Photo-thermal power generation system mirror surface light following angle control system and method based on temperature control

Abstract

The invention discloses a system and a method for controlling a mirror surface light following angle of a photo-thermal power generation system based on temperature control, and aims to solve the problems that an existing photo-thermal power generation system often depends on a fixed mirror surface angle adjusting strategy and cannot respond to complex illumination and temperature changes in time, so that the heat collection efficiency is low, and the system is inconvenient to use. The system can accurately adjust the angle of the heat collector in real time, maximize the illumination receiving efficiency and optimize the heat collection effect through the cooperation of a plurality of intelligent modules such as the data acquisition module, the illumination prediction module, the temperature prediction module and the mirror surface adjustment module, in addition, the system ensures that the heat collection efficiency is not influenced by angle adjustment through the heat collection efficiency detection and feedback module, and the system is suitable for popularization and application. According to the combined adjusting method based on temperature self-sensing, the self-adaptive capacity, the heat collecting efficiency and the system stability of the photo-thermal power generation system are improved, and the hysteresis quality and instability in the traditional technology are overcome.

Description

Technical Field

[0001] The present application relates to the field of molten salt heat storage technology, and in particular to a temperature-controlled mirror tracking angle control system and method for a solar thermal power generation system. Background Art

[0002] The solar thermal power generation system based on molten salt heat storage can achieve efficient heating and energy storage of high-temperature salt media by directionally reflecting solar energy through a field of collecting mirrors, providing stable high-temperature heat source support for the thermal power generation link. It is one of the core links in building a large-scale renewable energy thermal energy system.

[0003] While molten salt thermal storage technology has been widely adopted in some large-scale concentrated solar power projects, the delayed response of many systems to changes in light and temperature has resulted in suboptimal thermal storage efficiency. In high-temperature molten salt thermal storage systems, in particular, temperature control often exhibits a certain degree of lag. This can lead to the collector system failing to adjust its mirror angle in response to rapidly changing light conditions, resulting in a failure to effectively focus light onto the molten salt, thus affecting thermal storage efficiency.

[0004] Furthermore, most existing solar collector systems rely on fixed regulation strategies and lack adaptive control capabilities. This prevents the systems from effectively self-adjusting in the face of complex weather conditions, temperature fluctuations, or changes in sunlight. In particular, when the collector surface temperature is high, failure to adjust the mirror angle in a timely manner can further increase heat loss, affecting the stability and sustainability of heat storage. Summary of the Invention

[0005] The main purpose of this application is to provide a temperature-controlled mirror tracking angle control system and method for a solar thermal power generation system to solve the problems raised by the above-mentioned background technology.

[0006] To achieve the above objectives, this application provides the following technical solutions: A temperature-controlled mirror tracking angle control system and method for a solar thermal power generation system, comprising a data acquisition module, an illumination prediction module, a temperature prediction module, a mirror adjustment module, a heat collection efficiency detection module, and a feedback module; The data acquisition module is used to collect multi-source data from the device and pre-process the collected parameters, and then reorganize them into a first data group, a second data group, and a third data group; The illumination prediction module is used to perform data coupling on the first data group and the second data group to generate an illumination prediction coefficient LCF, analyze the LCF, and determine whether angle adjustment is required in advance based on the analysis results; The temperature prediction module is used to perform data coupling on the second data group and the third data group, generate a temperature change prediction coefficient TCF, analyze the coefficient TCF, and determine whether angle adjustment is required in advance based on the analysis results; The mirror adjustment module is used to couple the first data and the third data group to generate a mirror positioning coefficient MLC, analyze the MLC, and determine whether an angle adjustment is required in advance based on the analysis result; The heat collection efficiency detection module is used to couple the first data group, the second data group, and the third data group to generate a heat collection efficiency coefficient (CPF), and analyze the CPF to determine whether the pre-performed angle adjustment will affect the heat collection efficiency. The feedback module is used to feed back various data to the visualization terminal.

[0007] Preferably, the data acquisition module includes a data acquisition unit and a data preprocessing unit; The data acquisition unit is used to collect multi-source data for the equipment, including solar radiation intensity, solar altitude angle, solar azimuth angle, incident angle, mirror adjustment angle, ambient temperature, collector temperature, temperature change rate, target temperature, temperature feedback adjustment angle, thermal efficiency, incident light power, heat loss rate, collector surface temperature and gain adjustment angle; The data preprocessing unit is used to preprocess and dimensionlessly process the collected multi-source data, and group the processed data to generate a first data group, a second data group, and a third data group; The first data set includes solar radiation intensity A, solar altitude angle B, solar azimuth angle C, incident angle D, and mirror adjustment angle E; The second data set includes the ambient temperature F, the collector temperature G, the temperature change rate H, the target temperature I, and the temperature feedback adjustment angle J; The third data group includes the heat collection efficiency K, the incident light power L, the heat loss rate M, the collector surface temperature N, and the gain adjustment angle O.

[0008] Preferably, the illumination prediction module includes an illumination prediction data coupling unit and an illumination data analysis unit; The illumination prediction data coupling unit is used to extract data from the first data group and the second data group, including solar radiation intensity A, incident angle D, mirror adjustment angle E, collector temperature G, and temperature feedback adjustment angle J, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the illumination prediction coefficient LCF; The illumination data analysis unit is used to perform data analysis on the calculated illumination prediction coefficient LCF, and determine whether angle adjustment is required in advance based on the analysis result, specifically in the following manner: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

[0009] Preferably, the illumination prediction data coupling unit calculates and obtains the illumination prediction coefficient LCF by the following formula: ; Where: A is the solar radiation intensity, D is the incident angle, E is the surface adjustment angle, and G is the collector temperature.

