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

This application claims the benefit of U.S. Application No. 63/660,327, filed Jun. 14, 2024, the entirety of which is hereby incorporated by reference.

The present disclosure is generally in the field of gas fired heating systems. For example, systems and methods are provided herein for detecting a fuel type in a gas fired heat exchanger system such as a hydronic system, a boiler, a water heater, an air handler, or other heating systems.

Hydronic systems such as boilers conveniently and efficiently heat fluids such as water for heating purposes and/or consumption in residential and commercial use. For example, hydronic systems may include a heat exchanger that consumes (e.g., burns) a fuel such as propane or natural gas to heat a water source. The heated water may then be circulated throughout residential or commercial structure to heat such spaces. For example, the hydronic system may include radiators for exchanging heat between the heated water and the surrounding environment.

Other heating systems such as water heaters, pool heaters, gas fired water heaters, gas furnaces, and other gas fired systems may use a similar technique in that such systems may use fuel and a heat exchanger to heat a fluid such as water or a refrigerant. The heated water and/or refrigerant may be used to exchange heat with the surrounding environment or the heated water may be used as a hot water supply. For systems such as gas furnaces, the fuel may be used to heat air for circulation throughout a residential or commercial structure.

While hydronic and other gas fired heating systems may be capable of consuming different types of fuel, the system must be adjusted based on the fuel type. For example, a boiler may be tuned to consume natural gas as well as propane. However, for efficiency and safety purposes, a technician is required to fine tune operation of the system including adjusting gas valve settings, fan speed settings, emergency shut down settings, and other settings depending on the fuel to be used. If the wrong fuel is input into the system, the efficiency of the system will be significantly impacted as the air-to-fuel ratio as a result of the valve and fan settings will be less than ideal. Additionally, inputting the wrong fuel into the system can result in unintended combustion and temperature profiles, which may result in malfunctions.

Gas fired appliances such as a hydronic system, a boiler, water heater, furnace, and other fuel powered heating systems have been developed which are capable detecting a fuel type being consumed by the system and adjusting operation of the system based on the fuel type detected. For example, the gas fired appliance, which may be a hydronic or other heating system 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 appliance. For example, the inlet and/or outlet temperature of water in the gas fired system, a vent temperature, and/or a flame current may be used to determine the type of fuel (e.g., propane, natural gas, etc.).

Once the type of fuel is determined operation of the gas fired system or other heating system may be adjusted. 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. In one example, the gas valve and the fan speed may be adjusted to achieve an optimal air-to-fuel ratio for the given fuel type.

Referring now to, an exemplary gas fired system is depicted for heating a structure as well as a remote server in communication with a controller of the gas fired system for providing fuel detection machine learning models. In one example, the gas fired system may be boiler though different types of gas fired (e.g., hydronic) systems may be used. While gas fired systems are described for illustrative purposes in, it is understood that other fuel fired heating systems (e.g., pool heaters, heat pumps, water heaters, gas furnaces, etc.) may be used instead.

As shown in, gas fired systemmay be used to heat a structure. Gas fired systemmay be any suitable boiler system or system that exchanges heat with water or other fluid for heating a residence or commercial structure. In the example shown in, the structureis a residential structure. Other structures and configurations of zones are contemplated by this disclosure. Gas fired systemmay include heat exchangerwhich may burn a fuel from fuel sourceto generate a flame for combustion to generate heat. The heat exchanger may exchange heat with a fluid such as water that may enter gas fired systemvia fluid inletand may exit via outlet. For example, water may be circulated throughout residential structureand may traverse heater exchangerto exchange thermal energy between the heated water and the surrounding environment.

Fuel sourcemay be a fuel tank or fuel line that may be connected to gas fired systemto provide a fuel supply to heat exchanger. Fuel sourcemay provide natural gas, propane, biogas, hydrogen, or any other fuel for consumption by gas fired system. Gas fired systemmay further include fanwhich may provide an airflow for adjusting a fuel-to-air ratio for combustion of the fuel for heat exchange. Fanmay have an adjustable speed (e.g., revolutions per minute (RPM)) such that the airflow may be manipulated to adjust the air-to-fuel ratio.

