Floor heating intelligent control system and method
By training Bayesian networks and machine learning models, the fan speed is dynamically adjusted, solving the problem of unstable temperature when users enter the room, realizing intelligent floor heating control, and improving the user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI DELONG ELECTRIC HEATING MATERIAL TECH CO LTD
- Filing Date
- 2023-08-16
- Publication Date
- 2026-07-07
Smart Images
Figure CN117006506B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of airflow-assisted underfloor heating technology, specifically an intelligent control system and method for underfloor heating. Background Technology
[0002] Underfloor heating is a radiant heating system that uses an electric heating film embedded under the floor to conduct heat into the room, which then radiates heat to evenly warm the entire space. Underfloor heating systems primarily provide a comfortable indoor temperature through radiant heat.
[0003] During the underfloor heating process, the electric heating film of the underfloor heating system is usually placed under the indoor floor. Heat is dissipated upward through the floor, forming convective heat transfer; hot air rises and cold air sinks, forming thermal convection airflow, thereby ultimately achieving uniform and stable indoor temperature.
[0004] Therefore, a fan can be installed on the underfloor heating system to promote indoor air circulation and speed up the transfer of heat from the electric heating film of the underfloor heating system to the indoor air, thereby making the entire indoor space heat up more evenly and quickly.
[0005] Currently, users often have the need for the indoor temperature to be already comfortable when they enter the room. However, due to the subjectivity of users, it is difficult for them to accurately assess when to turn on the underfloor heating and the appropriate temperature. Furthermore, when the time between the user's arrival at the room and the actual arrival time is short, underfloor heating alone is insufficient to achieve the user's expected effect in a timely manner, further increasing the difficulty of meeting user needs. Therefore, there is an urgent need for a method that can intelligently meet user needs.
[0006] Chinese patent CN104748320B discloses an intelligent floor heating control system and method. This system integrates the floor heating system with an air conditioning system. When the floor heating is controlled in zones, there is no need to add a floor heating thermostat or manually control the manifold. Only the air conditioning controller needs to be set to control the floor heating or the combined heating of the floor heating and air conditioning, achieving intelligent linkage control between the two systems. However, this invention does not solve the problem of users experiencing the expected stable temperature upon entering the room.
[0007] Therefore, this invention proposes an intelligent control system and method for underfloor heating. Summary of the Invention
[0008] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes an intelligent control system and method for underfloor heating, which dynamically and intelligently adjusts the fan speed to control the indoor air flow speed, thereby controlling the indoor temperature circulation speed, so as to ensure that the indoor temperature is already in a stable state when the user returns to the room, thus improving the user experience.
[0009] To achieve the above objectives, an intelligent control method for underfloor heating is proposed according to an embodiment of the first aspect of the present invention, comprising the following steps:
[0010] Collect data on underfloor heating usage habits, travel time habits, and convective heat transfer training data;
[0011] Based on data on underfloor heating usage habits, a Bayesian network model was trained to predict the appropriate temperature for underfloor heating; based on training data on convective heat transfer, a machine learning model was trained to predict the output wind speed of the fan.
[0012] The underfloor heating control backend monitors in real time whether the user sends a start command. Upon receiving the start command, it calculates the user's return time based on the user's location and return time habit data.
[0013] Collect real-time environmental data; based on the real-time environmental data, use a Bayesian network model to obtain the predicted suitable temperature for underfloor heating control;
[0014] Based on real-time environmental data, user return trip duration, and suitable temperature control, a machine learning model is used to output the predicted control output wind speed of the fan.
[0015] The underfloor heating control panel sets the temperature of the underfloor heating system to a suitable temperature and the fan speed to a controlled output speed.
[0016] The data on underfloor heating usage habits includes environmental data each time a user uses underfloor heating and the corresponding suitable temperature for underfloor heating.
[0017] The environmental data includes the indoor temperature and humidity before the user turns on the underfloor heating, as well as the time period during which the underfloor heating is turned on.
[0018] The method for determining the opening time period is as follows:
[0019] The day from 0:00 to 24:00 is divided into a preset intraday period H. The system divides the system into daily time periods and numbers these time periods in chronological order. The daily time period H is a preset positive integer less than 25. The activation time period is the number of the daily time period corresponding to the time when the user turns on the underfloor heating.
