Building system with performance identification through equipment exercising and entity relationships

1 . A building system of a building comprising:

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

identify, based on a relational model, one or more first relationships between a first building entity and a second building entity and one or more second relationships between a third building entity and the first building entity, wherein the one or more first relationships indicate an expected effect on the first building entity caused by operation of the second building entity when the building is not experiencing a performance issue, and the one or more second relationships indicate an expected effect on the first building entity caused by operation of the third building entity when the building is not experiencing a performance issue;

select a first exercise for the second building entity to test the one or more first relationships between the first building entity and the second building entity;

exercise the second building entity by operating building equipment represented by the second building entity in accordance with an adjusted setting defined by the first exercise to generate first building entity data associated with the second building entity, the first building entity data indicating a result of the first exercise;

identify that the building is experiencing the performance issue by analyzing the first building entity data and the one or more first relationships, wherein the performance issue is identified in response to determining, based on the first building entity data, that operating the building equipment represented by the second building entity in accordance with the first exercise did not produce the expected effect on the first building entity;

determine, based on the first building entity data, that the building equipment represented by the second building entity did not cause the performance issue;

exercise, in response to determining that the building equipment represented by the second building entity did not cause the performance issue, the third building entity by operating building equipment represented by the third building entity in accordance with an adjusted setting defined by a second exercise to generate second building entity data associated with the third building entity, the second building entity data indicating a result of the second exercise;

determine, based on the second building entity data, that the building equipment represented by the third building entity caused the performance issue; and

automatically cause an action to be initiated in response to determining that the building equipment represented by the third building entity caused the performance issue, the action comprising attempting to repair the building equipment represented by the third building entity, shutting-down the building equipment represented by the third building entity, or working around the performance issue by directing control activities around the building equipment represented by the third building entity.

2 . The building system of claim 1 , wherein the one or more instructions cause the one or more processors to identify the performance issue by analyzing at least third building entity data of the first building entity, wherein performance of the building entity is related to performance of the first building entity.

3 . The building system of claim 1 , wherein the relational model is a building graph;

wherein the one or more instructions cause the one or more processors to: receive at least a portion of the building graph, the building graph comprising a plurality of nodes representing a plurality of building entities and a plurality of edges between the plurality of nodes representing relationships between the plurality of building entities; and

identify, based on the portion of the building graph, the first building entity by identifying a particular edge of the plurality of edges between a first node of the plurality of nodes representing the second building entity and one or more second nodes of the plurality of nodes representing the first building entity.

4 . The building system of claim 1 , wherein the second building entity is a space of the building;

wherein the building equipment represented by the second building entity is associated with the space of the building.

5 . The building system of claim 1 , wherein the one or more memory devices are devices of at least one of:

a cloud platform located remote from the second building entity and configured to collect the first building entity data via one or more networks;

an on-premises server located within the building, wherein the second building entity is located within the building, wherein the on-premises server is configured to receive the first building entity data via one or more building networks of the building;

a gateway device located within the building, the gateway device configured to collect the first building entity data via the one or more building networks and push at least one of the first building entity data an indication of the performance issue to a building control platform; or

a piece of building equipment, wherein the second building entity and the first building entity are components of the piece of building equipment.

6 . The building system of claim 1 , wherein the performance issue is at least one of an equipment fault, a configuration error, or a user error.

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

perform a plurality of building entity exercises, wherein each exercise of the plurality of building entity exercises causes particular building entity data to be generated; and

in response to completing each of the plurality of building entity exercises:

determine whether the performance issue is identified by the particular building entity data of the exercise and one or more results of one or more previous exercises of the plurality of building entity exercises; and

perform a subsequent exercise in response to a determination that the performance issue is not identified by the particular building entity data and the one or more results of the one or more previous exercises.

8 . The building system of claim 7 , wherein each of the plurality of building entity exercises corresponds to one control level of a plurality of control levels of a control algorithm.

9 . The building system of claim 1 , wherein the second building entity is a first building subsystem of a plurality of building subsystems comprising a plurality of pieces of equipment;

wherein the one or more instructions cause the one or more processors to:

collect subsystem data of the plurality of building subsystems;

identify each of the plurality of building subsystems based on the subsystem data;

identify the first building subsystem of the plurality of building subsystems experiencing the performance issue by analyzing the subsystem data; and

identify one piece of equipment of the plurality of pieces of equipment of the building based on equipment data of the plurality of pieces of equipment in response to an identification of the first building subsystem experiencing the performance issue.

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

identify the first building subsystem experiencing the performance issue by comparing the subsystem data to other subsystem data of buildings similar to the building; and

identify the one piece of equipment of the plurality of pieces of equipment based on the equipment data by comparing the equipment data to other equipment data of equipment similar to the one piece of equipment of the buildings similar to the building.

11 . The building system of claim 1 , further comprising a building device comprising a processing circuit configured to:

collect building device data of the building device, the building device data indicating operations of the building device and environmental conditions measured by a sensor of the building device;

perform a self-analysis with the building device data to determine a device performance flag indicating performance of the building device; and

send, via a network, the building device data with the device performance flag to at least one of an artificial intelligence (AI) platform or the one or more processors.

12 . The building system of claim 11 , wherein the processing circuit of the building device comprises a memory device configured to store manufacturer data indicating design characteristics of the building device;

wherein the processing circuit of the building device is configured to send, via the network, the manufacturer data to at least one of the AI platform or the one or more processors.

