Photothermal comprehensive utilization system based on artificial intelligence

Abstract

The invention discloses a photo-thermal comprehensive utilization system based on artificial intelligence, which relates to the technical field of photo-thermal utilization and comprises a mode division unit, an energy analysis unit, a model construction unit and an energy prediction unit. The mode division unit divides the power generation modes into three modes according to the solar radiation intensity, the three modes are the sunshine sufficient mode, the sunshine insufficient mode and the sunshine lack mode, redundant energy is stored on the premise that normal operation of power generation equipment is guaranteed, the photo-thermal utilization rate is increased, and the power generation efficiency is improved. Meanwhile, the energy analysis unit combines the air pressure value, the temperature value, the humidity value, the wind speed value, the receiver parameter value, the solar altitude angle, the azimuth angle and the radiation intensity with the actual energy value, so that a correlation function is determined, and a subsequent LSTM prediction model can conveniently analyze the corresponding radiation intensity according to the meteorological data; the power generation mode of the photo-thermal power station is determined through the radiation intensity, the photo-thermal power station can be set in advance, and the overall operation efficiency of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of solar thermal utilization, and specifically to a solar thermal comprehensive utilization system based on artificial intelligence. Background Art

[0002] The solar thermal comprehensive utilization system can collect all the energy in the solar radiation spectrum, convert it into utilizable heat energy, and through optimized design and control strategies, this system can maximize the energy utilization efficiency and reduce energy waste. In the invention patent with the application number 202411408335.7, "A photovoltaic-thermal comprehensive utilization system optimized based on a tower-type solar thermal power station" is disclosed, belonging to the field of power generation technology. In the present invention, by optimizing the structure of the concentrating tower, the traditional scheme of directly concentrating sunlight from the mirror field to the heat receiver is optimized into a two-stage reflection design, that is: the mirror field serves as the first-stage reflection, and the position where the frequency-dividing film is located is the second-stage reflection, and the photovoltaic cells and the frequency-dividing film are placed at the second-stage reflection position. A frequency-dividing film is plated on the surface of the photovoltaic cell panel to improve the transmission and absorption of the high-quality energy band of visible light while maintaining a certain degree of reflection of visible light and low-quality infrared light to ensure the normal operation of the concentrating solar thermal system, complete the spatial separation of high-quality visible light photon energy and low-quality near-infrared photon energy, thereby realizing the frequency-division utilization of solar energy, and realizing the utilization of solar energy through the combination of photovoltaic and solar thermal systems to improve the power generation efficiency.

[0003] The above-mentioned prior art solves problems such as the too low photoelectric conversion efficiency of photovoltaic cells under large incident angle conditions. However, during the operation of the system, since the power generation mode is not divided, there may be an unreasonable situation in the energy distribution under different sunshine conditions, and this system cannot predict the solar radiation intensity in advance, resulting in the conversion between modes not being able to be executed in advance, thus affecting the overall operation efficiency of the system. Summary of the Invention

[0004] The purpose of the present invention is to provide a solar thermal comprehensive utilization system based on artificial intelligence to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A solar thermal comprehensive utilization system based on artificial intelligence, including an energy prediction unit;

[0006] A mode division unit that divides the power generation mode into three types according to the solar radiation intensity, namely, sufficient sunlight mode, insufficient sunlight mode, and lack of sunlight mode. If the solar radiation intensity value is higher than the first preset value, it is determined that the current power generation mode is the sufficient sunlight mode. After collecting the energy generated by sunlight radiation through the concentrating and heat-collecting device, the energy in the heat-collecting device is extracted according to the minimum energy value, and is transmitted to the generator set for power supply, and the remaining energy is transmitted to the heat storage tank for storage. If the solar radiation intensity is lower than or equal to the first preset value and higher than the second preset value, it is determined that the current power generation mode is the insufficient sunlight mode, and energy storage is stopped. The collected energy and the energy in the heat storage tank are directly transmitted to the steam generator to generate high-temperature steam using the received energy, and are transmitted to the generator set for power supply. If the solar radiation intensity is lower than or equal to the second preset value, it is determined that the current power generation mode is the lack of sunlight mode, the concentrating and heat-collecting device is closed, energy storage is stopped, and the energy in the heat storage tank is transmitted to the generator set for power supply;