Gas fired systemmay further include fuel valvewhich may be an adjustable value for adjusting an amount of fuel entering a combustion chamber of the heat exchanger. The fuel-to-air ratio for gas fired systemmay be modified by adjusting the speed of fanand/or the opening of fuel valve. For example, certain combustion or heat profiles or curves and efficiencies may be achieved for a given fuel with known combustion qualities by adjusting fuel valveand/or the speed of fan. In one example, gas fired systemmay be tuned for optimal efficiency and/or performance with one or more fan and fuel valves settings and gas fired systemmay have one or more different settings for optimal efficiency and/or performance for natural gas.

Gas fired systemmay further include ventwhich may be a vent or flue for expelling exhaust gas from the combustion chamber of heat exchangeras well as a safety feature which may include a sensor designed to cause the gas fired system to cease to operate and thus shut down (e.g., to prevent operational malfunctions). Gas fired systemmay further include inlet sensor, outlet sensor, flame current sensor, vent sensor, fan sensor, and any other sensors or device for generating operational information about gas fired system. Controllermay control the operation of gas fired systemand may be any suitable computing device having a processor and memory.

Controllermay communicate with and/or receive information from inlet sensor, outlet sensor, flame current sensor, vent sensor, and/or fan sensor. Inlet sensormay generate inlet temperatures which may be indicative of a temperature of the fluid (e.g., water) as it enters gas fired system. Outlet sensormay generate outlet temperatures which may be indicative of a temperature of the fluid (e.g., water) as it leaves gas fired system. Flame current sensoris a flame current value indicative of an intensity of combustion in the heat exchanger of the gas fired system. Vent sensormay generate a vent temperature indicative of a temperature in vent. Fan sensormay generate a fan speed reading indicative of a speed of the fan (e.g., RPMs). Controllermay also be programmed to know the altitude of the gas fired system, which may be included in the operational data processed by the machine learning model.

Controllermay communicate with remote servervia any well-known wireless communication technology (e.g., cellular, satellite, WiFi, etc.). Remote servermay send machine learning models trained to detect a type of fuel consumed by gas fired system. For example, remote servermay send controllera recurrent neural network trained using operational data (e.g., inlet temperature, outlet temperature, vent temperature, fan speed, flame current data, etc.) known to correspond to a certain fuel type to train a model to detect the same fuel type using only such operational data.

Controllermay further be in communication with user device, which may include a processor and memory, and may communicate wireless with controllervia any suitable wireless communication technology. User devicemay include a touch screen and/or buttons and may be used to select settings (e.g., set points) for gas fired system.

Referring now to, a fuel detection machine learning model in the form of a recurrent neural network is illustrated. For example, machine learning modelmay be a recurrent neural network and may capture historical information from prior inputs into machine learning model. Alternatively, machine learning modelmay be a feed-forward network or any other type of suitable neural network.

Inputsmay be input into machine learning modeland processed or otherwise analyzed by machine learning model. Inputsmay include one or more types of operational data and/or may include data indicative of operation of the gas fired system not shown in. Inputsmay be operational data and may be received by the controller from one or more sensors of the gas fired system, may be generated by one or more signals in the gas fired system, may be received from the user device, and/or may be generated and/or calculated based on one or more of the foregoing.

As shown in, input layermay include inlet temperaturewhich may be indicative of a temperature at a fluid inlet of a gas fired system, outlet temperaturewhich may be indicative of temperature at a fluid outlet of the gas fired system, a difference between the inlet and outlet temperatures, fan speed setpointwhich may be indicative of fan setting (e.g., fan speed setting), fan speed feedbackwhich may be indicative of the actual or measured speed at which the fan is moving, vent temperature, which may be indicative of the temperature in the vent, flame current, which may be indicative of a degree of intensity of combustion, oxygen value, which may indicative of a level or percentage of oxygen, calculated heat output, which may be a calculated value of heat generated by the gas fired system, and/or operating status, which may indicative operational settings (e.g., system modes, cycles, set points, or the like). Input layermay include fewer or greater number of operational parameters in input layerand/or may include operational parameters different from those illustrated in. Including several input parameters (e.g., input parameters-) significantly improves accuracy of outputsandas compared to a single input parameter or only a select number of parameters from sensors.

