Tracking angle correction method and device of heliostat, storage medium and electronic equipment

Abstract

The application provides a heliostat tracking angle correction method and device, a storage medium and electronic equipment. The method comprises the following steps: in response to a correction instruction, obtaining a to-be-processed gray image, wherein the gray image is converted from a heliostat image; the heliostat image is obtained by photographing at least one heliostat by a camera device; determining a gray image area of each heliostat in the gray image; determining a gray characteristic of each heliostat according to the gray image area of each heliostat; determining a tracking error parameter corresponding to the gray characteristic of each heliostat; and correcting the tracking angle of each heliostat according to the tracking error parameter corresponding to the gray characteristic of each heliostat. According to the method provided by the application, the heliostat can be accurately tracked and corrected without a heliostat light condensation characteristic analysis system.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a method, device, storage medium, and electronic device for correcting the tracking angle of a heliostat. Background Technology

[0002] With the continuous development of new energy technologies, tower solar power plants have been increasingly widely used. Tower solar power plants can convert solar energy into thermal energy, and then convert thermal energy into electrical energy. In order to ensure the efficient power generation of tower solar power plants, it is necessary to track and correct the heliostats of tower solar power plants so as to effectively convert solar energy into thermal energy.

[0003] In existing technologies, the tracking axis reference position misalignment method is typically used for heliostat tracking correction. Specifically, this involves calculating the correction amount of the heliostat's tracking axis reference position using the heliostat's tracking trajectory data to compensate for the initial angle of the tracking axis, thereby reducing the tracking error of the heliostat over time. However, both the tracking axis reference position misalignment method and tracking correction based on geometric error models require a heliostat focusing characteristic analysis system. Since the accuracy of existing heliostat focusing characteristic analysis systems is relatively poor, they cannot accurately perform tracking correction on the heliostat. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a method, device, storage medium, and electronic device for tracking angle correction of a heliostat, capable of accurately tracking and correcting the heliostat. The specific solution is as follows:

[0005] A method for correcting the tracking angle of a heliostat, comprising:

[0006] In response to a correction command, a grayscale image to be processed is obtained, which is converted from a heliostat image; the heliostat image is obtained by a camera device capturing images of at least one heliostat.

[0007] The grayscale image region of each heliostat is determined in the grayscale image;

[0008] The grayscale characteristics of each heliostat are determined based on the grayscale image region of each heliostat;

[0009] Determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat;

[0010] The tracking angle of each heliostat is corrected based on the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0011] Optionally, in the above method, determining the grayscale image region of each heliostat in the grayscale image includes:

[0012] The grayscale image is detected using a pre-trained target detection model to determine the grayscale image region of each heliostat.

[0013] Optionally, the training process of the target detection model in the above method includes:

[0014] Obtain a training dataset and an initial object detection model; the training dataset includes multiple training data, including heliostat grayscale images and corresponding label information for the heliostat grayscale images;

[0015] Select the target training data to be input from the training dataset;

[0016] The target training data is input into the initial target detection model to obtain the detection result corresponding to the target training data;

[0017] The loss function value is calculated using a preset loss function based on the label information in the target training data and the detection results.

[0018] The model parameters of the initial object detection model are updated using the loss function value;

[0019] If the initial target detection model after updating the model parameters does not meet the preset training conditions, the process returns to the step of selecting the target training data to be input from the training dataset.

[0020] If the initial target detection model after updating the model parameters meets the preset training conditions, the initial target detection model after updating the model parameters is determined as the trained target detection model.

[0021] Optionally, the above method involves determining the grayscale characteristics of each heliostat based on the grayscale image region of each heliostat, including:

[0022] Determine the grayscale value of each pixel within the grayscale image region of each heliostat;

[0023] The grayscale characteristics of each heliostat are calculated based on the grayscale value of each pixel within the grayscale image region of each heliostat.

[0024] Optionally, the above method involves determining the tracking error parameters corresponding to the grayscale characteristics of each heliostat, including:

[0025] Based on the grayscale characteristics of each heliostat and the corresponding relationship curve of each heliostat, the tracking error parameters corresponding to the grayscale characteristics of each heliostat are obtained.

[0026] Optionally, in the above method, correcting the tracking angle of each heliostat based on the tracking error parameter corresponding to the grayscale characteristics of each heliostat includes:

[0027] The tracking angle correction amount for each heliostat is determined based on each of the tracking error parameters;

[0028] The tracking angle of each heliostat is corrected based on the tracking angle correction amount of each heliostat.

