System and method for refrigerant leak detection

Patent metadata

Field	Value
Publication number	US-12566006-B2
Application number	US-202318227093-A
Country	US
Kind code	B2
Filing date	Jul 27, 2023
Priority date	Jul 29, 2022
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

A system for refrigerant leak detection includes one or more sensors configured to detect one or more parameters of a heating, ventilation, and/or air conditioning (HVAC) system. The system further includes one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to receive sensor data from the one or more sensors; apply the sensor data to one or more machine learning models, the one or more machine learning models trained to identify refrigerant leaks associated with HVAC systems; determine, using the one or more machine learning models, that the sensor data is indicative of a refrigerant leak; and, in response to determining that the sensor data is indicative of the refrigerant leak, initiate a response action.

First claim

What is claimed is:

1 . A system for refrigerant leak detection, the system comprising:
one or more sensors configured to detect one or more parameters of a heating, ventilation, and/or air conditioning (HVAC) system; one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to:
receive at least one of temperature sensor data, pressure sensor data, or gas sensor data from the one or more sensors;
apply the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data to one or more machine learning models, the one or more machine learning models trained to identify refrigerant leaks associated with HVAC systems;
determine, using the one or more machine learning models, that the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data is indicative of a refrigerant leak; and
in response to determining that the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data is indicative of the refrigerant leak, initiate a response action.

2 . The system of claim 1 , wherein the response action is at least one of generating an alert indicative of the refrigerant leak, actuating one or more components of a ventilation unit, or shutting down the HVAC system.

3 . The system of claim 1 , wherein the one or more sensors include at least one of an evaporator coil temperature sensor, a return air temperature sensor, a return air pressure sensor, a supply air temperature sensor, or a supply air pressure sensor.

4 . The system of claim 1 , wherein the one or more sensors include one or more refrigerant detecting sensors.

5 . The system of claim 1 , wherein the instructions further cause the one or more processors to:
collect test data corresponding to one or more refrigerant leaks associated with HVAC systems; and train the one or more machine learning models to identify the refrigerant leaks associated with HVAC systems using the test data.

6 . The system of claim 5 , wherein the test data is generated using one or more simulated test setups configured to produce test conditions corresponding to different amounts of refrigerant leakage.

7 . The system of claim 5 , wherein the test data is collected periodically and the one or more machine learning models are continuously trained using the periodically collected test data.

8 . A system for refrigerant leak detection, the system comprising:
one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to:
collect test data corresponding to one or more refrigerant leaks associated with heating, ventilation, and/or air conditioning (HVAC) systems;
train one or more machine learning models to identify refrigerant leaks associated with HVAC systems using the test data;
receive at least one of temperature sensor data, pressure sensor data, or gas sensor data from one or more sensors associated with an HVAC system; and
determine, using the one or more machine learning models, that the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data is indicative of a refrigerant leak.

9 . The system of claim 8 , wherein the test data is generated using one or more simulated test setups configured to produce test conditions corresponding to different amounts of refrigerant leakage.

10 . The system of claim 8 , wherein the test data is collected periodically and the one or more machine learning models are continuously trained using the periodically collected test data.

11 . The system of claim 8 , wherein the one or more sensors include at least one of an evaporator coil temperature sensor, a return air temperature sensor, a return air pressure sensor, a supply air temperature sensor, or a supply air pressure sensor.

12 . The system of claim 8 , wherein the one or more sensors include one or more refrigerant detecting sensors.

13 . The system of claim 8 , wherein the instructions further cause the one or more processors to, in response to determining that the sensor data is indicative of the refrigerant leak, initiate a response action.

14 . The system of claim 13 , wherein the response action is at least one of generating an alert indicative of the refrigerant leak, actuating one or more components of a ventilation unit, or shutting down the HVAC system.

15 . A method for refrigerant leak detection, the method comprising:
receiving, by one or more processors of a system, at least one of temperature sensor data, pressure sensor data, or gas sensor data from one or more sensors associated with a heating, ventilation, and/or air conditioning (HVAC) system; applying, by the one or more processors, the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data to one or more machine learning models, the one or more machine learning models trained to identify refrigerant leaks associated with HVAC systems; determining, by the one or more processors using the one or more machine learning models, that the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data is indicative of a refrigerant leak; and in response to determining that the at least one of the temperature sensor data, the pressure sensor data, or the gas sensor data is indicative of the refrigerant leak, initiating, by the one or more processors, a response action.

16 . The method of claim 15 , wherein the response action is at least one of generating an alert indicative of the refrigerant leak, actuating one or more components of a ventilation unit, or shutting down the HVAC system.

17 . The method of claim 15 , wherein the one or more sensors include at least one of an evaporator coil temperature sensor, a return air temperature sensor, a return air pressure sensor, a supply air temperature sensor, or a supply air pressure sensor.

18 . The method of claim 15 , wherein the one or more sensors include one or more refrigerant detecting sensors.

19 . The method of claim 15 , further comprising:
collecting test data corresponding to one or more refrigerant leaks associated with HVAC systems; and train the one or more machine learning models to identify the refrigerant leaks associated with HVAC systems using the test data.

20 . The method of claim 19 , wherein the test data is collected periodically and the one or more machine learning models are continuously trained using the periodically collected test data.

Assignees

• Tyco Fire & Security Gmbh

Inventors

• Mohammad Mujibul Rehaman
• Melwin Ewin Ramster
• Garg Karan
• Blanton Norman Jack
• Dulange Anand Mallinath

Classifications

• F24F11/63

  Electronic processing · CPC title

• F24F11/88

  Electrical aspects, e.g. circuits · CPC title

• F24F11/89

  Arrangement or mounting of control or safety devices · CPC title

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G05B2219/2614

  HVAC, heating, ventillation, climate control · CPC title