprises one or more subsystems of related ones of the components, and wherein said related ones of the components are tagged according to type, size, and relative location.

6. The apparatus as recited in claim 1, wherein said AFD element further comprises:

a data normalizing element, configured to generate and store for use by said run time modeling element, equations used to normalize said data samples, along with corresponding properties of said data samples.

7. The apparatus as recited in claim 1, wherein said AFD element further comprises:

a virtual datapoint creating element, configured to estimate one or more synthesized datapoints that may be required by said one or more fault algorithms during execution by said run time modeling element.

8. An apparatus for detecting faults of components, the apparatus comprising:

a building management system (BMS), configured to control and monitor operative states of the components, and configured to generate data samples of said operative states;

an automatic fault detection (AFD) element, coupled to said BMS, configured to monitor, in real time, said data samples, and configured to employ said data samples to determine if one or more of the components are faulty, said AFD element comprising;

a run time modeling element, configured employ said data samples as inputs to execute one or more fault algorithms retrieved from a system configuration model, and configured to generate outputs to said one or more fault algorithms that indicate if said one or more of the components are faulty; and

a fault detection algorithm element, coupled to said system configuration model, configured to employ normalized and standardized datapoints representing said data samples to automatically select said one or more fault algorithms for storage in said system configuration model, wherein said one or more fault algorithms are selected from a standard fault algorithm data base.

9. The apparatus as recited in claim 8, wherein said AFD element is also coupled to one or more energy consumption meters, and wherein said run time modeling element additionally employs energy consumption data generated by said one or more energy consumption meters as inputs to said one or more fault algorithms.

10. The apparatus as recited in claim 9, wherein said AFD element is coupled to an analytics server, and wherein said analytics server is configured to provide additional data for use by said fault detection algorithm element in selection of said one or more fault algorithms.

11. The apparatus as recited in claim 10, wherein said additional data comprises meteorological data, a building plan, a site survey, or installer notes.

12. The apparatus as recited in claim 8, wherein said system configuration model comprises one or more subsystems of related ones of the components, and wherein said related ones of the components are tagged according to type, size, and relative location.

13. The apparatus as recited in claim 8, wherein said AFD element further comprises:

a data normalizing element, configured to generate and store for use by said run time modeling element, equations used to normalize said data samples, along with corresponding properties of said data samples.

14. The apparatus as recited in claim 8, wherein said AFD element further comprises:

a virtual datapoint creating element, configured to estimate one or more synthesized datapoints that may be required by said one or more fault algorithms during execution by said run time modeling element.

15. A method for detecting faults of components monitored by a building management system (BMS), the method comprising:

monitoring, in real time, data samples generated by the BMS indicating operative states of the components, and employing the data samples to determine if one or more of the components are faulty, said monitoring comprising;

first using the data samples as inputs to execute one or more fault algorithms retrieved from a system configuration model, and generating outputs to the one or more fault algorithms that indicate if the one or more of the components are faulty; and

second using normalized and standardized datapoints representing the data samples to automatically select the one or more fault algorithms for storage in the system configuration model, wherein the one or more fault algorithms are selected from a standard fault algorithm data base.

16. The method as recited in claim 15, wherein said first using comprises:

third using energy consumption data generated by the one or more energy consumption meters as inputs to the one or more fault algorithms.

17. The method as recited in claim 16, further comprising:

providing additional data for said second using in selection of the one or more fault algorithms.

18. The method as recited in claim 17, wherein the additional data comprises meteorological data, a building plan, a site survey, or installer notes.

19. The method as recited in claim 15, wherein the system configuration model comprises one or more subsystems of related ones of the components, and wherein the related ones of the components are tagged according to type, size, and relative location.

20. The method as recited in claim 15, further comprising:

generating and storing for use by said first using, equations used to normalize the data samples, along with corresponding properties of the data samples.

21. The method as recited in claim 15, further comprising:

estimating one or more synthesized datapoints that may be required by the one or more fault algorithms during execution by said first using.