US-20260126197-A1 - SYSTEM AND METHOD FOR MANAGEMENT OF VARIABLE AIR VOLUME UNIT IN A FACILITY

Abstract

Various embodiments described herein relate to a method and system for managing variable Air volume (VAV) units in a facility. In this method, initially the processor receives sensor data from a plurality of sensors associated with a VAV system that comprises one or more components. Further, the processor retrieves historical data associated with at least one component of the one or more components from a database. Then, the processor compares the sensor data with configuration data of the at least one component and the historical data and determines at least one anomaly in one or more operations of the at least one component using a ML model. Finally, the processor identifies at least one corrective action to modify one or more operations of the at least one component and renders one or more notifications to an operator via a user interface based on the at least one corrective action.

Inventors

• Vishu Rajappa
• Velmurugan R
• ELDHOSE GEORGE
• Rajendra Kumar S
• Vivek Bhat

Assignees

• HONEYWELL INTERNATIONAL INC.

Dates

Publication Date

20260507

Application Date

20241106

Claims (20)

1. 1 . A method comprising: receiving, by a processor, sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system, wherein the VAV system comprises one or more components; retrieving, by the processor, configuration data of the one or more components and historical data associated with at least one component of the one or more components from a database; comparing, by the processor, the sensor data with the configuration data and the historical data; determining, by the processor, at least one anomaly in one or more operations of the at least one component of the one or more components based on comparison, wherein the at least one anomaly is determined using a machine learning (ML) model; identifying, by the processor, at least one corrective action to modify one or more operations of the at least one component of the one or more components based on the at least one anomaly; and rendering, by the processor via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the at least one component of the one or more components.
2. 2 . The method of claim 1 , wherein the sensor data comprises at least: actual air flow rate data, damper position data, and actual zone temperature.
3. 3 . The method of claim 1 , wherein the method further comprising: triggering, by the processor, at least one control signal to adjust the one or more operations of the at least one component of the one or more components of the VAV system based on the at least one corrective action.
4. 4 . The method of claim 1 , further comprising: training, by the processor, the ML model to detect anomalies in the one or more operations of the at least one component of the one or more components of the VAV system based on at least: configured rules, operator feedback, and predictions associated with configuration data of the VAV system, and wherein the ML model is trained to detect operation anomalies of the VAV system using the sensor data and the historical data.
5. 5 . The method of claim 1 , wherein the historical data associated with the plurality of sensors comprises at least: operational status of one or more VAV controller associated with the VAV system, configuration of temperature at the VAV controller, operational status of Air handling Unit (AHU), the configuration data and maintenance data of the one or more components associated with the VAV system.
6. 6 . The method of claim 1 , wherein the one or more components of the VAV system comprises at least: a Variable Air Volume (VAV) controller, a damper, a plurality of air ducts/tubes, a plurality of air flowmeter, a plurality of temperature sensors, and other plurality of sensors associated with the VAV system.
7. 7 . The method of claim 6 , further comprising: obtaining operational status of the VAV controller and other VAV controllers that are connected to the VAV system; comparing the operational status of the VAV controller with at least: historical data associated with the VAV controller, the operational status of the other VAV controllers, and a user input; and determining the at least one anomaly associated with the VAV controller due to at least one of: power outage of the VAV controller, and a Network cable disconnection based on comparison of the operational status of the VAV controller using the ML model.
8. 8 . The method of claim 6 , further comprising: configuring temperature for a specified zone at the VAV controller; comparing the configured temperature with an actual temperature at the specified zone; receiving a damper position data from the plurality of sensors; comparing the damper position data with an expected damper position data based on the configured temperature and historical data associated with a damper; and determining the at least one anomaly associated with a damper stuck or an actuator malfunction based on comparison of the damper position data with the expected damper position data using the ML model.
9. 9 . The method of claim 6 , further comprising: receiving an actual CFM value based on air flow data measured by the plurality of sensors at a specified area/zone; acquiring a configured CFM value using configuration data of the VAV controller at the specified zone, and historical data associated with the air flow data from the database; determining an expected CFM value based on volume of the specified zone; identifying whether the actual CFM value is below or above a threshold based on comparison of the actual CFM value with the configured CFM value and the expected CFM value; and determining the at least one anomaly associated with a damper malfunction or a disconnection of air duct using the ML model based on identification that the actual CFM value is below or above the threshold and the historical data.