[0010] 5. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 4, characterized in that the temperature prediction module includes a temperature prediction data coupling unit and a temperature prediction analysis unit; The temperature prediction data coupling unit is used to extract data from the second data group and the second data group, including the collector temperature G, the ambient temperature F, the target temperature I, the heat collection efficiency K, the heat loss rate M, the temperature feedback adjustment angle J, and the temperature change rate H, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the temperature change prediction coefficient TCF; The temperature prediction and analysis unit is used to analyze the calculated data and determine whether the angle adjustment needs to be performed in advance based on the analysis results. The specific method is as follows: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

[0011] Preferably, the temperature prediction data coupling unit calculates and obtains the temperature change prediction coefficient TCF by the following formula: ; Where: G is the collector temperature, F is the ambient temperature, I is the target temperature, K is the collector efficiency, M is the heat loss rate, J is the temperature feedback adjustment angle, and H is the temperature change rate.

[0012] Preferably, the mirror adjustment module includes a mirror adjustment data coupling unit and a mirror adjustment analysis unit; The mirror adjustment data coupling unit is used to extract data from the first data group and the third data, including solar radiation intensity A, incident angle D, solar altitude angle B, mirror adjustment angle E, thermal collection efficiency K, heat loss rate M, gain adjustment angle O, and incident light power L, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the temperature change prediction coefficient TCF; The mirror adjustment analysis unit is used to perform data analysis on the calculated mirror positioning coefficient MLC, and determine whether the mirror needs to be adjusted in advance based on the analysis results. The specific method is as follows: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

[0013] Preferably, the mirror adjustment data coupling unit calculates and obtains the mirror positioning coefficient MLC by the following formula: ; Where: A is the solar radiation intensity, D is the incident angle, B is the solar altitude angle, E is the mirror adjustment angle, K is the heat collection efficiency, M is the heat loss rate, O is the gain adjustment angle, and L is the incident light power.

[0014] Preferably, the heat collection efficiency detection module includes a heat collection efficiency data coupling unit and a heat collection efficiency analysis unit; The heat collection efficiency data coupling unit is used to extract data from the first data group, the second data group, and the third data group, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the heat collection efficiency coefficient CPF; The heat collection efficiency analysis unit is used to perform data analysis on the calculated heat collection efficiency coefficient CPF, and based on the analysis results, determine whether the angle adjustment will affect the heat collection efficiency. The specific method is as follows: when When , it means that the current adjustment of the equipment will not affect the heat collection performance and can be executed; when When , it means that the current adjustment of the equipment will affect the heat collection performance, causing the first level of heat collection attenuation, and the execution needs to be delayed by 0.5 seconds; when When the device is adjusted, it means that the current adjustment will affect the heat collection performance, causing secondary heat collection attenuation, and the execution needs to be delayed by 1.5 seconds; when When , it means that the current adjustment of the equipment will affect the heat collection performance, causing the third level heat collection to be attenuated and unable to be executed;

[0015] The heat collection efficiency data coupling unit calculates the heat collection efficiency coefficient CPF using the following formula: ; Where: A is the solar radiation intensity, B is the solar altitude angle, C is the solar azimuth angle, D is the incident angle, E is the mirror adjustment angle, F is the ambient temperature, G is the collector temperature, H is the temperature change rate, I is the target temperature, J is the temperature feedback adjustment angle, K is the thermal efficiency, L is the incident light power, M is the heat loss rate, N is the collector surface temperature, and O is the gain adjustment angle.

[0016] A method for jointly adjusting the angles of multiple mirrors for heating in a solar thermal power generation system based on temperature self-sensing is provided, and the specific steps are as follows: S1. Collect multi-source data from the device through a data acquisition module, pre-process the collected parameters, and then reorganize them into a first data group, a second data group, and a third data group; S2. Couple the first data group and the second data group using a light prediction module to generate a light prediction coefficient LCF, analyze the coefficient LCF, and determine whether angle adjustment is required in advance based on the analysis results. S3. Couple the second data set and the third data set using a temperature prediction module to generate a temperature change prediction coefficient TCF, analyze the coefficient, and determine whether angle adjustment is required in advance based on the analysis results. S4. Couple the first data and the third data group through the mirror adjustment module to generate a mirror positioning coefficient MLC, analyze the MLC, and determine whether to perform angle adjustment in advance based on the analysis result. S5. Using a heat collection efficiency detection module, the first data set, the second data set, and the third data set are coupled to generate a heat collection efficiency coefficient (CPF), and the CPF is analyzed to determine whether the pre-performed angle adjustment affects the heat collection efficiency. S6. Feedback various data to the visualization terminal through the feedback module. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is the flow chart of the application system.

[0018] Figure 2 This is a step diagram of the application method.

[0019] In the figure: 1. Data acquisition module; 11. Data acquisition unit; 12. Data preprocessing unit; 2. Illumination prediction module; 21. Illumination prediction data coupling unit; 22. Illumination data analysis unit; 3. Temperature prediction module; 31. Temperature prediction data coupling unit; 32. Temperature prediction analysis unit; 4. Mirror adjustment module; 41. Mirror adjustment data coupling unit; 42. Mirror adjustment analysis unit; 5. Thermal collection efficiency detection module; 51. Thermal collection efficiency data coupling unit; 52. Thermal collection efficiency analysis unit; 6. Feedback module. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are intended only to illustrate the relative positional relationships and movement of components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements and may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to such process, method, product, or apparatus.

