Graphene heating temperature control method, device and equipment

Abstract

The application provides a graphene heating temperature control method, device and equipment, and the method comprises the following steps: acquiring real-time environment data; pre-processing the real-time environment data to obtain target environment data; inputting the target environment data into a target feature extraction layer of a temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained according to historical environment data; inputting the first intermediate result into a target feature fusion layer of the temperature curve prediction model for feature fusion to obtain a target temperature control parameter; and independently controlling the temperature of each micro area of a graphene heating system according to the target temperature control parameter. The application can improve the accuracy and comfort of graphene heating temperature control and reduce heating energy consumption.

Description

Technical Field

[0001] This invention relates to the field of temperature control technology, and in particular to a graphene heating temperature control method, device, and equipment. Background Technology

[0002] Graphene heating offers significant advantages, with an electrothermal conversion efficiency of up to 99%. Achieving precise and comfortable temperature control is key to the intelligentization of graphene heating, and currently faces several main challenges: ① Insufficient system precision: Many current temperature control systems adopt a "one-size-fits-all" single-area unified control mode, which cannot make fine adjustments according to differences in room orientation, function, etc., which can easily lead to local overheating or insufficient temperature; they either heat at full power or do not heat at all, and cannot be fine-tuned, which can easily overshoot the temperature and waste electricity.

[0003] ② Uneven temperature distribution and large fluctuations: Common thermostats are usually installed at a certain point on the wall, and the temperature they measure cannot represent the entire room. Moreover, their response is delayed, which can easily lead to a significant temperature difference of 5-6℃ in the room; the temperature fluctuates greatly, and the feeling of being hot or cold generally fluctuates between ±1~2℃, or even more. Graphene heats up and cools down quickly, so the room temperature will fluctuate significantly.

[0004] ③ Low temperature control accuracy: Due to factors such as sensor accuracy and algorithm logic, existing temperature control systems generally cannot accurately stabilize the indoor temperature near the set value, and are prone to overshoot or fluctuations, which not only affect comfort but also waste energy; relays / contaminants are prone to aging and damage, switching on and off dozens or hundreds of times a day, the contacts are prone to burning, abnormal noise, and a significant reduction in lifespan; they cannot maintain a precise constant temperature and are not suitable for scenarios that require a stable temperature, such as bedrooms, elderly rooms, and children's rooms.

[0005] ④ Insufficient response speed: Although the graphene heating element itself heats up extremely quickly (thermal response time can be less than 3 seconds), the heat transfer to the indoor space is affected by factors such as the floor structure and furniture arrangement. If the room is spacious, the heat can easily directly heat the walls, resulting in slower heating. At the same time, local malfunctions may also lead to insufficient overall power, affecting the heating speed. Summary of the Invention

[0006] The technical problem to be solved by this invention is to provide a method, apparatus, and equipment for controlling temperature in graphene heating. This can improve the accuracy and comfort of temperature control in graphene heating, and reduce heating energy consumption.

[0007] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows: A graphene heating temperature control method includes: Obtain real-time environmental data; The real-time environmental data is preprocessed to obtain the target environmental data; The target environmental data is input into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained based on historical environmental data. The first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain the target temperature control parameters. The temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters.

[0008] Optionally, the training process of the temperature curve prediction model includes: Obtain historical environmental data; The historical environmental data is input into the initial feature extraction layer of the initial neural network model for feature extraction to obtain the first training result; The first training result is input into the initial feature fusion layer of the initial neural network model for feature fusion to obtain the second training result; Based on the second training results, the parameters of the initial neural network model are optimized using a loss function to obtain a temperature curve prediction model.

[0009] Optionally, the loss function expression is:

[0010] Where L represents the loss value, This represents the i-th predicted energy consumption value. This represents the actual energy consumption value of the i-th element. This represents the predicted value of the i-th vertical temperature difference. This represents the actual value of the i-th vertical temperature difference. This represents the comfort weighting coefficient, and batch represents the batch size.

