Low-energy-consumption heat supply method and system based on vacuum flat plate collector

Abstract

The invention provides a low-energy-consumption heat supply method and system based on a vacuum flat plate collector, and relates to the technical field of intelligent heat supply. Heat supply environment parameters and indoor temperature are collected in a fixed point mode through a preset monitoring array, the preset monitoring array is deployed in a heat supply circulation network, and a heat demand prediction model is constructed based on the integrated learning principle; and the heat supply environment parameters and the indoor temperature are input into the heat demand prediction model, demand prediction in a future window is carried out, the predicted heat demand is obtained, heat supply parameter optimization analysis is carried out with the purpose of meeting the predicted heat demand, and optimal heat supply parameters are determined to carry out self-adaptive control on a heat collector in the future window. The technical problems of insufficient heat supply and energy waste caused by lack of effective analysis of heat collection equipment in a low-temperature environment in the prior art are solved. The technical effects that the heat supply efficiency is improved, the energy consumption is reduced, the heat supply stability is improved, and efficient heat supply management under the cold climate condition is achieved are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent heating technology, and in particular to a low-energy heating method and system based on a vacuum flat-plate collector. Background Art

[0002] In current heating technology, especially in cold regions, the application of thermal collectors faces severe challenges. Although the existing technology system has developed a variety of thermal collector technologies, there is a general lack of in-depth analysis and optimization strategies for the performance changes of thermal collectors under low temperature conditions. This lack of technology directly leads to a significant decrease in the thermal energy capture efficiency of thermal collectors at extremely low temperatures, which cannot meet the expected heating demand, and thus causes the problem of insufficient heating. At the same time, since the system cannot be accurately controlled, it often causes excessive consumption and waste of energy, increasing operating costs.

[0003] The existing technology lacks effective analysis of thermal collection equipment in low-temperature environments, which leads to technical problems such as insufficient heating and energy waste. Summary of the invention

[0004] The present application provides a low-energy heating method and system based on a vacuum flat-plate collector, which is used to solve the technical problem in the prior art of lacking effective analysis of thermal collection equipment in low-temperature environments, resulting in insufficient heating and energy waste.

[0005] In view of the above problems, the present application provides a low-energy heating method and system based on a vacuum flat-plate collector.

[0006] The first aspect of the present application provides a low-energy heating method based on a vacuum flat-plate collector, the method comprising: collecting heating environment parameters and indoor temperature at fixed points through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in a heating cycle network; constructing a heat demand prediction model based on the principle of integrated learning; inputting the heating environment parameters and indoor temperature into the heat demand prediction model, performing demand prediction within a future window, and obtaining predicted heat demand; for the purpose of meeting the predicted heat demand, performing heating parameter optimization analysis, and determining the optimal heating parameters to perform adaptive control of the collector within the future window.

[0007] The second aspect of the present application provides a low-energy heating system based on a vacuum flat-plate collector, the system comprising: a data acquisition module, the data acquisition module is used to collect heating environment parameters and indoor temperature at a fixed point through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in a heating cycle network; a model construction module, the model construction module is used to construct a heat demand prediction model based on the principle of ensemble learning; a heat demand prediction module, the heat demand prediction module is used to input the heating environment parameters and indoor temperature into the heat demand prediction model, perform demand prediction within a future window, and obtain predicted heat demand; a data optimization analysis module, the data optimization analysis module is used to perform heating parameter optimization analysis for the purpose of meeting the predicted heat demand, and determine the optimal heating parameters to perform adaptive control of the collector within the future window.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method provided in the embodiment of the present application collects heating environment parameters and indoor temperature at fixed points through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in a heating cycle network; a heat demand prediction model is constructed based on the principle of integrated learning; the heating environment parameters and indoor temperature are input into the heat demand prediction model to predict the demand in the future window and obtain the predicted heat demand; in order to meet the predicted heat demand, the heating parameter optimization analysis is performed to determine the optimal heating parameters to perform adaptive control on the collector in the future window. The technical effect of improving heating efficiency, reducing energy consumption, improving heating stability, and realizing efficient heating management under cold climate conditions is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a low-energy heating method based on a vacuum flat-plate collector provided in this application;

[0012] Figure 2 A schematic structural diagram of a low-energy heating system based on a vacuum flat-plate collector provided in this application.