As shown in, machine learning modelmay include hidden layers, which may include multiple hidden layers. For example, three hidden layers may be used. Hidden layersmay be used to account for prior inputs in addition to the current inputs. Finally, machine learning modelmay include output layer, which may include outputand output. Outputmay be indicative of a likelihood of a presence or a confidence in the presence of a first fuel type. Outputmay be indicative of a likelihood of a presence or a confidence in the presence of a second fuel type. While the model illustrated ingenerates outputs for only two fuel types, it is understood that machine learning modelcould alternatively generate outputs for more than two fuel types (e.g., three, four, five, six, etc.). In one example, outputsandmay be a numeral value between 0 and 100 or between 0 and 1. Outputsandmay be integer values or decimal values.

Referring now to, a schematic block diagram of a controller of a gas fired system, a remote server, and a user device is depicted. Controllermay be the same as or similar to controllerof. Controllermay include several modules for controlling operation of the gas fired system and detecting a fuel type consumed by the gas fired system. Controllermay include an implementation module for overseeing tasks and operations performed by other modules of controller. Sensors module may communicate with implementation module and may determine and/or generate sensor data (e.g., temperature data, speed data, status data, etc.).

Fuel determination modulemay oversee execution of the machine learning module and may also communicate with implementation module. Communication modulemay permit controllerto communicate with user device controllerand remote server controller. For example, communication module may communicate with remote server controllerto receive the machine learning model from remote server controller. Systems operations modulemay control operation of the components of the gas fired system (e.g., heat exchanger, fuel valve, fan, etc.). For example, operations modulemay send instructions to the fuel valve to cause the fuel valve to open or close. Fuel type settingsmay maintain optimal settings for operating components of the gas fired system for each fuel type. For example, certain fan speed and fuel valve settings may be maintained for achieving an optimal or desired air-to-fuel ratio for each fuel type.

Remote server controllermay include communication module for communicating with controlleras well as fuel detection module. Fuel detection modulemay maintain a robust machine learning model that was trained using operational data known to correspond to a certain fuel type and verified using different operational data known to correspond to that certain fuel type. The model may be trained to take into account performance changes over time as the gas fired system ages and/or experiences wear and tear. Further, data from various of gas fired systems that are operational and in use may be used to train the model to improve accuracy. In one example, training data may include operational data from different equipment models, years, ages, locations, and the like. As remote server controllermay have greater computing capability (e.g., memory, processor speed, etc.) the model maintained on remote server controllermay be a more robust version of the model shared with controller. For example, the model on remote servermay be shrunken down for execution on controller. Techniques for shrinking the model may include model pruning (e.g., removing inputs and/or weights with little impact), quantization (e.g., truncating data and/or using integers), knowledge distillation (e.g., recreating simpler inner layers of model), embedded optimized code (e.g., using direct memory manipulation), use of optimized libraries (e.g., libraries optimized for certain hardware), and the like. The model may be reduced such that it may be run on a thread under the main application program for operating the gas fired system.

User device controllermay include communication modulefor communicating with controllerof the gas fired system and may further include system settings module. System settings module may oversee input received from a user of the gas fired system and may generate operational settings, instructions or commands to be processed by controllerand which may be indicative of desired temperatures, setpoints, or the like.