[0029] A tracking angle correction device for a heliostat, comprising:

[0030] An execution unit is configured to, in response to a correction command, obtain a grayscale image to be processed, the grayscale image being converted from a heliostat image; the heliostat image being obtained by a camera device capturing images of at least one heliostat.

[0031] The first determining unit is used to determine the grayscale image region of each of the heliostats in the grayscale image;

[0032] The second determining unit is used to determine the grayscale characteristics of each heliostat based on the grayscale image region of each heliostat.

[0033] The third determining unit is used to determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0034] The correction unit is used to correct the tracking angle of each heliostat according to the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0035] Optionally, the first determining unit in the aforementioned apparatus includes:

[0036] The detection subunit is used to detect the grayscale image using a pre-trained target detection model to determine the grayscale image region of each heliostat.

[0037] Optionally, the second determining unit in the aforementioned apparatus includes:

[0038] The first determining subunit is used to determine the gray value of each pixel within the grayscale image region of each heliostat;

[0039] The calculation subunit is used to calculate the grayscale characteristics of each heliostat based on the grayscale value of each pixel within the grayscale image region of each heliostat.

[0040] Optionally, the third determining unit in the aforementioned apparatus includes:

[0041] The second determining subunit is used to obtain the tracking error parameters corresponding to the grayscale characteristics of each heliostat based on the grayscale characteristics of each heliostat and the corresponding relationship curve of each heliostat.

[0042] A storage medium comprising storage instructions, wherein, when the instructions are executed, the device in which the storage medium is located executes a heliostat tracking angle correction method as described above.

[0043] An electronic device includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described above for the tracking angle correction method of a heliostat.

[0044] Compared with the prior art, the present invention has the following advantages:

[0045] This invention provides a method, apparatus, storage medium, and electronic device for correcting the tracking angle of a heliostat. Responding to a correction command, a grayscale image to be processed is obtained, which is converted from a heliostat image. The heliostat image is obtained by a camera capturing images of at least one heliostat. A grayscale image region for each heliostat is determined within the grayscale image. Grayscale characteristics of each heliostat are determined based on its grayscale image region. Tracking error parameters corresponding to the grayscale characteristics of each heliostat are determined. The tracking angle of each heliostat is corrected based on the tracking error parameters corresponding to its grayscale characteristics. Using the method provided in this invention, accurate tracking correction of a heliostat can be achieved without a heliostat focusing characteristic analysis system. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0047] Figure 1 A flowchart of a method for correcting the tracking angle of a heliostat provided by the present invention;

[0048] Figure 2 An example diagram illustrating an implementation scenario of the present invention;

[0049] Figure 3 A flowchart of the image processing procedure for a target detection model provided by the present invention;

[0050] Figure 4A flowchart illustrating the process of training a target detection model provided by this invention;

[0051] Figure 5 An example diagram of a relationship curve provided by the present invention;

[0052] Figure 6 A schematic diagram of the structure of a tracking angle correction device for a heliostat provided by the present invention;

[0053] Figure 7 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0056] In existing technologies, the tracking axis reference position misalignment method is typically used for heliostat tracking correction. Specifically, this involves calculating the correction amount of the heliostat's tracking axis reference position using the heliostat's tracking trajectory data to compensate for the initial angle of the tracking axis, thereby reducing the tracking error of the heliostat over time. However, both the tracking axis reference position misalignment method and tracking correction based on geometric error models require a heliostat focusing characteristic analysis system. Since the accuracy of existing heliostat focusing characteristic analysis systems is relatively poor, they cannot accurately perform tracking correction on the heliostat.

[0057] Based on this, embodiments of the present invention provide a tracking angle correction method for a heliostat, which can be applied to electronic devices. The flowchart of the method is shown below. Figure 1 As shown, it specifically includes:

[0058] S101: In response to a correction command, obtain a grayscale image to be processed, the grayscale image being converted from a heliostat image; the heliostat image being obtained by a camera device capturing images of at least one heliostat.

[0059] In this embodiment, see Figure 2 The number of camera devices can be one or more, and the field of view of each camera device can include one or more heliostats. The camera device can be a CCD camera. When there are multiple camera devices, the specifications of each camera device can be the same.

[0060] Optionally, the heliostats in the heliostat field can be photographed using a camera to obtain heliostat images. These images are then converted to RGB mode. Next, the RGB-converted heliostat images are scaled, for example, to 416×416. After scaling, the scaled heliostat images are processed using bicubic interpolation. Finally, the processed heliostat images are converted to grayscale.