[0020] Furthermore, the suitable temperature is the stable indoor temperature when the indoor temperature reaches a stable level each time the underfloor heating is turned on;
[0021] The condition for determining that the indoor temperature has reached a stable level is:
[0022] Temperature sensors are placed at N locations indoors; where N is the preset number of temperature sensors, and the location of each temperature sensor is set according to the specific indoor structure and layout.
[0023] For each temperature sensor, if the user does not control the floor heating or fan to perform any function within a preset stable time threshold before any time, and the difference between the highest and lowest detected temperature values is less than a preset first temperature fluctuation threshold, then the temperature at the location of the temperature sensor is considered to have reached stability, and the average of the highest and lowest detected temperature values is taken as the stable temperature of the sensor.
[0024] When the temperature at all the locations of the temperature sensors has reached a stable state, if the difference between the maximum and minimum stable temperatures of all the sensors is less than the preset second temperature fluctuation threshold, then the indoor temperature is determined to have reached a stable state, and the average of the maximum and minimum stable temperatures of the sensors is taken as the indoor stable temperature.
[0025] The return trip time habit data includes the time it takes for a user to travel from entering the residential area to arriving indoors each time.
[0026] The convective heat transfer training data includes convective heat transfer characteristic data after each turn on of the underfloor heating and the output wind speed label of the fan.
[0027] The convective heat transfer characteristic data includes the indoor temperature, indoor humidity and operating time when the underfloor heating is turned on, the time from when the underfloor heating is turned on until the indoor temperature reaches a stable state, and the suitable temperature when the indoor temperature reaches a stable state.
[0028] The output wind speed label is the wind speed set for the fan each time the underfloor heating is turned on and the fan equipped with the underfloor heating is started.
[0029] The method for training a Bayesian network model to predict the suitable temperature for underfloor heating is as follows:
[0030] Construct a Bayesian network model;
[0031] Using environmental data from underfloor heating usage habit data as input to a Bayesian network model, the Bayesian network model outputs the predicted suitable temperature for underfloor heating for each set of environmental data, with the suitable temperature for underfloor heating corresponding to the environmental data in the underfloor heating usage habit data as the prediction target, and minimizing the sum of prediction errors for the suitable temperature of all underfloor heating systems as the training objective; the Bayesian network model is trained until the sum of prediction errors converges, at which point training stops, thus training a Bayesian network model that outputs the predicted suitable temperature for underfloor heating based on environmental data;
[0032] The method for constructing a Bayesian network model is as follows:
[0033] Construct a two-layer Bayesian network model, where the first layer contains three nodes and the second layer contains one node; each node in the first layer represents the indoor temperature, indoor humidity, and the time period during which the underfloor heating is turned on; the nodes in the second layer represent the suitable temperature for the underfloor heating.
[0034] Each node in the first layer has a directed edge pointing to a node in the second layer;
[0035] The method for training a machine learning model to predict the output wind speed of a wind turbine is as follows:
[0036] The convective heat transfer feature data in the convective heat transfer training data is used as the input to the machine learning model. The machine learning model outputs the predicted wind speed label for each set of convective heat transfer feature data, and the prediction target is the corresponding output wind speed label in the convective heat transfer training data. The training objective is to minimize the sum of prediction errors for all output wind speed labels. The machine learning model is trained until the sum of prediction errors converges, at which point training stops, thus training a machine learning model that outputs predicted output wind speed labels based on the convective heat transfer feature data.
[0037] The start command is a command sent by the user to the underfloor heating control backend via a remote terminal and wireless network.
[0038] The activation command includes the user's location and movement speed;
[0039] The method for calculating a user's return trip time is as follows:
[0040] Based on the user's location and the location of the residential area, obtain the shortest route for the user to reach the residential area;
[0041] Divide the distance of the shortest route by the user's movement speed to obtain the first return trip time T1;
[0042] In the habitual data on return trip duration, the average time from entering a residential area to arriving indoors is marked as the second return trip duration T2;
[0043] If the return trip duration is denoted as T, then the formula for calculating the return trip duration T is T = T1 + T2;
[0044] The real-time environmental data includes the indoor temperature, indoor humidity, and the corresponding intraday time period number when the underfloor heating control backend receives the start command.