[0022] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] Example 1: Please refer to Figure 1A temperature-controlled mirror tracking angle control system and method for a solar thermal power generation system includes a data acquisition module 1, an illumination prediction module 2, a temperature prediction module 3, a mirror adjustment module 4, a heat collection efficiency detection module 5, and a feedback module 6. The data acquisition module 1 is used to collect multi-source data from the device and pre-process the collected parameters, and then reorganize them into a first data group, a second data group, and a third data group; The illumination prediction module 2 is used to couple the first data group and the second data group to generate an illumination prediction coefficient LCF, analyze the LCF, and determine whether angle adjustment is required in advance based on the analysis results. The temperature prediction module 3 is used to couple the second data group and the third data group to generate a temperature change prediction coefficient TCF, analyze the coefficient, and determine whether the angle adjustment needs to be performed in advance based on the analysis results; The mirror adjustment module 4 is used to couple the first data and the third data group to generate a mirror positioning coefficient MLC, analyze the MLC, and determine whether an angle adjustment is required in advance based on the analysis result. The heat collection efficiency detection module 5 is used to couple the first data set, the second data set, and the third data set to generate a heat collection efficiency coefficient CPF, and analyze the CPF to determine whether the pre-performed angle adjustment will affect the heat collection efficiency. The feedback module 6 is used to feed back various data to the visualization terminal.

[0024] In this embodiment, Data Acquisition Module 1 is the system's foundational module, primarily responsible for real-time, multi-source data collection of various parameters of the CSP system. This data includes solar radiation intensity, solar altitude, angle of incidence, collector temperature, temperature change rate, target temperature, and other key parameters. By monitoring these key parameters, the system ensures accurate input information. This module preprocesses and dimensionlessly transforms the collected raw data, organizing it into first, second, and third data sets to provide accurate input for subsequent data analysis and prediction modules. The core mission of this module is to ensure the system can acquire data in real time and stably, providing a reliable basis for subsequent operations such as prediction and adjustment.

[0025] The main function of the illumination prediction module 2 is to predict the illumination conditions based on the combination of the first data group and the second data group, and to generate an illumination prediction coefficient LCF. This module analyzes data such as solar radiation intensity, incident angle, and mirror adjustment angle, and combines the collector temperature and temperature feedback adjustment angle to evaluate the current illumination conditions in real time and predict future illumination change trends. Through data coupling and feature fusion in the deep learning framework, the system can derive the illumination prediction coefficient LCF and determine whether the mirror angle needs to be adjusted in advance based on the preset analysis criteria, thereby avoiding efficiency losses caused by lag. This module significantly improves the response capability of the solar thermal system to rapidly changing illumination conditions, thereby ensuring that the solar collector system receives the maximum amount of illumination and improving the overall efficiency of the system.

[0026] The core task of Temperature Prediction Module 3 is to generate a temperature change prediction coefficient (TCF) based on the coupling of the second and third data sets. This module predicts the collector's temperature trend by analyzing data such as collector temperature, ambient temperature, temperature change rate, heat collection efficiency, and heat loss rate. Based on the difference between the current and target temperatures, it determines whether the mirror angle needs to be adjusted in advance. By analyzing the temperature change rate and feedback adjustment angle, the temperature prediction module effectively addresses the system's lag in responding to temperature changes. This ensures that the system can adjust the collector angle promptly at the initial stage of temperature change, thereby avoiding the adverse effects of temperature fluctuations on system performance and improving heat collection efficiency and system stability.

[0027] The mirror adjustment module 4 is responsible for data coupling based on the first data group and the third data group to generate the mirror positioning coefficient MLC. This module combines information such as solar radiation intensity, incident angle, solar altitude angle, mirror adjustment angle, and heat collection efficiency, and through analysis and calculation, determines in real time whether the mirror angle needs to be adjusted. Through the feature fusion of the deep learning framework, the system can automatically evaluate whether the current mirror position is optimal and determine whether the mirror angle needs to be adjusted in advance to optimize the focus of light and the heat collection effect. This module solves the shortcomings of traditional solar thermal systems that rely on fixed adjustment strategies, making mirror adjustment more intelligent and adaptive, thereby improving heat collection efficiency.

[0028] The thermal collection efficiency detection module 5 couples the first, second, and third data sets to generate a thermal collection performance factor (CPF). This module monitors the system's thermal collection efficiency in real time and, based on the CPF, determines whether a preset angle adjustment will affect the thermal collection effect. When the CPF exceeds a certain value, the system initiates angle adjustment. If the CPF is too low, angle adjustment is delayed to avoid wasting energy. By accurately detecting the system's thermal collection efficiency, this module ensures that the CSP system consistently maintains optimal thermal collection performance under varying light and temperature conditions, effectively preventing efficiency loss due to improper adjustment.

[0029] Feedback Module 6 uses real-time collected data and calculation results to feed information such as sunlight forecasts, temperature forecasts, and thermal efficiency back to the visualization terminal. This allows operators to view the system's operating status in real time, understand the changing trends of various parameters, and make timely adjustments. This module not only provides actionable feedback but also provides an intuitive basis for decision-making through data visualization, helping to optimize system management and maintenance, and improving system reliability and usability.

[0030] Existing solar thermal power generation systems often rely on fixed mirror angle adjustment strategies and are unable to respond to complex changes in light and temperature in a timely manner, resulting in low heat collection efficiency. However, this system, through the collaboration of multiple intelligent modules such as data acquisition module, light prediction, temperature prediction, and mirror adjustment, can accurately adjust the collector angle in real time, maximize light reception efficiency, and optimize the heat collection effect. In addition, the system also uses a heat collection efficiency detection and feedback module to ensure that angle adjustment does not affect the heat collection efficiency, and makes the operation more intelligent and automated. Overall, this joint adjustment method based on temperature self-perception improves the adaptability, heat collection efficiency, and system stability of the solar thermal power generation system, and overcomes the lag and instability in traditional technologies.