Referring now to, a process flow for detecting a fuel type consumed by a gas fired system and adjusting operation of the gas fired system based on the detected fuel type is depicted. While example embodiments of the disclosure may be described in the context of a controller (e.g., controllerof), it should be appreciated that the disclosure is more broadly applicable to various types of computing devices as well as a controller in combination with a computing device, such as a server. Some or all of the blocks of the process flows in this disclosure may be performed in a distributed manner across any number of devices. The operations of process flowmay be optional and may be performed in a different order.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to determine a fuel detection model and/or an updated fuel detection model. This may the shrunken or reduced model provided by the remote server. The remote server may periodically provide the model and/or the controller may periodically inquire whether an updated model is available.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to determine sensor data and/or request sensor data. The sensor data may include inlet temperature of the fluid, outlet temperature of the fluid, vent temperature, flame current, fan speed, operational status, or any other operational information that may be sensed by the gas fired system.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to determine calculate input data based on the sensor data. Such input data may include temperature differentials, speed differentials, current differentials, calculated heat values, fluid flow rates, and the like. At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to analyze and/or process the sensor data, settings data corresponding to operation of the gas fired system, and/or calculated input data, each being operational data, using the fuel detection model determined at block. Alternatively, a remote server in communication with the controller may execute the machine learning model to analyze and/or process the sensor data, settings data and/or calculated input data. In this example, the controller may send such data to the remote server and may receive from the remote server predictions of a fuel type (e.g., based on fuel confidence levels). Based on the fuel type predictions, the controller can adjust system operations as described at block.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to determine fuel confidence values based on the outputs of the machine learning model. For example, the machine learning model may output a likelihood value of a presence of a certain type of fuel or a confidence level that a certain type of fuel is being consumed by the gas fired system. At decision, the presence of a given fuel type may be determined by comparing the likelihood value or confidence level to a threshold value. For example, the threshold value may be 0.95 or 95% and if the confidence level or likelihood value is the same as or exceeds the threshold value, the fuel may be determined to be present (e.g., to be currently consumed by the gas fired system).

At decision, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to consider whether the fuel type has changed. To make this determination the fuel type determined to be present may be compared against a last known fuel type determine to be present. If the fuel type has not changed, the blockmay be reinitiated. If the fuel types are different, then fuel type may be determined to have changed. The last known fuel type may be saved locally on the controller. If the fuel type has changed, the new fuel type may be saved as the current fuel type.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to determine the settings for the new fuel type. For example, for each fuel type the controller may maintain fuel valve settings, fan settings, and other operational settings to achieve optimal or desired fuel-to-air ratios and/or efficiency of the gas fired system.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to adjust operation of the gas fired system based on the operational settings determined at block. For example, the fan speed may be adjusted and/or the gas valve may be adjusted to increase or reduce the fuel flow into the combustion chamber. Alternatively, the gas fired system may be immediately shut down for safety purposes. The adjustments made at blockmay depend on the air-to-fuel mixture of the fuel type determined at block. In one example, the fan speed may be increased for a fuel type with a lean mixture or may be reduced for fuel type having a rich mixture. For example, propane may be considered a richer mixture than natural gas and natural gas may be considered a leaner mixture than propane. In another example, a fuel valve may be caused to be opened by the controller for a rich mixture and caused to be closed for a lean mixture. In yet another example, the fan speed may be increased and the fuel valve may be closed for a fuel type with a lean mixture and/or the fan speed may be decreased and the fuel valve may be opened for a fuel type with a rich mixture.

At block, computer-executable instructions stored on a memory of a device, such as a controller, may be executed to generate an alert and/or cause the user device to present an alert regarding the new fuel type or changes to operational settings. For example, the controller may cause the user device to generate an alert that a new fuel type was detected and certain settings of the gas fired system were automatically adjusted for the new fuel type. Alternatively, if the gas fired system is shut down at block, the alert may inform the user that the fuel type changed and the system was powered off.

is a schematic block diagram of controller, in accordance with one or more example embodiments of the disclosure. Controllermay be the same as controllerof. While the schematic block diagram is described with respect to controller, it is understood that other controllers, servers, and/or computing devices may additionally or alternatively be used.