[0013] Explanation of the reference numerals: data collection module 11 , model building module 12 , heat demand prediction module 13 , data optimization and analysis module 14 . DETAILED DESCRIPTION

[0014] This application provides a low-energy heating method and system based on a vacuum flat plate collector, which is used to solve the technical problem that the existing technology lacks effective analysis of heat collection equipment in low-temperature environments, resulting in insufficient heating and energy waste. It achieves the technical effect of improving heating efficiency, reducing energy consumption, and improving heating stability, and realizing efficient heating management in cold climate conditions.

[0015] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a low-energy heating method based on a vacuum flat plate collector, the method comprising:

[0017] The heating environment parameters and indoor temperature are collected at fixed points through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in the heating circulation network.

[0018] Specifically, the scheduled monitoring array is composed of a variety of sensors, such as temperature sensors, humidity sensors, radiation sensors, etc., which can monitor key environmental parameters such as ambient temperature, humidity, and light intensity in real time. According to the heat flow path and the location of the vacuum flat-plate collector, combined with expert experience, the scheduled monitoring array is deployed at key locations of the heating circulation network, such as the collector inlet, outlet, different indoor areas, and along the heating pipeline. By laying out at key locations, changes in key environmental parameters can be accurately and in real time. Then, the deployed scheduled monitoring array uses a fixed-point collection method to collect heating environmental parameters and indoor temperature in real time to ensure the accuracy and real-time nature of the data. Through the collaborative work of sensors, it can achieve comprehensive and accurate monitoring of heating environmental parameters and indoor temperature, and provide comprehensive environmental data to support heat demand forecasting and heating management.

[0019] Furthermore, the heating environment parameters include outdoor temperature, solar radiation intensity and collector heat medium temperature.

[0020] Specifically, the heating environment parameters refer to the state of the external heating environment, including outdoor temperature, solar radiation intensity and collector heat medium temperature. Outdoor temperature is one of the important factors affecting the efficiency and heat demand of heat pumps. Usually in winter, the outdoor temperature is low, which will affect the heating capacity of the heater. The temperature changes of the external environment are monitored in real time through temperature sensors. For vacuum flat plate collectors that rely on solar energy, the intensity of solar radiation is a key factor that directly affects its heat collection efficiency. Using the radiation sensors in the predetermined monitoring array, the intensity changes of solar radiation are sensed and recorded in real time, providing an important basis for the optimized operation of the collector. For example, when the solar radiation is strong, the collector can increase the power to fully absorb solar energy; when the radiation is weak, the power can be appropriately reduced or other energy-saving measures can be taken. The collector heat medium temperature is an important indicator reflecting the working state and heating efficiency of the collector. By monitoring the temperature sensors in the array, the temperature data of the heat medium inside the collector can be obtained in real time, and then the working state and thermal energy conversion efficiency of the collector can be evaluated.

[0021] A heat demand prediction model is constructed based on the principle of ensemble learning.

[0022] Specifically, first collect historical data related to heat demand, including historical outdoor temperature, historical solar radiation intensity, historical collector heat medium temperature, historical indoor temperature, and historical heat demand data. Clean, denoise, normalize or standardize the collected data. Then select an ensemble learning algorithm, which combines the prediction results of multiple models to improve the overall prediction accuracy, such as random forest, gradient boosting tree or support vector machine. Use the preprocessed data to train the model and build a heat demand prediction model. Based on the real-time collected environmental parameters, use the constructed heat demand prediction module to predict heat demand, provide decision support for the regulation of vacuum flat plate collectors, and improve the intelligent management and operation efficiency of vacuum flat plate collectors.

[0023] Furthermore, a heat demand prediction model is constructed, including: taking the attribute parameters of the collector as similarity retrieval features, performing positive sample retrieval, and obtaining a sample data set, wherein the sample data includes sample outdoor temperature, sample radiation intensity, sample heat medium temperature, sample indoor temperature, and sample heat demand; and performing supervised training on the heat demand prediction model based on the sample data set to obtain a heat demand prediction model that meets the expected convergence conditions.