[0045] The method for obtaining the predicted suitable temperature for underfloor heating using a Bayesian network model is as follows:
[0046] Real-time environmental data is used as input to a Bayesian network model to obtain the predicted value of the suitable temperature for underfloor heating output by the Bayesian network model. The controlled suitable temperature is the predicted value of the suitable temperature for underfloor heating.
[0047] The method of using a machine learning model to output the predicted control output wind speed of the wind turbine is as follows:
[0048] Real-time environmental data, user return trip time, and controlled suitable temperature are used as a set of convective heat transfer characteristic data. This convective heat transfer characteristic data is input into a machine learning model to obtain the predicted value of the output wind speed label output by the machine learning model; the controlled output wind speed is the predicted value of the output wind speed label.
[0049] An embodiment of the second aspect of the present invention provides an intelligent control system for underfloor heating, comprising a historical data collection module, a model training module, and an intelligent control module; wherein the modules are electrically connected to each other.
[0050] The historical data collection module collects data on underfloor heating usage habits, travel time habits, and convection heat transfer training data. It then sends the underfloor heating usage habit data and convection heat transfer training data to the model training module and the travel time habit data to the intelligent control module.
[0051] The model training module trains a Bayesian network model to predict the appropriate temperature for underfloor heating based on underfloor heating usage data; and trains a machine learning model to predict the output wind speed of the fan based on convective heat transfer training data. The Bayesian network model and the machine learning model are then sent to the intelligent control module.
[0052] The intelligent control module uses return trip duration habit data, Bayesian network models, and machine learning models to intelligently control the underfloor heating system.
[0053] The method for intelligent control of underfloor heating is as follows:
[0054] The system monitors in real time whether the user sends a start command. Upon receiving the start command, it calculates the user's return time based on the user's location and return time habit data.
[0055] Collect real-time environmental data; based on the real-time environmental data, use a Bayesian network model to obtain the predicted suitable control temperature for the underfloor heating; based on the real-time environmental data, the user's return trip time, and the suitable control temperature, use a machine learning model to output the predicted control output wind speed of the fan.
[0056] The underfloor heating control panel sets the temperature of the underfloor heating system to a suitable level and the fan speed to a controlled output speed.
[0057] An electronic device according to an embodiment of a third aspect of the present invention includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;
[0058] The processor executes the above-described intelligent control method for underfloor heating by calling the computer program stored in the memory.
[0059] According to an embodiment of a fourth aspect of the present invention, a computer-readable storage medium is provided thereon storing an erasable and rewritable computer program.
[0060] When the computer program is run on a computer device, the computer device executes the above-described intelligent control method for underfloor heating.
[0061] Compared with the prior art, the beneficial effects of the present invention are:
[0062] (1) This invention collects data on underfloor heating usage habits, return trip time habits, and convective heat transfer training data in advance. Based on the underfloor heating usage habit data, a Bayesian network model is trained to predict the appropriate temperature of underfloor heating. Based on the convective heat transfer training data, a machine learning model is trained to predict the output wind speed of the fan. The system monitors whether the user sends a start command in real time. After receiving the start command, the system calculates the user's return trip time based on the user's location and return trip time habits, and collects real-time environmental data. Based on the real-time environmental data, the Bayesian network model is used to obtain the predicted appropriate temperature for underfloor heating control. Thus, the system automatically configures the underfloor heating temperature that matches the user's habits, thereby improving the user's underfloor heating experience.
[0063] (2) Based on real-time environmental data, user's return time and suitable temperature, the present invention uses a machine learning model to output the predicted control output speed of the fan, and sets the temperature of the underfloor heating to the suitable temperature and the fan speed to the control output speed. This enables the fan speed to be dynamically and intelligently adjusted according to the user's return time, environmental data and suitable temperature, so as to control the air flow speed in the room and thus control the circulation speed of the indoor temperature, so as to ensure that the indoor temperature is stable when the user returns to the room, thereby improving the user experience. Attached Figure Description
[0064] Figure 1 This is a flowchart of the intelligent control method for underfloor heating in Embodiment 1 of the present invention;
[0065] Figure 2 This is a diagram showing the module connection relationship of the intelligent underfloor heating control system in Embodiment 2 of the present invention;
[0066] Figure 3 This is a schematic diagram of the electronic device structure in Embodiment 3 of the present invention;
[0067] Figure 4 This is a schematic diagram of the computer-readable storage medium structure in Embodiment 4 of the present invention. Detailed Implementation
[0068] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0069] Example 1
[0070] like Figure 1 As shown, an intelligent control method for underfloor heating, used in an underfloor heating control backend, includes the following steps:
[0071] Step 1: Collect data on underfloor heating usage habits, travel time habits, and convection heat transfer training data;
[0072] Step 2: Based on data on underfloor heating usage habits, train a Bayesian network model to predict the appropriate temperature for underfloor heating; based on convective heat transfer training data, train a machine learning model to predict the output wind speed of the fan.
