Concentrating photovoltaic power generation system and control method thereof

Abstract

The invention provides a concentrating photovoltaic power generation system and a control method thereof. The system comprises a collecting lens, a guide rail bracket, an arc-shaped guide rail, a photovoltaic panel, a gear, a guide rail motor, a connecting piece, a guide rail sliding block and a roller, the arc-shaped guide rails are installed on the two sides of the collecting lens in parallel through guide rail supports, the convex face is provided with a rack structure, and the size of the rack structure is determined in advance according to the moving track of light gathered by the collecting lens. The end part of the photovoltaic panel is connected with a guide rail sliding block through a connecting piece; the guide rail sliding block and the arc-shaped guide rail form a sliding fit structure through a roller; the guide rail motor is fixedly installed on the guide rail sliding block, and an output shaft of the guide rail motor is connected with the gear meshed with the rack structure of the arc-shaped guide rail. When the guide rail motor drives the gear to rotate, the guide rail sliding block is driven to slide on the arc-shaped guide rail, the photovoltaic panel is controlled to move along the arc-shaped track of the arc-shaped guide rail, and light gathered by the collecting lens is irradiated on the photovoltaic panel. The optical loss can be reduced, and the solar power generation power and the utilization rate of unit land area can be improved.

Description

Technical Field

[0001] The present invention relates to the field of solar power generation control technology, and in particular to a concentrated photovoltaic power generation system and a control method thereof. Background Art

[0002] Due to the growth of population, industrialization and urbanization, global energy and electricity consumption are increasing rapidly. In order to cope with the problem of exponentially increasing electricity consumption in the future, it is necessary to fully develop and utilize new energy sources for power generation. Solar energy is widely used because it is green, low-cost and renewable. Photovoltaic power generation systems use the photovoltaic effect of semiconductor materials to generate electricity, and have the advantages of high efficiency, simple and flexible systems. Therefore, using solar energy to concentrate and collect heat to achieve photovoltaic power generation has become a research hotspot.

[0003] In the related technology, the trough photovoltaic power generation device mainly includes a concentrator and a photovoltaic panel. Its principle is mainly to focus light and reflect sunlight through the concentrator, and the photovoltaic panel absorbs light energy, thereby converting light energy into electrical energy. However, in actual application scenarios, the position of the sun in the sky changes with time, and the focal line of the concentrator focusing sunlight will also change continuously. It is necessary to continuously adjust the position of the power generation device to track the changes in the sun's angle in order to fully absorb light energy.

[0004] However, the commonly used trough photovoltaic power generation devices all track the changes in the azimuth and altitude angles of the sun by controlling the rotation of the concentrator. This method requires a sufficiently large concentrator rotation space to be reserved for each photovoltaic power generation device, so the distance between two adjacent photovoltaic power generation devices is large, which makes the entire power generation system occupy a large area, reducing the land utilization rate and the solar energy utilization rate per unit land area. Summary of the invention

[0005] The embodiment of the present invention provides a concentrated photovoltaic power generation system and a control method thereof to solve the problems of low land utilization rate and low solar energy utilization rate per unit land area in the existing technology.

[0006] In a first aspect, an embodiment of the present invention provides a concentrated photovoltaic power generation system, comprising: a condenser (1), a guide rail bracket (2), an arc-shaped guide rail (3), a photovoltaic panel (4), a gear (5), a guide rail motor (6), a connecting piece (7), a guide rail slider (8), and a roller (9) fixedly mounted on one side of the guide rail slider (8);

[0007] The arc-shaped guide rail (3) is installed in parallel on both sides of the condenser (1) through the guide rail bracket (2), and the convex surface of the arc-shaped guide rail (3) is provided with a rack structure; the size of the arc-shaped guide rail (3) is determined in advance according to the moving trajectory of the light condensed by the condenser (1);

[0008] The end of the photovoltaic panel (4) is connected to the guide rail slider (8) through the connecting member (7), and the guide rail slider (8) forms a sliding fit structure with the arc guide rail (3) through the rollers (9);

[0009] The guide rail motor (6) is fixedly installed on the guide rail slider (8), the output shaft of the guide rail motor (6) is connected to the gear (5), and the gear (5) meshes with the rack structure of the arc guide rail (3) to form a driving connection;

[0010] When the guide rail motor (6) drives the gear (5) to rotate, it drives the guide rail slider (8) to slide on the arc guide rail (3), so as to control the photovoltaic panel (4) to move along the arc track of the arc guide rail (3), so that the light concentrated by the condenser (1) irradiates on the photovoltaic panel (4).

[0011] In a possible implementation manner, the concentrating photovoltaic power generation system further includes: a photovoltaic motor (10);

[0012] The output shaft of the photovoltaic motor (10) is connected to the central axis of the photovoltaic panel (4), and is used to drive the photovoltaic panel (4) to rotate around its own central axis, so as to adjust the pitch angle of the photovoltaic panel (4), so that the incident angle of the light concentrated by the condenser (1) irradiating on the photovoltaic panel (4) is less than a preset threshold value.

[0013] In a possible implementation manner, the concentrating photovoltaic power generation system further includes: a Global Positioning System (GPS) module, a wireless communication module and a controller. The GPS module and the wireless communication module are both in communication with the controller, and the controller is electrically connected to the guide rail motor (6) and the photovoltaic motor (10);

[0014] The GPS module is used to collect geographical location data and send the geographical location data to the controller;

[0015] The wireless communication module is used to obtain real-time meteorological data and send the real-time meteorological data to the controller;

[0016] The controller is used to: determine the predicted position and predicted inclination angle of the photovoltaic panel (4) at the next moment according to the geographical location data, the real-time meteorological data and the time data at the current moment;

[0017] According to the predicted position and predicted inclination angle at the next moment, determine the target travel corresponding to the photovoltaic panel (4) moving to the predicted position and the target rotation angle corresponding to rotating to the predicted inclination angle;

[0018] Generate a pulse control signal according to the target travel and the target rotation angle, and send the pulse control signal to the guide rail motor (6) and the photovoltaic motor (10) to drive the guide rail motor (6) and the photovoltaic motor (10) to rotate, driving the movement of the photovoltaic panel (4) to the predicted position and rotating to the predicted inclination angle.

[0019] In a possible implementation, the concentrating photovoltaic power generation system further includes: light intensity sensors (11) symmetrically installed on both sides of the photovoltaic panel (4), communicating with the controller, for detecting the light intensity on both sides of the photovoltaic panel (4) in real time, and sending the light intensity on both sides of the photovoltaic panel (4) to the controller;

[0020] The controller determines the rotation angle of the guide rail motor (6) according to the light intensity on both sides of the photovoltaic panel (4), and generates a first correction instruction according to the rotation angle of the guide rail motor (6). The first correction instruction is used to instruct the guide rail motor (6) to rotate to drive the photovoltaic panel (4) to move along the arc guide rail (3), correcting the position prediction error of the photovoltaic panel (4) so that the difference in light intensity between both sides of the photovoltaic panel (4) is less than a preset light intensity error threshold.

