Solar heating system and control method thereof

Abstract

The invention provides a solar heating system and a control method thereof, and the system comprises a water temperature control module which is used for distributing electric energy; the environment monitoring module is used for collecting environment parameter data; the component detection module is used for collecting operation parameter data of each component; the heat collection module is used for collecting solar heat energy, converting the heat energy into electric energy and transmitting the electric energy to the water temperature control module; the combined type heat storage module is connected with the heat collection module through an inverter and used for achieving heat exchange with the heat collection module; and the heat supply module communicates with the combined type heat storage module through a circulating pump and is used for achieving heat exchange with the combined type heat storage module or converting electric energy into heat energy. By means of the solar heating system and the control method thereof, the energy utilization efficiency can be improved, the service life of equipment is prolonged, and therefore the overall performance of the solar heating system is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of heating, and in particular to a solar heating system and a control method thereof. Background Art

[0002] The solar heating system in the prior art usually has only one working mode and cannot change the operating mode according to actual needs, resulting in low energy saving rate of the system and poor heating effect. Summary of the invention

[0003] In one aspect, the present invention provides a solar heating system, mainly comprising: Water temperature control module for distributing electrical energy; An environmental monitoring module is used to collect environmental parameter data, including solar radiation intensity, temperature and wind speed; A component detection module is used to collect operating parameter data of each component, wherein the operating parameter data includes temperature, pressure and flow; A heat collection module, used for collecting solar thermal energy and converting the thermal energy into electrical energy and transmitting it to the water temperature control module; A composite heat storage module, which is connected to the heat collection module via an inverter and is used to achieve heat exchange with the heat collection module; A heating module is connected to the composite heat storage module through a circulation pump and is used to achieve heat exchange with the composite heat storage module, or to convert electrical energy into thermal energy.

[0004] On the other hand, the present invention also provides a control method for a solar heating system, which mainly includes: Obtaining the solar radiation intensity of the environmental monitoring module; If the solar radiation intensity is greater than a preset first radiation intensity threshold, controlling the solar heating system to operate in a heating-power supply control mode; If the solar radiation intensity is less than the first radiation intensity threshold, and the solar radiation intensity is greater than a preset second radiation intensity threshold, controlling the solar heating system to operate in a heating control mode; If the solar radiation intensity is less than the second radiation intensity threshold, the solar heating system is controlled to operate in a power supply mode.

[0005] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: The present invention discloses a solar heating system and a control method thereof. The present invention realizes the intelligent operation of the solar heating system by organically combining multiple links such as environmental monitoring, load prediction, heat storage optimization and equipment monitoring. A composite heat storage device is also designed, and an optimized heat storage strategy is formulated to dynamically adjust its operating parameters. In addition, the present invention also installs status monitoring sensors on key components of the heating system to collect operating data in real time, and uses a machine learning model to evaluate equipment performance and remaining life. Through the solar heating system and the control method thereof, the system operation can be flexibly adjusted according to weather changes and user needs, the energy utilization efficiency can be improved, and the service life of the equipment can be extended, thereby significantly improving the overall performance of the solar heating system. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 A structural block diagram of a solar heating system of the present invention; Figure 2 A flow chart of a control method of a solar heating system of the present invention; Figure 3 It is a structural schematic diagram of a solar heating system of the present invention.

[0007] Reference numerals 1. Water temperature control module; 2. Environmental monitoring module; 3. Component detection module; 4. Heat collection module; 5. Composite heat storage module; 6. Heating module. DETAILED DESCRIPTION

[0008] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0009] See also Figure 1-3 , a solar heating system in this embodiment specifically includes: A water temperature control module 1, for distributing electric energy; Environmental monitoring module 2, used to collect environmental parameter data, the environmental parameter data including solar radiation intensity, temperature and wind speed; Component detection module 3, used to collect operating parameter data of each component, the operating parameter data including temperature, pressure and flow; The heat collecting module 4 is used to collect solar thermal energy and convert the thermal energy into electrical energy and transmit it to the water temperature control module 1; A composite heat storage module 5, which is connected to the heat collection module 4 via an inverter and is used to achieve heat exchange with the heat collection module 4; The heating module 6 is connected to the composite heat storage module 5 via a circulation pump, and is used to achieve heat exchange with the composite heat storage module 5, or to convert electrical energy into thermal energy.