[0061] S102: Determine the grayscale image region of each of the heliostats in the grayscale image.

[0062] In this embodiment, the grayscale image can be normalized, and then the coordinate range of each heliostat in the grayscale image can be determined. Based on the coordinate range, the grayscale image region of each heliostat in the grayscale image can be determined.

[0063] S103: Determine the grayscale characteristics of each heliostat based on the grayscale image region of each heliostat.

[0064] In this embodiment, the grayscale characteristics of each heliostat may include the average grayscale value within the grayscale image region of each heliostat.

[0065] S104: Determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0066] Optionally, the tracking error parameters corresponding to the grayscale characteristics of each heliostat can be obtained by using the grayscale characteristics of each heliostat and a preset relationship curve.

[0067] S105: Correct the tracking angle of each heliostat according to the tracking error parameter corresponding to the grayscale characteristics of each heliostat.

[0068] In this embodiment, the tracking angle correction amount of each heliostat can be determined according to the tracking error parameters corresponding to the grayscale characteristics of each heliostat. Then, a correction instruction corresponding to each heliostat is generated based on the tracking angle correction amount of each heliostat. The correction instruction is used to instruct the tracking angle of the heliostat to be corrected based on the tracking angle correction amount of the heliostat.

[0069] By applying the method provided in this embodiment of the invention, accurate tracking and correction of heliostats can be achieved without a heliostat focusing characteristic analysis system, and the tracking angles of multiple heliostats can be corrected simultaneously, which greatly improves the tracking and correction efficiency of heliostats.

[0070] In one embodiment of the present invention, based on the above implementation process, optionally, determining the grayscale image region of each heliostat in the grayscale image includes:

[0071] The grayscale image is detected using a pre-trained target detection model to determine the grayscale image region of each heliostat.

[0072] In this embodiment, a pre-trained target detection model is used to detect the grayscale image, obtaining detection results. These results include the pixel coordinates, score, and shape type of the heliostat. The target detection model can be the YOLOv3 model. The YOLOv3 model works by dividing the heliostat field image into N×N grid cells, each with an equal-sized region. Each of these N×N grid cells is responsible for detecting and locating the target contained within that grid.

[0073] YOLOv3 employs the Darknet-53 network architecture, consisting of convolutional and residual structures. The output has three scales, with local feature interactions achieved through convolutional kernels within each scale. These three scales correspond to different target detection types: 13×13 for large targets, 26×26 for medium targets, and 52×52 for small targets. A schematic diagram of the heliostat detection process based on YOLOv3 is shown below. Figure 3 As shown, multi-scale outputs can detect targets of different sizes.

[0074] Optionally, a corner detection algorithm can be used to obtain the coordinates of each corner point of the heliostat based on the detection results. The number of corner point coordinates can be multiple, for example, four. Specifically, Canny edge detection is used to find edges in the image. By calculating the gradient and direction of each pixel in the image, the intensity and direction of the edges are determined. Then, non-maximum suppression and double thresholding are used to extract the final edge results. Next, a contour detection algorithm is used to extract the boundary contour of the object while preserving its shape and structure, and various features of the contour can be calculated. Finally, the Douglas-Peucker algorithm is used to traverse the contour, and the leftmost, rightmost, topmost, and bottommost points of the contour are obtained, which are the four corner points of the heliostat.

[0075] In some embodiments, after obtaining the corner coordinates of the heliostat, the grayscale characteristics of the heliostat can be calculated based on these corner coordinates. For example, the first... The coordinates of the corner point of the heliostat are , , and Then the grayscale characteristics of this heliostat It is the average value of all gray values ​​within the parallelogram corresponding to the four corner points. This parallelogram can be the grayscale image region of the heliostat.

[0076] In one embodiment of the present invention, based on the above implementation process, optionally, the training process of the target detection model is as follows: Figure 4 As shown, it includes:

[0077] S401: Obtain the training dataset and the initial object detection model; the training dataset includes multiple training data, including heliostat grayscale images and the label information corresponding to the heliostat grayscale images.

[0078] In this embodiment, the tag information may include the pixel coordinates of the heliostat, its score, and its type.

[0079] S402: Select the target training data to be input from the training dataset.

[0080] In this embodiment, training data can be selected as target training data in sequence according to the arrangement order of the training data in the training dataset.

[0081] Optionally, the target training data can be the training data to be input into the initial target detection model.