[0024] Specifically, the attribute parameters of the collector, such as model, specification, efficiency, etc., are first determined, and the attribute parameters of the collector are used as features for similar retrieval. Using these features, sample data similar to the current collector attribute parameters are retrieved from the historical data set through similarity measurement methods, such as Euclidean distance or cosine similarity. These sample data include sample outdoor temperature, sample radiation intensity, sample heat medium temperature, sample indoor temperature and sample heat demand. Then, the retrieved sample data are sorted to obtain a sample data set, which includes multiple sample records, each of which includes outdoor temperature, radiation intensity, heat medium temperature, indoor temperature and corresponding heat demand. Then, the collected sample data are cleaned, missing values ​​and outliers are processed, noise is eliminated by data smoothing technology, and standardized. The preprocessed sample data set is used to supervise the training of the heat demand prediction model. The heat demand prediction model gradually adjusts the internal parameters to optimize the prediction accuracy by learning the mapping relationship between the input features and the target heat demand. Finally, a heat demand prediction model that meets the expected convergence conditions is obtained. By building a heat demand prediction model, we can accurately predict future heat demand, and then flexibly adjust heating parameters to ensure stable heating even under extreme weather conditions while reducing energy waste.

[0025] Furthermore, supervised training is performed on the heat demand prediction model based on the sample data set, including: dividing the sample data set into ten equal parts, and selecting ten times with replacement to obtain a first data set, and iteratively selecting ten times to obtain ten data sets; randomly selecting five of the ten data sets as a first training set, and the remaining five as a second training set; configuring a prediction operator, wherein the prediction operator includes at least a time series analysis operator and a BP neural network; constructing a first prediction unit and a second prediction unit based on the time series analysis operator and the BP neural network, respectively; using the first training set and the second training set to train the first prediction unit and the second prediction unit, respectively, to obtain a first prediction unit and a second prediction unit that meet the convergence requirements, as well as a first convergence degree and a second convergence degree; based on the principle of ensemble learning, the heat demand prediction model is constructed according to the first prediction unit, the second prediction unit, the first convergence degree, and the second convergence degree.

[0026] Specifically, the sample data set is first divided into ten equal parts, each of which contains a subset of the original data set, and these subsets do not overlap. Then, ten random selections are made from the ten parts with replacement, and a data set is obtained each time, thereby obtaining ten data sets. Then, five data sets are randomly selected from the ten data sets as the first training set, and the remaining five data sets are used as the first training set to ensure the diversity of each training set. A prediction operator is configured, and the prediction operator is an algorithm or model for prediction, which includes at least a time series analysis operator and a BP neural network. The time series analysis operator is used to capture the time series features in the data, such as ARIMA, LSTM, etc. The BP neural network is trained by the back propagation algorithm and is responsible for learning the nonlinear relationship between input and heat demand. A first prediction unit is constructed based on the time series analysis operator, and the first prediction unit is used to process and analyze time series data, extract key features and predict heat demand. A second prediction unit is constructed based on the BP neural network, which is used to learn the nonlinear relationship between input and heat demand and make predictions based on these relationships. After constructing the first prediction unit and the second prediction unit, the first prediction unit is trained using the first training set until a preset convergence condition is reached, such as a loss function value less than a preset threshold, and the convergence degree is recorded. The convergence degree is the change in the loss function value during the training process, and the first prediction unit and the first convergence degree that meet the convergence are obtained. Similarly, the second prediction unit is trained using the second training set until the preset convergence condition is reached, and the second prediction unit and the second convergence degree that meet the convergence are obtained. Finally, based on the first prediction unit, the second prediction unit, the first convergence degree and the second convergence degree, an integrated learning method, such as weighted average, voting or other strategies, is used to build the final heat demand prediction module, which integrates the prediction results of different units, can effectively capture complex heat demand dynamics, and improve the accuracy and stability of the prediction.

[0027] Furthermore, building the heat demand prediction model includes: performing a credibility analysis based on the first convergence degree and the second convergence degree, and configuring a first credibility weight and a second credibility weight; integrating the first credibility weight and the second credibility weight with the first prediction unit and the second prediction unit to obtain the heat demand prediction model.

