Building management system with auto-configuration using existing points

Patent metadata

Field	Value
Publication number	US-12058212-B2
Application number	US-202117170668-A
Country	US
Kind code	B2
Filing date	Feb 8, 2021
Priority date	Oct 30, 2020
Publication date	Aug 6, 2024
Grant date	Aug 6, 2024

Abstract

A method for commissioning a building comprises identifying a building asset within a digital representation of a building having one or more parameters describing relationships of the building asset within the building, controlling one or more other building assets included within the digital representation to change an environmental parameter of the building, monitoring a response of at least one of the building asset or one of the one or more other building assets to the change in the environmental parameter, generating a parameter for the digital representation associated with the building asset based on the monitoring, and updating the digital representation using the parameter.

First claim

What is claimed is:

1. A method for commissioning a building, comprising:
identifying a building asset within a digital representation of the building having one or more parameters describing relationships of the building asset within the building;
selecting and executing, based on a type of sensor data monitored by the building asset, a predetermined control action for one or more other building assets included within the digital representation to change an environmental parameter of the building;
monitoring a response of at least one of the building asset or one of the one or more other building assets to the change in the environmental parameter; and
updating the digital representation to include a parameter defining a health metric for a relationship between the building asset and at least one of the one or more other building assets based on a comparison of the monitored response to the predetermined control action to an expected response, wherein the parameter defining the health metric describes a confidence level in a validity of one of the one or more parameters.

2. The method of claim 1 , further comprising updating at least one of the one or more parameters using the parameter defining the health metric.

3. The method of claim 1 , wherein updating the digital representation includes analyzing a covariance between sensor measurements of the one or more other building assets associated with the change in the environmental parameter of the building.

4. The method of claim 1 , wherein the digital representation includes a graph data structure and wherein the method further comprises updating one or more portions of the graph data structure to represent the relationship of the building asset.

5. The method of claim 1 , wherein the digital representation includes a graph data structure and wherein the method further comprises comparing versions of the graph data structure representing at least a portion of the building to identify changes between the versions.

6. The method of claim 5 , wherein identifying the building asset includes selecting an asset based on an identified change between the versions of the graph data structure.

7. One or more non-transitory computer-readable storage media having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive a digital representation of a building having nodes describing entities representing spaces, locations, building assets, points, or events within the building and edges describing one or more relationships between nodes, the digital representation comprising an identified building asset;
control, based on a type of sensor data monitored by the identified building asset, one or more first building assets included within the digital representation to change an environmental parameter of the building;
monitor a response of the identified building asset, at least one of the one or more first building assets, or one or more second building assets to the change in the environmental parameter; and
update the digital representation to include a parameter defining a health metric of a node or edge associated with the one or more second building assets or the identified building asset based on a comparison of the monitored response to an expected response, wherein the parameter defining the health metric describes a confidence level in a validity of one of the one or more relationships.

8. The one or more non-transitory computer-readable storage media of claim 7 , wherein the node or edge is generated based upon the confidence level in the validity of the one or more relationships.

9. The one or more non-transitory computer-readable storage media of claim 7 , wherein the instructions, when executed, further cause the one or more processors to control another building asset based upon the monitored response to at least one of the identified building asset, the one or more first building assets, or the one or more second building assets.

10. The one or more non-transitory computer-readable storage media of claim 7 , wherein generating the confidence level includes analyzing a covariance between sensor measurements of the identified building asset or the one or more second building assets associated with the change in the environmental parameter of the building.

11. The one or more non-transitory computer-readable storage media of claim 7 , wherein the digital representation includes a graph data structure and wherein the instructions, when executed, further cause the one or more processors to update one or more portions of the graph data structure to represent a relationship.

12. The one or more non-transitory computer-readable storage media of claim 7 , wherein the digital representation includes a graph data structure and wherein the one or more processors are further configured to compare versions of the graph data structure representing at least a portion of the building to identify changes between the versions.

13. The one or more non-transitory computer-readable storage media of claim 12 , wherein the identified building asset is selected based on an identified change between the versions of the graph data structure.

14. A building management system (BMS) comprising a processing circuit including a processor and memory, the memory having instructions stored thereon that, when executed by the processor, cause the processing circuit to:
identify a building asset within a digital representation of a building having nodes representative of building assets within the building and edges describing one or more relationships of the building asset within the building;
select and execute, based on a type of data monitored by the building asset, a predetermined control action for one or more other building assets included within the digital representation to change an environmental parameter of the building;
monitor a response of at least one of the building asset or one of the one or more other building assets to the predetermined control action; and
update the digital representation to include a parameter defining a health metric of a node or edge associated with the building asset based on a comparison of the monitored response to the predetermined control action to an expected response, wherein the parameter defining the health metric describes a confidence level in a validity of one of the one or more relationships.

15. The building management system (BMS) of claim 14 , wherein the node or edge is generated based upon the confidence level in the validity of the one or more relationships.

16. The building management system (BMS) of claim 14 , wherein the processing circuit is further configured to execute another predetermined control action based upon the monitored response to the predetermined control action.

17. The building management system (BMS) of claim 14 , wherein generating the confidence level includes analyzing a covariance between sensor measurements of the one or more other building assets associated with the change in the environmental parameter of the building.

18. The building management system (BMS) of claim 14 , wherein the digital representation includes a graph data structure and wherein the processing circuit is further configured to update one or more portions of the graph data structure to represent a relationship of the building asset.

19. The building management system (BMS) of claim 14 , wherein the digital representation includes a graph data structure and wherein the processing circuit is further configured

Assignees

• Tyco Fire & Security Gmbh

Inventors

• Paulson Erik S
• Shatdal Ambuj
• Jin Zhongyi
• Zhang Chenlu
• Park Youngchoon

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06F18/213

  Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods · CPC title

• G06F18/23

  Clustering techniques · CPC title