[0082] S403: Input the target training data into the initial target detection model to obtain the detection result corresponding to the target training data.

[0083] Optionally, the detection results corresponding to the training data may include the pixel coordinates, scores, and types of heliostats identified by the initial target detection model.

[0084] S404: Calculate the loss function value based on the label information in the target training data and the detection results using a preset loss function.

[0085] In this embodiment, the loss function can be composed of at least one of the following: center coordinate error function (dist_xy), width and height coordinate error function (dist_wh), confidence error function (dist_C), and classification error function (dist_P), as follows:

[0086]

[0087] Optionally, the center coordinate error function (dist_xy) is:

[0088]

[0089] Optionally, the width and height coordinate error function (dist_wh) is:

[0090]

[0091] The confidence error function (dist_C) is:

[0092]

[0093] The classification error function (dist_P) is:

[0094]

[0095] In the formula, Let be the predicted value of the j-th anchor box in the i-th grid from the output of the initial object detection model. For the initial object detection model, the first The first grid The actual label of each anchor box.

[0096] Wherein, the width and height coordinate error functions are squared error functions, the center coordinate error function, the confidence error function, and the classification error function are cross-entropy loss functions; S is the tensor output by the convolutional model. The size of B; B is the tensor. The number of anchor boxes generated for each grid cell; and The weights are used to increase the loss value of grid cells containing objects and decrease the loss value of grid cells without objects, thus facilitating the convergence of the convolution kernel parameters. To determine the first The first grid in the nth grid Does each predicted bounding box contain the target to be detected? If so, then... If not included, then .

[0097] S405: Update the model parameters of the initial target detection model using the loss function value.

[0098] S406: Determine whether the initial object detection model after updating the model parameters meets the preset training conditions; if yes, execute S407; if no, execute S402.

[0099] In this embodiment, the training conditions can be that the number of training iterations meets a preset training iteration threshold, the detection accuracy of the initial object detection model is greater than a preset accuracy threshold, or the loss function value converges.

[0100] S407: The initial target detection model after updating the model parameters is determined as the trained target detection model.

[0101] In one embodiment of the present invention, based on the above implementation process, optionally, the grayscale characteristics of each heliostat are determined according to the grayscale image region of each heliostat, including:

[0102] Determine the grayscale value of each pixel within the grayscale image region of each heliostat;

[0103] The grayscale characteristics of each heliostat are calculated based on the grayscale value of each pixel within the grayscale image region of each heliostat.

[0104] In this embodiment, for each heliostat, the average gray value of each pixel within the grayscale image region of the heliostat can be calculated to obtain the grayscale characteristics of the heliostat.

[0105] In some embodiments, it can be determined whether each heliostat meets the preset tracking correction conditions based on the grayscale characteristics of each heliostat. For a heliostat that meets the tracking correction conditions, the tracking error parameter corresponding to the grayscale characteristics of the heliostat that meets the tracking correction conditions is determined. Then, the tracking angle of the heliostat that meets the tracking correction conditions is corrected based on the tracking error parameter corresponding to the grayscale characteristics of the heliostat that meets the tracking correction conditions.

[0106] Optionally, the grayscale characteristic ratio of the effective region of the heliostat in the grayscale image of the mirror field acquired by the symmetrical image acquisition device (camera device) is... ,when If the tracking error of the heliostat does not meet the tracking correction condition, then the heliostat is determined to meet the tracking correction condition. This enables rapid identification of heliostats that need tracking correction without polling the heliostats, greatly improving the efficiency of heliostat field tracking correction.

[0107] In one embodiment of the present invention, based on the above implementation process, optionally, determining the tracking error parameter corresponding to the grayscale characteristics of each heliostat includes:

[0108] Based on the grayscale characteristics of each heliostat and the corresponding relationship curve of each heliostat, the tracking error parameters corresponding to the grayscale characteristics of each heliostat are obtained.

[0109] In this embodiment, for each heliostat, the ratio between the grayscale characteristic of the heliostat and the standard grayscale characteristic corresponding to the heliostat is determined. Determine the ratio from the relationship curve. The corresponding tracking error parameters.

[0110] Optionally, the tracking error parameters may include horizontal tracking error parameters. and pitch tracking error parameters The horizontal tracking error parameter characterizes the degree of tracking error of the heliostat in the horizontal direction; the pitch tracking error parameter characterizes the degree of tracking error of the heliostat in the pitch direction.

[0111] In this embodiment, as Figure 5 As shown, the relationship curves corresponding to each heliostat record the correspondence between different grayscale characteristic ratios of that heliostat and different tracking error parameters.

