Predictive diagnostics system with fault detector for preventative maintenance of connected equipment
A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.
1. A controller for one or more building subsystems for a building, comprising:
a processor configured to:
receive room usage data regarding use of a respective room of the building, the room usage data including information regarding at least one of a temperature setpoint, a light level, an occupancy count, a time of a day, or a day of a week correlated to a respective occupant of the respective room;
determine a usage pattern in the room usage data;
generate at least one of a time profile or a user profile comprising preferences for the respective room for a respective occupant based on a usage pattern of the usage patterns; and
control the one or more building subsystems based on the at least one of the time profile or the user profile, wherein the one or more building subsystems comprise at least one of a heating, ventilation, and air conditioning (HVAC) system, a lighting system, or a security system, and wherein the one or more building subsystems are controlled by an automated control action comprising increasing an output of equipment to preemptively compensate for an expected decrease in performance in a future based on a predicted fault.
2. The controller of claim 1 , wherein the one or more building subsystems comprises the heating, ventilation, and air conditioning (HVAC) system.
3. The controller of claim 1 , wherein the controller is a smart thermostat that is positioned in the respective room.
4. The controller of claim 1 , wherein the processor is configured to:
receive the room usage data regarding a plurality of rooms within the building, wherein the room usage data includes a room ID for each room of the plurality of rooms;
segregate and aggregate the room usage data by room based on the room ID associated therewith;
determine usage patterns in each of the plurality of rooms; and
control the building subsystems based on the at least one of the time profile or the user profile for each of the plurality of rooms individually.
5. The controller of claim 1 , wherein the processor is configured to generate the at least one of the time profile or the user profile absent manual operator intervention.
6. The controller of claim 1 , wherein the processor is configured to:
identify a current time; and
control the building subsystems according to the time profile based on the current time.
7. The controller of claim 1 , wherein the processor is configured to:
identify an occupant within the room; and
control the building subsystems based on the user profile associated with the occupant.
8. A method for controlling an environment of a room of a building, the method comprising:
receiving room usage data regarding use of a room of the building, the room usage data including information regarding a temperature setpoint, time data, a light level, and an occupant of the room;
determine usage patterns in the room usage data;
generating a user profile comprising preferences for the room for the occupant based on a usage pattern of the usage patterns; and
controlling the environment using one or more building subsystems based on the user profile and the occupant occupying the room, wherein the one or more building subsystems comprise at least one of a heating, ventilation, and air conditioning (HVAC) system, a lighting system, or a security system, and wherein the environment is controlled by an automated control action comprising increasing an output of equipment to preemptively compensate for an expected decrease in performance in a future based on a predicted fault.
9. The method of claim 8 , wherein the one or more building subsystems comprises a heating, ventilation, and air conditioning (HVAC) system and a controller.
10. The method of claim 8 , wherein the one or more building subsystems comprise at least one of the lighting system, or the security system.
11. The method of claim 9 , wherein the controller is a smart thermostat that is positioned in the room.
12. The method of claim 8 , further comprising:
presenting the room usage data graphically to the occupant and allowing the occupant to modify the room usage data.
13. The method of claim 8 , wherein the room usage data is generated by unsupervised learning.
14. A building management system for a building comprising building subsystems, the building management system comprising:
a controller coupled to at least one building subsystem, the controller configured to:
receive room usage data regarding use of a respective room of the building, the room usage data including information regarding at least one of a temperature setpoint, a light level, an occupancy count, a time of a day, or the day of a week;
determine usage patterns in the room usage data and present the usage patterns to a user on a web interface;
receive changes provided by the user;
generate at least one of a time profile or a user profile to correlate the usage patterns with preferences for the respective room for at least one of a respective time or a respective occupant; and
control the at least one building subsystem based on the at least one of the time profile or the user profile, wherein the at least one building subsystem comprises at least one of a heating, ventilation, and air conditioning (HVAC) system, a lighting system, or a security system, wherein the at least one building subsystem is controlled by an automated control action comprising increasing an output of equipment to preemptively compensate for an expected decrease in performance in a future based on a predicted fault.
15. The building management system of claim 14 , wherein the controller is a smart thermostat that is disposed in the respective room.
16. The building management system of claim 14 , wherein the controller is configured to:
receive the room usage data regarding a plurality of rooms within the building, wherein the room usage data includes a room ID for each room of the plurality of rooms;
segregate and aggregate the room usage data by room based on the room ID associated therewith;
determine the usage patterns in each of the plurality of rooms; and
control the at least one building subsystem based on the at least one of the time profile or the user profile for each of the plurality of rooms individually.
17. The building management system of claim 14 , wherein the controller is configured to generate the at least one of the time profile or the user profile using unsupervised machine learning.
18. The building management system of claim 14 , wherein the controller is configured to:
identify a current time; and
control the at least one building subsystem according to the time profile based on the current time.
19. The building management system of claim 14 , wherein the controller is configured to:
identify that the respective occupant is within the room; and
control the at least one building subsystem based on the user profile associated with the respective occupant being in the room.