[0010] In this embodiment, the water temperature control module 1 includes a human-computer interactive LCD screen, which can display the current functional mode, intuitively see the system operation mode, and display the temperature of each module in real time (the temperature of the heating module 6 and the temperature of the composite heat storage module 5).

[0011] In this embodiment, the composite heat storage module 5 and the heating module 6 are equipped with a dual-circulation water pump, which has high pressure, high head, dual water flow direction and safer effect. The pipeline is provided with a 5cm insulation layer, which is more resistant to freezing and can be operated in cold areas. The component detection module 3 is used to monitor whether the components are operating normally. For example, if the component detection module 3 detects that the water channel has frozen, it is prohibited to start the composite heat storage module 5 and the heating module 6 for heat exchange to avoid damage to the equipment.

[0012] Continue to see Figure 1-3 In this embodiment, a control method of a solar heating system specifically includes steps S101-S104: Step S101, obtaining the solar radiation intensity of the environment monitoring module.

[0013] In the specific implementation, by deploying environmental monitoring sensors around the target building, environmental parameter data such as solar radiation intensity, temperature and wind speed are obtained, and the data are transmitted to the cloud database in real time for storage. According to the location and environmental characteristics of the target building, the type of environmental parameters to be monitored and the location of the monitoring points are determined, and appropriate environmental monitoring sensors are selected for deployment. Environmental parameter data such as solar radiation intensity, temperature and wind speed are collected in real time by the deployed environmental monitoring sensors, and the collected data are transmitted to the cloud server in real time through the wireless communication module. After the cloud server receives the environmental parameter data uploaded by the sensor, it parses and preprocesses the data to extract the values ​​of key parameters such as solar radiation intensity, temperature and wind speed. The preprocessed environmental parameter data is classified and marked according to the timestamp and sensor number, and then stored in the corresponding data table in the cloud database. According to the type of environmental parameters and monitoring requirements, a suitable data storage structure and index method are designed to facilitate subsequent data query and analysis. Statistical analysis is performed on the historical environmental parameter data stored in the cloud database to calculate the average, maximum and minimum values ​​of solar radiation intensity, temperature and wind speed in different time periods. The statistical results of the environmental parameters obtained by the analysis are compared with the preset thresholds to determine whether any abnormalities occur. If an abnormality is detected, the alarm mechanism is triggered and a notification is sent to relevant personnel.

[0014] Specifically, according to the location and environmental characteristics of the target building, 10 environmental monitoring points are arranged around the building, and each monitoring point is equipped with an environmental monitoring device containing solar radiation intensity, temperature and wind speed sensors. The sensor collects data every 5 minutes and uploads the data to the cloud server through the Zigbee wireless communication module. The server uses a data parsing script written in Python to parse the received data, extract the values ​​of solar radiation intensity, temperature and wind speed, and mark them according to the timestamp and sensor number, and store them in the MySQL database. When designing the database table, indexes are established according to the sensor type and time dimension to optimize data query performance. SQL statements are used to aggregate and count the data to calculate the average, maximum and minimum values ​​of solar radiation intensity, temperature and wind speed on a daily, weekly and monthly basis. When it is detected that the solar radiation intensity exceeds 800W / m², the temperature exceeds 35℃, or the wind speed exceeds 20m / s, the alarm mechanism is triggered to send SMS and email notifications to the building management personnel. Through real-time monitoring and statistical analysis of environmental parameters, the environmental conditions around the building can be grasped in a timely manner, providing data support for the building's energy management and equipment scheduling, and also preventing damage to the building caused by extreme weather.

[0015] Step S102: If the solar radiation intensity is greater than a preset first radiation intensity threshold, the solar heating system is controlled to operate in a heating-power supply control mode.

[0016] In one embodiment, the heat collection module is controlled to be turned on, the heat supply module is controlled to be turned on, and the composite heat storage module is controlled to be turned on.

[0017] Specifically, the heating-power supply control mode of the solar heating system refers to the solar heating system generating electricity for heating and supplying household appliances at the same time, and converting excess electricity into heat energy for storage, so that the solar heating system can save a lot of electricity bills. Usually, when the solar radiation intensity is greater than the first radiation intensity threshold, which means at noon when the light intensity is strong, the electricity converted by the heat collection module is simultaneously supplied to the composite heat storage module, the heating module and household appliances.