Controllermay be configured to communicate with one or more servers, computing devices, controllers, user devices, other systems, or the like. Controllermay be configured to communicate via one or more networks. Such network(s) may include, but are not limited to, any one or more different types of communications networks such as, for example, cable networks, public networks (e.g., the Internet), private networks (e.g., frame-relay networks), wireless networks, cellular networks, telephone networks (e.g., a public switched telephone network), or any other suitable private or public packet-switched or circuit-switched networks.

In an illustrative configuration, controllermay include one or more processors, one or more memory devices(also referred to herein as memory), one or more input/output (I/O) interface(s), one or more network interface(s), one or more transceiver(s), one or more antenna(s), and data storage. The controllermay further include one or more bus(es)that functionally couple various components of the controller.

The bus(es)may include at least one of a system bus, a memory bus, an address bus, or a message bus, and may permit exchange of information (e.g., data (including computer-executable code), signaling, etc.) between various components of the controller. The bus(es)may include, without limitation, a memory bus or a memory controller, a peripheral bus, an accelerated graphics port, and so forth. The bus(es)may be associated with any suitable bus architecture.

The memorymay include volatile memory (memory that maintains its state when supplied with power) such as random access memory (RAM) and/or non-volatile memory (memory that maintains its state even when not supplied with power) such as read-only memory (ROM), flash memory, ferroelectric RAM (FRAM), and so forth. Persistent data storage, as that term is used herein, may include non-volatile memory. In various implementations, the memorymay include multiple different types of memory such as various types of static random access memory (SRAM), various types of dynamic random access memory (DRAM), various types of unalterable ROM, and/or writeable variants of ROM such as electrically erasable programmable read-only memory (EEPROM), flash memory, and so forth.

The data storagemay include removable storage and/or non-removable storage including, but not limited to, magnetic storage, optical disk storage, and/or tape storage. The data storagemay provide non-volatile storage of computer-executable instructions and other data. The memoryand the data storage, removable and/or non-removable, are examples of computer-readable storage media (CRSM) as that term is used herein. The data storagemay store computer-executable code, instructions, or the like that may be loadable into the memoryand executable by the processor(s)to cause the processor(s)to perform or initiate various operations. The data storagemay additionally store data that may be copied to memoryfor use by the processor(s)during the execution of the computer-executable instructions. Moreover, output data generated as a result of execution of the computer-executable instructions by the processor(s)may be stored initially in memory, and may ultimately be copied to data storagefor non-volatile storage.

The data storagemay store one or more operating systems (O/S); one or more optional database management systems (DBMS); and one or more program module(s), applications, engines, computer-executable code, scripts, or the like such as, for example, one or more implementation modules, system operation modules, communication modules, fuel determination module, and sensor module. Some or all of these modules may be sub-modules. Any of the components depicted as being stored in data storagemay include any combination of software, firmware, and/or hardware. The software and/or firmware may include computer-executable code, instructions, or the like that may be loaded into the memoryfor execution by one or more of the processor(s). Any of the components depicted as being stored in data storagemay support functionality described in reference to correspondingly named components earlier in this disclosure.

Referring now to other illustrative components depicted as being stored in the data storage, the O/Smay be loaded from the data storageinto the memoryand may provide an interface between other application software executing on the controllerand hardware resources of the controller. More specifically, the O/Smay include a set of computer-executable instructions for managing hardware resources of the controllerand for providing common services to other application programs (e.g., managing memory allocation among various application programs). In certain example embodiments, the O/Smay control execution of the other program module(s) to for content rendering. The O/Smay include any operating system now known or which may be developed in the future including, but not limited to, any server operating system, any mainframe operating system, or any other proprietary or non-proprietary operating system.

The optional DBMSmay be loaded into the memoryand may support functionality for accessing, retrieving, storing, and/or manipulating data stored in the memoryand/or data stored in the data storage. The DBMSmay use any of a variety of database models (e.g., relational model, object model, etc.) and may support any of a variety of query languages. The DBMSmay access data represented in one or more data schemas and stored in any suitable data repository including, but not limited to, databases (e.g., relational, object-oriented, etc.), file systems, flat files, distributed datastores in which data is stored on more than one node of a computer network, peer-to-peer network datastores, or the like.