[0007] An energy analysis unit that, after determining the solar radiation intensity, optical efficiency, total number of heliostats, and area in the heliostat field, calculates the incident energy value and the energy value actually collected by the receiver of the heat-collecting device, combines the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity with the actual energy value to determine the correlation function, and statistics the energy storage power, energy release power, medium heat preservation coefficient, and the heat storage capacity value in the previous moment in the heat storage tank. The energy loss value of the current heat storage tank is calculated according to the energy storage power, energy release power, medium heat preservation coefficient, and the heat storage capacity value in the previous moment;

[0008] A model construction unit that determines the conditional function corresponding to each power generation mode, constructs a mirror field model using MATLAB software, completes the construction of the receiver model in combination with the correlation function, analyzes the energy storage power, energy release power of the heat storage tank, and the energy loss value of the heat storage tank at each moment, obtains the heat storage tank model, adds the generator model and the conditional function corresponding to each power generation mode, thereby constructing a complete solar thermal model.

[0009] Preferably, the mode division unit includes a preset value setting module and a sufficient sunlight operation module. The preset value setting module divides the power generation mode into three types according to the solar radiation intensity, namely, sufficient sunlight mode, insufficient sunlight mode, and lack of sunlight mode, sets a first preset value and a second preset value, and the first preset value is greater than the second preset value. If the solar radiation intensity value is higher than the first preset value, the sufficient sunlight operation module determines that the current power generation mode is the sufficient sunlight mode, determines the power generation power, sets the minimum energy value according to the power generation power, collects the energy generated by the sunlight radiation through the concentrating heat collection device, extracts the energy in the heat collection device according to the minimum energy value, generates high-temperature steam by using the extracted energy, transmits it to the generator set for power supply, and transmits the remaining energy to the heat storage tank for storage.

[0010] Preferably, the mode division unit further includes an insufficient sunlight operation module and a lack of sunlight operation module. If the solar radiation intensity is less than or equal to the first preset value and higher than the second preset value, the insufficient sunlight operation module determines that the current power generation mode is the insufficient sunlight mode, stops energy storage, collects energy by using the concentrating heat collection device, directly transmits the energy to the steam generator, determines the difference between the minimum energy value and the energy transmitted this time, extracts the energy in the heat storage tank according to the difference, transmits it to the steam generator, and the steam generator generates high-temperature steam by using the received energy and transmits it to the generator set for power supply. If the solar radiation intensity is less than or equal to the second preset value, the lack of sunlight operation module determines that the current power generation mode is the lack of sunlight mode, closes the concentrating heat collection device, stops energy storage, transmits the energy in the heat storage tank to the steam generator, generates high-temperature steam by using the received energy, and transmits it to the generator set for power supply.

[0011] Preferably, the energy analysis unit includes an incident energy determination module and a correlation function output module. The incident energy determination module determines the solar radiation intensity D, optical efficiency η, total number of heliostats n, and area S in the heliostat field, and calculates the incident energy value Q according to the solar radiation intensity D, optical efficiency η, total number of heliostats n, and area S z , where Q z = D·η·S·n. The correlation function output module determines the loss energy value Q loss , and calculates the energy value Q z actually collected by the receiver of the heat collection device according to the incident energy value Q loss and the loss energy value Q s , where Q s = Q z - Q loss, after obtaining the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity, combine the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity with the actual energy value to determine the correlation function.

[0012] Preferably, the energy analysis unit further includes an energy loss calculation module, and the energy loss calculation module counts the energy storage power P in the heat storage tank t c , the energy release power P t f , the medium heat preservation coefficient ε, and the heat storage capacity value O within the previous moment t-1 , according to the energy storage power P t c , the energy release power P t c , the medium heat preservation coefficient ε, and the heat storage capacity value O within the previous moment t-1 calculate the energy loss value O of the current heat storage tank t , where O t = ε·O t-1 + (P t c - P t f )·Δt, and Δt is the time interval value.

[0013] Preferably, the model construction unit includes a conditional function generation module, a component model analysis module, and a component merging module. After the conditional function generation module determines the heat preservation coefficient of the heat storage tank, it calculates the conditional function corresponding to each power generation mode according to different power generation modes, the correlation function, the energy loss value of the heat storage tank, the energy storage power, and the energy release power. The component model analysis module uses MATLAB software to construct a mirror field model based on the incident energy value, solar radiation intensity, optical efficiency, total number of heliostats, and area in the heliostat field, completes the construction of the receiver model in combination with the correlation function, analyzes the energy storage power, energy release power of the heat storage tank, and the energy loss value of the heat storage tank at each moment to obtain the heat storage tank model. The component merging module combines the mirror field model, the receiver model, and the heat storage tank model, and then adds the generator model and the conditional function corresponding to each power generation mode to construct a complete solar thermal model.