[0018] Step S103: If the solar radiation intensity is less than the first radiation intensity threshold and the solar radiation intensity is greater than a preset second radiation intensity threshold, the solar heating system is controlled to operate in a heating control mode.

[0019] In one embodiment, the heat collection module is controlled to be turned on, and the heat supply module is controlled to be turned on.

[0020] Specifically, the heating control mode of the solar heating system refers to generating electricity for heating through the solar heating system. Usually, when the solar radiation intensity is less than the preset first radiation intensity threshold, and the solar radiation intensity is greater than the preset second radiation intensity threshold, it means that in the early morning when the light intensity is weak, the electric energy converted by the heat collection module is preferentially supplied to the heating module, and the heating module maintains heating through electric-heat conversion.

[0021] Step S104: if the solar radiation intensity is less than the second radiation intensity threshold, control the solar heating system to operate in a power supply mode.

[0022] In one embodiment, the heat collection module is controlled to be turned off, the heat supply module is controlled to be turned on, and the composite heat storage module is controlled to be turned on.

[0023] Specifically, the power supply mode of the solar heating system refers to supplying the heating module and the composite heat storage module with external alternating current. Usually, at night when the solar radiation intensity is less than the second radiation intensity threshold, which means the light intensity is weak, the water temperature control module supplies power to the composite heat storage module and the heating module through the mains. If the composite heat storage module stores enough hot water, the composite heat storage module is controlled to exchange heat with the heating module to achieve heating. If the composite heat storage module does not store enough hot water, the heating module is controlled to generate heat to achieve heating. For example: when the light intensity is less than the second radiation intensity threshold, the composite heat storage module includes water tank No. 1 and water tank No. 2, the heating module is a heater, the heater is provided with a radiator, and the room temperature is heated by heat released by the water tank. When the room temperature is lower than the set temperature, water tank No. 2 is used to release heat to the room radiator. When water tank No. 2 has released heat and is lower than the lower limit temperature, water tank No. 1 is started to release heat to the radiator to maintain the room temperature. When the radiators of water tanks No. 1 and No. 2 are both lower than the lower limit temperature, the heater will start to heat the radiator for electric-to-thermal conversion to release heat to the room, and stop the heat exchange between water tanks No. 1 and No. 2 and the heater.

[0024] Furthermore, the temperature of the composite heat storage module is acquired in real time, and if the temperature of the composite heat storage module is less than a first preset temperature threshold, the composite heat storage module is controlled to be turned off.

[0025] In one embodiment, the composite heat storage module includes a hot water storage device and a phase change heat storage device, and the heat release relationship of the composite heat storage module is Qtotal=p1*t+p2*t, ​​wherein p1+p2=1, Qtotal is the heat release of the composite heat storage module, p1 is the heat release power of the hot water storage device, and p2 is the heat release power of the phase change heat storage device.

[0026] Furthermore, the method also includes: inputting weather characteristic data into a pre-trained weather prediction model to obtain a predicted weather change trend table; the weather characteristic data includes historical weather data stored in a database and monitoring data of an environmental monitoring module; and generating a power generation plan with a preset time span based on the weather change trend table and historical electricity consumption data.

[0027] In a specific implementation, the cloud server reads the historical weather data and the current monitoring data from the database, inputs them into the pre-built weather prediction model, and predicts the trend of solar energy resources changes in the future. According to the weather prediction model pre-built in the cloud server, the historical weather data and the current monitoring data stored in the database are obtained, and the obtained data are input into the weather prediction model for processing. Standardized weather feature data is obtained by extracting features and preprocessing the input historical weather data and current monitoring data. The standardized weather feature data is input into the pre-trained machine learning model, and the support vector machine algorithm is used to predict the weather change trend in the future. According to the predicted weather change trend data, combined with the correlation between solar energy resources and weather conditions, the change of solar energy resources in the future is judged. If the predicted weather change trend indicates that the solar radiation intensity is high in the future, it is determined that the solar energy resources are sufficient in this time period, and efficient solar power generation can be carried out. If the predicted weather change trend indicates that there will be more cloudy or rainy weather in the future, it is judged that the solar energy resources in this time period are relatively small, and the strategy of solar power generation needs to be adjusted. According to the predicted changes in solar energy resources, the solar power generation plan and scheduling scheme for the future period are automatically generated and transmitted to the power generation scheduling system to guide the optimization of the power generation process.