[0028] Specifically, the first convergence degree and the second convergence degree are indicators for measuring the stable prediction ability and convergence of the first prediction unit and the second prediction unit during the training process. Based on the first convergence degree and the second convergence degree, the credibility analysis is performed. The credibility is used to reflect the reliability or confidence level of the prediction unit in the current task. The higher the convergence degree, the more stable the prediction unit is during the training process, the higher the credibility of its prediction results, and the more reliable the performance of the model. For example, according to the specific value of the convergence degree, a conversion function, such as a linear function, is set to calculate the credibility score of each prediction unit, and the credibility score is normalized so that the sum of the credibility scores of the first prediction unit and the second prediction unit is 1. Based on the credibility score, the first convergence degree and the second convergence degree are assigned corresponding weights in proportion to obtain the first credibility weight and the second credibility weight. Finally, the first credibility weight and the second credibility weight are fused with the first prediction unit and the second prediction unit by weighted average, weighted voting or other ensemble learning methods to obtain the final heat demand prediction result. Through the convergence and credibility analysis based on different prediction units, multiple prediction units are effectively integrated and fused to obtain a more accurate and reliable heat demand prediction model, thereby improving the accuracy and reliability of the prediction data.

[0029] The heating environment parameters and indoor temperature are input into the heat demand prediction model to perform demand prediction within a future window to obtain predicted heat demand.

[0030] Specifically, the real-time collected heating environment parameters and indoor temperature are used as inputs of feature vectors and input into the heat demand prediction model. The heating environment parameters include outdoor temperature, solar radiation intensity, and collector heat medium temperature. A future time window is set, such as the next few hours or days. After receiving the input, the heat demand prediction model calculates the heat demand in the future window based on the currently input heating environment parameters and indoor temperature using the previously trained weights and parameters. After the calculation is completed, the heat demand prediction model will output the predicted heat demand in the future window. The model can obtain accurate and reliable predicted heat demand results, adjust the operating parameters of the heating equipment according to the predicted heat demand, provide data support for the scheduling and operation of the heating equipment, and achieve efficient and low-energy heating management.

[0031] For the purpose of meeting the predicted heat demand, a heating parameter optimization analysis is performed to determine the optimal heating parameters for adaptively controlling the collector within the future window.

[0032] Specifically, first, the optimization target is determined according to the predicted heat demand to ensure that the collector can provide enough heat supply in the future window to meet the predicted heat demand. At the same time, considering improving the energy efficiency of the collector, reducing energy consumption and operating costs, select appropriate optimization algorithms, such as genetic algorithms, particle swarm optimization, etc., to optimize and analyze the heating parameters. According to the analysis results, the optimal heating parameter combination is determined. Finally, according to the optimal heating parameter combination, the collector is adaptively controlled in the future window to ensure that the collector can dynamically adjust the working state according to environmental changes and heat demand to achieve efficient heating, and at the same time, ensure the safe and efficient operation of the collector.

[0033] Furthermore, in order to meet the predicted heat demand, a heating parameter optimization analysis is performed, including: constructing an optimization evaluation function based on energy consumption, heating stability and thermal regulation efficiency; based on the optimization evaluation function, in order to meet the predicted heat demand, a heating parameter optimization analysis is performed, and the optimal heating parameters when the optimization converges are output.

[0034] Specifically, the evaluation indicators are obtained, including energy consumption, heating stability and thermal regulation efficiency. Energy consumption refers to the total energy consumption of the collector when meeting the heat demand. Heating stability refers to the fluctuation of the collector under different environmental conditions. Thermal regulation efficiency is used to measure the response speed and regulation accuracy of the collector to the heat demand. According to actual needs, expert scores and historical data, corresponding weight coefficients are assigned to the above three evaluation indicators, and then according to energy consumption, heating stability, thermal regulation efficiency and their respective weight coefficients, an optimization evaluation function is constructed. The optimization evaluation function is the weighted sum of energy consumption, heating stability and thermal regulation efficiency. Finally, based on the optimization evaluation function, a suitable optimization algorithm, such as genetic algorithm, particle swarm optimization, etc., is selected to perform optimization analysis of heating parameters. In the optimization process, the evaluation function value is continuously evaluated to determine whether the preset convergence standard is reached with the goal of meeting the predicted heat demand. The convergence standard can be that the rate of change of the objective function is less than a certain threshold or reaches a predetermined optimal value. Once the convergence condition is met, the current optimal heating parameters are output, including water supply temperature, return water temperature, flow rate, pressure, etc. These parameters will be used to adaptively control the collectors in the future window to ensure low energy consumption, high heating stability and thermal regulation efficiency while meeting the predicted heat demand. By constructing an optimization evaluation function and performing heating parameter optimization analysis to output the optimal heating parameters, efficient and energy-saving heating management can be achieved.