[0073] Step 3: The underfloor heating control backend monitors in real time whether the user sends a start command. After receiving the start command, it calculates the user's return time based on the user's location and return time habit data.
[0074] Step 4: Collect real-time environmental data; based on the real-time environmental data, use a Bayesian network model to obtain the predicted suitable temperature for underfloor heating control;
[0075] Step 5: Based on real-time environmental data, user return trip duration, and suitable temperature control, use a machine learning model to output the predicted control output wind speed of the fan;
[0076] Step Six: Set the floor heating temperature to a suitable temperature in the control panel and set the fan speed to the control output speed.
[0077] The data on underfloor heating usage habits includes environmental data each time a user uses underfloor heating and the corresponding suitable temperature for underfloor heating.
[0078] The environmental data includes the indoor temperature and humidity before the user turns on the underfloor heating, as well as the time period during which the underfloor heating is turned on; it should be noted that the indoor temperature and humidity can be obtained in real time using temperature sensors and humidity sensors, respectively.
[0079] Preferably, the method for determining the start time period is as follows:
[0080] Preset daily division period; divide each day from 0:00 to 24:00 into the preset daily division period H. The system divides the system into daily time periods and numbers these time periods in chronological order. The daily time period H is a preset positive integer less than 25. The activation time period is the number of the daily time period corresponding to the time when the user turns on the underfloor heating.
[0081] Furthermore, the suitable temperature is the stable indoor temperature when the indoor temperature reaches a stable level each time the underfloor heating is turned on;
[0082] Preferably, the condition for determining that the indoor temperature has reached a stable state is:
[0083] Temperature sensors are placed at N locations indoors; where N is the preset number of temperature sensors, and the location of each temperature sensor is set according to the specific indoor structure and layout.
[0084] For each temperature sensor, if the user does not control the floor heating or fan to perform any function within a preset stable time threshold before any time, and the difference between the highest and lowest detected temperature values is less than a preset first temperature fluctuation threshold, then the temperature at the location of the temperature sensor is considered to have reached stability, and the average of the highest and lowest detected temperature values is taken as the stable temperature of the sensor.
[0085] When the temperature at all the locations of the temperature sensors has reached a stable state, if the difference between the maximum and minimum stable temperatures of all the sensors is less than the preset second temperature fluctuation threshold, then the indoor temperature is determined to have reached a stable state, and the average of the maximum and minimum stable temperatures of the sensors is taken as the indoor stable temperature.
[0086] The return trip time habit data includes the time it takes for a user to travel from entering the residential area to arriving indoors each time.
[0087] The residential area is a pre-defined area based on the location of the underfloor heating installation. This residential area can be a community, office park, etc. The specific division method can be determined according to the actual urban building area planning. It is understood that outside the residential area, users have many ways to return home, such as walking, driving, or cycling. However, inside the residential area, users generally use their usual way of returning home after entering the residential area, so the time spent is generally fixed.
[0088] The convective heat transfer training data includes convective heat transfer characteristic data after each turn on of the underfloor heating and the output wind speed label of the fan.
[0089] The convective heat transfer characteristic data includes the indoor temperature, indoor humidity and operating time when the underfloor heating is turned on, the time from when the underfloor heating is turned on until the indoor temperature reaches a stable state, and the suitable temperature when the indoor temperature reaches a stable state.
[0090] The output wind speed label is the wind speed set for the fan each time the underfloor heating is turned on and the fan equipped with the underfloor heating is started.