[0014] Preferably, the energy prediction unit includes a historical data receiving module and a model parameter determination module. The historical data receiving module receives the historical meteorological data and historical radiation data of the solar thermal power station. The historical meteorological data includes historical solar altitude angle, historical solar azimuth angle, historical air pressure value, historical temperature value, historical humidity value, and historical wind speed value. The historical radiation data is specifically the historical solar radiation intensity. The model parameter determination module constructs a training set and a test set using the historical meteorological data and historical radiation data, transmits the data in the training set to the LSTM prediction model to complete the training of the LSTM prediction model, and calculates the error value corresponding to each parameter using a parameter analysis algorithm. Then, the data in the test set is transmitted to the LSTM prediction model to determine the parameters of the LSTM prediction model. The parameter analysis algorithm is specifically as follows:

[0015]

[0016] Among them, G(i) represents the error value of the i-th parameter, and y(i) represents the predicted value of the i-th parameter. represents the actual value corresponding to the data in the training set, m represents the number of data in the training set, and i represents the parameter number.

[0017] Preferably, the energy prediction unit further includes a radiation intensity analysis module and an energy output module. The radiation intensity analysis module determines the solar altitude angle, solar azimuth angle, air pressure value, temperature value, humidity value, and wind speed value of the current solar thermal power station, transmits them to the LSTM prediction model for analysis, and obtains the predicted solar radiation intensity value. The energy output module transmits the predicted solar radiation intensity value to the solar thermal model, and determines the power generation mode and incident energy value of the current solar thermal power station according to the solar altitude angle, solar azimuth angle, air pressure value, temperature value, humidity value, wind speed value, and solar radiation intensity value of the current solar thermal power station.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0019] The present invention divides the power generation mode into three types according to the solar radiation intensity through the mode division unit, namely the sufficient sunshine mode, the insufficient sunshine mode, and the lack of sunshine mode, stores the excess energy on the premise of ensuring the normal operation of the power generation equipment, improves the utilization rate of solar heat. At the same time, the energy analysis unit combines the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity with the actual energy value to determine the correlation function, which facilitates the subsequent LSTM prediction model to analyze the corresponding radiation intensity according to the meteorological data, determines the power generation mode of the solar thermal power station through the radiation intensity, ensures that the solar thermal power station can be pre-set, improves the overall operation efficiency of the system, and enables the reception and use of energy to be more reasonable and effective. Brief Description of the Drawings

[0020] Figure 1 This is a schematic diagram of the overall system process provided by an embodiment of the present invention;

[0021] Figure 2 This is an internal module block diagram of the mode division unit provided by an embodiment of the present invention;

[0022] Figure 3 This is an internal module block diagram of the energy analysis unit provided by an embodiment of the present invention;

[0023] Figure 4 This is an internal module block diagram of the model construction unit provided by an embodiment of the present invention;

[0024] Figure 5 This is an internal module block diagram of the energy prediction unit provided by an embodiment of the present invention.

[0025] In the figure: 1. Mode division unit; 101. Preset value setting module; 102. Sufficient sunlight operation module; 103. Insufficient sunlight operation module; 104. Lack of sunlight operation module; 2. Energy analysis unit; 201. Incident energy determination module; 202. Correlation function output module; 203. Energy loss calculation module; 3. Model construction unit; 301. Condition function generation module; 302. Component model analysis module; 303. Component merging module; 4. Energy prediction unit; 401. Historical data receiving module; 402. Model parameter determination module; 403. Radiation intensity analysis module; 404. Energy output module. Specific implementation manners

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] Please refer to Figures 1-5 , the present invention provides a technical solution: a solar thermal comprehensive utilization system based on artificial intelligence, including an energy prediction unit 4;

