Smart hvac rooftop units with integrated ai and thermal imaging for enhanced operational control

Abstract

Improved apparatus and methods for a Smart Rooftop Unit (SRTU) incorporating infrared (IR) thermal imaging and artificial intelligence (AI) for enhanced HVAC performance are disclosed. The SRTU integrates multiple IR cameras positioned strategically on, around, or within the unit to capture comprehensive thermal images, enabling real-time monitoring and predictive maintenance. An AI-driven control system analyzes the thermal images to optimize defrost cycles, heating and cooling loads, and overall system efficiency. The control system interfaces with building management systems (BMS) for dynamic adjustments based on occupancy, air quality, and weather conditions. The modular design of the SRTU facilitates easy assembly, maintenance, and component upgrades. Advanced sensors and environmental monitors provide continuous data to ensure optimal operation and energy efficiency. The methods include steps for data acquisition, AI analysis, and system adjustments to maintain peak performance and extend the lifespan of the SRTU components.

What is claimed is: 
     
         1 . A Smart Rooftop Unit (SRTU) for a Heating, Ventilation, and Air Conditioning (HVAC) system, the SRTU comprising:
 a plurality of SRTU components comprising two or more of: an air hood, an economizer hood, a high efficiency particulate air (HEPA) filter, a heat wheel, a subsequent filter, a mixing damper, a heating coil, a cooling coil, an evaporator coil, and a centrifugal electronically commutated (EC) fan;   at least one infrared (IR) camera strategically positioned on or within the SRTU to capture thermal images of at least one of: a surface of the SRTU, and at least one of the plurality of SRTU components; and   a control system comprising: a processor; a memory storing instructions executable by the processor; and an artificial intelligence (AI) engine; wherein the Control System and/or AI engine is configured to analyze the thermal images captured by the at least one IR camera to control at least one of: the SRTU, the HVAC system, and at least one of the plurality of SRTU components.   
     
     
         2 . The SRTU of  claim 1 , wherein the Control System and/or AI engine is configured to analyze the thermal images captured by the at least one IR camera to perform one or more of:
 a. convert the thermal images into digital value patterns representing temperature distributions;   b. assess the digital value patterns to identify temperature anomalies and operational inefficiencies;   c. map the digital value patterns against variable operational trends including defrost cycles, power use, and equipment performance;   d. optimize operation of at least one of the plurality of SRTU components by adjusting control parameters based on the assessed digital value patterns and mapped trends to enhance energy efficiency and system performance;   e. predict maintenance needs and potential equipment failures based on historical and real-time analysis of the thermal images;   f. provide real-time updates and actionable recommendations for SRTU modifications to improve efficiency and performance of the SRTU;   g. receive and process commands, for additional cooling or heating requirements, from a user or a building management system (BMS) and anticipate temperature maps based on expected load; and   h. continuously monitor and adjust the SRTU based on ambient conditions including temperature, humidity, and airflow within building spaces to ensure optimal indoor climate control.   
     
     
         3 . The SRTU of  claim 1 , further comprising a plurality of IR cameras positioned externally around the SRTU to capture thermal images of outer surface of the SRTU from different directions and angles. 
     
     
         4 . The SRTU of  claim 1 , wherein the SRTU is constructed from a Polypropylene Random Copolymer (PPR) core layer, and at least one protective layer affixed to the PPR core layer; wherein the at least one protective layer is selected from at least one of: a metallic layer, a non-metallic layer, and a nanocomposite coating. 
     
     
         5 . The SRTU of  claim 1 , wherein the control system comprises machine learning algorithms to improve thermal image analysis over time. 
     
     
         6 . The SRTU of  claim 1 , wherein the control system optimizes operation of the heating coil during defrost cycles based on thermal image analysis. 
     
     
         7 . The SRTU of  claim 1 , wherein the AI engine provides predictive analytics for maintenance scheduling based on analysis of the thermal images. 
     
     
         8 . The SRTU of  claim 7 , wherein the AI engine is capable of self-learning to improve the analysis of the thermal images over time. 
     
     
         9 . The SRTU of  claim 1 , wherein the control system is capable of sending alerts and notifications to maintenance personnel when anomalies are detected in the thermal images. 
     
     
         10 . The SRTU of  claim 1 , further comprising at least one sensor comprising one or more of: a temperature sensor, a pressure sensor, a humidity sensor, and an air-quality sensor. 
     
     
         11 . The SRTU of  claim 1 , wherein the AI engine provides automated recommendations for design modifications related to one or both of: the SRTU and at least one of the plurality of SRTU components. 
     
     
         12 . The SRTU of  claim 1 , wherein the air hood is configured to guide atmospheric air into the SRTU. 
     
     
         13 . The SRTU of  claim 1 , wherein the economizer hood is configured to utilize external air for cooling when conditions allow. 
     
     
         14 . The SRTU of  claim 1 , wherein the HEPA filter is configured to remove fine particulates from incoming air. 
     
     
         15 . The SRTU of  claim 1 , wherein the evaporator coil facilitates cooling process by absorbing heat from air. 
     