[0031] Example 2: Please refer to Figure 1 , the data acquisition module 1 includes a data acquisition unit 11 and a data preprocessing unit 12; The data acquisition unit 11 is used to collect multi-source data for the equipment, including solar radiation intensity, solar altitude angle, solar azimuth angle, incident angle, mirror adjustment angle, ambient temperature, collector temperature, temperature change rate, target temperature, temperature feedback adjustment angle, heat collection efficiency, incident light power, heat loss rate, collector surface temperature and gain adjustment angle; The data preprocessing unit 12 is used to preprocess and dimensionlessly process the collected multi-source data, and group the processed data to generate a first data group, a second data group, and a third data group; The first data set includes solar radiation intensity A, solar altitude angle B, solar azimuth angle C, incident angle D, and mirror adjustment angle E; The second data set includes the ambient temperature F, the collector temperature G, the temperature change rate H, the target temperature I, and the temperature feedback adjustment angle J; The third data group includes the heat collection efficiency K, the incident light power L, the heat loss rate M, the collector surface temperature N, and the gain adjustment angle O.

[0032] In this embodiment, the data acquisition unit 11 collects multi-source data from the device, enabling the system to monitor and collect multiple key parameters in real time, including solar radiation intensity, solar altitude, collector temperature, temperature change rate, and thermal efficiency. This comprehensive data collection allows the system to simultaneously obtain all important information related to factors such as light intensity, temperature, and thermal efficiency. Traditional systems, however, often rely on relatively simple parameters and fail to fully capture all factors that affect system efficiency.

[0033] After data collection, the data preprocessing unit 12 processes and dimensionlessly transforms the raw data. This helps eliminate dimensional differences between the data, allowing all data to be processed using a unified standard. Dimensionless data improves the stability and accuracy of subsequent analysis and avoids calculation errors caused by dimensional differences.

[0034] Through the above improvements, the multi-mirror angle joint adjustment system for heating in the solar thermal power generation system based on temperature self-sensing has been optimized in all aspects of data acquisition, processing and analysis. Compared with traditional solar thermal systems, this system based on real-time multi-source data acquisition and intelligent analysis has significantly improved its responsiveness to changes in light, temperature and thermal collection efficiency. Through modular data grouping, real-time feedback and dimensionless processing, the system can more accurately adjust the mirror angle and collector settings, effectively improving the thermal collection efficiency and system stability. In addition, the system's adaptive ability enables it to maintain efficient operation under different environmental conditions, overcoming the lag and instability in traditional technologies.

[0035] Example 3: Please refer to Figure 1 , the illumination prediction module 2 includes an illumination prediction data coupling unit 21 and an illumination data analysis unit 22; The illumination prediction data coupling unit 21 is used to extract data from the first data group and the second data group, including solar radiation intensity A, incident angle D, mirror adjustment angle E, collector temperature G, and temperature feedback adjustment angle J, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the illumination prediction coefficient LCF; The illumination data analysis unit 22 is used to perform data analysis on the calculated illumination prediction coefficient LCF, and determine whether angle adjustment is required in advance based on the analysis result. The specific method is as follows: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

[0036] In this embodiment, the illumination prediction data coupling unit 21 extracts key data from the first and second data sets, such as solar radiation intensity, incident angle, mirror adjustment angle, collector temperature, and temperature feedback adjustment angle. This data is then fed into a pre-trained deep learning framework for feature fusion within a multi-layer neural network. This data fusion method automatically learns the complex relationships between various factors through a deep learning model, providing more accurate and intelligent illumination predictions.

[0037] The illumination data analysis unit 22 analyzes the calculated illumination prediction coefficient (LCF) and, based on the analysis results, determines whether mirror angle adjustment is necessary. Based on a set threshold, when the LCF value is greater than 0.25, the system automatically determines that the device angle adjustment is necessary to avoid lag. When the LCF value is less than or equal to 0.25, the system determines that no adjustment is necessary.

[0038] By setting a critical value for the Light Prediction Factor (LCF), the system can accurately determine when angle adjustment is necessary, thus preventing hysteresis from impacting heat collection efficiency. An LCF value greater than 0.25 indicates significant light variation, requiring pre-adjustment. A value less than or equal to 0.25 indicates minimal light variation, allowing the system to delay adjustment, thus avoiding frequent and unnecessary adjustments.

[0039] This illumination prediction module 2, through the integration of data coupling and a deep learning framework, effectively addresses the issues of delayed illumination prediction and slow response in traditional CSP systems. Compared to traditional systems, this system significantly improves the accuracy of illumination prediction and the precision of adjustment decisions through multi-source data fusion and real-time analysis, ensuring that the mirror angle can be adjusted in real time according to lighting conditions to maximize heat collection efficiency. This intelligent, automated adjustment method not only improves the system's heat collection efficiency but also enables it to better adapt to environmental changes, ensuring stable operational performance and overcoming the hysteresis issues of traditional CSP systems.

[0040] Example 4: Please refer to Figure 1 The illumination prediction data coupling unit 21 calculates the illumination prediction coefficient LCF using the following formula: ; Where: A is the solar radiation intensity, D is the incident angle, E is the surface adjustment angle, and G is the collector temperature.

[0041] In this embodiment, the formula combines solar radiation intensity A, incident angle D, mirror adjustment angle E, and collector temperature G to form a comprehensive light prediction coefficient (LCF) that considers these multiple factors. The inclusion of incident angle and collector temperature, in particular, more accurately reflects actual light reception and collector operating conditions.

[0042] By adding the mirror adjustment angle E, the system can adjust the collector's mirror angle in real time to optimize the light focusing effect. A reasonable mirror adjustment angle can ensure that the collector is always at the optimal angle, thereby maximizing the light absorption rate.

[0043] By adjusting the ratio of angle J to collector temperature G through temperature feedback, the system can adjust the response of the solar collector system in real time when the collector temperature changes, avoiding unnecessary adjustments caused by temperature changes. This feedback mechanism makes the light prediction coefficient LCF more sensitive, allowing the system to respond quickly to environmental changes.