[0011] Optionally, the target environmental data is input into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result, including: The target feature extraction layer of the temperature curve prediction model is obtained through Feature extraction is performed to obtain the first intermediate result, where This indicates the first intermediate result. This represents the connection weight between the j-th data point and the k-th node. This represents the j-th input value. This represents the bias term of the k-th node in the target feature extraction layer.

[0012] Optionally, the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain the target temperature control parameters, including: The target feature fusion layer of the temperature curve prediction model is through Feature fusion is performed to obtain the target temperature control parameters, where... This indicates the target temperature control parameter. This represents the connection weight between the l-th node of the target feature extraction layer and the n-th node of the target feature fusion layer. This indicates the first intermediate result. This represents the bias term of the nth node in the target feature fusion layer.

[0013] Optionally, the temperature of each micro-zone of the graphene heating system can be independently controlled according to the target temperature control parameters, including: The target temperature control parameters are matched with each micro-zone to obtain the first temperature control strategy; Based on peak and off-peak electricity prices, the power of the first temperature control strategy is adjusted to obtain the second temperature control strategy; Based on the vertical temperature difference monitoring results, the second temperature control strategy is adjusted to obtain the target temperature control strategy.

[0014] Optionally, the vertical temperature difference is achieved through... Received, among which Indicates vertical temperature difference. Indicates ground temperature. This represents the preset altitude air temperature, k represents the wind speed correction factor, and v represents the indoor wind speed.

[0015] Embodiments of the present invention also provide a graphene heating temperature control device, comprising: The acquisition module is used to acquire real-time environmental data; The processing module is used to input the target environmental data into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained based on historical environmental data; the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain target temperature control parameters; and the temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters.

[0016] Embodiments of the present invention also provide a computing device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the graphene heating temperature control method of the present invention.

[0017] Embodiments of the present invention also provide a computer-readable storage medium storing a program that, when executed by a processor, implements the graphene heating temperature control method of the present invention.

[0018] The above-described technical solution of the present invention has at least the following technical effects: The graphene heating temperature control method of the present invention involves: acquiring real-time environmental data; preprocessing the real-time environmental data to obtain target environmental data; inputting the target environmental data into the target feature extraction layer of a temperature curve prediction model for feature extraction to obtain a first intermediate result; training the temperature curve prediction model based on historical environmental data; inputting the first intermediate result into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain target temperature control parameters; and independently controlling the temperature of each micro-zone of the graphene heating system according to the target temperature control parameters. This improves the accuracy and comfort of graphene heating temperature control while reducing heating energy consumption. Attached Figure Description

[0019] Figure 1 This is a schematic flowchart of the graphene heating temperature control method of the present invention. Figure 2 This is a schematic diagram of the graphene heating temperature control device of the present invention. Detailed Implementation

[0020] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0021] like Figure 1 As shown, an embodiment of the present invention proposes a graphene heating temperature control method, comprising: Step S1: Obtain real-time environmental data; Step S2: Preprocess the real-time environmental data to obtain the target environmental data; Step S3: Input the target environmental data into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain the first intermediate result; the temperature curve prediction model is trained based on historical environmental data. Step S4: Input the first intermediate result into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain the target temperature control parameters. Step S5: Perform independent temperature control on each micro-zone of the graphene heating system according to the target temperature control parameters.

[0022] In this embodiment, as Figure 1As shown, in the graphene heating temperature control method, firstly, real-time environmental data is acquired; each graphene heating film is divided into 3-8 independent micro-zones, the specific number of which can be flexibly adjusted according to the heating area and furniture placement, prioritizing areas where furniture is fixedly placed; each micro-zone is equipped with an independent drive circuit and established with an electrical connection to the main control module; simultaneously, an overheat protection sensor is connected in series in the heating film circuit, and surge and short-circuit protection is implemented at the power input and output terminals. This achieves the physical basis of "single film, multiple zones," breaking the limitations of traditional heating films that heat the entire surface, and providing hardware support for subsequent independent temperature control of different zones and energy saving in areas covered by furniture; the overheat protection sensor and circuit protection design can effectively avoid faults such as local overheating and short circuits of the heating film, improving system operational safety and eliminating the risk of smoldering.