[0112] In some embodiments, a relationship curve for the heliostat can be constructed. Specifically, this process involves controlling the position of the heliostat's spot while simultaneously controlling four image acquisition systems to acquire images of the mirror field. The grayscale characteristics of the heliostat in these four images are then analyzed. This process is repeated, controlling the position of the heliostat's spot to vary, to obtain multiple sets of relationships between the spot positions and the grayscale characteristics within the effective region of the heliostat. Based on the spot positions, the tracking error parameters of the heliostat are determined. Based on these tracking error parameters corresponding to the multiple sets of spot positions and the grayscale characteristics within the effective region of the heliostat, a relationship curve between the ratio of grayscale values ​​within the effective region and the tracking error of the heliostat is fitted.

[0113] In one embodiment of the present invention, based on the above implementation process, optionally, the step of correcting the tracking angle of each heliostat according to the tracking error parameter corresponding to the grayscale characteristics of each heliostat includes:

[0114] The tracking angle correction amount for each heliostat is determined based on each of the tracking error parameters;

[0115] The tracking angle of each heliostat is corrected based on the tracking angle correction amount of each heliostat.

[0116] In this embodiment, the correction amounts for the azimuth and pitch tracking angles corresponding to the tracking errors in the horizontal and pitch directions can be calculated based on the geometrical relationship between the heliostat and the receiver. , The tracking angle of the heliostat after tracking correction is shown below:

[0117]

[0118] in, For the heliostat's azimuth tracking angle, The elevation tracking angle of the heliostat. The initial angle for the heliostat's azimuth. This is the initial pitch angle of the heliostat.

[0119] The heliostat tracking and correction system is equipped with a database that stores the image acquisition time, grayscale characteristics of the effective area of ​​the heliostat in the image, azimuth tracking error, pitch tracking error, azimuth tracking angle correction, and pitch tracking angle correction in the database.

[0120] In some embodiments, the heliostat correction frequency can be determined based on the tracking quality of the heliostat. For example, a correction frequency of once per hour can be used to obtain a set of correction values ​​for the tracking angles. Simultaneously, this set of correction values ​​can be used for all tracking angles of the heliostat within this hour.

[0121] and Figure 1 Corresponding to the method described above, this embodiment of the invention also provides a tracking angle correction device for a heliostat, used for... Figure 1 The specific implementation of the method, the tracking angle correction device for the heliostat provided in this embodiment of the invention, can be applied to electronic devices, and its structural schematic diagram is shown below. Figure 6 As shown, it specifically includes:

[0122] The execution unit 601 is configured to obtain a grayscale image to be processed in response to a correction command, the grayscale image being converted from a heliostat image; the heliostat image being obtained by a camera device capturing an image of at least one heliostat.

[0123] The first determining unit 602 is used to determine the grayscale image region of each heliostat in the grayscale image;

[0124] The second determining unit 603 is used to determine the grayscale characteristics of each heliostat based on the grayscale image region of each heliostat.

[0125] The third determining unit 604 is used to determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0126] The correction unit 605 is used to correct the tracking angle of each heliostat according to the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0127] In one embodiment of the present invention, based on the above-described solution, optionally, the first determining unit 602 includes:

[0128] The detection subunit is used to detect the grayscale image using a pre-trained target detection model to determine the grayscale image region of each heliostat.

[0129] In one embodiment of the present invention, based on the above-described solution, optionally, the second determining unit 603 includes:

[0130] The first determining subunit is used to determine the gray value of each pixel within the grayscale image region of each heliostat;

[0131] The calculation subunit is used to calculate the grayscale characteristics of each heliostat based on the grayscale value of each pixel within the grayscale image region of each heliostat.

[0132] In one embodiment of the present invention, based on the above-described solution, optionally, the third determining unit 604 includes:

[0133] The second determining subunit is used to obtain the tracking error parameters corresponding to the grayscale characteristics of each heliostat based on the grayscale characteristics of each heliostat and the corresponding relationship curve of each heliostat.

[0134] The specific principles and execution processes of each unit and module in the heliostat tracking angle correction device disclosed in the above embodiments of the present invention are the same as those of the heliostat tracking angle correction method disclosed in the above embodiments of the present invention. Please refer to the corresponding parts of the heliostat tracking angle correction method provided in the above embodiments of the present invention, and they will not be repeated here.