[0035] Furthermore, the optimal heating parameters are determined to adaptively control the collector, which then includes: using a dynamic feedback mechanism to regularly perform monitoring and evaluation of the heating quality; if the evaluation results do not meet the expected indicators, the heating parameters are adaptively corrected according to the heating quality deviation.

[0036] Specifically, according to the optimal heating parameters output by the optimization analysis, the collector is set and regulated to ensure that the collector can dynamically adjust these parameters during operation to adapt to the actual heat demand and environmental changes. In this process, the dynamic feedback mechanism is used to monitor the operating status of the collector in real time and compare and analyze it with the expected target value to evaluate whether the heating effect meets the expected indicators, such as the stability of heat output and the rationality of energy consumption. If the monitoring and evaluation results show that there is a deviation in the heating quality, and the deviation is greater than the preset deviation threshold, it means that there is a problem with the heating, and the adaptive correction mechanism is immediately started. Adaptive control analyzes the deviation of heating quality, identifies the cause of the deviation, and adaptively corrects the heating parameters according to actual needs, and readjusts the heating parameters, such as fine-tuning the water supply temperature, adjusting the flow or pressure, etc., to quickly respond to and correct the problem of heating quality deviation, and ensure that the collector can continuously and stably provide high-quality heat output, achieve efficient heating, and meet the actual needs of users.

[0037] Embodiment 2 is based on the same inventive concept as the low energy consumption heating method based on vacuum flat plate collector in the above embodiment. Figure 2 As shown, the present application provides a low-energy heating system based on a vacuum flat-plate collector, wherein the system comprises:

[0038] The data acquisition module 11 is used to collect heating environment parameters and indoor temperature at fixed points through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in a heating circulation network.

[0039] The model building module 12 is used to build a heat demand prediction model based on the ensemble learning principle.

[0040] The heat demand prediction module 13 is used to input the heating environment parameters and the indoor temperature into the heat demand prediction model, perform demand prediction in a future window, and obtain predicted heat demand.

[0041] The data optimization analysis module 14 is used to perform heating parameter optimization analysis for the purpose of meeting the predicted heat demand, and determine the optimal heating parameters to perform adaptive control on the collector within the future window.

[0042] Furthermore, the data acquisition module 11 is used to perform the following steps: the heating environment parameters include outdoor temperature, solar radiation intensity and collector heat medium temperature.

[0043] Furthermore, the model building module 12 is used to perform the following steps: using the attribute parameters of the collector as similarity retrieval features, performing positive sample retrieval to obtain a sample data set, wherein the sample data includes sample outdoor temperature, sample radiation intensity, sample heat medium temperature, sample indoor temperature and sample heat demand; based on the sample data set, supervised training is performed on the heat demand prediction model to obtain a heat demand prediction model that meets the expected convergence conditions.

[0044] Furthermore, the model building module 12 is also used to perform the following steps: divide the sample data set into ten equal parts, and select ten times with replacement to obtain a first data set, and iterate ten times to obtain ten data sets; randomly select five from the ten data sets as a first training set, and the remaining five as a second training set; configure a prediction operator, wherein the prediction operator includes at least a time series analysis operator and a BP neural network; construct a first prediction unit and a second prediction unit based on the time series analysis operator and the BP neural network, respectively; use the first training set and the second training set to train the first prediction unit and the second prediction unit, respectively, to obtain a first prediction unit, a second prediction unit, and a first convergence degree and a second convergence degree that meet the convergence requirements; based on the principle of ensemble learning, build the heat demand prediction model according to the first prediction unit, the second prediction unit, the first convergence degree, and the second convergence degree.

[0045] Furthermore, the model building module 12 is also used to perform the following steps: perform a credibility analysis based on the first convergence degree and the second convergence degree, and configure a first credibility weight and a second credibility weight; integrate the first credibility weight and the second credibility weight with the first prediction unit and the second prediction unit to obtain the thermal demand prediction model.

[0046] Furthermore, the data optimization analysis module 14 is used to perform the following steps: construct an optimization evaluation function according to energy consumption, heating stability and thermal regulation efficiency; based on the optimization evaluation function, perform heating parameter optimization analysis for the purpose of meeting the predicted heat demand, and output the optimal heating parameters when the optimization converges.