[0044] By integrating multiple key parameters into the calculation formula for the light prediction coefficient (LCF), the light prediction data coupling unit 21 provides the system with a more accurate and real-time light adjustment strategy. The core advantage of this approach is that it can flexibly adjust the mirror angle and collector state to maximize heat collection efficiency. This avoids the performance losses caused by hysteresis, over-adjustment, or under-adjustment in traditional systems, ensuring efficient operation of the system under various environmental conditions and significantly improving the overall efficiency of the CSP system.

[0045] Example 5: Please refer to Figure 1 , the temperature prediction module 3 includes a temperature prediction data coupling unit 31 and a temperature prediction analysis unit 32; The temperature prediction data coupling unit 31 is used to extract data from the second data group and the second data group, including the collector temperature G, the ambient temperature F, the target temperature I, the heat collection efficiency K, the heat loss rate M, the temperature feedback adjustment angle J, and the temperature change rate H, and input the extracted multiple data into the pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the temperature change prediction coefficient TCF; The temperature prediction and analysis unit 32 is used to analyze the data obtained by calculation and determine whether the angle adjustment needs to be performed in advance based on the analysis results. The specific method is as follows: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

[0046] In this embodiment, the temperature prediction data coupling unit 31 extracts multiple key parameters from the second data set: collector temperature G, ambient temperature F, target temperature I, heat collection efficiency K, heat loss rate M, temperature feedback adjustment angle J, and temperature change rate H. This data is then fed into a pre-trained deep learning framework. By integrating features through a multi-layer neural network, the system is able to process and analyze this complex temperature change data and accurately predict future temperature trends.

[0047] By calculating the temperature change prediction coefficient (TCF), this module quantifies the relationship between temperature changes and factors such as heat collection efficiency and heat loss. By analyzing factors such as collector temperature, ambient temperature, target temperature, and heat collection efficiency, it calculates a real-time TCF value, indicating whether angle adjustment is necessary. When the TCF value exceeds a certain threshold, such as 0.35, the system determines that angle adjustment is necessary in advance to avoid a decrease in heat collection efficiency due to delayed temperature changes.

[0048] The temperature prediction and analysis unit 32 analyzes the calculated temperature change prediction coefficient (TCF) and determines whether the collector angle needs to be adjusted in advance based on the TCF value. When the TCF value is greater than 0.35, the system indicates that angle adjustment is necessary; when the TCF value is less than or equal to 0.35, the system determines that adjustment is not necessary. This allows the system to respond to temperature changes at an early stage, avoiding a decrease in heat collection efficiency due to delayed adjustment.

[0049] Through the innovative design of the temperature prediction module, particularly the introduction of a deep learning framework and the calculation of the temperature change prediction coefficient (TCF), this system significantly improves the temperature regulation capabilities of the CSP system. Compared to traditional CSP systems, which often rely on simpler temperature control strategies and have slower responses, this system analyzes multi-dimensional data such as collector temperature, ambient temperature, and thermal efficiency to rapidly predict temperature changes and make adjustments in advance. This not only improves thermal efficiency but also significantly enhances the system's stability and adaptability, overcoming the lag inherent in traditional technologies.

[0050] Example 6: Please refer to Figure 1 A temperature-controlled mirror tracking angle control system and method for a solar thermal power generation system is provided. The temperature prediction data coupling unit 31 calculates the temperature change prediction coefficient TCF using the following formula: ; Where: G is the collector temperature, F is the ambient temperature, I is the target temperature, K is the collector efficiency, M is the heat loss rate, J is the temperature feedback adjustment angle, and H is the temperature change rate.

[0051] In this embodiment, the formula represents the ratio of the difference between the collector temperature G and the ambient temperature F to the difference between the target temperature I and the ambient temperature F. This relationship helps the system assess in real time how close the current collector temperature is to the target temperature, thereby determining whether advance adjustments are necessary. Based on temperature trends, the system can predict whether the collector has reached the target temperature, thereby optimizing heat collection efficiency.

[0052] This formula combines the heat collection efficiency (K) and the heat loss rate (M). The system achieves optimal heat collection when the heat collection efficiency is high and the heat loss rate is low. This allows the system to adjust its regulation strategy in real time to optimize heat collection efficiency under varying light and temperature conditions, thus avoiding performance degradation caused by excessive heat loss or low heat collection efficiency.

[0053] The formula combines the temperature feedback adjustment angle J and the temperature change rate H. The temperature feedback adjustment angle reflects the difference between the collector temperature and the target temperature, while the temperature change rate indicates how quickly the temperature changes. This term allows for timely adjustment of the collector angle based on the temperature change rate and the feedback adjustment angle, ensuring that the system can quickly respond to temperature changes and maximize heat collection efficiency.

[0054] Example 7: Please refer to Figure 1 , the mirror adjustment module 4 includes a mirror adjustment data coupling unit 41 and a mirror adjustment analysis unit 42; The mirror adjustment data coupling unit 41 is used to extract data from the first data group and the third data, including solar radiation intensity A, incident angle D, solar altitude angle B, mirror adjustment angle E, heat collection efficiency K, heat loss rate M, gain adjustment angle O, and incident light power L, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the temperature change prediction coefficient TCF; The mirror adjustment analysis unit 42 is used to perform data analysis on the calculated mirror positioning coefficient MLC, and determine whether the mirror needs to be adjusted in advance based on the analysis results. The specific method is as follows: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

[0055] In this embodiment, the mirror adjustment data coupling unit 41 extracts multiple key parameters from the first and third data sets, including solar radiation intensity A, incident angle D, solar altitude angle B, mirror adjustment angle E, thermal efficiency K, heat loss rate M, gain adjustment angle O, and incident light power L. This data is then fed into a pre-trained deep learning framework for multi-layer neural network feature fusion. Through this comprehensive analysis, the system accurately calculates the temperature change prediction coefficient (TCF), providing intelligent decision support for subsequent mirror adjustment.