[0028] The mode division unit 1 divides the power generation mode into three types according to the solar radiation intensity, namely, the sufficient sunshine mode, the insufficient sunshine mode, and the lack of sunshine mode. If the solar radiation intensity value is higher than the first preset value, it is determined that the current power generation mode is the sufficient sunshine mode. After collecting the energy generated by solar radiation through the concentrating heat collection device, the energy in the heat collection device is extracted according to the minimum energy value, and then transmitted to the generator set for power supply, and the remaining energy is transmitted to the heat storage tank for storage. If the solar radiation intensity is lower than or equal to the first preset value and higher than the second preset value, it is determined that the current power generation mode is the insufficient sunshine mode. The energy storage is stopped, and the collected energy and the energy in the heat storage tank are directly transmitted to the steam generator to generate high-temperature steam by using the received energy, and then transmitted to the generator set for power supply. If the solar radiation intensity is lower than or equal to the second preset value, it is determined that the current power generation mode is the lack of sunshine mode. The concentrating heat collection device is closed, the energy storage is stopped, and the energy in the heat storage tank is transmitted to the generator set for power supply;

[0029] The energy analysis unit 2 determines the solar radiation intensity, optical efficiency, total number of heliostats, and area in the heliostat field, and then calculates the incident energy value and the energy value actually collected by the receiver of the heat collection device. The air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity are combined with the actual energy value to determine the correlation function. The energy storage power, energy release power, medium heat preservation coefficient, and the heat storage capacity value in the previous moment in the heat storage tank are statistically analyzed, and the energy loss value of the current heat storage tank is calculated according to the energy storage power, energy release power, medium heat preservation coefficient, and the heat storage capacity value in the previous moment;

[0030] The model construction unit 3 determines the conditional function corresponding to each power generation mode, constructs the mirror field model by using MATLAB software, completes the construction of the receiver model in combination with the correlation function, analyzes the energy storage power, energy release power of the heat storage tank, and the energy loss value of the heat storage tank at each moment, obtains the heat storage tank model, adds the generator model and the conditional function corresponding to each power generation mode, so as to construct a complete solar thermal model.

[0031] The mode division unit 1 includes a preset value setting module 101 and a sufficient sunlight operation module 102. The preset value setting module 101 divides the power generation mode into three types according to the solar radiation intensity, namely the sufficient sunlight mode, the insufficient sunlight mode, and the lack of sunlight mode. The first preset value and the second preset value are set, and the first preset value is greater than the second preset value. If the solar radiation intensity value is higher than the first preset value, the sufficient sunlight operation module 102 determines that the current power generation mode is the sufficient sunlight mode, determines the power generation power, and sets the minimum energy value according to the power generation power. After collecting the energy generated by the sunlight radiation through the concentrating and heat collecting device, the energy in the heat collecting device is extracted according to the minimum energy value, and the extracted energy is used to generate high-temperature steam, which is transmitted to the generator set for power supply, and the remaining energy is transmitted to the heat storage tank for storage;

[0032] The mode division unit 1 further includes an insufficient sunlight operation module 103 and a lack of sunlight operation module 104. If the solar radiation intensity is lower than or equal to the first preset value and higher than the second preset value, the insufficient sunlight operation module 103 determines that the current power generation mode is the insufficient sunlight mode, stops energy storage, and directly transmits the energy to the steam generator after collecting the energy by the concentrating and heat collecting device. After determining the difference between the minimum energy value and the energy transmitted this time, the energy in the heat storage tank is extracted according to the difference and transmitted to the steam generator. The steam generator uses the received energy to generate high-temperature steam and transmits it to the generator set for power supply. If the solar radiation intensity is lower than or equal to the second preset value, the lack of sunlight operation module 104 determines that the current power generation mode is the lack of sunlight mode, closes the concentrating and heat collecting device, stops energy storage, transmits the energy in the heat storage tank to the steam generator, uses the received energy to generate high-temperature steam, and transmits it to the generator set for power supply;

[0033] The energy analysis unit 2 includes an incident energy determination module 201 and a correlation function output module 202. The incident energy determination module 201 determines the solar radiation intensity D, the optical efficiency η, the total number of heliostats n, and the area S in the heliostat field, and calculates the incident energy value Q based on the solar radiation intensity D, the optical efficiency η, the total number of heliostats n, and the area S z , where Q z = D·η·S·n. The correlation function output module 202 determines the loss energy value Q loss , and calculates the energy value Q z actually collected by the receiver of the heat collecting device according to the incident energy value Q loss and the loss energy value Q s , where Q s = Q z - Q loss, after obtaining the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity, combine the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity with the actual energy value to determine the correlation function;