[0028] Specifically, first, the pre-built weather forecast model is retrieved from the cloud server. The model uses the support vector machine algorithm to train historical weather data to predict future weather trends. Next, the historical weather data for the past 10 years and the real-time meteorological data collected by the current monitoring station are obtained from the database, including data in multiple dimensions such as temperature, humidity, air pressure, wind speed, and cloud cover. The acquired data is feature extracted and standardized to extract key features that affect weather changes, such as average temperature and average humidity. The data is normalized and mapped to the [0,1] interval to form a standardized weather feature data set. Then, the standardized data is input into the weather forecast model. The model analyzes and calculates the data through the support vector machine algorithm to obtain the weather change trend for each day in the next week, including predicted temperature, humidity, solar radiation intensity, and other data. According to the forecast results, the solar energy resources in the next week are judged. When the predicted average solar radiation intensity is greater than 800W / m², the solar energy resources are considered sufficient; when the predicted average solar radiation intensity is less than 500W / m², or cloudy and rainy weather is predicted for more than 3 days, the solar energy resources are considered to be less. Finally, based on the judged solar energy resources, combined with the power generation efficiency of the photovoltaic power station, the grid scheduling needs and other factors, the solar power generation plan for the next week is automatically generated, the power generation period and power scheduling are optimized, and the generated power generation plan data is transmitted to the power generation scheduling system to accurately control the operation of the photovoltaic power station. Through the above process, the full process from weather forecasting to solar power generation is realized, and the utilization efficiency of solar energy resources is improved.

[0029] In one embodiment, the method further includes: inputting the weather change trend table and the thermal conductivity coefficient and heat capacity of the building into a pre-constructed building heat load prediction model to obtain a heat load demand prediction curve of the heating system for a preset time span; and dynamically adjusting the parameters of the phase change thermal storage device according to the heat load demand prediction curve.

[0030] In the specific implementation, the desired indoor temperature and heating time period parameters set by the user are obtained as the heating demand. At the same time, by accessing the pre-established building information model database, the parameters such as the wall material, window type and floor height of the target building are obtained, and the thermal conductivity coefficient and heat capacity of the building are calculated accordingly.

[0031] The desired room temperature and heating time period set by the user are obtained as input parameters for heating demand. The pre-established building information model database is accessed to obtain the building parameters of the target building, such as wall materials, window types, and floor heights. Based on the obtained building parameters, the heat transfer calculation method is used to calculate the thermal conductivity and heat capacity of the building. The heating demand parameters and the building thermal characteristic parameters are input into the heating load prediction model, and the model is trained by the machine learning algorithm. In the heating load prediction model, the support vector machine regression algorithm is used to train the load prediction function based on historical data. The current outdoor temperature, wind speed and other environmental parameters are input into the trained load prediction model to predict the heating load curve for a period of time in the future. Based on the predicted heating load curve, combined with the operating characteristics of the heating equipment, the optimal heating equipment operation strategy is determined through the optimization algorithm to achieve energy-saving and efficient heating control.

[0032] Specifically, the user sets the desired room temperature to 20 degrees Celsius and the heating time period to 7 am to 10 pm every day through the smart home system. The system automatically accesses the building information model database to obtain parameters such as the building's exterior wall material is aerated concrete blocks, the windows are double-layer insulating glass, and the floor height is 8 meters. Based on these parameters, the heat transfer coefficient of the building wall is calculated to be 8W / (m²·K) and the heat capacity is 920J / (kg·K) using Fourier's law of heat conduction. The room temperature, heating time period, and calculated building thermal characteristic parameters set by the user are input into the heating load prediction model. The model uses the support vector machine regression algorithm and is trained using historical data from the past three years to obtain the load prediction function. The current outdoor temperature is -5 degrees Celsius and the wind speed is 3m / s. These environmental parameters are substituted into the trained load prediction model to predict the heating load curve for the next 24 hours. Based on the prediction results, the genetic algorithm is used to optimize the operation strategy of the heating equipment. By adjusting the boiler outlet water temperature and the circulation pump frequency, energy consumption is minimized while meeting the user's comfort requirements. After calculation, the best operating strategy is a boiler outlet water temperature of 65 degrees Celsius and a circulation pump frequency of 30Hz. It is estimated that the electricity consumption per square meter of heating area is 5 degrees per day, and the heating efficiency is increased by 15%.

