Granted Patent B2

US 12,664,444 · App. 18/390,461 · Granted Jun 23, 2026

Inventors: Kirk H. Drees (Cedarburg, WI); Donald R. Albinger (New Berlin, WI); Shawn D. Schubert (Oak Creek, WI); Karl F. Reichenberger (Mequon, WI); Daniel M. Curtis (Franklin, WI); Andrew J. Boettcher (Wauwatosa, WI); Jason T. Sawyer (Greendale, WI); Miguel Galvez (Milwaukee, WI); Walter Martin (Ballymena, GB); Ryan A. Piaskowski (Milwaukee, WI); Vaidhyanathan Venkiteswaran (Brookfield, WI); Clay G. Nesler (Milwaukee, WI); Siddharth Goyal (Milwaukee, WI); Thomas M. Seneczko (Milwaukee, WI); Young M. Lee (Old Westbury, NY); Sudhi R. Sinha (Milwaukee, WI)

Assignee: Tyco Fire & Security GmbH

G06N5/022G06N3/0442G06N5/04G06N20/10G16Y10/80H04L12/2803H04L12/2821H04L12/2827H04L41/0645H04L43/08H04L67/12H04L67/125

Abstract

Claims (66)

1 . A building system comprising:

one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to:

collect building device data of a building device, the building device data comprising a plurality of data samples of a data point of the building device;

collect network traffic level data of a building network of a building;

determine whether the building device data is reliable based on the network traffic level data;

generate a time correlated data stream for the data point based on a determination whether the building device data is reliable based on the network traffic level data, the time correlated data stream comprising values of the plurality of data samples of the data point; and

generate a time correlated reliability data stream for the data point, the time correlated reliability data stream comprising a plurality of reliability values time correlated to corresponding values of the plurality of data samples of the data point and indicating reliability of the values of the plurality of data samples of the data point.

2 . The building system of claim 1 , wherein the instructions cause the one or more processors to send, via a network, the time correlated data stream and the time correlated reliability data stream to an artificial intelligence (AI) platform.

3 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

generate, based on the time correlated data stream for the data point, a virtual time correlated data stream for a virtual data point, the virtual time correlated data stream comprising a plurality of virtual values based on the values of the plurality of data samples of the data point; and

generate, based on the time correlated reliability data stream, a virtual time correlated reliability data stream for the virtual data point, the virtual time correlated reliability data stream comprising a plurality of virtual reliability values indicating reliability of the plurality of virtual values, the plurality of virtual reliability values based on the plurality of reliability values.

4 . The building system of claim 3 , wherein the time correlated data stream, the time correlated reliability data stream, the virtual time correlated data stream, and the virtual time correlated reliability data stream are each a timeseries data stream comprising a plurality of time indicators and a plurality of timeseries values, each timeseries value of the plurality of timeseries values linked to a time indicator of the plurality of time indicators.

5 . The building system of claim 1 , wherein the instructions cause the one or more processors to use both the time correlated data stream and the time correlated reliability data stream to train an artificial intelligence (AI) model;

wherein training the AI model using both the time correlated data stream and the time correlated reliability data stream provides the AI model with a higher number of dimensions relative to training the AI model using only the time correlated data stream.

6 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

use the time correlated data stream and the time correlated reliability data stream to train an artificial intelligence (AI) model; and

use the AI model to perform a fault detection or diagnostics process.

7 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

determine a period of time associated with a network traffic level above a predefined level based on the network traffic level data;

filter the building device data to exclude a portion of the building device data associated with the period of time; and

send, via a network, the building device data filtered by the one or more processors to an AI platform.

8 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

determine network activity associated with the building device based on the network traffic level data;

determine whether a data network burst has occurred for the building device by determining whether the network activity is greater than a predefined amount during a predefined period of time; and

generate the time correlated reliability data stream for the data point based on a second determination that the data network burst has occurred.

9 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

determine whether a time period is associated with high network activity by determining whether the network traffic level data indicates a network traffic level greater than a predefined amount during the time period; and

update the time correlated data stream by reordering one or more data values of the time correlated data stream collected during the time period in response to a second determination that the network traffic level is greater than the predefined amount during the time period.