[0021] In a possible implementation, the concentrating photovoltaic power generation system further includes: an inclination sensor installed on the photovoltaic panel, the inclination sensor communicating with the controller, for detecting the actual inclination angle when the photovoltaic panel (4) moves to the predicted position, and sending the actual inclination angle to the controller;

[0022] The controller determines the rotation angle of the photovoltaic motor (10) according to the actual inclination angle and the predicted inclination angle, and generates a second correction instruction according to the rotation angle of the photovoltaic motor (10). The second correction instruction is used to instruct the photovoltaic motor (10) to rotate to drive the photovoltaic panel (4) to rotate around its own central axis, correcting the inclination prediction error of the photovoltaic panel (4) so that the difference between the actual inclination angle and the predicted inclination angle of the photovoltaic panel (4) is less than a preset angle error threshold.

[0023] In a second aspect, an embodiment of the present invention provides a control method for a concentrating photovoltaic power generation system, including:

[0024] Obtain the geographical location data, real-time meteorological data, and time data at the current moment of the target area where the concentrating photovoltaic power generation system is located;

[0025] According to the geographical location data, the real-time meteorological data, the time data at the current moment, and the trained long short-term memory network model, predict the target travel and the target rotation angle of the photovoltaic panel from the current moment to the next moment;

[0026] Generate a first pulse control signal according to the target travel distance, and generate a second pulse control signal according to the target rotation angle;

[0027] Send the first pulse control signal to the guide rail motor, so that the guide rail motor controls the movement of the photovoltaic panel according to the first pulse signal, and send the second pulse signal to the photovoltaic motor, so that the photovoltaic motor controls the rotation of the photovoltaic panel around its own central axis according to the second pulse signal to adjust the pitch angle.

[0028] In a possible implementation manner, the control method of the concentrating photovoltaic power generation system further includes:

[0029] Determine a training sample set, where each training sample in the training sample set includes: geographical location data, time series data, and historical meteorological data of the target area, as well as the optimal position label and optimal inclination label of the photovoltaic panel corresponding to different meteorological conditions and different times at the geographical location, and the travel label corresponding to moving to the optimal position and the rotation angle label corresponding to rotating to the optimal inclination;

[0030] Input the training sample set into the preset long short-term memory network model for training to obtain a trained long short-term memory network model;

[0031] Wherein, the optimal position and optimal inclination are the position and inclination of the photovoltaic panel when the light concentrated by the concentrator is perpendicularly incident on the photosensitive surface of the photovoltaic panel.

[0032] In a possible implementation manner, the long short-term memory network model includes an input layer, a hidden layer, and an output layer, and the hidden layer includes a three-layer fully connected structure;

[0033] Predicting the target travel distance and target rotation angle of the photovoltaic panel from the current moment to the next moment according to the geographical location data, the real-time meteorological data, the time data at the current moment, and the trained long short-term memory network model includes:

[0034] Input the geographical location data, the real-time meteorological data, and the time data at the current moment through the input layer into the first-layer fully connected structure. The first-layer fully connected structure outputs the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment, and inputs the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment into the second-layer fully connected structure;

[0035] The second-layer fully connected structure determines the predicted position and predicted inclination of the photovoltaic panel at the next moment according to the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment, and inputs the predicted position and predicted inclination of the photovoltaic panel into the third-layer fully connected structure;

[0036] The third fully-connected structure determines a target stroke corresponding to the photovoltaic panel moving to the predicted position and a target rotation angle corresponding to the photovoltaic panel rotating to the predicted inclination angle according to the predicted position and the predicted inclination angle.

[0037] The output layer outputs the target stroke and the target rotation angle.

[0038] In a possible implementation, the control method of the concentrating photovoltaic power generation system further includes:

[0039] Real-time detect the light intensities on both sides of the photovoltaic panel;

[0040] Determine a first rotation angle according to the light intensities on both sides of the photovoltaic panel;

[0041] Generate a first correction instruction according to the first rotation angle, where the first correction instruction is used to instruct the photovoltaic motor to drive the photovoltaic panel to rotate by the first rotation angle so that the difference between the light intensities on both sides of the photovoltaic panel is less than a preset light intensity error threshold.

[0042] In a possible implementation, the control method of the concentrating photovoltaic power generation system further includes:

[0043] Detect the actual inclination angle of the photovoltaic panel when the photovoltaic panel moves to the predicted position;

[0044] Determine a second rotation angle according to the actual inclination angle and the predicted inclination angle;

[0045] Generate a second correction instruction according to the second rotation angle, where the second correction instruction is used to instruct the photovoltaic motor to drive the photovoltaic panel to rotate by the second rotation angle so that the difference between the actual inclination angle and the predicted inclination angle of the photovoltaic panel is less than a preset angle error threshold.

[0046] In the embodiment of the present invention, a condenser lens (1), a guide rail bracket (2), an arc guide rail (3), a photovoltaic panel (4), a gear (5), a guide rail motor (6), a connecting member (7), a guide rail slider (8), and a roller (9) fixedly installed on one side of the guide rail slider (8) are provided; the arc guide rail (3) is horizontally installed on both sides of the condenser lens (1) through the guide rail bracket (2), and a rack structure is provided on the convex surface of the arc guide rail (3); the size of the arc guide rail (3) is determined in advance according to the movement track of the light rays concentrated by the condenser lens (1); the end of the photovoltaic panel (4) is connected to the guide rail slider (8) through the connecting member (7), and the guide rail slider (8) and the arc guide rail (3) form a sliding fit structure through the roller (9); the guide rail motor (6) is fixedly installed on the guide rail slider (8), the output shaft of the guide rail motor (6) is connected to the gear (5), and the gear (5) meshes with the rack structure of the arc guide rail (3) to form a transmission connection; since the size of the arc guide rail (3) is determined according to the movement track of the light rays concentrated by the condenser lens (1), when the guide rail motor (6) works, driving the gear (5) to rotate drives the guide rail slider (8) to slide on the arc guide rail (3), controlling the photovoltaic panel (4) to move along the arc track of the arc guide rail (3), so that the light rays concentrated by the condenser lens (1) always irradiate on the photovoltaic panel (4). The condenser lens does not need to rotate, and the photovoltaic panel is controlled by the guide rail motor to track the movement of the light rays, reducing optical losses. The embodiment of the present invention can realize the dense paving of condenser lenses on the ground, effectively reduce the optical losses in the condenser lens field, and improve the solar energy concentrating power generation power and solar energy utilization efficiency per unit land area. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic structural diagram of a concentrating photovoltaic power generation system provided by an embodiment of the present invention;

[0048] Figure 2 is a partially enlarged schematic structural diagram of a concentrating photovoltaic power generation system provided by an embodiment of the present invention;

[0049] Figure 3 is a partially enlarged schematic structural diagram of a concentrating photovoltaic power generation system provided by another embodiment of the present invention;

[0050] Figure 4 is a schematic connection diagram of the control structure of a concentrating photovoltaic power generation system provided by an embodiment of the present invention;

[0051] Figure 5 is a flowchart of the implementation of a control method for a concentrating photovoltaic power generation system provided by an embodiment of the present invention;

[0052] Figure 6 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this disclosure without creative efforts belong to the scope of protection of the present invention.

[0054] In the related art, a trough-type photovoltaic power generation device mainly includes a condenser and a photovoltaic panel. Its principle is mainly to focus light and reflect sunlight through the condenser, and the photovoltaic panel absorbs light energy, thereby converting light energy into electrical energy. However, in actual application scenarios, the position of the sun in the sky changes with time, and the focal line of the sunlight focused by the condenser will also change continuously. It is necessary to continuously adjust the pose of the power generation device to track the change of the sun's angle to fully absorb light energy. However, the commonly used trough-type photovoltaic power generation devices all track the changes in the azimuth angle and altitude angle of the sun by controlling the rotation of the condenser. This method requires a sufficiently large rotation space for the condenser to be reserved for each photovoltaic power generation device. Therefore, the distance between two adjacent photovoltaic power generation devices is relatively large, resulting in a large floor area for the entire power generation system, reducing the land utilization rate and the solar energy utilization rate per unit land area.

