Systems and Methods for Fuel Type Detection for Hydronic and Other Heating Systems

Abstract

Systems and methods are provided for gas fired systems, such as boilers, hydronic systems, and other fuel powered heating systems which are capable detecting a fuel type being consumed by the system and adjusting operation of the system based on the fuel type detected. The gas fired or other heating systems may have a controller capable of a running a machine learning model trained to detect a fuel type based on operational data corresponding to the gas fired or other heating system. Once the type of fuel is determined, operation of the gas fired or other heating system may be adjusted according to the fuel type detected. For example, the system may be powered down, a gas valve may be adjusted to adjust fuel injected into the heat exchanger, or a fan (e.g., blower) speed (e.g., revolutions per minute) may be adjusted.

We claim: 
     
         1 . A method for detecting a fuel type consumed by a gas fired system comprising an inlet, an outlet, a vent, and a heat exchanger for heating a fluid, the method comprising:
 determining a machine learning model trained to determine a first likelihood of a first fuel type and a second likelihood of a second fuel type;   determining operational data comprising one or more of a vent temperature indicative of a first temperature in the vent, an inlet temperature indicative of a second temperature of the fluid at the inlet, an outlet temperature indicative of a third temperature of the fluid at the outlet, or a flame current value corresponding to the heat exchanger;   generating a first output value and a second output value using the machine learning model and based on the operational data, the first output value representing the first likelihood of the first fuel type and the second output value representing the second likelihood of the second fuel type; and   determining the first fuel type is being consumed by the gas fired system based on the first output value and a first threshold value.   
     
     
         2 . The method of  claim 1 , further comprising:
 determining, based on determining the first fuel type is being consumed, to cease operation of the gas fired system; and   causing the gas fired system to cease operation.   
     
     
         3 . The method of  claim 1 , wherein the gas fired system has a fuel valve for restricting an amount of fuel provided to the heat exchanger, the method further comprising:
 determining, based on determining the first fuel type is being consumed, to transition the fuel valve from a first position to a second position; and   causing the fuel valve to transition from the first position to the second position.   
     
     
         4 . The method of  claim 1 , wherein the gas fired system further comprises a fan for generating an airflow, the method further comprising:
 determining, based on determining the first fuel type is being consumed, to transition the fan from a first speed to a second speed; and   causing the fan to transition from the first speed to the second speed.   
     
     
         5 . The method of  claim 1 , further comprising:
 determining, before determining the first fuel type is being consumed by the gas fired system, that the second fuel type was consumed by the gas fired system; and   determining that the fuel type has changed from the second fuel type to the first fuel type.   
     
     
         6 . The method of  claim 5 , further comprising generating an alert that the fuel type has changed. 
     
     
         7 . The method of  claim 1 , wherein the machine learning model is a recurrent neural network, the method comprising receiving the machine learning model from a remote server. 
     
     
         8 . The method of  claim 1 , wherein the gas fired system further comprises a fan for generating an airflow, and wherein the operational data further comprises one or more of a differential between the inlet temperature and the outlet temperature, a fan speed setting, a fan speed reading, an altitude value corresponding to an altitude of the gas fired system, an oxygen value, a heat output value corresponding to heat generated by the heat exchanger, or an operational status value indicative of an operational mode of the gas fired system. 
     
     
         9 . The method of  claim 1 , wherein the first fuel type is natural gas and the second fuel type is propane. 
     
     
         10 . The method of  claim 1 , wherein the gas fired system is a boiler, a hydronic system, a water heater, or an air handler. 
     
     
         11 . A gas fired system comprising:
 an inlet for receiving a fluid an outlet for outputting the fluid;   a heat exchanger for heating the fluid using fuel;   a vent for releasing heated gas; and   memory configured to store computer-executable instructions, and   at least one computer processor configured to access memory and execute the computer-executable instructions to:
 determine a machine learning model trained to determine a likelihood of at least one fuel type; 
 determine operational data comprising one or more of a vent temperature indicative of a first temperature in the vent, an inlet temperature indicative of a second temperature of the fluid at the inlet, an outlet temperature indicative of a third temperature of the fluid at the outlet, or a flame current value indicative of an intensity of combustion in the heat exchanger; 
 generate a first output value and a second output value using the machine learning model and based on the operational data, the first output value representing the first likelihood of the first fuel type and the second output value representing the second likelihood of the second fuel type; and 
 determine the first fuel type is being consumed by the gas fired system based on the first output value and a first threshold value. 
   
     
     
         12 . The gas fired system of  claim 11 , wherein the at least one computer processor is further configured to access memory and execute the computer executable instructions to:
 determine, based on determining the first fuel type is being consumed, to cease operation of the gas fired system; and   cause the gas fired system to cease operation.   
     
     
         13 . The gas fired system of  claim 11 , wherein the gas fired system has a fuel valve for restricting an amount of fuel provided to the heat exchanger, and wherein the at least one computer processor is further configured to access memory and execute the computer executable instructions to:
 determine, based on determining the first fuel type is being consumed, to transition the fuel valve from a first position to a second position; and   cause the fuel valve to automatically transition from the first position to the second position.   
     
     
         14 . The gas fired system of  claim 11 , wherein the gas fired system has a fan for generating an airflow, and wherein the at least one computer processor is further configured to access memory and execute the computer executable instructions to:
 determine, based on determining the first fuel type is being consumed, to transition the fan from a first speed to a second speed; and   cause the fan to transition from the first speed to the second speed.   
     
     
         15 . The gas fired system of  claim 11 , wherein the at least one computer processor is further configured to access memory and execute the computer executable instructions to:
 determine, before determining the first fuel type is being consumed by the gas fired system, that the second fuel type was consumed; and   determine that the fuel type has changed from the second fuel type to the first fuel type.   
     
     
         16 . The gas fired system of  claim 15 , further comprising generating an alert that the fuel type has changed. 
     
     
         17 . The gas fired system of  claim 11 , wherein the machine learning model is a recurrent neural network, and wherein the at least one computer processor is further configured to access memory and execute the computer executable instructions to receive the machine learning model from a remote server. 
     
     
         18 . The gas fired system of  claim 11 , wherein the gas fired system has a fan for generating an airflow, and wherein the operational data further comprises one or more of a differential between the inlet temperature and the outlet temperature, a fan speed setting, a fan speed reading, an altitude value corresponding to an altitude of the gas fired system, an oxygen value, a heat output value corresponding to heat generated by the heat exchanger, or an operational status value indicative of an operational mode of the gas fired system. 
     
     
         19 . The gas fired system of  claim 11 , wherein the first fuel type is natural gas and the second fuel type is propane. 
     
     
         20 . The gas fired system of  claim 11 , wherein the gas fired system is a boiler, a hydronic system, a water heater, or an air handler.