[0091] The method for training a Bayesian network model to predict the suitable temperature for underfloor heating is as follows:
[0092] Construct a Bayesian network model;
[0093] Using environmental data from underfloor heating usage habit data as input to a Bayesian network model, the Bayesian network model outputs the predicted suitable temperature for underfloor heating for each set of environmental data, with the suitable temperature for underfloor heating corresponding to the environmental data in the underfloor heating usage habit data as the prediction target, and minimizing the sum of prediction errors for the suitable temperature of all underfloor heating systems as the training objective; the Bayesian network model is trained until the sum of prediction errors converges, at which point training stops, thus training a Bayesian network model that outputs the predicted suitable temperature for underfloor heating based on environmental data;
[0094] Preferably, the method for constructing a Bayesian network model is as follows:
[0095] Construct a two-layer Bayesian network model, where the first layer contains three nodes and the second layer contains one node; each node in the first layer represents the indoor temperature, indoor humidity, and the time period during which the underfloor heating is turned on; the nodes in the second layer represent the suitable temperature for the underfloor heating.
[0096] Each node in the first layer has a directed edge pointing to a node in the second layer;
[0097] The method for training a machine learning model to predict the output wind speed of a wind turbine is as follows:
[0098] The convective heat transfer feature data in the convective heat transfer training data is used as input to a machine learning model. The machine learning model outputs a predicted wind speed label for each set of convective heat transfer feature data, and uses the corresponding output wind speed label in the convective heat transfer training data as the prediction target. The training objective is to minimize the sum of prediction errors for all output wind speed labels. The machine learning model is trained until the sum of prediction errors converges, at which point training stops, resulting in a machine learning model that outputs predicted output wind speed labels based on the convective heat transfer feature data. The machine learning model can be either a multinomial regression model or an SVR model.
[0099] It should be noted that the formula for calculating the prediction error is: Where c is the feature data number, zc is the prediction error, ac is the predicted state value corresponding to the c-th group of feature data, and wc is the actual state value corresponding to the c-th group of training data; for example, in a Bayesian network model, the feature data corresponds to environmental data, and the state value corresponds to the suitable temperature for underfloor heating; in a machine learning model, the feature data corresponds to convective heat transfer feature data, and the state value corresponds to the output wind speed label.
[0100] Furthermore, the start command is a command sent by the user to the underfloor heating control backend via a remote terminal and wireless network.
[0101] The activation command includes the user's location and movement speed; it is understood that the movement speed can be calculated based on the user's real-time location changes.
[0102] The method for calculating a user's return trip time is as follows:
[0103] Based on the user's location and the location of the residential area, the shortest route to the residential area is obtained. It is understood that most current electronic maps have the function of generating the shortest route given a starting location and a destination location, which will not be elaborated here.
[0104] Divide the distance of the shortest route by the user's movement speed to obtain the first return trip time T1;
[0105] In the habitual data on return trip duration, the average time from entering a residential area to arriving indoors is marked as the second return trip duration T2;
[0106] If the return trip duration is denoted as T, then the formula for calculating the return trip duration T is T = T1 + T2;
[0107] The real-time environmental data includes the indoor temperature, indoor humidity, and the corresponding intraday time period number when the underfloor heating control backend receives the start command.
[0108] The method for obtaining the predicted suitable temperature for underfloor heating using a Bayesian network model is as follows:
[0109] Real-time environmental data is used as input to a Bayesian network model to obtain a predicted value of the suitable temperature for underfloor heating from the Bayesian network model output. The controlled suitable temperature is the predicted value of the suitable temperature for underfloor heating. Thus, based on the user's underfloor heating usage habits, the system automatically configures the underfloor heating temperature to match the user's habits, thereby improving the user's underfloor heating experience.
[0110] The method of using a machine learning model to output the predicted control output wind speed of the wind turbine is as follows:
[0111] Real-time environmental data, user return travel time, and suitable temperature are used as a set of convective heat transfer characteristic data. This convective heat transfer characteristic data is input into a machine learning model to obtain the predicted value of the output wind speed label output by the machine learning model. The controlled output wind speed is the predicted value of the output wind speed label. This enables the dynamic and intelligent adjustment of the fan speed based on the user's return time indoors, environmental data, and suitable temperature to ensure that the indoor temperature is stable when the user returns indoors.
[0112] Example 2
[0113] like Figure 2 As shown, an intelligent control system for underfloor heating includes a historical data collection module, a model training module, and an intelligent control module; wherein the modules are electrically connected to each other.