[0056] The mirror adjustment analysis unit 42 is responsible for analyzing the calculated mirror positioning coefficient (MLC). When the MLC is greater than 0.45, it indicates that advance angle adjustment is necessary to avoid lag. When the MLC is less than or equal to 0.45, no advance adjustment is necessary. This analysis allows the system to determine in real time whether mirror angle adjustment is necessary to maximize heat collection efficiency.

[0057] The design of the Mirror Adjustment Module 4, leveraging a deep learning framework and intelligent data analysis, significantly improves the adjustment capabilities and efficiency of the CSP system. Compared to traditional systems, this module not only adjusts the mirror angle in real time but also intelligently determines whether to adjust the angle in advance based on factors such as light intensity, temperature, and heat collection efficiency, thus avoiding lag and energy loss.

[0058] Example 8: Please refer to Figure 1 The mirror adjustment data coupling unit 41 calculates and obtains the mirror positioning coefficient MLC by the following formula: ; Where: A is the solar radiation intensity, D is the incident angle, B is the solar altitude angle, E is the mirror adjustment angle, K is the heat collection efficiency, M is the heat loss rate, O is the gain adjustment angle, and L is the incident light power.

[0059] In this example, the formula combines solar radiation intensity A, incident angle D, solar altitude B, and mirror adjustment angle E. This combination takes into account both the effectiveness of solar radiation reaching the collector surface and the effectiveness of the collector mirror adjustment. By calculating the product of these factors, the system accurately assesses the angular relationship between current lighting conditions and the collector surface, thereby optimizing light focusing and heat collection.

[0060] The combination of the thermal collection efficiency (K) and the heat loss ratio (M) reflects the collector's energy conversion capacity under different operating conditions. When the thermal collection efficiency is high and the heat loss ratio is low, the system can more effectively utilize the collected heat. Using this ratio, the system can assess the collector's performance under current conditions and adjust the mirror angle accordingly to maintain optimal heat collection.

[0061] By comprehensively considering multiple key parameters, the mirror adjustment data coupling unit 41 enables the system to assess mirror adjustment needs in real time, ensuring timely and accurate adjustment of mirror angles under varying lighting conditions. This module utilizes a deep learning framework for real-time calculations and adjustments, enabling the CSP system to rapidly respond to environmental changes and improving the system's adaptability.

[0062] Example 9: Please refer to Figure 1 , the heat collection efficiency detection module 5 includes a heat collection efficiency data coupling unit 51 and a heat collection efficiency analysis unit 52; The heat collection efficiency data coupling unit 51 is used to extract data from the first data group, the second data group, and the third data group, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the heat collection efficiency coefficient CPF; The heat collection efficiency analysis unit 52 is used to perform data analysis on the calculated heat collection efficiency coefficient CPF and, based on the analysis results, determine whether the angle adjustment will affect the heat collection efficiency. The specific method is as follows: when When , it means that the current adjustment of the equipment will not affect the heat collection performance and can be executed; when When , it means that the current adjustment of the equipment will affect the heat collection performance, causing the first level of heat collection attenuation, and the execution needs to be delayed by 0.5 seconds; when When the device is adjusted, it means that the current adjustment will affect the heat collection performance, causing secondary heat collection attenuation, and the execution needs to be delayed by 1.5 seconds; when When , it means that the current adjustment of the equipment will affect the heat collection performance, causing the third level heat collection to attenuate and cannot be executed.

[0063] In this embodiment, the thermal collection efficiency data coupling unit 51 extracts multiple data points from the first, second, and third data groups, inputs the extracted parameters into a pre-trained deep learning framework, and uses a multi-layer neural network to perform feature fusion to calculate the thermal collection efficiency factor (CPF). This deep learning method not only automatically learns complex relationships from the data but also accurately predicts thermal collection efficiency under constantly changing environmental conditions.

[0064] The heat collection efficiency analysis unit 52 is responsible for analyzing the calculated heat collection performance factor (CPF) and determining whether to perform angle adjustment based on the analysis results. Through a hierarchical management of CPF values, when the CPF value is greater than or equal to 1, the current adjustment will not affect heat collection efficiency and can be executed immediately. When the CPF value is between 0.9 and 1, the system delays the adjustment by 0.5 seconds. When the CPF value is between 0.75 and 0.9, it causes a first-level heat collection degradation, with a delay of 1.5 seconds. When the CPF value is less than 0.75, the system determines that the adjustment will have a significant impact on heat collection efficiency and therefore does not perform angle adjustment.

[0065] The system effectively avoids over- and under-regulation by delaying regulation based on the different CPF ranges. For example, when the CPF value is low (less than 0.75), the system will not perform regulation, avoiding unnecessary energy waste. However, when the CPF value is high (greater than 1), the system will immediately perform regulation to ensure optimal heat collection.

[0066] By introducing the thermal collection efficiency detection module 5, the system not only achieves real-time calculation and monitoring of thermal collection efficiency, but also can intelligently determine whether the collector angle needs to be adjusted through deep learning algorithms and thermal collection efficiency coefficient (CPF) analysis. This mechanism significantly improves the response speed and adaptability of the solar thermal power generation system, enabling the system to dynamically adjust the thermal collection efficiency under complex environmental conditions, avoiding energy waste caused by over- or under-regulation. Compared with traditional solar thermal systems, this system can monitor thermal collection efficiency in real time and make intelligent decisions, ensuring that the system always maintains the highest thermal collection efficiency under different lighting and temperature conditions, thereby improving overall efficiency and system stability.