[0034] The energy analysis unit 2 further includes an energy loss calculation module 203. The energy loss calculation module 203 counts the energy storage power P in the heat storage tank t c , the energy release power P t f , the medium heat preservation coefficient ε, and the heat storage capacity value O in the previous moment t-1 , according to the energy storage power P t c , the energy release power P t c , the medium heat preservation coefficient ε, and the heat storage capacity value O in the previous moment t-1 calculate the energy loss value O of the current heat storage tank t , where O t = ε·O t-1 +(P t c -P t f )·Δt, where Δt is the time interval value;

[0035] The model construction unit 3 includes a conditional function generation module 301, a component model analysis module 302, and a component merging module 303. After the conditional function generation module 301 determines the heat preservation coefficient of the heat storage tank, it calculates the conditional function corresponding to each power generation mode according to different power generation modes, the correlation function, the energy loss value of the heat storage tank, the energy storage power, and the energy release power. The component model analysis module 302 uses MATLAB software to construct a mirror field model based on the incident energy value, solar radiation intensity, optical efficiency, total number of heliostats, and area in the heliostat field, completes the construction of the receiver model in combination with the correlation function, analyzes the energy storage power, energy release power of the heat storage tank, and the energy loss value of the heat storage tank at each moment to obtain the heat storage tank model. The component merging module 303 combines the mirror field model, the receiver model, and the heat storage tank model, and then adds the generator model and the conditional function corresponding to each power generation mode to construct a complete solar thermal model;

[0036] The energy prediction unit 4 includes a historical data receiving module 401 and a model parameter determination module 402. The historical data receiving module 401 receives the historical meteorological data and historical radiation data of the solar thermal power station. The historical meteorological data includes the historical solar altitude angle, historical solar azimuth angle, historical air pressure value, historical temperature value, historical humidity value, and historical wind speed value. The historical radiation data is specifically the historical solar radiation intensity. The model parameter determination module 402 constructs a training set and a test set using the historical meteorological data and historical radiation data, transmits the data in the training set to the LSTM prediction model to complete the training of the LSTM prediction model, and calculates the error value corresponding to each parameter using a parameter analysis algorithm. Then, it transmits the data in the test set to the LSTM prediction model to determine the LSTM prediction model parameters. The parameter analysis algorithm is specifically as follows:

[0037]

[0038] Among them, G(i) represents the error value of the i-th parameter, and y(i) represents the predicted value of the i-th parameter. represents the actual value corresponding to the data in the training set, m represents the number of data in the training set, and i represents the parameter number;

[0039] The energy prediction unit 4 further includes a radiation intensity analysis module 403 and an energy output module 404. The radiation intensity analysis module 403 determines the solar altitude angle, solar azimuth angle, air pressure value, temperature value, humidity value, and wind speed value of the current solar thermal power station, transmits them to the LSTM prediction model for analysis, and obtains the predicted solar radiation intensity value. The energy output module 404 transmits the predicted solar radiation intensity value to the solar thermal model, and determines the power generation mode and incident energy value of the current solar thermal power station according to the solar altitude angle, solar azimuth angle, air pressure value, temperature value, humidity value, wind speed value, and solar radiation intensity value of the current solar thermal power station.

[0040] Working principle: In the present invention, the preset value setting module 101 in the mode division unit 1 divides the power generation mode into three types according to the solar radiation intensity, namely, sufficient sunlight mode, insufficient sunlight mode, and lack of sunlight mode. The sufficient sunlight operation module 102, insufficient sunlight operation module 103, and lack of sunlight operation module 104 are used to determine the execution processes in the sufficient sunlight mode, insufficient sunlight mode, and lack of sunlight mode. The incident energy determination module 201 in the energy analysis unit 2 calculates the incident energy value. The correlation function output module 202 combines the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle, and radiation intensity with the actual energy value to determine the correlation function. The energy loss calculation module 203 calculates the energy loss value of the current heat storage tank. The condition function generation module 301 in the model construction unit 3 calculates the condition function corresponding to each power generation mode. The component model analysis module 302 constructs the mirror field model, receiver model, and heat storage tank model. After the component combination module 303 combines the mirror field model, receiver model, and heat storage tank model, a complete solar thermal model is constructed. The historical data receiving module 401 in the energy prediction unit 4 receives the historical meteorological data and historical radiation data of the solar thermal power station. The model parameter determination module 402 completes the training of the LSTM prediction model. The radiation intensity analysis module 403 obtains the predicted solar radiation intensity value. The energy output module 404 determines the power generation mode and incident energy value of the current solar thermal power station.