10. 10 . The method of claim 6 , further comprising: receiving actual air flow data, actual zone temperature and damper position data from the plurality of sensors at a specified zone; acquiring configuration of temperature at the VAV controller from the database, operational status of Air handling unit (AHU), and historical data associated with one or more air ducts from the database; identifying absence of the actual air flow data based on analysis of the actual zone temperature, the configuration of temperature at the VAV controller, operational status of AHU, and position of a damper; and determining the at least one anomaly associated with disconnection of the one or more air ducts based on identification of absence of the actual air flow data and the historical data using the ML model.
11. 11 . The method of claim 6 , further comprising: receiving actual sensor data from a plurality of sensors at a specified zone and neighboring zone; retrieving customized sensor parameters from configuration data of the plurality of sensors, and baseline value from historical data associated with the plurality of sensors; comparing the actual sensor data with the customized sensor parameters and historical data; and determining at least one anomaly associated with thermostat malfunction at a specified area/zone based on comparison of the actual sensor data with the customized sensor parameters and the historical data using the ML model.
12. 12 . A system, comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs executed by the one or more processors comprising instructions configured to: receive sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system, wherein the VAV system comprises one or more components; retrieve configuration data of the one or more components and historical data associated with at least one component of the one or more components from a database; compare the sensor data with the configuration data and the historical data; determine at least one anomaly in one or more operations of the at least one component of the one or more components based on comparison, wherein the at least one anomaly is determined using a machine learning (ML) model; identify at least one corrective action to modify one or more operations of the at least one component based on the at least one anomaly; and render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the at least one component.
13. 13 . The system of claim 12 , wherein the sensor data comprises at least: actual air flow rate data, damper position data, and actual zone temperature.
14. 14 . The system of claim 12 , wherein the one or more processors configured to: trigger at least one control signal to adjust the one or more operations of the at least one component of the VAV system based on the at least one corrective action.
15. 15 . The system of claim 12 , wherein the one or more processors configured to: train the ML model to detect anomalies in the one or more operations of the at least one component of the VAV system based on at least: configured rules, operator feedback, and predictions associated with configuration data of the VAV system, and wherein the ML model is trained to detect operation anomalies of the VAV system using the sensor data and the historical data.
16. 16 . The system of claim 12 , wherein the historical data associated with the plurality of sensors comprises at least: operational status of one or more VAV controller associated with the VAV system, configuration of temperature at the VAV controller, operational status of Air handling Unit (AHU), the configuration data and maintenance data of the one or more components associated with the VAV system.
17. 17 . The system of claim 12 , wherein the one or more components of the VAV system comprises at least: a Variable Air Volume (VAV) controller, a damper, a plurality of air ducts/tubes, a plurality of air flowmeter, a plurality of temperature sensors, and other plurality of sensors associated with the VAV system.
18. 18 . The system of claim 17 , wherein the one or more processor configured to: receive an actual CFM value based on air flow data measured by the plurality of sensors at a specified area/zone; acquire a configured CFM value using configuration data of the VAV controller at the specified zone, and historical data associated with the air flow data from the database; determine an expected CFM value based on volume of the specified zone; identify whether the actual CFM value is below or above a threshold based on comparison of the actual CFM value with the configured CFM value and the expected CFM value; and determine the at least one anomaly associated with a damper malfunction or a disconnection of air duct using the ML model based on identification that the actual CFM value is below or above the threshold and the historical data
19. 19 . The system of claim 17 , wherein the one or more processors configured to: receive actual air flow data, actual zone temperature and damper position data from the plurality of sensors at a specified zone; acquire configuration of temperature at the VAV controller from the database, operational status of Air handling unit (AHU), and historical data associated with one or more air ducts from the database; identify absence of the actual air flow data based on analysis of the actual zone temperature, the configuration of temperature at the VAV controller, operational status of AHU, and position of a damper; and determine the at least one anomaly associated with disconnection of the one or more air ducts based on identification of absence of the actual air flow data and the historical data using the ML model.
20. 20 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising an executable portion configured to: receive sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system, wherein the VAV system comprises one or more components; retrieve configuration data of the one or more components and historical data associated with at least one component of the one or more components from a database; compare the sensor data with the configuration data and the historical data; determine at least one anomaly in one or more operations of the at least one component of the one or more components based on comparison, wherein the at least one anomaly is determined using a machine learning (ML) model; identify at least one corrective action to modify one or more operations of the at least one component based on the at least one anomaly; and render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the at least one component.