[0023] For ground temperature sensor deployment, a thermistor probe array is evenly arranged on the surface of the graphene electrothermal film at 50-80cm intervals, with at least one ground probe corresponding to each micro-area. This ensures the probes are in close contact with the electrothermal film and avoids obstruction. For air temperature sensor deployment, air temperature probes are placed at 1.2m (human height) within the heating area, according to the range of human activity. At least one air probe is placed in each independent heating area. For probe calibration, all temperature probes are connected to the temperature acquisition module, and the probe error is calibrated using standard temperature measurement equipment to ensure measurement accuracy ≤ ±0.5℃. Simultaneously, a probe abnormality threshold is set; if there is no signal or the measured value exceeds the range of -10℃ to 50℃, it is considered a fault.

[0024] By constructing a dual-dimensional temperature sensing matrix of ground and air, the problem of inaccurate temperature measurement and inability to reflect temperature differences within a region by traditional single probes is solved; the ground probe array with a spacing of 50-80cm can accurately capture the actual heating temperature of each micro-area, and the air probe at a height of 1.2m can truly reflect the comfortable temperature around the human body; probe calibration ensures the accuracy of temperature measurement data and provides a reliable basis for subsequent temperature control logic.

[0025] Indoor temperature and humidity are collected using indoor sensors; outdoor temperature, humidity and light intensity are obtained using local weather forecasts, with environmental data collected once per hour. Then, by preprocessing the real-time environmental data, target environmental data is obtained; the target environmental data is input into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained based on historical environmental data; the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain target temperature control parameters; and the temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters.

[0026] This invention employs a zoned micro-control, a temperature sensing matrix (multi-probe collaboration), and an intelligent networked temperature control solution to achieve local and remote intelligent temperature control via WiFi / Bluetooth. Users can implement time-sharing control, pre-setting a 7×24-hour temperature curve, such as maintaining 16℃ during the day for energy saving, raising the temperature to 22℃ in the evening, and maintaining 18℃ at night to promote sleep, while adjusting real-time power based on peak and off-peak electricity prices. Utilizing zoned micro-control technology, single-film multi-zone control is achieved, dividing one film into 3-8 independent micro-zones. Each micro-zone can independently adjust its power; areas covered by furniture automatically reduce power to prevent smoldering, while exposed areas maintain normal heating. A multi-point temperature sensing array (ground + air dual sensing) is used, with a thermistor probe array on the ground and air temperature measured at human height (1.2m), controlling the vertical temperature difference to <2℃. Simultaneously, multi-probe feedback enables real-time temperature, power, energy consumption, and fault alarm functions. This reduces ineffective heating, lowers heating energy consumption, and improves environmental comfort.

[0027] In an optional embodiment of the present invention, step S2 involves preprocessing the real-time environmental data to obtain target environmental data, including: Step S21: Perform data cleaning on the real-time environmental data to obtain the first intermediate data; Step S22: Standardize the first intermediate data to obtain the target environment data.

[0028] In this embodiment, the real-time environmental data is first cleaned to obtain the first intermediate data; data that exceeds the reasonable range in the real-time environmental data is removed to obtain the first intermediate data; for example, abnormal temperature and energy consumption data caused by sensor failure. Then, the first intermediate data is standardized to obtain the target environment data; all collected data are standardized to the [0,1] interval, and the standardization formula is: ,in The data is standardized, and x represents the original data. The minimum value of the data in this dimension. This is the maximum value of the data in this dimension, to avoid the impact of differences in the amount of data in different dimensions on the accuracy of the algorithm.

[0029] In an optional embodiment of the present invention, step S3, the training process of the temperature curve prediction model, includes: Step S301: Obtain historical environmental data; Step S302: Input the historical environmental data into the initial feature extraction layer of the initial neural network model to extract features and obtain the first training result; Step S303: Input the first training result into the initial feature fusion layer of the initial neural network model to perform feature fusion and obtain the second training result; Step S304: Based on the second training results, the parameters of the initial neural network model are optimized using a loss function to obtain a temperature curve prediction model.