[0114] The historical data collection module is mainly used to collect data on underfloor heating usage habits, travel time habits, and convection heat transfer training data. It sends the underfloor heating usage habit data and convection heat transfer training data to the model training module and the travel time habit data to the intelligent control module.
[0115] The model training module is mainly used to train a Bayesian network model to predict the appropriate temperature of the underfloor heating system based on underfloor heating usage data; and to train a machine learning model to predict the output wind speed of the fan based on convective heat transfer training data. The Bayesian network model and the machine learning model are then sent to the intelligent control module.
[0116] The intelligent control module is mainly used to intelligently control the floor heating system based on return trip duration habit data, Bayesian network model, and machine learning model.
[0117] The method for intelligent control of underfloor heating is as follows:
[0118] The system monitors in real time whether the user sends a start command. Upon receiving the start command, it calculates the user's return time based on the user's location and return time habit data.
[0119] Collect real-time environmental data; based on the real-time environmental data, use a Bayesian network model to obtain the predicted suitable control temperature for the underfloor heating; based on the real-time environmental data, the user's return trip time, and the suitable control temperature, use a machine learning model to output the predicted control output wind speed of the fan.
[0120] The underfloor heating control panel sets the temperature of the underfloor heating system to a suitable level and the fan speed to a controlled output speed.
[0121] Example 3
[0122] Figure 3This is a schematic diagram of an electronic device structure provided in one embodiment of this application. Figure 3 As shown, according to another aspect of this application, an electronic device 100 is also provided. The electronic device 100 may include one or more processors and one or more memories. The memories store computer-readable code, which, when executed by the one or more processors, can perform the intelligent floor heating control method described above.
[0123] The method or system according to the embodiments of this application can also be used by means of Figure 3 The architecture of the electronic device shown is used to implement this. For example... Figure 3 As shown, the electronic device 100 may include a bus 101, one or more CPUs 102, a read-only memory (ROM) 103, a random access memory (RAM) 104, a communication port 105 connected to a network, an input / output component 106, a hard disk 107, etc. The storage device in the electronic device 100, such as the ROM 103 or the hard disk 107, may store the intelligent floor heating control method provided in this application. The intelligent control method for underfloor heating may include the following steps: Step 1: Collect data on underfloor heating usage habits, return trip time habits, and convective heat transfer training data; Step 2: Based on the underfloor heating usage habit data, train a Bayesian network model to predict the suitable temperature for underfloor heating; based on the convective heat transfer training data, train a machine learning model to predict the output wind speed of the fan; Step 3: The underfloor heating control backend monitors in real time whether the user sends a start command. Upon receiving the start command, it calculates the user's return trip time based on the user's location and return trip time habits; Step 4: Collect real-time environmental data; based on the real-time environmental data, use the Bayesian network model to obtain the predicted suitable temperature for underfloor heating control; Step 5: Based on the real-time environmental data, the user's return trip time, and the suitable temperature, use the machine learning model to output the predicted control output wind speed of the fan; Step 6: The underfloor heating control backend sets the underfloor heating temperature to the suitable temperature and sets the fan speed to the control output wind speed.
[0124] Furthermore, the electronic device 100 may also include a user interface 108. Of course, Figure 3 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 3 One or more components in the illustrated electronic device.
[0125] Example 4
[0126] Figure 4 This is a schematic diagram of a computer-readable storage medium structure provided in one embodiment of this application. Figure 4The diagram illustrates a computer-readable storage medium 200 according to one embodiment of this application. The computer-readable storage medium 200 stores computer-readable instructions. When executed by a processor, the computer-readable instructions can perform the intelligent floor heating control method according to an embodiment of this application described with reference to the above figures. The computer-readable storage medium 200 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.
[0127] Furthermore, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, this application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the method steps provided in this application. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the method of this application.
[0128] The methods, apparatus, and devices of this application may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the method is for illustrative purposes only, and the steps of the method of this application are not limited to the order specifically described above, unless otherwise specifically stated. Furthermore, in some embodiments, this application may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the method according to this application. Thus, this application also covers recording media storing programs for performing the method according to this application.