[0055] Based on the above defects, the present invention proposes the following concept: fix the condenser on the ground, set an arc-shaped guide rail, and design parameters such as the size and curvature of the arc-shaped guide rail according to the movement trajectory of the light collected by the condenser. Install the arc-shaped guide rail parallel to both sides of the condenser through brackets. The photovoltaic panel straddles above the condenser, and drives the guide rail slider to slide on the arc-shaped guide rail through a guide rail motor to drive the photovoltaic panel to move along an arc-shaped trajectory. Drive the photovoltaic panel to rotate around its own central axis through a photovoltaic motor, thereby adjusting the position and inclination angle of the photovoltaic panel so that the light collected by the condenser is always aligned with the photovoltaic panel. And, use time series data, geographical location data, and historical meteorological data to train a long short-term memory network model in advance, and based on the trained long short-term memory network model, achieve accurate prediction of the position of the photovoltaic panel at different latitudes and longitudes and different times, so as to design the pulse control signals of the guide rail motor and the photovoltaic motor according to the prediction results to control the movement and rotation of the photovoltaic panel.

[0056] The following will describe the embodiments of the present invention in detail with reference to the accompanying drawings.

[0057] Figure 1 It is a schematic structural diagram of a concentrating photovoltaic power generation system provided by an embodiment of the present invention.

[0058] As Figure 1As shown in the figure, the concentrating photovoltaic power generation system provided in this embodiment includes: a concentrating mirror (1), a guide rail bracket (2), an arc guide rail (3), a photovoltaic panel (4), a gear (5), a guide rail motor (6), a connecting piece (7), a guide rail slider (8), and a roller (9) fixedly installed on one side of the guide rail slider (8);

[0059] The arc guide rail (3) is installed in parallel on both sides of the concentrating mirror (1) through the guide rail bracket (2), and a rack structure is provided on the convex surface of the arc guide rail (3); the size of the arc guide rail (3) is determined in advance according to the movement track of the light concentrated by the concentrating mirror (1);

[0060] The end of the photovoltaic panel (4) is connected to the guide rail slider (8) through the connecting piece (7), and the guide rail slider (8) and the arc guide rail (3) form a sliding fit structure through the roller (9);

[0061] The guide rail motor (6) is fixedly installed on the guide rail slider (8), the output shaft of the guide rail motor (6) is connected to the gear (5), and the gear (5) meshes with the rack structure of the arc guide rail (3) to form a transmission connection;

[0062] When the guide rail motor (6) drives the gear (5) to rotate, it drives the guide rail slider (8) to slide on the arc guide rail (3), so as to control the photovoltaic panel (4) to move along the arc track of the arc guide rail (3), so that the light concentrated by the concentrating mirror (1) irradiates on the photovoltaic panel (4).

[0063] In this embodiment, the concentrating mirror (1) is a trough-type concentrating mirror, and the trough-type concentrating mirror is fixed on the ground through a concentrating mirror bracket. Its concentrating surface adopts a parabolic reflecting mirror surface, and a nano-coating with a high reflectivity is plated on the surface. The arc guide rail (3) is fixed on the guide rail bracket (2) and is arranged in parallel on both sides of the concentrating mirror (1) through the guide rail bracket (2). The photovoltaic panel (4) straddles above the light (i.e., the focal line) concentrated by the concentrating mirror (1), and both ends are respectively connected to one side of the guide rail slider (8) through the connecting piece (7). Four rollers (9) are installed on the other side of the guide rail slider (8), as Figure 2As shown, a sliding fit structure is formed by four rollers (9) slidably sleeved on an arc-shaped guide rail (3). The guide rail motor (6) is fixedly installed on one side of the guide rail slider (8), and its output shaft passes through the guide rail slider (8) and is connected to a gear (5). A rack structure is provided on the convex surface of the arc-shaped guide rail (3), and the gear (5) meshes with the rack structure to form a transmission connection. When the guide rail motor (6) operates, the power output shaft rotates to drive the gear (5) to rotate, and the guide rail slider (8) is driven to slide on the arc-shaped guide rail (3) by means of the meshing transmission connection, so that the photovoltaic panel (4) moves along the arc-shaped trajectory of the arc-shaped guide rail (3). Since parameters such as the size and curvature of the arc-shaped guide rail (3) are determined in advance by the moving trajectory of the focused light of the optical simulation concentrator (1), when the guide rail slider (8) slides along the arc-shaped guide rail (3), the arc-shaped trajectory that drives the photovoltaic panel (4) to move along the arc-shaped guide rail (3) just coincides with the moving trajectory of the light focused by the concentrator (1). By controlling the rotation of the guide rail motor (6) at different times, the photovoltaic panel (4) can always follow the moving light.

[0064] In a possible implementation manner, monocrystalline silicon solar cells and liquid cooling pipelines are integrated on the surface of the photovoltaic panel (4) to achieve efficient conversion and output of light energy into electrical energy.

[0065] In this embodiment, the concentrator is fixed to the ground, and the photovoltaic panel is controlled by a guide rail motor to move along an arc-shaped trajectory to dynamically track the light focused by the concentrator. There is no need to move the concentrator, and the moving process does not occupy extra space. It is possible to densely pave the concentrators on the ground, effectively reducing the optical losses in the concentrator field and improving the solar concentrating power generation power and solar energy utilization efficiency per unit land area.

[0066] In specific implementation, since the concentrating photovoltaic power generation system may be used in different regions and different terrains, and the altitude angle, azimuth angle, and hour angle parameters of the sun at different times in different regions and different terrains will be different, the movement change of the focal line of the concentrator changes with the altitude angle, azimuth angle, and hour angle parameters of the sun at different times in different regions and different terrains. Therefore, it is necessary to customize various parameters of the concentrating photovoltaic power generation system in combination with geographical location information and user requirements. For example, comprehensively considering geographical coordinates (such as longitude, latitude, altitude), terrain parameters, land area, and expected power generation power of the photovoltaic, design the number of rows and columns of the photovoltaic array, the orientation, select the width of the photovoltaic panel, the width of the concentrator, and the focal length parameters required for each row. Then, according to the width and focal length parameters of the concentrator, using optical simulation software, with the power generation power as the objective function and using the Levenberg-Marquardt algorithm, calculate the focal coordinates of the concentrator with different focal lengths at different times, and then determine the maximum moving distance of the photovoltaic panel in the horizontal direction according to the focal coordinates at different times.

[0067] In a possible implementation, the focal coordinates (x, y) of the condenser lens at different focal lengths and different times can be calculated using the first formula and the second formula. The first formula is: x = a + b * sin(pi * (t - c) / d); the second formula is y = e + f * sin 2 (pi * (t - g) / h); where a, b, c, d, e, f, g, and h are all constants related to the concentration ratio, and t is the local local time. Exemplarily, when the concentration ratio is 10, a = -1.82656×10 -4 , b = 0.77982, c = -0.36712, d = 6.18647, e = 0.10337, f = 1.39726, g = 6.30086, h = 11.39828. According to the above formula, the intersection coordinates of the condenser lens with different focal lengths at different times can be calculated.