[0033] The prediction results of the solar energy resource change trend and the thermal conductivity and heat capacity of the building are input into a pre-constructed building heat load prediction model, and a heat load demand prediction curve of the heating system in the future period of time is dynamically calculated.

[0034] Obtain the predicted trend data of solar energy resources, including the changes of parameters such as solar radiation intensity and sunshine hours in the future; obtain the thermophysical parameters of the building, including the thermal conductivity of building materials, the thermal capacity of building structures, etc.; input the solar energy resource trend data and the thermophysical parameters of the building into the pre-built building heat load prediction model; in the building heat load prediction model, according to the solar energy resource trend data, use the energy balance equation to calculate the heat balance of the building in the future; in the heat balance calculation process, comprehensively consider the influence of the thermal conductivity and heat capacity of the building on the indoor temperature change, and solve the dynamic heat load demand of the building through the differential equation; perform curve fitting on the calculated dynamic heat load demand data of the building to obtain the heat load demand prediction curve of the heating system in the future; use the heat load demand prediction curve of the heating system as an important reference for the operation optimization of the heating system and energy scheduling, reasonably arrange the heat source operation plan, improve the efficiency of solar energy utilization, and reduce the energy consumption of the heating system.

[0035] Specifically, first, the forecast data of solar radiation intensity and sunshine hours for the next week are obtained from the meteorological department, where the average solar radiation intensity is 800W / m² and the average sunshine hours is 6 hours. Then, the thermal conductivity coefficient of the building exterior wall material is obtained from the architectural design drawings, which is 8W / (m·K) and the thermal capacity of the building structure is 1MJ / (m³·K). The above data are input into the pre-built BP neural network heat load prediction model. The model uses the energy balance equation to comprehensively consider factors such as solar radiation intensity, sunshine hours, thermal conductivity coefficient and thermal capacity of building materials, and uses the difference format to solve the dynamic heat load demand of the building. For example, the heat load demand of a building on the first day of the forecast period is Q=800W / m²×6h×8W / (m·K)×1MJ / (m³·K)=216MJ. The least squares curve fitting is performed on the heat load demand data for each day during the forecast period, and the heat load demand forecast curve for the next week is obtained as Q=216+05t(MJ), where t is the number of days in the forecast period. Finally, the prediction curve is used as an important reference for optimizing the operation of the heating system. By rationally scheduling the heat source, for example, using solar collectors to provide heat during the day when there is sufficient sunshine, and using gas boilers to provide heat at night when there is insufficient sunshine, the efficiency of solar energy utilization can be maximized, the energy consumption of the heating system can be reduced, and a comfortable heating environment can be provided for the building.

[0036] For the heating system, a composite heat storage device consisting of a hot water storage tank and a phase change heat storage material is designed. According to the change trend of the solar energy resources and the heat load demand prediction curve, an optimized heat storage strategy is determined, and the operating parameters of the composite heat storage device are dynamically adjusted.

[0037] Obtain historical data and future forecast data of solar energy resources and establish a solar energy resource change trend model; obtain historical heat load demand data and future forecast data of the heating system and establish a heat load demand forecast model; according to the solar energy resource change trend model and the heat load demand forecast model, use the dynamic programming algorithm to determine the optimal capacity ratio of the hot water storage tank and the phase change thermal storage material in the composite thermal storage device; according to the solar energy resource change trend model and the heat load demand forecast model, use the model predictive control algorithm to predict the changes in solar energy resources and heat load demand in the future in real time; according to the real-time predicted changes in solar energy resources and heat load demand, dynamically adjust the heat storage and heat release power of the hot water storage tank and the phase change thermal storage material in the composite thermal storage device to ensure that the heat load demand of the heating system is met; during the operation of the composite thermal storage device, use the Kalman filter algorithm to estimate and correct the key parameters such as temperature and flow of the hot water storage tank and the phase change thermal storage material in real time; according to the key parameters estimated and corrected in real time, dynamically optimize the operation strategy of the composite thermal storage device to improve the utilization efficiency of solar energy and the operation performance of the heating system.

