Air-quality monitoring driven building system control
An air quality monitoring system integrated with the building management system observes and records air quality data and building system data. Based on the observed air quality data and building system data, one or more training data sets can be generated. Such training data sets are used to train one or more machine-learning models configured to determine one or more threshold values for the air quality. These thresholds are then used to modify or adjust one or more building systems based on monitored air quality data.
1 . A method, comprising:
training a first machine-learning model using a first training data set associated with an environment such that the first machine learning model is configured to receive data indicating a location within the environment as an input and output a baseline value for an aerosolized substance of interest;
training a second machine-learning model according to the first training data set such that the second machine-learning model is configured to receive data indicating the aerosolized substance of interest as an input and output a substance threshold value based on the first training data set;
activating, at the location in the environment, a chemical sensor;
monitoring, by the chemical sensor, a presence of the aerosolized substance of interest based on the baseline value; and
in response to detecting the presence of the substance of interest by the chemical sensor, modifying a building system associated with the location of the environment based on the aerosolized substance.
2 . The method of any of claim 1 , further comprising:
generating a second training data set from historical air quality data; and
training a third machine-learning model according to the second training data set such that the third machine-learning model is configured to receive a particle count of the aerosolized substance as an input and output a mitigation action including an adjustment associated with the building system.
3 . The method of claim 2 , wherein modifying the building system is further based on the adjustment.
4 . The method of claim 1 , further comprising:
determining a particle count of the aerosolized substance of interest in response to detecting the presence of the substance of interest by the chemical sensor.
5 . The method of claim 4 , further comprising:
in response to the particle count of the aerosolized substance of interest exceeding the substance threshold value, adjusting a second building system associated with a second location in the environment.
6 . A method, comprising:
classifying a historical air quality data associated with an air quality detection system at an environment so as to produce a first training data set;
training a first machine-learning model using the first training data set such that the first machine learning model is configured to receive data indicating a location in the environment as an input and output baseline value;
training a second machine-learning model according to the first training data set such that the second machine-learning model is configured to receive data indicating a certain aerosolized substance as an input and output a threshold value based on the first training data set;
determining, by at least a portion of the air quality detection system, a particle count of the certain aerosolized substance at the location in the environment; and
in response to the particle count of the certain aerosolized substance exceeding the threshold value, adjusting a building management system associated with the environment.
7 . The method of claim 6 , further comprising:
in response to the particle count of the certain aerosolized substance exceeding the threshold value, modifying a second building management system associated with the environment.
8 . The method of claim 6 , wherein the first training data set includes correlations of a plurality of particle counts of the certain aerosolized substance to respective ones of a plurality of thresholds.
9 . The method of claim 6 , further comprising:
determining an activation event, wherein determining the particle count of the certain aerosolized substance is in response to the determined activation event.
10 . The method of claim 6 , wherein the environment comprises one of a school, warehouse, or office building.
11 . The method of any of claim 6 , wherein the building system comprises one of a security system, fire system, HVAC system, or power system.
12 . The method of any claim 6 , further comprising:
capturing a video of the location in the environment; and
associating the video with the certain aerosolized substance based on the particle count of the certain aerosolized substance exceeding the threshold value.
13 . The method of any of claim 6 , further comprising: generating an alarm associated with the building management system in response to the particle count of the certain aerosolized substance exceeding the threshold value.
14 . An air quality system comprising:
an air quality sensor disposed at a first location in an environment and configured to determine a particle count of a certain aerosolized substance at the first location in the environment; and
a server including at least one processor configured to:
classify a historical air quality data associated with the environment so as to produce a first training data set;
train a first machine-learning model using the first training data set such that the first machine learning model is configured to receive data indicating the location in the environment as an input and output a baseline value; and
train a second machine-learning model according to the first training data set such that the second machine-learning model is configured to receive data indicating the certain aerosolized substance as an input and output a substance threshold value based on the first training data set;
in response to the particle count of the certain aerosolized substance exceeding the threshold value, modify a building system associated with the first location in the environment based on the aerosolized substance.
15 . The air quality system of claim 14 , wherein the at least one processor is further configured to:
generate a second training data set from the historical air quality data; and
train a third machine-learning model according to the second training data set such that the third machine-learning model is configured to receive the particle count of the certain aerosolized substance as an input and output a mitigation action including an adjustment of the building system.
16 . The air quality system of claim 15 , wherein the at least one processor is further configured to:
modify the building system based on the adjustment.
17 . The air quality system of claim 14 , wherein the at least one processor is further configured to:
determine an entry into the first environment, wherein the air quality sensor is configured to determine the particle count of the certain aerosolized substance is in response to determining the entry.