[0135] This invention also provides a storage medium that includes stored instructions, wherein when the instructions are executed, the device containing the storage medium is controlled to perform the above-described heliostat tracking angle correction method.

[0136] This invention also provides an electronic device, the structural schematic of which is shown below. Figure 7 As shown, it specifically includes a memory 701 and one or more instructions 702, wherein one or more instructions 702 are stored in the memory 701 and configured to be executed by one or more processors 703 to perform the following operations:

[0137] In response to a correction command, a grayscale image to be processed is obtained, which is converted from a heliostat image; the heliostat image is obtained by a camera device capturing images of at least one heliostat.

[0138] The grayscale image region of each heliostat is determined in the grayscale image;

[0139] The grayscale characteristics of each heliostat are determined based on the grayscale image region of each heliostat;

[0140] Determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat;

[0141] The tracking angle of each heliostat is corrected based on the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

[0142] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0143] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0144] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this invention, the functions of each unit can be implemented in one or more software and / or hardware components.

[0145] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0146] The above provides a detailed description of the tracking angle correction method for a heliostat provided by the present invention. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for correcting the tracking angle of a heliostat, characterized in that, include: In response to a correction command, a grayscale image to be processed is obtained, which is converted from a heliostat image; the heliostat image is obtained by a camera device capturing images of at least one heliostat. The grayscale image region of each heliostat is determined in the grayscale image; The grayscale characteristics of each heliostat are determined based on the grayscale image region of each heliostat; Determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat; The tracking angle of each heliostat is corrected based on the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

2. The method according to claim 1, characterized in that, Determining the grayscale image region of each heliostat in the grayscale image includes: The grayscale image is detected using a pre-trained target detection model to determine the grayscale image region of each heliostat.

3. The method according to claim 2, characterized in that, The training process of the target detection model includes: Obtain a training dataset and an initial object detection model; the training dataset includes multiple training data, including heliostat grayscale images and corresponding label information for the heliostat grayscale images; Select the target training data to be input from the training dataset; The target training data is input into the initial target detection model to obtain the detection result corresponding to the target training data; The loss function value is calculated using a preset loss function based on the label information in the target training data and the detection results. The model parameters of the initial object detection model are updated using the loss function value; If the initial target detection model after updating the model parameters does not meet the preset training conditions, the process returns to the step of selecting the target training data to be input from the training dataset. If the initial target detection model after updating the model parameters meets the preset training conditions, the initial target detection model after updating the model parameters is determined as the trained target detection model.

4. The method according to claim 1, characterized in that, The grayscale characteristics of each heliostat are determined based on the grayscale image region of each heliostat, including: Determine the grayscale value of each pixel within the grayscale image region of each heliostat; The grayscale characteristics of each heliostat are calculated based on the grayscale value of each pixel within the grayscale image region of each heliostat.

5. The method according to claim 1, characterized in that, Determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat, including: Based on the grayscale characteristics of each heliostat and the corresponding relationship curve of each heliostat, the tracking error parameters corresponding to the grayscale characteristics of each heliostat are obtained.

6. The method according to claim 1, characterized in that, The step of correcting the tracking angle of each heliostat based on the tracking error parameters corresponding to the grayscale characteristics of each heliostat includes: The tracking angle correction amount for each heliostat is determined based on each of the tracking error parameters; The tracking angle of each heliostat is corrected based on the tracking angle correction amount of each heliostat.

7. A tracking angle correction device for a heliostat, characterized in that, include: An execution unit is configured to, in response to a correction command, obtain a grayscale image to be processed, the grayscale image being converted from a heliostat image; the heliostat image being obtained by a camera device capturing images of at least one heliostat. The first determining unit is used to determine the grayscale image region of each of the heliostats in the grayscale image; The second determining unit is used to determine the grayscale characteristics of each heliostat based on the grayscale image region of each heliostat. The third determining unit is used to determine the tracking error parameters corresponding to the grayscale characteristics of each heliostat. The correction unit is used to correct the tracking angle of each heliostat according to the tracking error parameters corresponding to the grayscale characteristics of each heliostat.

8. The apparatus according to claim 7, characterized in that, The first determining unit includes: The detection subunit is used to detect the grayscale image using a pre-trained target detection model to determine the grayscale image region of each heliostat.

9. A storage medium, characterized in that, The storage medium includes stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the tracking angle correction method for a heliostat as described in any one of claims 1 to 6.

10. An electronic device comprising a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors using the tracking angle correction method for a heliostat as described in any one of claims 1 to 6.

Images