[0038] Specifically, in order to establish a solar energy resource change trend model, data such as solar radiation intensity and sunshine hours in the past 10 years can be collected, and trend prediction can be performed using time series analysis methods such as the ARIMA model. For example, by fitting the ARIMA (1,1,2) model to the solar radiation intensity data of the preset time span (10 years) in the target area, the predicted value of solar radiation intensity in the next year can be obtained. At the same time, a neural network algorithm such as LSTM is used to train the data such as the heat consumption and water supply temperature of the heating system in the past 5 years to establish a heat load demand prediction model with a prediction accuracy of more than 90%. On this basis, the dynamic programming algorithm is applied to calculate the optimal capacity ratio of a 200 cubic meter hot water storage tank and 10 tons of phase change thermal storage material in the composite thermal storage device with solar energy utilization efficiency and heating cost as the optimization goals. During operation, the model predictive control algorithm predicts the changes in solar energy resources and heat load demand in the next 4 hours every 30 minutes, and dynamically adjusts the operating power of the thermal storage device according to the prediction results. For example, when it is predicted that the heat consumption at night is large, the heat release power of the hot water storage tank is increased by 20% in advance. At the same time, the Kalman filter algorithm calibrates the key parameters of the heat storage device every 10 minutes. When it is found that the actual temperature of the heat storage tank deviates from the predicted value by more than 2 degrees Celsius, the operation strategy is adjusted in time, such as increasing the flow of the circulation pump to speed up the heat release rate. Through the comprehensive application of the above methods, the solar energy utilization rate of the solar seasonal heat storage heating system can be increased by more than 10%, and the heating effect is more stable and reliable.

[0039] In one embodiment, the method further includes: collecting operating parameter data of each component according to the component detection module, inputting the operating parameter data into a pre-trained equipment health assessment model to obtain the health status and remaining life estimation value of the equipment.

[0040] In the specific implementation, condition monitoring sensors are installed on key components of the heating system, such as the collector, heat storage device, circulation pump and pipeline, to collect operating parameters such as temperature, pressure and flow of each component in real time, and monitor the operating conditions of the heating system. At the same time, a pre-built equipment health assessment model based on machine learning is used to analyze the monitoring data and evaluate the performance degradation and remaining life of key equipment.

[0041] According to the types of key components of the heating system and the monitoring requirements, appropriate condition monitoring sensors, such as temperature sensors, pressure sensors, and flow sensors, are selected and installed on the corresponding components. The operating parameter data of key components, including temperature, pressure, and flow, are collected in real time through sensors, and the collected data is transmitted to the data processing center. The collected operating parameter data is preprocessed, including data cleaning, normalization, and feature extraction, to facilitate subsequent machine learning model training and prediction. According to the historical operation data and equipment health status data of the heating system, a machine learning-based equipment health assessment model is constructed, such as support vector machine (SVM), random forest (RandomForest) or neural network (NeuralNetwork). The preprocessed real-time monitoring data is input into the trained equipment health assessment model to evaluate and predict the performance degradation of the equipment, and obtain the health status and remaining life estimation of the equipment. If the evaluation results show that the equipment has a performance degradation or failure risk, an early warning message is generated and sent to relevant personnel so that maintenance or replacement measures can be taken in time to ensure the normal operation of the heating system. The equipment’s operating parameter data and health status feedback are continuously collected and used to update and optimize the equipment health assessment model to improve the accuracy and robustness of the model and realize intelligent operation and maintenance of the heating system.