[0030] In this embodiment, historical environmental data is first acquired; indoor and outdoor temperature and humidity data are collected; and user temperature control operation data for more than 15 days is collected. The data collection dimensions include: the time point of manual temperature adjustment, the temperature before adjustment, the temperature after adjustment, the micro-zone number of the adjustment, the duration of adjustment, and the operation frequency. The input data includes standardized data in 8 dimensions, all of which are continuous variables, specifically: outdoor temperature (x1), indoor humidity (x2), outdoor humidity (x3), light intensity (x4), user adjustment time (x5), adjusted temperature (x6), micro-area number (x7), and energy consumption for the current period (x8). The preprocessed historical environmental data was divided into training, validation, and test sets in a ratio of 7:2:1: The training set (70%) was used for iterative updates of model parameters and fitting the mapping relationship between input and output; the validation set (20%) was used to verify the generalization ability of the model, adjust the model hyperparameters, and avoid overfitting; and the test set (10%) was used to finally test the optimization accuracy of the model and evaluate the model performance.

[0031] Initialize model parameters. Randomly initialize all connection weights and biases, with initial weight values ​​ranging from -0.5 to 0.5 and initial bias values ​​ranging from -0.1 to 0.1. Simultaneously set training hyperparameters: learning rate α = 0.01, controlling the parameter update step size to avoid non-convergence due to excessively large step sizes or slow training due to excessively small step sizes; iteration count epochs = 1000, the maximum number of training iterations, to avoid undertraining or overtraining; batch size batch_size = 32, selecting 32 sets of data for parameter updates each training iteration to balance training speed and accuracy; early stopping threshold patience = 50, stopping training if the validation set error does not decrease for 50 consecutive iterations to avoid overfitting.

[0032] The historical environmental data is input into the initial feature extraction layer of the initial neural network model for feature extraction to obtain the first training result; the initial feature extraction layer of the initial neural network model includes a first activation function, which is used to fit the nonlinear relationship between the input data and the first training result; The first training result is input into the initial feature fusion layer of the initial neural network model for feature fusion to obtain the second training result; the initial feature fusion layer of the initial neural network model includes a second activation function, which is used to fit the nonlinear relationship between the first training result and the second training result; The input data in the training set is fed into the initial neural network model, which then passes through the initial feature extraction layer and the initial feature fusion layer in sequence. The output values ​​of each layer are calculated, and finally the second training result predicted by the model is obtained. Using the loss function, the second training result is compared with the measured parameters, and backpropagation and parameter optimization are performed on the initial neural network model based on the comparison results. The partial derivatives of the loss function with respect to the parameters (weights, bias terms) of each layer are calculated, and the parameters are updated according to the direction of the partial derivatives. The loss function is minimized. The smaller the value of the loss function, the closer the model prediction result is to the actual situation, and the better the performance of the initial neural network model. Finally, the temperature curve prediction model is obtained.

[0033] In an optional embodiment of the present invention, in step S304, the loss function expression is:

[0034] Where L represents the loss value, This represents the i-th predicted energy consumption value. This represents the actual energy consumption value of the i-th element. This represents the predicted value of the i-th vertical temperature difference. This represents the actual value of the i-th vertical temperature difference. This represents the comfort weighting coefficient, and batch represents the batch size.

[0035] In this embodiment, a bi-objective loss function is adopted to balance energy consumption and comfort; the i-th energy consumption prediction value Derived from power and temperature; comfort weighting coefficient The preferred value is 0.8.

[0036] In an optional embodiment of the present invention, step S3 involves inputting the target environmental data into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result, including: Step S31, the target feature extraction layer of the temperature curve prediction model is obtained through... Feature extraction is performed to obtain the first intermediate result, where This indicates the first intermediate result. This represents the connection weight between the j-th data point and the k-th node. This represents the j-th input value. This represents the bias term of the k-th node in the target feature extraction layer.