[0129] In addition, the parts of the technical solutions provided in the embodiments of this application that are consistent with the implementation principles of the corresponding technical solutions in the prior art have not been described in detail, so as to avoid excessive elaboration.
[0130] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
[0131] The preset parameters or preset thresholds mentioned above are all set by those skilled in the art based on actual conditions or obtained through large-scale data simulation.
[0132] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.
Claims
1. A method for intelligent control of underfloor heating, characterized in that, Includes the following steps: Collect data on underfloor heating usage habits, travel time habits, and convective heat transfer training data; Based on data on underfloor heating usage habits, a Bayesian network model was trained to predict the appropriate temperature for underfloor heating; based on training data on convective heat transfer, a machine learning model was trained to predict the output wind speed of the fan. The underfloor heating control backend monitors in real time whether the user sends a start command. Upon receiving a start command, it calculates the user's return time based on the user's location and return time habit data. The start command includes the user's location and movement speed. Collect real-time environmental data; Based on real-time environmental data, a Bayesian network model is used to obtain the predicted suitable temperature for underfloor heating control. Based on real-time environmental data, user return trip duration, and suitable temperature control, a machine learning model is used to output the predicted control output wind speed of the fan. The underfloor heating control panel sets the temperature of the underfloor heating system to a suitable temperature and the fan speed to a controlled output speed. The data on underfloor heating usage habits includes environmental data each time a user uses underfloor heating and the corresponding suitable temperature for underfloor heating. The environmental data includes the indoor temperature and humidity before the user turns on the underfloor heating, as well as the time period during which the underfloor heating is turned on. The suitable temperature is the stable indoor temperature when the indoor temperature reaches a stable level after each time the underfloor heating is turned on. The return trip time habit data includes the time it takes for a user to travel from entering the residential area to arriving indoors each time. The convective heat transfer training data includes convective heat transfer characteristic data after each turn on the floor heating system and the output wind speed label of the fan. The convective heat transfer characteristic data includes the indoor temperature, indoor humidity and the time period of the floor heating when it is turned on, the time from when the floor heating is turned on until the indoor temperature reaches a stable state, and the suitable temperature when the indoor temperature reaches a stable state. The output wind speed label is the wind speed set for the fan each time the underfloor heating is turned on and the fan equipped with the underfloor heating is started. The method for calculating a user's return trip duration is as follows: Based on the user's location and the location of the residential area, obtain the shortest route for the user to reach the residential area; Divide the distance of the shortest route by the user's movement speed to obtain the first return trip time T1; In the habitual data on return trip duration, the average time from entering a residential area to arriving indoors is marked as the second return trip duration T2; If the return trip duration is denoted as T, then the formula for calculating the return trip duration T is T = T1 + T2.
2. The intelligent control method for underfloor heating according to claim 1, characterized in that, The method for determining the opening time period is as follows: The day from 0:00 to 24:00 is divided into a preset intraday period H. The system divides the system into daily time periods and numbers these time periods in chronological order. The daily period H is a preset positive integer less than 25. The activation time period is the number of the daily time period corresponding to the time when the user turns on the underfloor heating.
3. The intelligent control method for underfloor heating according to claim 2, characterized in that, The condition for determining that the indoor temperature has reached a stable level is: Temperature sensors are placed at N locations indoors; where N is the preset number of temperature sensors, and the location of each temperature sensor is set according to the specific indoor structure and layout. For each temperature sensor, if the user does not control the floor heating or fan to perform any function within a preset stable time threshold before any time, and the difference between the highest and lowest detected temperature values is less than a preset first temperature fluctuation threshold, then the temperature at the location of the temperature sensor is considered to have reached stability, and the average of the highest and lowest detected temperature values is taken as the stable temperature of the sensor. When the temperature at all temperature sensor locations reaches a stable state, if among all sensors, the stable temperature of the sensor is... If the difference between the maximum and minimum temperatures is less than the preset second temperature fluctuation threshold, the indoor temperature is considered to have reached a stable state. The average of the maximum and minimum stable temperatures of the sensor is taken as the stable indoor temperature.
