HVAC system with automated device pairing

1. A building system for a building, the building system comprising one or more memory devices configured to store instructions thereon that, when executed by one or more processors, cause the one or more processors to:

operate an actuation device of the building to affect a variable of the building;

generate an actuation data time series indicating operation of the actuation device;

receive a plurality of sensor response signals from a plurality of sensors, the plurality of sensor response signals indicating an effect of the operation of the actuation device;

generate a plurality of sensor data time series based on the plurality of sensor response signals;

perform a time series analysis on the actuation data time series and the plurality of sensor data time series, wherein performing the time series analysis includes:

determining a plurality of delay times based on the plurality of sensor data time series and the actuation data time series, each of the plurality of delay times being a delay time between a sensor of the plurality of sensors and the actuation device; and

identifying one sensor of the plurality of sensors associated with the actuation device by identifying a minimum delay time of the plurality of delay times; and

establish a device pairing comprising the actuation device and the one sensor of the plurality of sensors based on the time series analysis.

2. The building system of claim 1 , wherein the device pairing defines a control relationship between the actuation device in the device pairing and the one sensor of the plurality of sensors;

wherein the control relationship indicates that the actuation device in the device pairing is operable to control a variable measured by the one sensor of the plurality of sensors in the device pairing.

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

create a feedback control loop comprising the actuation device in the device pairing and the one sensor of the plurality of sensors in the device pairing; and

use the feedback control loop to generate and provide control signals to the actuation device based on measurements received from the one sensor of the plurality of sensors.

4. The building system of claim 1 , wherein the building system is a heating, ventilation, and air conditioning (HVAC) system comprising:

the actuation device configured to control the variable in the building;

the plurality of sensors configured to measure the variable; and

a building controller communicably coupled to the actuation device and the plurality of sensors, wherein the building controller includes the one or more memory devices and the one or more processors.

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

detect a dimensional mismatch between the actuation data time series and a particular sensor data time series; and

correct the dimensional mismatch by modifying at least one of the actuation data time series and the particular sensor data time series.

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

receive baseline sensor signals from each of the plurality of sensors, the baseline sensor signals indicating values of the variable during a time period before the operation of the actuation device; and

for each of the baseline sensor signals, calculate a baseline similarity metric indicating a baseline similarity between one of the baseline sensor signals and the actuation device.

7. A method of a building for pairing building devices, the method comprising:

operating, by one or more processing circuits, an actuation device of the building to affect a variable of the building;

generating, by the one or more processing circuits, an actuation data time series indicating operation of the actuation device;

receiving, by the one or more processing circuits, a plurality of sensor response signals from a plurality of sensors, the plurality of sensor response signals indicating an effect of the operation of the actuation device;

generating, by the one or more processing circuits, a plurality of sensor data time series based on the plurality of sensor response signals;

performing, by the one or more processing circuits, a time series analysis on the actuation data time series and the plurality of sensor data time series, wherein performing the time series analysis includes:

detecting a dimensional mismatch between the actuation data time series and a particular sensor data time series; and

correcting the dimensional mismatch by modifying at least one of the actuation data time series and the particular sensor data time series; and

establishing, by the one or more processing circuits, a device pairing comprising the actuation device and one sensor of the plurality of sensors based on the time series analysis.

8. The method of claim 7 , wherein the device pairing defines a control relationship between the actuation device in the device pairing and the one sensor of the plurality of sensors;

wherein the control relationship indicates that the actuation device in the device pairing is operable to control a variable measured by the one sensor of the plurality of sensors in the device pairing.

9. The method of claim 7 , further comprising:

creating a feedback control loop comprising the actuation device in the device pairing and the one sensor of the plurality of sensors in the device pairing; and

using the feedback control loop to generate and provide control signals to the actuation device based on measurements received from the one sensor of the plurality of sensors.

10. The method of claim 7 , wherein performing, by the one or more processing circuits, the time series analysis comprises:

determining one or more sensor coefficients for each of the plurality of sensors based on the plurality of sensor data time series;

determining one or more actuation device coefficients based on the actuation data time series; and

identifying the one sensor of the plurality of sensors associated with the actuation device based on the one or more sensor coefficients and the one or more actuation device coefficients.

11. The method of claim 10 , wherein performing, by the one or more processing circuits, the time series analysis comprises:

determining the one or more sensor coefficients for each of the plurality of sensors and the one or more actuation device coefficients by applying a discrete cosine transformation (DCT) to each of the plurality of sensor data time series and to the actuation data time series, each DCT generating a plurality of DCT coefficients, wherein one or more actuation device DCT coefficients resulting from the DCT of the actuation data time series are the one or more actuation device coefficients and one or more sensor DCT coefficients resulting from the DCT of each of the plurality of sensor data time series are the one or more sensor coefficients; and

generating one or more quantized sensor DCT coefficients for each of the plurality of sensors by quantizing the one or more sensor DCT coefficients resulting from the DCT of each of the plurality of sensor data time series and generate one or more quantized actuator DCT coefficients by quantizing the one or more actuation device DCT coefficients resulting from the DCT of the actuation data time series.

12. The method of claim 10 , wherein performing, by the one or more processing circuits, the time series analysis comprises:

generating one or more quantized sensor coefficients for each of the plurality of sensors by quantizing the one or more sensor coefficients of each of the plurality of sensors and generating one or more quantized actuation device coefficients by quantizing the one or more actuation device coefficients;

for each of the plurality of sensor response signals, calculating a plurality of similarity metrics indicating a similarity between the plurality of sensors and the actuation device based on the one or more quantized sensor coefficients and the one or more quantized actuation device coefficients; and

identifying the one sensor of the plurality of sensors associated with the actuation device based on the plurality of similarity metrics.

13. One or more non-transitory computer readable storage media configured to store instructions thereon that, when executed by one or more processors, cause the one or more processors to:

operate an actuation device of a building to affect a variable of the building;

generate an actuation data time series indicating operation of the actuation device;

receive a plurality of sensor response signals from a plurality of sensors, the plurality of sensor response signals indicating an effect of the operation of the actuation device;

generate a plurality of sensor data time series based on the plurality of sensor response signals;

perform a time series analysis on the actuation data time series and the plurality of sensor data time series, wherein performing the time series analysis includes:

determining one or more sensor coefficients for each of the plurality of sensors based on the plurality of sensor data time series;

determining one or more actuation device coefficients based on the actuation data time series; and

identifying the one sensor of the plurality of sensors associated with the actuation device based on the one or more sensor coefficients and the one or more actuation device coefficients; and

establish a device pairing comprising the actuation device and the one sensor of the plurality of sensors based on the time series analysis.

14. The one or more non-transitory computer readable storage media of claim 13 , wherein the device pairing defines a control relationship between the actuation device in the device pairing and the one sensor of the plurality of sensors;

wherein the control relationship indicates that the actuation device in the device pairing is operable to control a variable measured by the one sensor of the plurality of sensors in the device pairing.

15. The one or more non-transitory computer readable storage media of claim 13 , wherein the instructions, when executed by the one or more processors, cause the one or more processors cause the one or more processors to:

create a feedback control loop comprising the actuation device in the device pairing and the one sensor of the plurality of sensors in the device pairing; and

use the feedback control loop to generate and provide control signals to the actuation device based on measurements received from the one sensor of the plurality of sensors.