[0037] In this embodiment, the input value of the k-th node of the target feature extraction layer of the temperature curve prediction model is the weighted sum of all data input nodes and their corresponding weights, plus a bias term, i.e. Based on this, the first intermediate result is obtained through processing.

[0038] In an optional embodiment of the present invention, in step S4, the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain target temperature control parameters, including: Step S41, the target feature fusion layer of the temperature curve prediction model is fused through... Feature fusion is performed to obtain the target temperature control parameters, where... This indicates the target temperature control parameter. This represents the connection weight between the l-th node of the target feature extraction layer and the n-th node of the target feature fusion layer. This indicates the first intermediate result. This represents the bias term of the nth node in the target feature fusion layer.

[0039] In this embodiment, the input value of the nth node of the target feature fusion layer is the weighted sum of the output values ​​of all nodes in the target feature extraction layer and their corresponding weights, plus a bias term, i.e. Based on this, the target temperature control parameters are obtained through processing.

[0040] In an optional embodiment of the present invention, step S5, which involves independently controlling the temperature of each micro-zone of the graphene heating system according to the target temperature control parameters, includes: Step S51: Match the target temperature control parameters with each micro-zone to obtain the first temperature control strategy; Step S52: Adjust the power of the first temperature control strategy according to the peak-valley electricity price to obtain the second temperature control strategy; Step S53: Based on the vertical temperature difference monitoring results, adjust the second temperature control strategy to obtain the target temperature control strategy.

[0041] In this embodiment, target temperature control parameters are matched according to each indoor zone and time period. The model outputs the corresponding target temperature and target power for each zone and each time period (with 1 hour as the smallest unit). The system organizes them according to the zone number and time period to generate an independent 7×24-hour first temperature control strategy for each zone. Example: Zone 1 (Living Room), 18:00-19:00 = 22℃ = 0.8kW; Zone 2 (Bedroom), 22:00-7:00 the next day, = 18℃ = 0.3kW; Combining peak-valley electricity pricing with secondary optimization, the predicted... By linking with local peak and off-peak electricity pricing periods, the power output is further adjusted to obtain a second temperature control strategy. Off-peak hours (low electricity prices): If <0.8kW, can be increased to 0.8-1.0kW, shortening heating time and storing heat; Peak hours (high electricity prices): If >0.5kW, can be reduced to 0.3-0.5kW (non-essential areas), ensuring the temperature does not fall below the baseline value; Temperature control strategies for all zones ( , The rules for adjusting peak and valley times are integrated into a set of executable instructions and synchronized to the cloud platform database and main control module. The discrete model predictions are transformed into a practical and refined time-sharing and zone-based temperature control strategy, enabling personalized intelligent temperature control for each user. This achieves on-demand temperature control and peak-shifting energy saving, avoiding ineffective energy consumption caused by constant temperature throughout the day. A base temperature of 16℃ during the day reduces ineffective heating, a comfortable evening temperature of 22℃ meets activity needs, and a nighttime temperature of 18℃ balances sleep comfort and energy saving. Peak-valley electricity pricing combined with a heat storage strategy has been tested to reduce peak energy consumption by 15%-20% and overall heating energy consumption by 10%-15%. The smooth temperature curve transition design avoids discomfort caused by sudden temperature changes, improving the user experience. Differentiated templates adapt to the needs of different groups, reducing the difficulty of user operation. The preset strategy, manual adjustment, and subsequent self-optimization modes balance convenience, flexibility, and intelligence.

[0042] In an optional embodiment of the present invention, in step S53, the vertical temperature difference is achieved through... Received, among which Indicates vertical temperature difference. Indicates ground temperature. This represents the preset altitude air temperature, k represents the wind speed correction factor, and v represents the indoor wind speed.