[0068] Exemplarily, taking the lowest position at the bottom of the condenser lens (1) as the coordinate origin, a three-dimensional coordinate system is established. When the concentration ratio is 10, the focal coordinates of the condenser lens with different focal lengths at different times are shown in Table 1.

[0069] Table 1: Focal coordinates of condenser lenses with different focal lengths at different times

[0070]

[0071] As can be seen from Table 1, the optimal positions corresponding to the focal points of the condenser lens (1) at different times are approximately connected in an arc shape. The larger the focal length, the greater the horizontal movement distance of the focal point at different times. When the focal length is 2 meters, the maximum horizontal movement distance is about 0.9 meters. Therefore, according to the above formula and parameters such as the focal length of the condenser lens, the specific geometric shape of the arc-shaped guide rail (such as parameters such as the guide rail length and curvature) can be determined.

[0072] In this embodiment, by pre-optical simulating the focal point changes of the condenser lens in different regions and at different times, fitting the focal point movement trajectory of the condenser lens, and then designing the size of the arc-shaped guide rail so that the arc-shaped trajectory of the arc-shaped guide rail matches the focal point movement trajectory of the condenser lens. When the photovoltaic panel moves along the arc-shaped trajectory of the arc-shaped guide rail, the photovoltaic panel can always be aligned with the focal line of the condenser lens, reducing the loss of focal spot offset, adapting to the intensive layout method, effectively reducing the optical loss in the condenser lens field, and improving the optical efficiency and land utilization rate of the concentrating photovoltaic power generation system. Moreover, the arc-shaped guide rail supports three-dimensional space curve design and can adapt to complex terrains such as hills and slopes to reduce the land leveling cost.

[0073] In a possible implementation, as Figures 1-3 shown, the concentrating photovoltaic power generation system further includes: a photovoltaic motor (10);

[0074] The output shaft of the photovoltaic motor (10) is connected to the central axis of the photovoltaic panel (4) and is used to drive the photovoltaic panel (4) to rotate around its own central axis so as to adjust the pitch angle of the photovoltaic panel (4), making the incident angle of the light concentrated by the condenser lens (1) on the photovoltaic panel (4) less than a preset threshold value.

[0075] In this embodiment, the photovoltaic motor (10) is fixedly installed on one side of the guide rail slider (8), and its output shaft passes through the guide rail slider (8) and is connected to the central axis of the photovoltaic panel (4). When the photovoltaic motor (10) works, its output shaft rotates to drive the photovoltaic panel (4) to rotate around its own central axis, dynamically adjusting the pitch angle of the photovoltaic panel (4).

[0076] It should be noted that the incident angle of the light on the photovoltaic panel (4) is the angle between the light and the normal line of the photosensitive surface of the photovoltaic panel (4). When the incident angle is 0 degree, it means that the light concentrated by the condenser lens is perpendicularly incident on the photosensitive surface of the photovoltaic panel (4), and at this time, the light energy utilization rate is the highest.

[0077] In this embodiment, by controlling the photovoltaic panel (4) to rotate around its own central axis through the photovoltaic motor (10) so that the incident angle of the light concentrated by the condenser lens on the photosensitive surface of the photovoltaic panel (4) is less than a preset threshold value, the optical utilization rate can be maximally improved, and the power generation per unit land area can be increased. The preset threshold value can be designed according to actual requirements. For example, the preset threshold value can be 5 degrees.

[0078] In a possible implementation manner, as Figure 4 shown, the concentrating photovoltaic power generation system further includes: a GPS module, a wireless communication module, and a controller. The GPS module and the wireless communication module are both in communication with the controller, and the controller is electrically connected to the guide rail motor (6) and the photovoltaic motor (10);

[0079] The GPS module is used to collect geographical location data and send the geographical location data to the controller;

[0080] The wireless communication module is used to obtain real-time meteorological data and send the real-time meteorological data to the controller;

[0081] The controller is used to: determine the predicted position and predicted inclination angle of the photovoltaic panel (4) at the next moment according to the geographical location data, the real-time meteorological data, and the time data at the current moment;

[0082] According to the predicted position and predicted inclination angle at the next moment, determine the target travel corresponding to the photovoltaic panel (4) moving to the predicted position and the target rotation angle corresponding to the photovoltaic panel (4) rotating to the predicted inclination angle;

[0083] Generate a pulse control signal according to the target travel and the target rotation angle, and send the pulse control signal to the guide rail motor (6) and the photovoltaic motor (10) to drive the guide rail motor (6) and the photovoltaic motor (10) to rotate, so as to drive the movement of the photovoltaic panel (4) to the predicted position and rotate to the predicted inclination angle.

[0084] In this embodiment, the GPS module, the wireless communication module and the controller can be integrally arranged inside the guide rail slider (8), or can be separately integrated into a control module and fixed on the guide rail bracket (2). The specific installation method can be determined according to factors such as the actual geographical environment.

[0085] In a possible implementation manner, the geographical location data collected by the GPS module may but is not limited to include: longitude, latitude and altitude of the target area where the concentrating photovoltaic power generation system is located; the real-time meteorological data obtained by the wireless communication module networking may but is not limited to include: real-time solar irradiance, temperature, wind speed, cloud cover rate, etc.; an algorithm model is preset in the controller, and the controller predicts the predicted position and predicted inclination angle of the photovoltaic panel at the next moment based on the algorithm model according to the geographical location data, real-time meteorological data and the time data at the current moment, and then determines the target travel corresponding to the photovoltaic panel (4) moving to the predicted position and the target rotation angle corresponding to rotating to the predicted inclination angle based on the algorithm model according to the predicted position and predicted inclination angle.

[0086] It should be noted that the predicted position and predicted inclination angle of the photovoltaic panel at the next moment predicted by the controller based on the algorithm model are the optimal position and optimal inclination angle corresponding to the photovoltaic panel when the light concentrated by the concentrator is vertically irradiated on the photosensitive surface of the photovoltaic panel at the next moment. The detailed implementation process of predicting the target travel that the photovoltaic panel needs to move and the target rotation angle that needs to be rotated from the current moment to the next moment based on the algorithm model will be described in the relevant method embodiments later.

[0087] In this embodiment, the inclination angle is the included angle between the photovoltaic panel and the horizontal direction; the target travel is the displacement of the photovoltaic panel from the current position to the predicted position at the next moment on the arc-shaped guide rail; the target rotation angle is the angle that the photovoltaic panel needs to rotate from the current inclination angle to the predicted inclination angle.

[0088] It should be noted that the time interval between the current moment and the next moment can be determined according to time requirements, such as 2 minutes, 5 minutes, 10 minutes, etc.

[0089] In a possible implementation, both the guide rail motor and the photovoltaic motor are stepper motors. After the controller predicts the target stroke corresponding to the predicted position of the photovoltaic panel (4) at the next moment and the target rotation angle corresponding to the predicted inclination angle at the next moment, the process of calculating the operating parameters of the guide rail motor based on the target stroke and generating a pulse control signal is as follows: Determine the gear ratio of the driving wheel in the guide rail motor and the driven wheel (i.e., the gear (5)) connected to the output shaft. Calculate the number of rotations of the guide rail motor based on the gear ratio and the target stroke; then, based on the number of rotations of the guide rail motor, convert it into the number of steps of the guide rail motor in combination with the step angle of the guide rail motor; determine the rotation speed of the guide rail motor based on the time interval from the current moment to the next moment, and then calculate the pulse frequency required by the guide rail motor based on the rotation speed and the number of steps of the guide rail motor. Then generate the corresponding pulse control signal and send the pulse control signal to the guide rail motor to make the guide rail motor rotate according to the pulse control signal and drive the photovoltaic panel to move to the predicted position.