[0042] Specifically, in order to realize the intelligent operation and maintenance of the heating system, it is necessary to first install appropriate condition monitoring sensors on key components. For example, a PT100 temperature sensor with a range of 0-200℃ and an accuracy of ±5℃ is installed on the boiler; an MPM489 pressure transmitter with a range of 0-6MPa and an accuracy of ±5%FS is installed on the pipeline; and an LWGY turbine flow sensor with a range of 5-50m³ / h and an accuracy of ±1% is installed on the pump. These sensors collect operating parameters in real time with a cycle of 1 minute and transmit the data to the data processing center through the RS485 bus. In the data preprocessing stage, the 3σ principle is used to clean the data and remove outliers beyond the normal range; then the maximum and minimum normalization method is used to normalize the data and map the data to the [0,1] interval; finally, 10 time domain features such as mean, variance, and kurtosis and 5 frequency domain features of the data are extracted. Based on historical operation data and equipment health status data, a support vector machine (SVM) is used to build an equipment health assessment model. Using the radial basis kernel function, the model parameters were optimized through grid search and cross-validation, and finally an SVM model with an accuracy of 95% was obtained. The real-time monitoring data was input into the model for health assessment. If the prediction results show that the equipment performance decline exceeds 20% or the failure probability exceeds 10%, an early warning message is sent to the maintenance personnel via SMS and email. At the same time, the actual health status of the equipment is fed back to the model, and the model is updated and optimized using the incremental learning method, so that the model can adapt to the dynamic changes of the equipment and realize the intelligent operation and maintenance of the heating system.

[0043] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A solar heating system, characterized in that: include: Water temperature control module for distributing electrical energy; An environmental monitoring module is used to collect environmental parameter data, including solar radiation intensity, temperature and wind speed; A component detection module is used to collect operating parameter data of each component, wherein the operating parameter data includes temperature, pressure and flow; A heat collection module, used for collecting solar thermal energy and converting the thermal energy into electrical energy and transmitting it to the water temperature control module; A composite heat storage module, which is connected to the heat collection module via an inverter and is used to achieve heat exchange with the heat collection module; A heating module is connected to the composite heat storage module through a circulation pump and is used to achieve heat exchange with the composite heat storage module, or to convert electrical energy into thermal energy.

2. A control method applied to the solar heating system as claimed in claim 1, characterized in that: The method comprises: Obtain the solar radiation intensity of the environmental monitoring module; If the solar radiation intensity is greater than a preset first radiation intensity threshold, controlling the solar heating system to operate in a heating-power supply control mode; If the solar radiation intensity is less than the first radiation intensity threshold, and the solar radiation intensity is greater than a preset second radiation intensity threshold, controlling the solar heating system to operate in a heating control mode; If the solar radiation intensity is less than the second radiation intensity threshold, the solar heating system is controlled to operate in a power supply mode.

3. The method according to claim 2, characterized in that The step of controlling the solar heating system to operate in a heating control mode comprises: Control the heat collection module to start, and control the heating module to start.

4. The method according to claim 2, characterized in that: The step of controlling the solar heating system to operate in a heating-power supply control mode comprises: Control the heat collection module to start, control the heating module to start, and control the composite heat storage module to start.

5. The method according to claim 2, characterized in that: The controlling the solar heating system to operate in a power supply mode comprises: Control the heat collection module to turn off, control the heating module to turn on, and control the composite heat storage module to turn on.

6. The method according to claim 5, characterized in that Control the opening of the composite thermal storage module, including: The temperature of the composite heat storage module is acquired in real time, and if the temperature of the composite heat storage module is less than a first preset temperature threshold, the composite heat storage module is controlled to be turned off.

7. The method according to claim 2, characterized in that The composite heat storage module includes a hot water storage device and a phase change heat storage device. The heat release relationship of the composite heat storage module is Q 总 =p1*t+p2*t, ​​where p1+p2=1, Q 总 is the heat release of the composite heat storage module, p1 is the heat release power of the hot water storage device, and p2 is the heat release power of the phase change heat storage device.

8. The method according to claim 2, characterized in that: Also includes: The component detection module collects operating parameter data of each component, and inputs the operating parameter data into a pre-trained equipment health assessment model to obtain the health status and remaining life estimation of the equipment.

9. The method according to claim 7, characterized in that: Also includes: Inputting weather characteristic data into a pre-trained weather prediction model to obtain a predicted weather change trend table; the weather characteristic data includes historical weather data stored in a database and monitoring data of an environmental monitoring module; A power generation plan with a preset time span is generated according to the weather change trend table and historical power consumption data.

10. The method according to claim 9, characterized in that Also includes: Input the weather change trend table and the thermal conductivity and heat capacity of the building into a pre-constructed building heat load prediction model to obtain a heat load demand prediction curve of the heating system for a preset time span; According to the heat load demand prediction curve, the parameters of the phase change thermal storage device are dynamically adjusted.

Images