[0047] Furthermore, the data optimization analysis module 14 is also used to perform the following steps: using a dynamic feedback mechanism to regularly perform monitoring and evaluation of the heating quality; if the evaluation result does not meet the expected indicators, adaptively correct the heating parameters according to the heating quality deviation.

[0048] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0049] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A low-energy heating method based on a vacuum flat plate collector, characterized in that: include: The heating environment parameters and indoor temperature are collected at fixed points through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in the heating circulation network; Construct a heat demand prediction model based on ensemble learning principles; Inputting the heating environment parameters and indoor temperature into the heat demand prediction model, performing demand prediction within a future window, and obtaining predicted heat demand; For the purpose of meeting the predicted heat demand, a heating parameter optimization analysis is performed to determine the optimal heating parameters for adaptively controlling the collector within the future window.

2. The low-energy heating method based on vacuum flat-plate collector according to claim 1 is characterized in that: The heating environment parameters include outdoor temperature, solar radiation intensity and collector heat medium temperature.

3. The low-energy heating method based on vacuum flat-plate collector according to claim 2 is characterized in that: Build a heat demand forecasting model, including: Using the collector's attribute parameters as similarity retrieval features, a positive sample retrieval is performed to obtain a sample data set, where the sample data includes sample outdoor temperature, sample radiation intensity, sample heat medium temperature, sample indoor temperature and sample heat demand; The heat demand prediction model is supervisedly trained based on the sample data set to obtain a heat demand prediction model that meets expected convergence conditions.

4. The low-energy heating method based on vacuum flat-plate collector according to claim 3 is characterized in that: Performing supervised training on the heat demand prediction model based on the sample data set includes: Divide the sample data set into ten equal parts, select ten parts with replacement to obtain a first data set, and iterate ten times to obtain ten data sets; Randomly select five of the ten data sets as the first training set, and the remaining five as the second training set; Configure a prediction operator, wherein the prediction operator includes at least a time series analysis operator and a BP neural network; Constructing a first prediction unit and a second prediction unit based on the time series analysis operator and the BP neural network respectively; Using the first training set and the second training set to train the first prediction unit and the second prediction unit respectively, to obtain the first prediction unit and the second prediction unit that meet the convergence requirements, as well as the first convergence degree and the second convergence degree; Based on the principle of integrated learning, the heat demand prediction model is built according to the first prediction unit, the second prediction unit, the first convergence degree and the second convergence degree.

5. The low energy consumption heating method based on vacuum flat plate collector according to claim 4 is characterized in that: Building the heat demand prediction model includes: Performing credibility analysis according to the first convergence degree and the second convergence degree, and configuring a first credibility weight and a second credibility weight; The first credible weight, the second credible weight, the first prediction unit, and the second prediction unit are integrated and fused to obtain the heat demand prediction model.

6. The low energy consumption heating method based on vacuum flat plate collector according to claim 1, characterized in that: To meet the predicted heat demand, a heating parameter optimization analysis is performed, including: Construct an optimization evaluation function based on energy consumption, heating stability and thermal regulation efficiency; Based on the optimization evaluation function, a heating parameter optimization analysis is performed for the purpose of satisfying the predicted heat demand, and the optimal heating parameters when the optimization converges are output.

7. The low energy consumption heating method based on vacuum flat plate collector according to claim 1, characterized in that: Determine the optimal heating parameters to adaptively control the collector, and then include: Regularly monitor and evaluate heating quality using dynamic feedback mechanisms; If the evaluation results do not meet the expected indicators, the heating parameters will be adaptively corrected according to the heating quality deviation.

8. A low energy consumption heating system based on vacuum flat plate collector, characterized in that: The steps for implementing the method according to any one of claims 1 to 7 include: A data acquisition module, the data acquisition module is used to collect heating environment parameters and indoor temperature at fixed points through a predetermined monitoring array, wherein the predetermined monitoring array is deployed in a heating circulation network; A model building module, wherein the model building module is used to build a heat demand prediction model based on an integrated learning principle; A heat demand prediction module, the heat demand prediction module is used to input the heating environment parameters and the indoor temperature into the heat demand prediction model, perform demand prediction in a future window, and obtain predicted heat demand; A data optimization analysis module is used to perform heating parameter optimization analysis for the purpose of meeting the predicted heat demand, and determine the optimal heating parameters to perform adaptive control of the collector within the future window.

Images