[0090] Similarly, determine the operating parameters of the photovoltaic motor based on the target rotation angle and generate the corresponding pulse control signal. Since the output shaft of the photovoltaic motor is directly connected to the central axis of the photovoltaic panel and drives the photovoltaic panel to rotate, the process of determining the operating parameters of the photovoltaic motor is as follows: Determine the step angle of the photovoltaic motor, and calculate the number of steps the photovoltaic motor needs to rotate based on the target rotation angle and the step angle; determine the rotation speed of the photovoltaic motor based on the time interval from the current moment to the next moment, and then calculate the pulse frequency required by the photovoltaic motor based on the rotation speed and the number of rotation steps of the photovoltaic motor. Then generate the corresponding pulse control signal and send the pulse control signal to the photovoltaic motor to make the photovoltaic motor rotate according to the pulse control signal and drive the photovoltaic panel to rotate to the target inclination angle.

[0091] In a possible implementation, the controller continuously predicts the predicted positions and predicted inclination angles corresponding to each moment within a future time period. For example, the time interval is 10 minutes, the current moment is 10 o'clock, the next moment is 10:10, the next moment after that is 10:20, 10:30... The controller will predict the values of discrete predicted position points and discrete predicted inclination angles, and predict the target stroke that the photovoltaic panel needs to move and the target rotation angle that it needs to rotate between adjacent moments. The controller uses the B-spline curve interpolation algorithm to convert these discrete predicted position points into a smooth motion trajectory, and then generates a continuous pulse control signal to control the continuous operation of the guide rail motor and the photovoltaic motor, driving the photovoltaic panel to track the light movement trajectory in real time, so that the light is always perpendicularly incident on the photosensitive surface of the photovoltaic panel.

[0092] In a possible implementation, such as Figure 3As shown in the figure, the concentrating photovoltaic power generation system further includes: light intensity sensors (11) symmetrically installed on both sides of the photovoltaic panel (4), communicating with the controller, for detecting the light intensity on both sides of the photovoltaic panel (4) in real time, and sending the light intensity on both sides of the photovoltaic panel (4) to the controller;

[0093] The controller determines the rotation angle of the guide rail motor (6) according to the light intensity on both sides of the photovoltaic panel (4), and generates a first correction instruction according to the rotation angle of the guide rail motor (6). The first correction instruction is used to instruct the guide rail motor (6) to rotate to drive the photovoltaic panel (4) to move along the arc guide rail (3), correct the position prediction error of the photovoltaic panel (4), and make the difference between the light intensities on both sides of the photovoltaic panel (4) less than a preset light intensity error threshold.

[0094] In this embodiment, referring to Figure 4 , the light intensity sensor is communicatively connected to the controller. The light intensity sensor is a photoresistor. The characteristic of the photoresistor is that its resistance value changes with the change of the light intensity. The stronger the light, the smaller the resistance, and vice versa. In this way, when the two sides of the photovoltaic panel are illuminated by different intensities of light, the photoresistors on both sides will generate different resistance values, thereby converting the light intensity signal into an electrical signal.

[0095] In specific implementation, the two light intensity sensors are used to monitor the offset of the focal spot position. They can be symmetrically installed on both sides of the end of the photovoltaic panel or symmetrically installed on both sides of the middle position of the photovoltaic panel. The light intensities on both sides of the photovoltaic panel collected by the two light intensity sensors are the first light intensity and the second light intensity respectively. If the difference between the first light intensity and the second light intensity is large, it means that the actual position of the photovoltaic panel deviates from the predicted optimal position, resulting in the photovoltaic panel not being aligned with the light concentrated by the condenser and a large focal spot offset. Therefore, the controller performs a differential operation on the first light intensity and the second light intensity, solves the rotation angle of the guide rail motor (6) according to the differential operation result, and calculates the rotation steps of the guide rail motor in combination with the step angle of the guide rail motor; then adjusts the rotation speed of the guide rail motor, and further calculates the pulse frequency required by the guide rail motor according to the rotation speed of the guide rail motor and the rotation steps of the guide rail motor, and then generates a first correction instruction. The first correction instruction is a pulse signal generated according to the pulse frequency required by the guide rail motor, which controls the guide rail motor to rotate to drive the photovoltaic panel to move a corresponding distance, dynamically corrects the position prediction error of the photovoltaic panel so that the light intensity error on both sides of the photovoltaic panel is less than a preset light intensity error threshold. Among them, the preset light intensity error threshold can be 20 lux.

[0096] In a possible implementation, to solve for the rotation angle of the guide rail motor based on the result of the differential operation of the light intensities on both sides, a corresponding relationship between the light intensity difference and the rotation angle of the guide rail motor needs to be established in advance. Generally, this relationship can be determined through experiments or theoretical calculations. Exemplarily, through experiments, it is found that when the light intensity difference between the two sides is 50 lux, the guide rail motor needs to rotate 10 degrees to make the light intensities on both sides of the photovoltaic panel tend to be balanced; when the light intensity difference is 100 lux, the stepper motor needs to rotate 20 degrees, and so on. Through the corresponding relationship between the light intensity difference and the rotation angle of the guide rail motor, the controller can calculate the rotation angle that the stepper motor needs to rotate based on the current light intensity difference, so that the light intensity error between the two sides of the photovoltaic panel is within 20 lux.

[0097] In this embodiment, due to the continuous change of the light illumination conditions in the actual environment and the possible errors in the system itself, the position of the photovoltaic panel may gradually deviate from the predicted optimal position. By continuously collecting the light intensity signal and performing the above-mentioned differential operation, controlling the rotation of the guide rail motor, etc., the system can continuously adjust the position of the photovoltaic panel to keep it in a state where the light intensity signal error between the two sides is within 20 lux. In this way, the function of dynamically correcting the position prediction error of the photovoltaic panel is realized, so that the photovoltaic panel can always face the direction with the strongest light as much as possible, improving the photovoltaic power generation efficiency.

[0098] In a possible implementation, the concentrating photovoltaic power generation system further includes: an inclination sensor installed on the photovoltaic panel, the inclination sensor communicates with the controller, and is used to detect the actual inclination angle when the photovoltaic panel (4) moves to the predicted position, and send the actual inclination angle to the controller;

[0099] The controller determines a second rotation angle according to the actual inclination angle and the predicted inclination angle, and generates a second correction instruction according to the second rotation angle, the second correction instruction is used to instruct the photovoltaic motor (10) to drive the photovoltaic panel (4) to rotate the second rotation angle, so that the difference between the actual inclination angle and the predicted inclination angle of the photovoltaic panel (4) is less than a preset angle error threshold.

[0100] In this embodiment, due to the existence of wind load disturbance and cumulative error during the actual operation process, it is necessary to detect the inclination angle of the photovoltaic panel, perform real-time feedback control, and dynamically correct the inclination angle error of the photovoltaic panel.