     
         16 . The SRTU of  claim 15 , wherein the Control System controls defrost cycles of the evaporator coil based on analysis of the thermal images captured by the at least one IR camera. 
     
     
         17 . The SRTU of  claim 16 , wherein the Control System and/or AI engine dynamically adjusts timing and duration of the defrost cycles based on the analysis of the thermal images to prevent frost buildup and maintain optimal cooling efficiency. 
     
     
         18 . The SRTU of  claim 2 , wherein the control system is configured to integrate with the BMS of a building for enhanced operational control of the SRTU. 
     
     
         19 . The SRTU of  claim 18 , wherein the Control System and/or AI engine receives real-time data from the BMS, including temperature, humidity, air-quality, and occupancy level within the building to optimize HVAC operations. 
     
     
         20 . The SRTU of  claim 18 , wherein the control system can receive commands from the BMS to adjust heating or cooling of different zones within the building. 
     
     
         21 . The SRTU of  claim 18 , wherein the control system can adjust airflow and temperature settings based on occupancy patterns for different zones within the building. 
     
     
         22 . The SRTU of  claim 18 , wherein the BMS integration allows the Control System and/or AI engine to schedule HVAC operations based on one or more or: planned building activities, occupancy patterns, day of a week, time of day, seasonal variations, and geographic location of the building to optimize energy usage and maintain optimal indoor climate conditions within the building. 
     
     
         23 . A method for controlling a Smart Roof Top Unit (SRTU) for a Heating, Ventilation, and Air Conditioning (HVAC) system, the method comprising:
 providing multiple SRTU components housed within the SRTU, wherein the multiple SRTU components comprising one or more of: an air hood, a damper, a filter, a heat wheel, subsequent filters, a mixing damper, a heating coil, a cooling coil, an evaporator coil, and a centrifugal electronically commutated (EC) fan;   capturing thermal images of the multiple SRTU components using at least one infrared (IR) camera positioned on, around, or within the SRTU, the thermal images comprising temperature signatures of at least one of: a surface of the SRTU, and at least one component of the multiple SRTU components;   transmitting the captured thermal images to a control system comprising a processor, a memory storing instructions executable by the processor, and an artificial intelligence (AI) engine;   converting, by a Controller and/or AI engine, the captured thermal images into digital value patterns representing temperature distributions across the at least one of: the surface of the SRTU, and the at least one component of the multiple SRTU components;   analyzing, by the Controller and/or AI engine, the digital value patterns to analyze the temperature distributions and identify anomalies indicative of operational inefficiencies, equipment failures, or potential maintenance needs; and   controlling one or both of the SRTU and the HVAC system based on the analysis of the temperature distributions and the identified anomalies in the temperature distributions.   
     
     
         24 . The method of  claim 23 , further comprising mapping the digital value patterns against variable operational trends, including defrost cycles, power use, and efficiency metrics, to optimize HVAC operations. 
     
     
         25 . The method of  claim 24 , further comprising adjusting control parameters of the multiple SRTU components based on the mapping to enhance energy efficiency, reduce wear and tear, and maintain optimal performance of the SRTU. 
     
     
         26 . The method of  claim 23 , further comprising initiating a defrost cycle for the evaporator coil based on the analysis of the digital value patterns, including dynamically adjusting timing and duration of the defrost cycle to prevent frost buildup and maintain cooling efficiency. 
     
     
         27 . The method of  claim 23 , further comprising receiving commands for additional cooling or heating requirements from a user or a building management system (BMS), and controlling at least one of: the SRTU, the multiple SRTU components, and HVAC system based on the received commands. 
     
     
         28 . The method of  claim 23 , further comprising continuously monitoring ambient conditions within a building, including temperature, humidity, air-quality, and airflow, using multiple sensors integrated within different spaces of the building. 
     
     
         29 . The method of  claim 28 , further comprising using the AI engine to predict HVAC demand based on real-time and historical data, including day of a week, time of day, seasonal variations, and geographic location of the building. 
     
     
         30 . The method of  claim 29 , further comprising adjusting HVAC operations dynamically based on the predicted HVAC demand to maintain optimal indoor climate conditions and energy efficiency. 
     
     
         31 . The method of  claim 23 , further comprising transmitting thermal images and operational data to a cloud server for storage and cumulative AI analysis of thermal images from a plurality of SRTU units. 
     
     
         32 . The method of  claim 23 , further comprising providing actionable recommendations for modifications to the SRTU or the multiple SRTU components to improve efficiency and performance of the SRTU. 
     
     
         33 . The method of  claim 23 , wherein the AI engine uses machine learning algorithms to improve an accuracy in identifying the anomalies in the temperature distributions over time. 
     
     
         34 . The method of  claim 23 , further comprising mapping the digital value patterns representing temperature distributions across the surface of the SRTU to corresponding SRTU components housed within the SRTU. 
     
     
         35 . The method of  claim 34 , wherein the mapping comprises identifying specific temperature zones on the surface of the SRTU that correspond to individual SRTU components inside the SRTU. 
     
     
         36 . The method of  claim 35 , wherein the Controller determines working conditions of the multiple SRTU components by analyzing the mapped temperature distributions across the surface of the SRTU.