[0041] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0042] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A light-heat comprehensive utilization system based on artificial intelligence, comprising an energy prediction unit (4), characterized in that: A mode division unit (1), wherein the mode division unit (1) divides the power generation mode into three types according to the solar radiation intensity, namely, a sufficient sunlight mode, an insufficient sunlight mode and a lack of sunlight mode. If the solar radiation intensity value is higher than a first preset value, the current power generation mode is determined to be a sufficient sunlight mode. After collecting the energy generated by the solar radiation through the concentrating and collecting device, the energy in the collecting device is extracted according to the minimum energy value and transmitted to the generator set for power supply. The remaining energy is transmitted to the heat storage tank for storage. If the solar radiation intensity is lower than or equal to the first preset value and higher than a second preset value, the current power generation mode is determined to be a lack of sunlight mode, energy storage is stopped, the collected energy and the energy in the heat storage tank are directly transmitted to the steam generator, high-temperature steam is generated by the received energy, and is transmitted to the generator set for power supply. If the solar radiation intensity is lower than or equal to the second preset value, the current power generation mode is determined to be a lack of sunlight mode, the concentrating and collecting device is turned off, energy storage is stopped, and the energy in the heat storage tank is transmitted to the generator set for power supply. An energy analysis unit (2), wherein the energy analysis unit (2) determines the solar radiation intensity, optical efficiency, total number and area of ​​heliostats in the heliostat field, calculates the incident energy value and the energy value actually collected by the receiver of the heat collection device, combines the air pressure value, temperature value, humidity value, wind speed value, receiver parameter value, solar altitude angle, azimuth angle and radiation intensity with the actual energy value, thereby determining a correlation function, and statistically calculates the energy storage power, energy release power, medium thermal insulation coefficient and heat storage capacity value in the heat storage tank at the previous moment, and calculates the energy loss value of the current heat storage tank according to the energy storage power, energy release power, medium thermal insulation coefficient and heat storage capacity value at the previous moment; A model building unit (3) is provided, wherein the model building unit (3) determines a condition function corresponding to each power generation mode, constructs a field model using MATLAB software, completes the construction of a receiver model in combination with a correlation function, analyzes the energy storage power and energy release power of the heat storage tank and the energy loss value of the heat storage tank at each moment, obtains a heat storage tank model, adds a generator model and the condition function corresponding to each power generation mode, and thus constructs a complete solar thermal model.

2. The light-heat comprehensive utilization system based on artificial intelligence according to claim 1 is characterized in that: The mode division unit (1) comprises a preset value setting module (101) and a sunshine sufficient operation module (102). The preset value setting module (101) divides the power generation mode into three types according to the solar radiation intensity, namely, a sunshine sufficient mode, a sunshine insufficient mode and a sunshine lack mode, sets a first preset value and a second preset value, and the first preset value is greater than the second preset value. If the solar radiation intensity value is higher than the first preset value, the sunshine sufficient operation module (102) determines that the current power generation mode is the sunshine sufficient mode, determines the power generation power, and sets a minimum energy value according to the power generation power. After collecting the energy generated by the solar radiation through the concentrating heat collection device, the energy in the heat collection device is extracted according to the minimum energy value, and the extracted energy is used to generate high-temperature steam, which is transmitted to the generator set for power supply, and the remaining energy is transmitted to the heat storage tank for storage.

3. The light-heat comprehensive utilization system based on artificial intelligence according to claim 2 is characterized in that: The mode division unit (1) further comprises a sunshine shortage operation module (103) and a sunshine deficiency operation module (104). If the solar radiation intensity is lower than or equal to a first preset value and higher than a second preset value, the sunshine deficiency operation module (103) determines that the current power generation mode is a sunshine shortage mode, stops energy storage, collects energy using a concentrating and collecting device, and directly transmits the energy to a steam generator. After determining the difference between the minimum energy value and the energy transmitted this time, the energy in the heat storage tank is extracted according to the difference, and the energy is transmitted to the steam generator. The steam generator generates high-temperature steam using the received energy, and transmits the steam to the generator set for power supply. If the solar radiation intensity is lower than or equal to the second preset value, the sunshine deficiency operation module (104) determines that the current power generation mode is a sunshine deficiency mode, turns off the concentrating and collecting device, stops energy storage, transmits the energy in the heat storage tank to the steam generator, generates high-temperature steam using the received energy, and transmits the steam to the generator set for power supply.