[0043] In this embodiment, the vertical temperature difference is monitored in real time using data collected by sensors. If ΔT ≥ 2℃, the floor heating power of that zone is reduced by 10% of the rated power per minute. Simultaneously, if a fresh air system is used, the system's wind speed is increased by 0.2 m / s to accelerate air circulation and shorten the temperature difference adjustment time. If no fresh air system is used, the floor heating power is continuously reduced until ΔT < 2℃. If 1℃ ≤ ΔT < 2℃, the current floor heating power is maintained, and temperature difference changes are continuously monitored. If ΔT < 1℃, the floor heating power is appropriately increased by 5% of the rated power per minute to ensure the vertical temperature difference is controlled within a comfortable range of 1-2℃. The wind speed correction coefficient k is calibrated every 30 minutes, combined with real-time data... , The data adjusts the k-value to ensure the accuracy of temperature difference calculation; when the outdoor temperature is ≤-10℃, the upper limit of vertical temperature difference control is automatically adjusted to 2.5℃, and the power of the ground foundation is increased to avoid the ground temperature being too low due to the low outdoor temperature, which would affect comfort.

[0044] This embodiment addresses the vertical temperature difference issue in traditional heating systems, where the floor is hot while the head is cold, thus improving environmental comfort. Through collaborative data acquisition using a temperature sensing matrix and precise algorithm correction, the accuracy of the vertical temperature difference between the floor and head is improved to ±0.2℃, stably maintaining it within the comfortable range of 1-2℃, increasing user satisfaction by over 30%. Integration with a fresh air system further shortens temperature adjustment time and improves efficiency. An extreme environment adaptability design ensures a comfortable temperature difference is maintained under varying outdoor temperatures. Simultaneously, it avoids energy waste caused by excessively high floor temperatures, balancing comfort and energy conservation. Testing shows that it can further reduce energy consumption by 3%-5%.

[0045] like Figure 2 As shown, an embodiment of the present invention also provides a graphene heating temperature control device 20, comprising: Module 21 is used to acquire real-time environmental data; Processing module 22 is used to input the target environmental data into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained based on historical environmental data; the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain target temperature control parameters; and the temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters.

[0046] Optionally, the training process of the temperature curve prediction model includes: Obtain historical environmental data; The historical environmental data is input into the initial feature extraction layer of the initial neural network model for feature extraction to obtain the first training result; The first training result is input into the initial feature fusion layer of the initial neural network model for feature fusion to obtain the second training result; Based on the second training results, the parameters of the initial neural network model are optimized using a loss function to obtain a temperature curve prediction model.

[0047] Optionally, the loss function expression is:

[0048] Where L represents the loss value, This represents the i-th predicted energy consumption value. This represents the actual energy consumption value of the i-th element. This represents the predicted value of the i-th vertical temperature difference. This represents the actual value of the i-th vertical temperature difference. This represents the comfort weighting coefficient, and batch represents the batch size.

[0049] Optionally, the target environmental data is input into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result, including: The target feature extraction layer of the temperature curve prediction model is obtained through Feature extraction is performed to obtain the first intermediate result, where This indicates the first intermediate result. This represents the connection weight between the j-th data point and the k-th node. This represents the j-th input value. This represents the bias term of the k-th node in the target feature extraction layer.

[0050] Optionally, the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain the target temperature control parameters, including: The target feature fusion layer of the temperature curve prediction model is through Feature fusion is performed to obtain the target temperature control parameters, where... This indicates the target temperature control parameter. This represents the connection weight between the l-th node of the target feature extraction layer and the n-th node of the target feature fusion layer. This indicates the first intermediate result. This represents the bias term of the nth node in the target feature fusion layer.

[0051] Optionally, the temperature of each micro-zone of the graphene heating system can be independently controlled according to the target temperature control parameters, including: The target temperature control parameters are matched with each micro-zone to obtain the first temperature control strategy; Based on peak and off-peak electricity prices, the power of the first temperature control strategy is adjusted to obtain the second temperature control strategy; Based on the vertical temperature difference monitoring results, the second temperature control strategy is adjusted to obtain the target temperature control strategy.