[0067] Example 10: Please refer to Figure 1 The heat collection efficiency data coupling unit 51 calculates the heat collection efficiency coefficient CPF using the following formula: ; Where: A is the solar radiation intensity, B is the solar altitude angle, C is the solar azimuth angle, D is the incident angle, E is the mirror adjustment angle, F is the ambient temperature, G is the collector temperature, H is the temperature change rate, I is the target temperature, J is the temperature feedback adjustment angle, K is the thermal efficiency, L is the incident light power, M is the heat loss rate, N is the collector surface temperature, and O is the gain adjustment angle.

[0068] In this example, the effects of solar radiation intensity A, incident angle D, solar altitude B, and mirror adjustment angle E on heat collection efficiency are reflected. This comprehensive formula allows the system to calculate the optimal combination of current light intensity and heat collection angle in real time, ensuring the collector operates under optimal lighting conditions.

[0069] The temperature feedback adjustment angle J and the temperature change rate H are combined, while considering the difference between the collector temperature G and the ambient temperature F. Through this part, the system can adjust according to the difference between the collector temperature and the target temperature and respond to temperature changes in a timely manner.

[0070] The combination of the heat collection efficiency K and the heat loss rate M ensures that heat loss can be minimized and the heat collection efficiency can be improved when the heat collection system is working. When the heat loss rate is low, the system can more efficiently convert light heat into actual heat energy. The relationship between the incident light power L and the collector surface temperature N is taken into account, and the gain adjustment angle O is introduced. The gain adjustment angle affects the focusing effect of the mirror, while the incident light power determines the actual light intensity. Through the combination of these two parameters, the system can adjust the angle of the collector and the heat collection efficiency in time when the lighting conditions change.

[0071] A method for joint adjustment of multi-mirror angles for heating in a solar thermal power generation system based on temperature self-sensing. Figure 2 , the specific steps are as follows: S1. Collect multi-source data from the device through the data acquisition module 1, pre-process the collected parameters, and then reorganize them into a first data group, a second data group, and a third data group; S2. The illumination prediction module 2 couples the first data group and the second data group to generate an illumination prediction coefficient LCF, analyzes the LCF, and determines whether angle adjustment is required in advance based on the analysis result. S3, coupling the second data group and the third data group through the temperature prediction module 3 to generate a temperature change prediction coefficient TCF, and analyzing the coefficient TCF. Based on the analysis results, it is determined whether the angle adjustment needs to be performed in advance; S4, coupling the first data and the third data group through the mirror adjustment module 4 to generate a mirror positioning coefficient MLC, analyzing the MLC, and determining whether an angle adjustment is required in advance based on the analysis result; S5. The heat collection efficiency detection module 5 couples the first data set, the second data set, and the third data set to generate a heat collection efficiency coefficient (CPF), and analyzes the CPF to determine whether the pre-performed angle adjustment affects the heat collection efficiency. S6. Feedback various data to the visualization terminal through the feedback module 6.

[0072] In addition, the functional units in the various embodiments of the present application 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. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0073] The above detailed description of the specific embodiments of the invention is intended only as an example, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions of the invention are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A temperature-controlled mirror tracking angle control system for a solar thermal power generation system, characterized by: It includes a data acquisition module (1), an illumination prediction module (2), a temperature prediction module (3), a mirror adjustment module (4), a heat collection efficiency detection module (5), and a feedback module (6); The data acquisition module (1) is used to collect multi-source data from the device, and pre-process the collected parameters, and then reorganize them into a first data group, a second data group, and a third data group; The illumination prediction module (2) is used to perform data coupling on the first data group and the second data group, generate an illumination prediction coefficient LCF, analyze the coefficient LCF, and determine whether angle adjustment needs to be performed in advance based on the analysis result; The temperature prediction module (3) is used to perform data coupling on the second data group and the third data group, generate a temperature change prediction coefficient TCF, analyze the coefficient, and determine whether angle adjustment is required in advance based on the analysis result; The mirror adjustment module (4) is used to couple the first data and the third data group, generate a mirror positioning coefficient MLC, analyze the coefficient MLC, and determine whether it is necessary to perform angle adjustment in advance based on the analysis result; The heat collection efficiency detection module (5) is used to perform data coupling on the first data group, the second data group and the third data group to generate a heat collection efficiency coefficient CPF, and analyze the generated heat collection efficiency coefficient CPF to determine whether the pre-performed angle adjustment will affect the heat collection efficiency; The feedback module (6) is used to feed back various data to the visualization terminal.

2. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 1 is characterized in that: The data acquisition module (1) comprises a data acquisition unit (11) and a data preprocessing unit (12); The data acquisition unit (11) is used to collect multi-source data for the device, including solar radiation intensity, solar altitude angle, solar azimuth angle, incident angle, mirror adjustment angle, ambient temperature, collector temperature, temperature change rate, target temperature, temperature feedback adjustment angle, heat collection efficiency, incident light power, heat loss rate, collector surface temperature and gain adjustment angle; The data preprocessing unit (12) is used to preprocess and dimensionlessly process the collected multi-source data, and group the processed data to generate a first data group, a second data group, and a third data group; The first data set includes solar radiation intensity A, solar altitude angle B, solar azimuth angle C, incident angle D, and mirror adjustment angle E; The second data set includes the ambient temperature F, the collector temperature G, the temperature change rate H, the target temperature I, and the temperature feedback adjustment angle J; The third data group includes the heat collection efficiency K, the incident light power L, the heat loss rate M, the collector surface temperature N, and the gain adjustment angle O.

3. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 2 is characterized in that: The illumination prediction module (2) includes an illumination prediction data coupling unit (21) and an illumination data analysis unit (22); The illumination prediction data coupling unit (21) is used to extract data from the first data group and the second data group, including solar radiation intensity A, incident angle D, mirror adjustment angle E, collector temperature G, and temperature feedback adjustment angle J, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the illumination prediction coefficient LCF; The illumination data analysis unit (22) is used to perform data analysis on the calculated illumination prediction coefficient LCF, and to determine whether angle adjustment is required in advance based on the analysis result, in the following specific manner: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

4. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 3 is characterized in that: The illumination prediction data coupling unit (21) calculates and obtains the illumination prediction coefficient LCF by the following formula: ； Middle: A is the solar radiation intensity, D is the incident angle, E is the surface adjustment angle, and G is the collector temperature.

5. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 4 is characterized in that: The temperature prediction module (3) includes a temperature prediction data coupling unit (31) and a temperature prediction analysis unit (32); The temperature prediction data coupling unit (31) is used to extract data from the second data group and the second data group, including the collector temperature G, the ambient temperature F, the target temperature I, the heat collection efficiency K, the heat loss rate M, the temperature feedback adjustment angle J and the temperature change rate H, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the temperature change prediction coefficient TCF; The temperature prediction and analysis unit (32) is used to analyze the data obtained by calculation and, based on the analysis results, determine whether angle adjustment needs to be performed in advance. The specific method is as follows: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

6. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 5 is characterized in that: The temperature prediction data coupling unit (31) calculates and obtains the temperature change prediction coefficient TCF by the following formula: ； Where: G is the collector temperature, F is the ambient temperature, I is the target temperature, K is the collector efficiency, M is the heat loss rate, J is the temperature feedback adjustment angle, and H is the temperature change rate.

7. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 6 is characterized in that: The mirror adjustment module (4) comprises a mirror adjustment data coupling unit (41) and a mirror adjustment analysis unit (42); The mirror adjustment data coupling unit (41) is used to extract data from the first data group and the third data, including solar radiation intensity A, incident angle D, solar altitude angle B, mirror adjustment angle E, heat collection efficiency K, heat loss rate M, gain adjustment angle O, and incident light power L, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain a temperature change prediction coefficient TCF; The mirror adjustment analysis unit (42) is used to perform data analysis on the calculated mirror positioning coefficient MLC, and judge whether the mirror needs to be adjusted in advance based on the analysis result, specifically in the following manner: when When , it means that the device needs to be adjusted to avoid lag. when , it means that there is no need to adjust the angle of the device to avoid lag.

8. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 7 is characterized in that: The mirror adjustment data coupling unit (41) calculates and obtains the mirror positioning coefficient MLC by the following formula: ； Where: A is the solar radiation intensity, D is the incident angle, B is the solar altitude angle, E is the mirror adjustment angle, K is the heat collection efficiency, M is the heat loss rate, O is the gain adjustment angle, and L is the incident light power.

9. The multi-mirror angle joint adjustment system for heating of a solar thermal power generation system based on temperature self-sensing according to claim 8 is characterized in that: The heat collection efficiency detection module (5) comprises a heat collection efficiency data coupling unit (51) and a heat collection efficiency analysis unit (52); The heat collection efficiency data coupling unit (51) is used to extract data from the first data group, the second data group, and the third data group, and input the extracted multiple data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate and obtain the heat collection efficiency coefficient CPF; The heat collection efficiency analysis unit (52) is used to perform data analysis on the heat collection efficiency coefficient CPF obtained by calculation, and to determine whether the angle adjustment will affect the heat collection efficiency based on the analysis results, in the following specific manner: when When , it means that the current adjustment of the equipment will not affect the heat collection performance and can be executed; when When , it means that the current adjustment of the equipment will affect the heat collection performance, causing the first level of heat collection attenuation, and the execution needs to be delayed by 0.5 seconds; when When the device is adjusted, it means that the current adjustment will affect the heat collection performance, causing secondary heat collection attenuation, and the execution needs to be delayed by 1.5 seconds; when When , it means that the current adjustment of the equipment will affect the heat collection performance, causing the third level heat collection to be attenuated and unable to be executed; The heat collection efficiency data coupling unit (51) calculates and obtains the heat collection efficiency coefficient CPF by the following formula: ； Where: A is the solar radiation intensity, B is the solar altitude angle, C is the solar azimuth angle, D is the incident angle, E is the mirror adjustment angle, F is the ambient temperature, G is the collector temperature, H is the temperature change rate, I is the target temperature, J is the temperature feedback adjustment angle, K is the thermal efficiency, L is the incident light power, M is the heat loss rate, N is the collector surface temperature, and O is the gain adjustment angle.

10. A method for jointly adjusting the angles of multiple mirrors for heating in a solar thermal power generation system based on temperature self-sensing, characterized by: The method for jointly adjusting the angles of multiple mirrors for heating in a solar thermal power generation system based on temperature self-sensing is performed by the method for jointly adjusting the angles of multiple mirrors for heating in a solar thermal power generation system based on temperature self-sensing according to any one of claims 1 to 9, and the specific steps are as follows: S1, collecting multi-source data from the device through the data collection module (1), pre-processing the collected parameters, and then reorganizing them into a first data group, a second data group, and a third data group; S2, coupling the first data group and the second data group through the illumination prediction module (2), generating an illumination prediction coefficient LCF, analyzing the coefficient, and judging whether angle adjustment is required in advance based on the analysis result; S3, coupling the second data group and the third data group through the temperature prediction module (3), generating a temperature change prediction coefficient TCF, analyzing the coefficient, and judging whether the angle adjustment needs to be performed in advance based on the analysis result; S4, coupling the first data and the third data group through the mirror adjustment module (4), generating a mirror positioning coefficient MLC, analyzing the mirror positioning coefficient MLC, and judging whether it is necessary to perform angle adjustment in advance based on the analysis result; S5, coupling the first data group, the second data group, and the third data group through the heat collection efficiency detection module (5), generating a heat collection efficiency coefficient CPF, and analyzing the CPF to determine whether the pre-performed angle adjustment will affect the heat collection efficiency; S6. Feedback various data to the visualization terminal through the feedback module (6).

Images