4. The light-heat comprehensive utilization system based on artificial intelligence according to claim 1 is characterized in that: The energy analysis unit (2) comprises an incident energy determination module (201) and a correlation function output module (202), wherein the incident energy determination module (201) determines the solar radiation intensity D, the optical efficiency η, the total number n of heliostats and the area S in the heliostat field, and calculates the incident energy value Q according to the solar radiation intensity D, the optical efficiency η, the total number n of heliostats and the area S. z , where Q z =D·η·S·n, the correlation function output module (202) determines the loss energy value Q loss , according to the incident energy value Q z And the energy loss value Q loss Calculate the energy value Q actually collected by the receiver of the collector s , where Q s =Q z -Q loss ,After obtaining the air pressure value, the temperature value, the humidity value, the wind speed value, the receiver parameter value, the sun altitude angle, the azimuth angle, and the radiation intensity, the air pressure value, the temperature value, the humidity value, the wind speed value, the receiver parameter value, the sun altitude angle, the azimuth angle, and the radiation intensity are combined with the actual energy value to determine the correlation function.

5. The light-heat comprehensive utilization system based on artificial intelligence according to claim 4 is characterized in that: The energy analysis unit (2) further comprises an energy loss calculation module (203), wherein the energy loss calculation module (203) counts the energy power P stored in the heat storage tank. t c , energy release power P t f , medium insulation coefficient ε and heat storage capacity value O in the previous moment t-1 , according to the energy storage power P t c , energy release power P t c , medium insulation coefficient ε and heat storage capacity value O in the previous moment t-1 Calculate the current energy loss value of the heat storage tank O t , where O t =ε·O t-1 +(P t c -P t f )·Δt, Δt is the time interval value.

6. The light-heat comprehensive utilization system based on artificial intelligence according to claim 1 is characterized in that: The model construction unit (3) comprises a condition function generation module (301), a component model analysis module (302) and a component merging module (303). After determining the thermal insulation coefficient of the heat storage tank, the condition function generation module (301) calculates the condition function corresponding to each power generation mode according to different power generation modes and correlation functions, energy loss values, energy storage power and energy release power of the heat storage tank. The component model analysis module (302) uses MATLAB software to construct a mirror field model according to the incident energy value, solar radiation intensity, optical efficiency, the total number and area of ​​heliostats in the heliostat field, completes the construction of the receiver model in combination with the correlation function, analyzes the energy storage power, energy release power of the heat storage tank and the energy loss value of the heat storage tank at each moment, and obtains the heat storage tank model. The component merging module (303) combines the mirror field model, the receiver model and the heat storage tank model, and then adds the generator model and the condition function corresponding to each power generation mode, thereby constructing a complete solar thermal model.

7. The light-heat comprehensive utilization system based on artificial intelligence according to claim 1 is characterized in that: The energy prediction unit (4) comprises a historical data receiving module (401) and a model parameter determination module (402), wherein the historical data receiving module (401) receives historical meteorological data and historical radiation data of the solar thermal power station, wherein the historical meteorological data comprises historical solar altitude angle, historical solar azimuth angle, historical air pressure value, historical temperature value, historical humidity value and historical wind speed value, and the historical radiation data is specifically historical solar radiation intensity, and the model parameter determination module (402) constructs a training set and a test set using the historical meteorological data and the historical radiation data, transfers the data in the training set to the LSTM prediction model, completes the training of the LSTM prediction model, and calculates the error value corresponding to each parameter using a parameter analysis algorithm, transfers the data in the test set to the LSTM prediction model, and determines the LSTM prediction model parameters.

8. The light-heat comprehensive utilization system based on artificial intelligence according to claim 7 is characterized in that: The energy prediction unit (4) also includes a radiation intensity analysis module (403) and an energy output module (404). The radiation intensity analysis module (403) determines the solar altitude angle, solar azimuth angle, air pressure value, temperature value, humidity value and wind speed value of the current solar thermal power station, and transmits them to the LSTM prediction model for analysis to obtain a predicted solar radiation intensity value. The energy output module (404) transmits the predicted solar radiation intensity value to the solar thermal model, and determines the power generation mode and incident energy value of the current solar thermal power station according to the solar altitude angle, solar azimuth angle, air pressure value, temperature value, humidity value, wind speed value and solar radiation intensity value of the current solar thermal power station.

Images