[0052] Optionally, the vertical temperature difference is achieved through... Received, among which Indicates vertical temperature difference. Indicates ground temperature. This represents the preset altitude air temperature, k represents the wind speed correction factor, and v represents the indoor wind speed.

[0053] It should be noted that all implementation methods in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0054] Embodiments of the present invention also provide a computing device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the graphene heating temperature control method of the present invention. All implementations in the above method embodiments are applicable to the embodiments of this computing device and can achieve the same technical effects.

[0055] Embodiments of the present invention also provide a computer-readable storage medium storing a program that, when executed by a processor, implements the graphene heating temperature control method described in this invention. All implementations in the above method embodiments are applicable to embodiments of this computing device and can achieve the same technical effects.

[0056] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0057] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0058] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0059] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0060] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0061] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0062] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0063] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code for implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps for performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0064] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A graphene heating temperature control method, characterized in that, include: Obtain real-time environmental data; The real-time environmental data is preprocessed to obtain the target environmental data; The target environmental data is input into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained based on historical environmental data. The first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain the target temperature control parameters. The temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters.

2. The graphene heating temperature control method according to claim 1, characterized in that, The training process of the temperature curve prediction model includes: Obtain historical environmental data; The historical environmental data is input into the initial feature extraction layer of the initial neural network model for feature extraction to obtain the first training result; The first training result is input into the initial feature fusion layer of the initial neural network model for feature fusion to obtain the second training result; Based on the second training results, the parameters of the initial neural network model are optimized using a loss function to obtain a temperature curve prediction model.

3. The graphene heating temperature control method according to claim 2, characterized in that, The loss function expression is as follows: Where L represents the loss value, This represents the i-th predicted energy consumption value. This represents the actual energy consumption value of the i-th element. This represents the predicted value of the i-th vertical temperature difference. This represents the actual value of the i-th vertical temperature difference. This represents the comfort weighting coefficient, and batch represents the batch size.

4. The graphene heating temperature control method according to claim 1, characterized in that, The target environmental data is input into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result, including: The target feature extraction layer of the temperature curve prediction model is obtained through Feature extraction is performed to obtain the first intermediate result, where This indicates the first intermediate result. This represents the connection weight between the j-th data point and the k-th node. This represents the j-th input value. This represents the bias term of the k-th node in the target feature extraction layer.

5. The graphene heating temperature control method according to claim 1, characterized in that, The first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain the target temperature control parameters, including: The target feature fusion layer of the temperature curve prediction model is through Feature fusion is performed to obtain the target temperature control parameters, where... This indicates the target temperature control parameter. This represents the connection weight between the l-th node of the target feature extraction layer and the n-th node of the target feature fusion layer. This indicates the first intermediate result. This represents the bias term of the nth node in the target feature fusion layer.

6. The graphene heating temperature control method according to claim 1, characterized in that, The temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters, including: The target temperature control parameters are matched with each micro-zone to obtain the first temperature control strategy; Based on peak and off-peak electricity prices, the power of the first temperature control strategy is adjusted to obtain the second temperature control strategy; Based on the vertical temperature difference monitoring results, the second temperature control strategy is adjusted to obtain the target temperature control strategy.

7. The graphene heating temperature control method according to claim 6, characterized in that, The vertical temperature difference is through Received, among which Indicates vertical temperature difference. Indicates ground temperature. This represents the preset altitude air temperature, k represents the wind speed correction factor, and v represents the indoor wind speed.

8. A graphene heating temperature control device, characterized in that, include: The acquisition module is used to acquire real-time environmental data; The processing module is used to input the target environmental data into the target feature extraction layer of the temperature curve prediction model for feature extraction to obtain a first intermediate result; the temperature curve prediction model is trained based on historical environmental data; the first intermediate result is input into the target feature fusion layer of the temperature curve prediction model for feature fusion to obtain target temperature control parameters; and the temperature of each micro-zone of the graphene heating system is independently controlled according to the target temperature control parameters.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images