10 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

analyze the network traffic level data to generate a building network report for the building network; and

generate the time correlated reliability data stream for the data point based on the building network report;

wherein the building network report comprises at least one of:

a first indication of equipment requiring service;

a second indication of whether resources of network equipment of the building network are being properly utilized; or

a third indication to perform one or more software updates for the building network.

11 . A method of a building system comprising:

collecting, by one or more processing circuits, building device data of a building device, the building device data comprising a plurality of data samples of a data point of the building device;

collecting, by the one or more processing circuits, network traffic level data of a building network of a building;

determining, by the one or more processing circuits, whether the building device data is reliable based on the network traffic level data;

generating, by the one or more processing circuits, a time correlated data stream for the data point based on a determination whether the building device data is reliable based on the network traffic level data, the time correlated data stream comprising values of the plurality of data samples of the data point; and

generating, by the one or more processing circuits, a time correlated reliability data stream for a reliability data point, the time correlated reliability data stream comprising a plurality of reliability values time correlated to corresponding values of the plurality of data samples of the data point and indicating reliability of the values of the plurality of data samples of the data point.

12 . The method of claim 11 , further comprising sending, via a network, the time correlated data stream and the time correlated reliability data stream to an artificial intelligence (AI) platform.

13 . The method of claim 11 , further comprising:

generating, by the one or more processing circuits, based on the time correlated data stream for the data point, a virtual time correlated data stream for a virtual data point, the virtual time correlated data stream comprising a plurality of virtual values based on the values of the plurality of data samples of the data point; and

generating, by the one or more processing circuits, based on the time correlated reliability data stream, a virtual time correlated reliability data stream for the virtual data point, the virtual time correlated reliability data stream comprising a plurality of virtual reliability values indicating reliability of the plurality of virtual values, the plurality of virtual reliability values based on the plurality of reliability values.

14 . The method of claim 13 , wherein the time correlated data stream, the time correlated reliability data stream, the virtual time correlated data stream, and the virtual time correlated reliability data stream are each a timeseries data stream comprising a plurality of time indicators and a plurality of timeseries values, each timeseries value of the plurality of timeseries values linked to a time indicator of the plurality of time indicators.

15 . The method of claim 11 , further comprising using both the time correlated data stream and the time correlated reliability data stream to train an artificial intelligence (AI) model;

wherein training the AI model using both the time correlated data stream and the time correlated reliability data stream provides the AI model with a higher number of dimensions relative to training the AI model using only the time correlated data stream.

16 . The method of claim 11 , further comprising:

using the time correlated data stream and the time correlated reliability data stream to train an artificial intelligence (AI) model; and

using the AI model to perform a fault detection or diagnostics process.

17 . A building device comprising:

one or more memory devices configured to store instructions; and

one or more processors configured to execute the instructions causing the one or more processors to:

collect building device data of the building device, the building device data comprising a plurality of data samples of a data point of the building device;

collect network traffic level data of a building network of a building;

generate a time correlated data stream for the data point, the time correlated data stream comprising values of the plurality of data samples of the data point;

determine whether the building device data is reliable based on the network traffic level data;

generate a time correlated reliability data stream for the data point based on a determination whether the building device data is reliable based on the network traffic level data, the time correlated reliability data stream comprising a plurality of reliability values time correlated to corresponding values of the plurality of data samples of the data point and indicating reliability of the values of the plurality of data samples of the data point.

18 . The building device of claim 17 , wherein executing the instructions causes the one or more processors to send, via a network, the time correlated data stream and the time correlated reliability data stream to an artificial intelligence (AI) platform.

19 . The building device of claim 17 , wherein executing the instructions causes the one or more processors to use both the time correlated data stream and the time correlated reliability data stream to train an artificial intelligence (AI) model;

wherein training the AI model using both the time correlated data stream and the time correlated reliability data stream provides the AI model with a higher number of dimensions relative to training the AI model using only the time correlated data stream.

20 . The building device of claim 17 , wherein the instructions cause the one or more processors to:

determine a period of time associated with a network traffic level above a predefined level based on the network traffic level data;

filter the building device data to exclude a portion of the building device data associated with the period of time; and

send, via a network, the building device data filtered by the one or more processors to an artificial intelligence (AI) platform.

Assignments (4)

Continuity (3)

References Cited (400)