[0101] In specific implementation, the inclination sensor senses the inclination state of the photovoltaic panel in space and converts it into an electrical signal or a digital signal for output. It can be set at any position inside the photovoltaic panel. The controller obtains the actual inclination information of the photovoltaic panel from the inclination sensor, performs a difference operation with the predicted inclination generated based on the algorithm model to generate a difference signal, which reflects the deviation degree and direction between the current actual inclination and the ideal inclination of the photovoltaic panel. The controller calculates the rotation angle of the photovoltaic motor according to the difference signal, generates a second correction instruction according to the rotation angle of the photovoltaic motor. The second correction instruction is a pulse signal generated according to the rotation angle of the photovoltaic motor, and is used to control the rotation of the photovoltaic motor to drive the photovoltaic panel to rotate by a corresponding angle around its own central axis, dynamically correcting the prediction error of the inclination of the photovoltaic panel so that the actual inclination of the photovoltaic panel and the predicted inclination are less than the preset angle error threshold. Among them, the preset angle error threshold can be 1 degree, so as to achieve precise control of the inclination of the photovoltaic panel.

[0102] In this embodiment, the system can detect the actual inclination of the photovoltaic panel in real time, compare it with the predicted inclination and make adjustments. Due to factors such as wind load disturbance and cumulative error, which will continuously affect the inclination of the photovoltaic panel, the system will continuously perform detection, comparison and adjustment operations, forming a closed-loop feedback control system. This can ensure that the photovoltaic panel can always maintain a state close to the optimal inclination under various complex actual operating conditions, improve the photovoltaic power generation efficiency, and reduce the power generation loss caused by inclination deviation.

[0103] Figure 5 It is the implementation flowchart of the control method of the concentrating photovoltaic power generation system provided by the embodiment of the present invention.

[0104] As Figure 5 shown, the method provided by this embodiment may include the following steps:

[0105] S501, obtain the geographical location data, real-time meteorological data and time data at the current moment of the target area where the concentrating photovoltaic power generation system is located.

[0106] In this step, the geographical location data may include, but is not limited to: longitude, latitude and altitude of the target area where the concentrating photovoltaic power generation system is located; the real-time meteorological data may include, but is not limited to: real-time solar irradiance, temperature, wind speed, and cloud cover rate, etc.; the time data includes date, the time at the current moment (accurate to seconds), true solar time and time zone, etc.

[0107] S502, predict the target travel and target rotation angle of the photovoltaic panel from the current moment to the next moment according to the geographical location data, the real-time meteorological data, the time data at the current moment and the trained long short-term memory network model.

[0108] In this step, the long short-term memory network model has been pre-trained with a large amount of training data, establishing a mapping relationship from geographical location data, meteorological data, and time series data to the target travel and target rotation angle of the photovoltaic panel. Therefore, when the geographical location data, real-time meteorological data, and time data at the current moment are input into the trained long short-term memory network model as input quantities, the model directly outputs the prediction result of the photovoltaic panel at the next moment.

[0109] S503. Generate a first pulse control signal according to the target travel, and generate a second pulse control signal according to the target rotation angle.

[0110] S504. Send the first pulse control signal to the guide rail motor, so that the guide rail motor controls the movement of the photovoltaic panel according to the first pulse signal, and send the second pulse signal to the photovoltaic motor, so that the photovoltaic motor controls the rotation of the photovoltaic panel around its own central axis according to the second pulse signal to adjust the pitch angle.

[0111] It should be noted that the guide rail motor and the photovoltaic motor in the above concentrating photovoltaic power generation system are both stepper motors. A stepper motor can convert an electrical pulse signal into an angular displacement or a linear displacement. For each received electrical pulse, it will rotate a fixed angle, which is called the step angle. By controlling the number and frequency of electrical pulses, the rotation angle and speed of the stepper motor can be accurately controlled. The guide rail motor can convert the first pulse control signal into a linear displacement and drive the photovoltaic panel to move along the arc-shaped guide rail; the photovoltaic motor can convert the second pulse control signal into an angular displacement and drive the photovoltaic panel to rotate around its own central axis.

[0112] It should be noted that the implementation process of generating the first pulse control signal and the second pulse control signal according to the target travel and the target rotation angle respectively can refer to the description in the above system embodiment and will not be elaborated here.

[0113] In a possible implementation manner, the long short-term memory network model includes an input layer, a hidden layer, and an output layer. The hidden layer includes a three-layer fully connected structure. The input layer has 15 dimensions. The number of neurons in each layer of the hidden layer is 128 - 256. The activation function uses the Rectified Linear Unit (ReLU), and a Dropout layer (ratio 0.2) is introduced to prevent overfitting. The Adam optimizer is used, with an initial learning rate of 0.001, a batch size of 64, and 200 training epochs; the loss function is the mean squared error (MSE), and the verification set accuracy reaches RMSE ≤ 0.2° (angle) and displacement error ≤ 2 mm (displacement). Finally, the trained model is quantized and burned into the Flash memory of the embedded controller.

[0114] In a possible implementation, the control method of the concentrating photovoltaic power generation system further includes:

[0115] Determine a training sample set, where each training sample in the training sample set includes: geographical location data, time series data, and historical meteorological data of the target area, as well as the optimal position label and optimal inclination angle label of the photovoltaic panel corresponding to different meteorological conditions and different moments at the geographical location, and the travel label corresponding to moving to the optimal position and the rotation angle label corresponding to rotating to the optimal inclination angle;

[0116] Input the training sample set into the preset long short-term memory network model for training to obtain a trained long short-term memory network model;

[0117] Wherein, the optimal position and the optimal inclination angle are the position and inclination angle of the photovoltaic panel when the light concentrated by the concentrator is perpendicularly incident on the photosensitive surface of the photovoltaic panel.

[0118] In specific implementation, collect the historical data of the target area where the concentrating photovoltaic power generation system is located in the past year, including about 100,000 sets of time series data, historical meteorological data, and geographical location data, and construct a training data set. Each training sample includes: geographical location data, time series data, and historical meteorological data, as well as the optimal position label and optimal inclination angle label of the photovoltaic panel corresponding to different meteorological conditions and different moments at the geographical location, and the travel label corresponding to moving to the optimal position and the rotation angle label corresponding to rotating to the optimal inclination angle. The optimal position and the optimal inclination angle are the position and inclination angle of the photovoltaic panel when the light concentrated by the concentrator is perpendicularly incident on the photosensitive surface of the photovoltaic panel, and are the position and inclination angle that enable the photovoltaic panel to receive solar energy to the greatest extent.

[0119] In a possible implementation, input the constructed training data set into the long short-term memory network model for training. The training process is as follows: input the training data set into the model through the input layer. The input layer converts the original training data set into a numerical form that can be processed by the model and inputs it to the first fully connected structure. The first fully connected structure establishes a complex mapping relationship between different geographical locations, different meteorological conditions, different times and the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter. Then, input the mapping result into the second fully connected structure. The second fully connected structure establishes a complex mapping relationship between different solar hour angles, different solar azimuth angles, and different solar altitude angles and the optimal position and optimal inclination angle of the photovoltaic panel at different moments. Then, input the mapping result into the third fully connected structure. The third fully connected structure establishes a complex mapping relationship between the optimal position and optimal inclination angle of the photovoltaic panel at different moments and the travel distance that the photovoltaic panel needs to move and the rotation angle that it needs to rotate between adjacent moments. Finally, output the travel distance and rotation angle that the photovoltaic panel needs to move between different moments through the linear activation function of the output layer.