Description

TECHNICAL FIELD OF INVENTION Various embodiments of the present disclosure relate generally to variable air volume (VAV) systems and more particularly to system and method for managing VAV units/systems in a facility. BACKGROUND In facilities such as commercial/industrial buildings, Variable Air Volume (VAV) system is widely used in a Heating Ventilation and Air-conditioning (HVAC) system. Common failures in VAV system may include actuator jamming/seizing, measured airflow being significantly lower than actual airflow, inability to effectively control airflow, and/or the like. In some instances, components of the VAV system may fail over a time due to deterioration of airflow station, dry out, duct leaks, or loosening. Typically, the common failures are detected by identifying the open position of damper actuator, which leads to maximum airflow. As a result, the air flow handler may increase air flow volume to maintain required static pressure and that leads to supplying of air more than a requirement. At the same time, for occupants, this often leads to excessive airflow and noise, and thus complicating temperature control in facilities like commercial buildings. Significant or multiple failures can result in insufficient airflow from the air flow handler, causing low airflow issues in other areas of the building. Overall, failures in the VAV system leads to higher utility costs and decreased occupant satisfaction. When it comes to energy optimization, energy loss is at times due to malfunction of VAV. There may be several reasons to this such as, but not limited to VAV Controller failure, damper malfunction, disconnection of air ducts/tubes, overflow of air in VAV, underflow of air in VAV, and sensor issue (e.g. thermostat issue, air flow sensor or air flow meter malfunction, etc. ,). Currently, there is no mechanism in place to identify root cause of the failures in VAVs. Usually, in VAV systems, parameters such as damper positions, cubic feet per minute (CFM) Flow, temperature setpoints/configurations and zone temperatures are usually monitored by building management system (BMS), but some challenging issues are still undetectable by an operator using the parameters alone. These challenging issues are mostly captured during a period of preventive maintenance that happens say, in every quarter/half year by vendor of the BMS. For instance, some challenging issues include but are not limited to inconsistent damper stuck issues, delayed response of the VAV system after configuring temperature setpoints, and incorrect CFM displays as per open/close conditions. Therefore, there is a need for system and method to identify problems in VAV units and generate alerts for facility managers/operators thereby to enable real-time response and guidance on taking necessary corrective actions to resolve issues promptly. The background description provided herein is for the purpose of generally presenting the context of the disclosure. Unless otherwise indicated herein, the materials described in this section are not prior art to the claims in this application and are not admitted to be prior art, or suggestions of the prior art, by inclusion in this section. SUMMARY According to certain aspects of the disclosure, systems and methods for managing Variable Air Volume (VAV) units in a facility are described. According to one aspect, embodiments of the present invention feature a method for managing VAV units in a facility is performed by a processor. Initially, the processor receives sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system in real-time. The VAV system comprises one or more components. Further, the processor retrieves historical data associated with at least one component of the one or more components from a database. Then, the processor compares the sensor data with configuration data of the at least one component and the historical data. Further, the processor determines at least one anomaly in one or more operations of the at least one component based on the comparison. The at least one anomaly is determined using a machine learning (ML) model. Further, the processor identifies at least one corrective action to modify one or more operations of the at least one component in real-time based on the at least one anomaly. Furthermore, the processor renders one or more notifications to an operator via a user interface, based on the at least one corrective action to modify the one or more operations of the at least one component. In some embodiments, the sensor data comprises at least: actual air flow rate data, damper position data, and actual zone temperature. In some embodiments, the method further comprises triggering at least one control signal to adjust the one or more operations of the at least one component of the VAV system based on the at least one corrective action. In some embodiments, the method further comprises training the ML model to detect anomalies in the one