4. The intelligent control method for underfloor heating according to claim 3, characterized in that, The method for training a Bayesian network model to predict the suitable temperature for underfloor heating is as follows: Construct a Bayesian network model; Using environmental data from underfloor heating usage habit data as input to a Bayesian network model, the Bayesian network model outputs the predicted suitable temperature for underfloor heating for each set of environmental data, with the suitable temperature corresponding to the environmental data in the underfloor heating usage habit data as the prediction target, and minimizing the sum of prediction errors for all suitable temperatures for underfloor heating as the training objective; the Bayesian network model is trained until the sum of prediction errors converges, at which point training stops, thus training a Bayesian network model that outputs the predicted suitable temperature for underfloor heating based on environmental data.
5. The intelligent control method for underfloor heating according to claim 4, characterized in that, The method for constructing a Bayesian network model is as follows: Construct a two-layer Bayesian network model, where the first layer contains three nodes and the second layer contains one node; each node in the first layer represents the indoor temperature, indoor humidity, and the time period during which the underfloor heating is turned on; the nodes in the second layer represent the suitable temperature for the underfloor heating. Each node in the first layer has a directed edge pointing to a node in the second layer.
6. The intelligent control method for underfloor heating according to claim 5, characterized in that, The method for training a machine learning model to predict the output wind speed of a wind turbine is as follows: The convective heat transfer feature data in the convective heat transfer training data is used as the input of the machine learning model. The machine learning model takes the predicted wind speed label of each set of convective heat transfer feature data as the output, takes the output wind speed label corresponding to the convective heat transfer feature data in the convective heat transfer training data as the prediction target, and takes minimizing the sum of prediction errors of all output wind speed labels as the training objective. The machine learning model is trained until the sum of prediction errors converges, at which point training stops, thus training a machine learning model that outputs predicted wind speed labels based on convective heat transfer characteristic data.
7. The intelligent control method for underfloor heating according to claim 6, characterized in that, The method for obtaining the predicted suitable temperature for underfloor heating using a Bayesian network model is as follows: Real-time environmental data is used as input to a Bayesian network model to obtain the predicted value of the suitable temperature for underfloor heating from the Bayesian network model output. The controlled suitable temperature is the predicted value of the suitable temperature for underfloor heating.
8. The intelligent control method for underfloor heating according to claim 7, characterized in that, The method of using a machine learning model to output the predicted control output wind speed of the wind turbine is as follows: Real-time environmental data, user return trip time, and controlled suitable temperature are used as a set of convective heat transfer characteristic data. This convective heat transfer characteristic data is input into a machine learning model to obtain the predicted value of the output wind speed label output by the machine learning model; the controlled output wind speed is the predicted value of the output wind speed label.
9. An intelligent control system for underfloor heating, based on the intelligent underfloor heating system described in any one of claims 1-8. The control method is implemented, characterized in that, It includes a historical data collection module, a model training module, and an intelligent control module; the modules are electrically connected to each other. The historical data collection module collects data on underfloor heating usage habits, travel time habits, and convection heat transfer training data. It then sends the underfloor heating usage habit data and convection heat transfer training data to the model training module and the travel time habit data to the intelligent control module. The model training module trains a Bayesian network model to predict the appropriate temperature for underfloor heating based on underfloor heating usage data; and trains a machine learning model to predict the output wind speed of the fan based on convective heat transfer training data. The Bayesian network model and the machine learning model are then sent to the intelligent control module. The intelligent control module uses return trip duration habit data, Bayesian network models, and machine learning models to intelligently control the underfloor heating system. The method for intelligent control of underfloor heating is as follows: The system monitors in real time whether the user sends a start command. Upon receiving the start command, it calculates the user's return time based on the user's location and return time habit data. Collect real-time environmental data; based on the real-time environmental data, use a Bayesian network model to obtain the predicted suitable control temperature for the underfloor heating; based on the real-time environmental data, the user's return trip time, and the suitable control temperature, use a machine learning model to output the predicted control output wind speed of the fan. The underfloor heating control panel sets the temperature of the underfloor heating system to a suitable level and the fan speed to a controlled output speed.
10. An electronic device, characterized in that, include: Processor and memory, wherein: The memory stores computer programs that can be called by the processor; The processor executes the intelligent floor heating control method according to any one of claims 1-8 by calling the computer program stored in the memory.
11. A computer-readable storage medium, characterized in that, It contains erasable and rewritable computer programs; When the computer program is run on a computer device, the computer device performs the intelligent control method for underfloor heating as described in any one of claims 1-8.