[0120] In a possible implementation, predicting the target travel and target rotation angle of the photovoltaic panel from the current moment to the next moment according to the geographical location data, the real-time meteorological data, the time data at the current moment, and the trained long short-term memory network model includes:

[0121] Input the geographical location data, the real-time meteorological data, and the time data at the current moment through the input layer into the first fully connected structure. The first fully connected structure outputs the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment, and inputs the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment into the second fully connected structure;

[0122] The second fully connected structure determines the predicted position and predicted inclination angle of the photovoltaic panel at the next moment according to the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment, and inputs the predicted position and predicted inclination angle of the photovoltaic panel into the third fully connected structure;

[0123] The third fully connected structure determines the target travel corresponding to the photovoltaic panel moving to the predicted position and the target rotation angle corresponding to rotating to the predicted inclination angle according to the predicted position and predicted inclination angle

[0124] The output layer outputs the target travel and target rotation angle.

[0125] In this embodiment, the long short-term memory network model establishes a complex mapping relationship between factors such as lighting conditions, time, geographical location, and weather, and the optimal position and optimal inclination angle of the photovoltaic panel, as well as the travel and rotation angle of the photovoltaic panel corresponding to adjacent moments through learning and analysis of a large amount of historical data. In actual use, the long short-term memory network model predicts the predicted position and predicted inclination angle of the photovoltaic panel at the next moment according to the parameters at the current moment (such as light intensity, direction, time, temperature, wind speed, etc.). This predicted position and predicted inclination angle are the ideal angles that enable the photovoltaic panel to receive solar energy to the greatest extent.

[0126] In this embodiment, by training and using the long short-term memory network model, accurate prediction of the optimal position and optimal inclination angle of the photovoltaic panel under different geographical locations, different meteorological conditions, and different moments is realized, and then corresponding pulse control instructions are generated to control the guide rail motor and the photovoltaic motor to drive the movement and rotation of the photovoltaic panel, realizing precise and stable control of the photovoltaic panel, so that the photovoltaic panel always moves with the changes of the solar altitude angle, azimuth angle, and hour angle, effectively improving the stability and reliability of the concentrating photovoltaic power generation system.

[0127] In a possible implementation, the control method of the concentrating photovoltaic power generation system further includes:

[0128] Detect the light intensity on both sides of the photovoltaic panel in real time;

[0129] Determine the rotation angle of the guide rail motor according to the light intensity on both sides of the photovoltaic panel;

[0130] And generate a first correction instruction according to the rotation angle of the guide rail motor, where the first correction instruction is used to instruct the guide rail motor to rotate to drive the photovoltaic panel to move along the arc-shaped guide rail, correct the position prediction error of the photovoltaic panel, and make the difference in light intensity between both sides of the photovoltaic panel less than a preset light intensity error threshold.

[0131] In a possible implementation manner, the control method of the concentrating photovoltaic power generation system further includes:

[0132] Detect the actual inclination angle of the photovoltaic panel when the photovoltaic panel moves to the predicted position;

[0133] Determine the rotation angle of the photovoltaic motor according to the actual inclination angle and the predicted inclination angle;

[0134] Generate a second correction instruction according to the rotation angle of the photovoltaic motor, where the second correction instruction is used to instruct the photovoltaic motor to rotate to drive the photovoltaic panel to rotate around its own central axis, correct the inclination angle prediction error of the photovoltaic panel, and make the difference between the actual inclination angle and the predicted inclination angle of the photovoltaic panel less than a preset angle error threshold.

[0135] It should be noted that in this embodiment, the detailed implementation process of correcting the position prediction error and the inclination angle prediction error of the photovoltaic panel can refer to the description in the above related embodiments, and will not be elaborated here.

[0136] In this embodiment, by training and using a long short-term memory network model, the optimal position and optimal inclination angle of the photovoltaic panel at different times can be accurately predicted, and the model integrates meteorological prediction data and moves stably under different meteorological conditions, improving the adaptability and reliability of the concentrating photovoltaic power generation system. Further, by real-time monitoring the sensors on both sides of the photovoltaic panel and the actual inclination angle, and dynamically adjusting the position and inclination angle of the photovoltaic panel, a comprehensive real-time feedback control of the position and inclination angle of the photovoltaic panel is achieved, maximizing the optical utilization rate. Effectively solves the problems of low land utilization rate, poor terrain adaptability, and high optical loss of traditional photovoltaic power generation devices.

[0137] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0138] Figure 6 It is a schematic diagram of the electronic device provided by the embodiment of the present invention. AsFigure 6 As shown, the electronic device 6 of this embodiment includes: a processor 60 and a memory 61. The memory 61 stores a computer program 62. When the processor 60 executes the computer program 62, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 60 executes the computer program 62, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0139] Exemplarily, the computer program 62 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the electronic device 6.

[0140] The electronic device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 6 merely examples of the electronic device 6 do not constitute a limitation on the electronic device 6. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the electronic device 6 may further include input / output devices, network access devices, buses, etc.

[0141] The processor 60 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0142] The memory 61 can be an internal storage unit of the electronic device 6, such as the hard disk or memory of the electronic device 6. The memory 61 can also be an external storage device of the electronic device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 6. Further, the memory 61 can also include both the internal storage unit of the electronic device 6 and the external storage device. The memory 61 is used to store the computer program 62 and other programs and data required by the electronic device 6. The memory 61 can also be used to temporarily store the data that has been output or will be output.

[0143] For the convenience and conciseness of description, only the above-mentioned division of each functional module / unit is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional modules / units according to needs. The above-mentioned module / unit can be implemented in the form of hardware, or in the form of software, or in the form of a combination of hardware and software.

[0144] The embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the methods in the above-mentioned method embodiments are implemented.

[0145] The embodiment of the present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the methods in the above-mentioned method embodiments are implemented.

[0146] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0147] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Without special instructions and logical conflicts, the terms and / or descriptions between different embodiments are consistent and can be referred to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0148] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A concentrating photovoltaic power generation system, characterized in that, Comprising: A condenser lens (1), a guide rail bracket (2), an arc guide rail (3), a photovoltaic panel (4), a gear (5), a guide rail motor (6), a connecting member (7), a guide rail slider (8), and a roller (9) fixedly installed on one side of the guide rail slider (8); The arc guide rail (3) is installed in parallel on both sides of the condenser lens (1) through the guide rail bracket (2), and a rack structure is provided on the convex surface of the arc guide rail (3); the size of the arc guide rail (3) is determined in advance according to the light movement trajectory concentrated by the condenser lens (1); The end of the photovoltaic panel (4) is connected to the guide rail slider (8) through the connecting member (7), and the guide rail slider (8) and the arc guide rail (3) form a sliding fit structure through the roller (9); The guide rail motor (6) is fixedly installed on the guide rail slider (8), the output shaft of the guide rail motor (6) is connected to the gear (5), and the gear (5) meshes with the rack structure of the arc guide rail (3) to form a transmission connection; When the guide rail motor (6) drives the gear (5) to rotate, it drives the guide rail slider (8) to slide on the arc guide rail (3), so as to control the photovoltaic panel (4) to move along the arc trajectory of the arc guide rail (3), so that the light concentrated by the condenser lens (1) irradiates on the photovoltaic panel (4).