The optional input/output (I/O) interface(s)may facilitate the receipt of input information by the controllerfrom one or more I/O devices as well as the output of information from the controllerto the one or more I/O devices. The I/O devices may include any of a variety of components such as a display or display screen having a touch surface or touchscreen; an audio output device for producing sound, such as a speaker; an audio capture device, such as a microphone; an image and/or video capture device, such as a camera; and so forth. Any of these components may be integrated into the controlleror may be separate.

The controllermay further include one or more network interface(s)via which the con controllermay communicate with any of a variety of other systems, platforms, networks, devices, and so forth. The network interface(s)may enable communication, for example, with one or more wireless routers, one or more host servers, one or more web servers, and the like via one or more of networks.

The antenna(s)may include any suitable type of antenna depending, for example, on the communications protocols used to transmit or receive signals via the antenna(s). Non-limiting examples of suitable antennas may include directional antennas, non-directional antennas, dipole antennas, folded dipole antennas, patch antennas, multiple-input multiple-output (MIMO) antennas, or the like. The antenna(s)may be communicatively coupled to one or more transceiversor radio components to which or from which signals may be transmitted or received. Antenna(s)may include, without limitation, a cellular antenna for transmitting or receiving signals to/from a cellular network infrastructure, an antenna for transmitting or receiving Wi-Fi signals to/from an access point (AP), a Global Navigation Satellite System (GNSS) antenna for receiving GNSS signals from a GNSS satellite, a Bluetooth antenna for transmitting or receiving Bluetooth signals including BLE signals, a Near Field Communication (NFC) antenna for transmitting or receiving NFC signals, a 900 MHz antenna, and so forth.

The transceiver(s)may include any suitable radio component(s) for, in cooperation with the antenna(s), transmitting or receiving radio frequency (RF) signals in the bandwidth and/or channels corresponding to the communications protocols utilized by the controllerto communicate with other devices. The transceiver(s)may include hardware, software, and/or firmware for modulating, transmitting, or receiving-potentially in cooperation with any of antenna(s)—communications signals according to any of the communications protocols discussed above including, but not limited to, one or more Wi-Fi and/or Wi-Fi direct protocols, as standardized by the IEEE 802.11 standards, one or more non-Wi-Fi protocols, or one or more cellular communications protocols or standards. The transceiver(s)may further include hardware, firmware, or software for receiving GNSS signals. The transceiver(s)may include any known receiver and baseband suitable for communicating via the communications protocols utilized by the controller. The transceiver(s)may further include a low noise amplifier (LNA), additional signal amplifiers, an analog-to-digital (A/D) converter, one or more buffers, a digital baseband, or the like.

Referring now to functionality supported by the various program module(s) depicted in, the implementation module(s)may include computer-executable instructions, code, or the like that responsive to execution by one or more of the processor(s)may perform functions including, but not limited to, overseeing coordination, communication, and interaction between one or more modules and computer executable instructions in data storage.

The system operation module(s)may include computer-executable instructions, code, or the like that responsive to execution by one or more of the processor(s)may perform functions including, but not limited to, controlling the operation of various components of the gas fired system including the fuel valve and/or the fan speed.

The communication module(s)may include computer-executable instructions, code, or the like that responsive to execution by one or more of the processor(s)may perform functions including, but not limited to, communicating with one or remote servers for receiving the machine learning model and/or more user devices for receiving setpoints and/or temperature settings.

The fuel determination module(s)may include computer-executable instructions, code, or the like that responsive to execution by one or more of the processor(s)may oversee operation of the heat pump and may perform functions including, but not limited to, executing one or more machine learning models using operational data and comparing outputs of the models to threshold values.

The sensor module(s)may include computer-executable instructions, code, or the like that responsive to execution by one or more of the processor(s)may oversee generation for operational data including sensor data, calculated values, operating information (e.g., status and/or modes), and the like.