13 . The building system of claim 11 , wherein the processing circuit of the building device is configured to:

determine whether the one or more memory devices store a filter and one or more filter parameters for the filter;

filter the environmental conditions with the filter and the one or more filter parameters in response to a determination that the one or more memory devices store the filter;

generate a filter flag based on whether the one or more memory devices store the filter and the one or more filter parameters for the filter; and

send, via the network, the building device data with the device performance flag and the filter flag to at least one of the AI platform or the one or more processors.

14 . The building system of claim 11 , wherein the processing circuit of the building device is configured to:

perform a calibration of the building device and record a calibration time indication identifying when the building device was calibrated;

generate a calibration flag based on the calibration time indication; and

send, via the network, the device performance flag and the calibration flag to at least one of the AI platform or the one or more processors.

15 . A method of a building system comprising:

identifying, by one or more processing circuits, based on a relational model, one or more first relationships between a first building entity of a building and a second building entity and one or more second relationships between a third building entity and the first building entity, wherein the one or more first relationships indicate an expected effect on the first building entity caused by operation of the second building entity when the building is not experiencing a performance issue, and the one or more second relationships indicate an expected effect on the first building entity caused by operation of the third building entity when the building is not experiencing a performance issue;

selecting, by the one or more processing circuits, a first exercise for the second building entity to test the one or more first relationships between the first building entity and the second building entity;

exercising, by the one or more processing circuits, the second building entity by operating building equipment represented by the second building entity in accordance with an adjusted setting defined by the first exercise to generate first building entity data associated with the second building entity, the first building entity data indicating a result of the first exercise;

identifying, by the one or more processing circuits, that the building is experiencing the performance issue by analyzing the first building entity data and the one or more first relationships, wherein the performance issue is identified in response to determining, based on the first building entity data, that operating the building equipment represented by the second building entity in accordance with the first exercise did not produce the expected effect on the first building entity;

determining, by the one or more processing circuits based on the first building entity data, that the building equipment represented by the second building entity did not cause the performance issue;

in response to determining that the building equipment represented by the second building entity did not cause the performance issue, exercising, by the one or more processing circuits, the third building entity by operating building equipment represented by the third building entity in accordance with an adjusted setting defined by a second exercise to generate second building entity data represented by the third building entity, the second building entity data indicating a result of the second exercise;

determining, by the one or more processing circuits based on the second building entity data, that the building equipment represented by the third building entity caused the performance issue; and

automatically causing an action to be initiated in response to determining that the building equipment represented by the third building entity caused the performance issue, the action comprising attempting to repair the building equipment represented by the third building entity, shutting-down the building equipment represented by the third building entity, or working around the performance issue by directing control activities around the building equipment represented by the third building entity.

16 . The method of claim 15 , further comprising identifying, by the one or more processing circuits, the performance issue by analyzing at least second building entity data of the first building entity, wherein performance of the second building entity is related to performance of the first building entity.

17 . The method of claim 15 , wherein the relational model is a building graph;

wherein the method further comprises:

receiving, by the one or more processing circuits, at least a portion of the building graph, the building graph comprising a plurality of nodes representing a plurality of building entities and a plurality of edges between the plurality of nodes representing relationships between the plurality of building entities; and

identifying, by the one or more processing circuits, based on the portion of the building graph, the first building entity by identifying one or more particular edges of the plurality of edges between a first node of the plurality of nodes representing the second building entity and a one or more second nodes of the plurality of nodes representing the first building entity.

18 . The method of claim 15 , wherein the second building entity is a space of the building;

wherein the building equipment represented by the second building entity is associated with the space of the building.

19 . A building management system of a building 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:

identify, based on a relational model, one or more first relationships between a first building entity and a second building entity and one or more second relationships between a third building entity and the first building entity, wherein the one or more first relationships indicate an expected effect on the first building entity caused by operation of the second building entity when the building is not experiencing a performance issue, and the one or more second relationships indicate an expected effect on the first building entity caused by operation of the third building entity when the building is not experiencing a performance issue;

select a first exercise for the second building entity to test the one or more first relationships between the first building entity and the second building entity;

exercise the second building entity by operating building equipment represented by the second building entity in accordance with an adjusted setting defined by the first exercise to generate first building entity data associated with the second building entity, the first building entity data indicating a result of the first exercise;

identify that the building is experiencing the performance issue by analyzing the first building entity data and the one or more first relationships, wherein the performance issue is identified in response to determining, based on the first building entity data, that operating the building equipment represented by the second building entity in accordance with the first exercise did not produce the expected effect on the first building entity;

determine, based on the first building entity data, that the building equipment represented by the second building entity did not cause the performance issue;

exercise, in response to determining that the building equipment represented by the second building entity did not cause the performance issue, the third building entity by operating building equipment represented by the third building entity in accordance with an adjusted setting defined by a second exercise to generate second building entity data represented by the third building entity, the second building entity data indicating a result of the second exercise;

determine, based on the second building entity data, that the building equipment represented by the third building entity caused the performance issue; and

automatically cause an action to be initiated in response to determining that the building equipment represented by the third building entity caused the performance issue, the action comprising attempting to repair the building equipment represented by the third building entity, shutting-down the building equipment represented by the third building entity, or working around the performance issue by directing control activities around the building equipment represented by the third building entity.

20 . The building management system of claim 19 , wherein the one or more processors are configured to execute the instructions causing the one or more processors to:

identify a data analysis problem associated with the first building entity data;

select an anomaly detection model from a plurality of anomaly detection models based on the data analysis problem, wherein each of the plurality of anomaly detection models is associated with one data analysis problem of a plurality of data analysis problems;

determine an anomaly score for the first building entity data based on the anomaly detection model and the first building entity data; and

ingest the first building entity data with an artificial intelligence (AI) service in response to a determination that the anomaly score is less than a predefined level.