2. The concentrating photovoltaic power generation system according to claim 1, characterized in that, Also comprising: A photovoltaic motor (10); The output shaft of the photovoltaic motor (10) is connected to the central axis of the photovoltaic panel (4), and is used to drive the photovoltaic panel (4) to rotate around its own central axis, so as to adjust the pitch angle of the photovoltaic panel (4), so that the incident angle of the light concentrated by the condenser lens (1) irradiating on the photovoltaic panel (4) is less than a preset threshold value.

3. The concentrating photovoltaic power generation system according to claim 2, wherein, Also comprising: A GPS module, a wireless communication module, and a controller. The GPS module and the wireless communication module are both in communication with the controller, and the controller is electrically connected to the guide rail motor (6) and the photovoltaic motor (10); The GPS module is used to collect geographical location data and send the geographical location data to the controller; The wireless communication module is used to obtain real-time meteorological data and send the real-time meteorological data to the controller; The controller is used to: determine the predicted position and predicted inclination angle of the photovoltaic panel (4) at the next moment according to the geographical location data, the real-time meteorological data, and the time data at the current moment; According to the predicted position and predicted inclination angle at the next moment, determine the target travel corresponding to the photovoltaic panel (4) moving to the predicted position and the target rotation angle corresponding to rotating to the predicted inclination angle; Generate a pulse control signal according to the target travel and the target rotation angle, and send the pulse control signal to the guide rail motor (6) and the photovoltaic motor (10), so as to drive the guide rail motor (6) and the photovoltaic motor (10) to rotate, and drive the photovoltaic panel (4) to move to the predicted position and rotate to the predicted inclination angle.

4. The concentrating photovoltaic power generation system according to claim 3, wherein, Also comprising: The light intensity sensors (11) symmetrically installed on both sides of the photovoltaic panel (4) communicate with the controller, and are used to detect the light intensity on both sides of the photovoltaic panel (4) in real time and send the light intensity on both sides of the photovoltaic panel (4) to the controller; The controller determines the rotation angle of the guide rail motor (6) according to the light intensity on both sides of the photovoltaic panel (4), and generates a first correction instruction according to the rotation angle of the guide rail motor (6). The first correction instruction is used to instruct the guide rail motor (6) to rotate to drive the photovoltaic panel (4) to move along the arc-shaped guide rail (3), correct the position prediction error of the photovoltaic panel (4), and make the difference between the light intensities on both sides of the photovoltaic panel (4) less than a preset light intensity error threshold.

5. The concentrating photovoltaic power generation system according to claim 3, wherein, It further includes: An inclination sensor installed on the photovoltaic panel. The inclination sensor communicates with the controller and is used to detect the actual inclination angle of the photovoltaic panel (4) when it moves to the predicted position and send the actual inclination angle to the controller; The controller determines the rotation angle of the photovoltaic motor (10) according to the actual inclination angle and the predicted inclination angle, and generates a second correction instruction according to the rotation angle of the photovoltaic motor (10). The second correction instruction is used to instruct the photovoltaic motor (10) to rotate to drive the photovoltaic panel (4) to rotate around its own central axis, correct the inclination prediction error of the photovoltaic panel (4), and make the difference between the actual inclination angle and the predicted inclination angle of the photovoltaic panel (4) less than a preset angle error threshold.

6. A control method for a concentrating photovoltaic power generation system according to any one of claims 2 to 5, characterized in that, It includes: Obtain the geographical location data, real-time meteorological data, and time data at the current moment of the target area where the concentrating photovoltaic power generation system is located; According to the geographical location data, the real-time meteorological data, the time data at the current moment, and the trained long short-term memory network model, predict the target travel and target rotation angle of the photovoltaic panel from the current moment to the next moment; Generate a first pulse control signal according to the target travel, and generate a second pulse control signal according to the target rotation angle; Send the first pulse control signal to the guide rail motor, so that the guide rail motor controls the movement of the photovoltaic panel according to the first pulse signal, and send the second pulse signal to the photovoltaic motor, so that the photovoltaic motor controls the photovoltaic panel to rotate around its own central axis according to the second pulse signal to adjust the pitch angle.

7. The control method of the concentrating photovoltaic power generation system according to claim 6, characterized in that Before predicting the target travel and target rotation angle of the photovoltaic panel from the current moment to the next moment according to the geographical location data, the real-time meteorological data, the time data at the current moment, and the trained long short-term memory network model, the method further includes: Determine a training sample set. Each training sample in the training sample set includes: the geographical location data of the target area, time series data, historical meteorological data, and the optimal position label and optimal inclination label of the photovoltaic panel corresponding to different meteorological conditions and different moments at the geographical location, as well as the travel label corresponding to moving to the optimal position and the rotation angle label corresponding to rotating to the optimal inclination; Input the training sample set into a preset long short-term memory network model for training to obtain a trained long short-term memory network model; Among them, the optimal position and the optimal inclination angle are the position and inclination angle corresponding to the photovoltaic panel when the light concentrated by the condenser is perpendicularly irradiated on the photosensitive surface of the photovoltaic panel.

8. The control method of the concentrating photovoltaic power generation system according to claim 6, characterized in that, The long short-term memory network model includes an input layer, a hidden layer, and an output layer, and the hidden layer includes a three-layer fully connected structure; Predicting the target travel and target rotation angle of the photovoltaic panel from the current moment to the next moment according to the geographical location data, the real-time meteorological data, the time data at the current moment, and the trained long short-term memory network model includes: Input the geographical location data, the real-time meteorological data, and the time data at the current moment through the input layer into the first fully connected structure. The first fully connected structure outputs the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment, and inputs the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment into the second fully connected structure; The second fully connected structure determines the predicted position and predicted inclination angle of the photovoltaic panel at the next moment according to the solar hour angle parameter, solar azimuth angle parameter, and solar altitude angle parameter corresponding to the next moment, and inputs the predicted position and predicted inclination angle of the photovoltaic panel into the third fully connected structure; The third fully connected structure determines the target travel corresponding to the photovoltaic panel moving to the predicted position and the target rotation angle corresponding to rotating to the predicted inclination angle according to the predicted position and predicted inclination angle The output layer outputs the target travel and target rotation angle.

9. The control method of the concentrating photovoltaic power generation system according to claim 8, characterized in that, It also includes: Detect the light intensity on both sides of the photovoltaic panel in real time; Determine the rotation angle of the guide rail motor according to the light intensity on both sides of the photovoltaic panel; And generate a first correction instruction according to the rotation angle of the guide rail motor. The first correction instruction is used to instruct the guide rail motor to rotate to drive the photovoltaic panel to move along the arc-shaped guide rail, correct the position prediction error of the photovoltaic panel, and make the difference in light intensity between both sides of the photovoltaic panel less than a preset light intensity error threshold.

10. The control method of the concentrating photovoltaic power generation system according to claim 8, characterized in that, It also includes: Detect the actual inclination angle of the photovoltaic panel when the photovoltaic panel moves to the predicted position; Determine the rotation angle of the photovoltaic motor according to the actual inclination angle and the predicted inclination angle; Generate a second correction instruction according to the rotation angle of the photovoltaic motor. The second correction instruction is used to instruct the photovoltaic motor to rotate to drive the photovoltaic panel to rotate around its own central axis, correct the inclination angle prediction error of the photovoltaic panel, and make the difference between the actual inclination angle and the predicted inclination angle of the photovoltaic panel less than a preset angle error threshold.

Images