Automatic tracking photovoltaic system for track plate

Abstract

The invention discloses an automatic tracking photovoltaic system for a track plate, and relates to the field of photovoltaic technology, and the system comprises a tracking support set obtaining module which is used for laying photovoltaic plates on a target ballastless track, and obtaining K rotating shafts which are laid and K tracking support sets which are connected through the K rotating shafts; the reliability evaluation module is used for obtaining K tracking reliability evaluation result sets; the driven rotating shaft determining module is used for determining a main rotating shaft and (K-1) driven rotating shafts in the K rotating shafts; the tracking regulation and control scheme obtaining module is used for obtaining a main rotating shaft tracking regulation and control scheme; and the automatic tracking regulation and control scheme obtaining module is used for obtaining K-1 driven rotating shaft tracking regulation and control schemes for regulating and controlling the K-1 driven rotating shafts and obtaining an automatic tracking regulation and control scheme after summarizing the K-1 driven rotating shaft tracking regulation and control schemes. The technical problems that in the prior art, the expectation cannot be achieved during photovoltaic automatic tracking, and the tracking regulation and control accuracy is low are solved, and the technical effect of improving the tracking regulation and control quality is achieved.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic technology, and particularly to an automatic tracking photovoltaic system for track slabs. Background Art

[0002] A large number of ballastless tracks are laid in the wild. Not only is the land utilization rate low, but the track slabs are also prone to buckling deformation and interlayer separation due to temperature changes under long-term sunlight irradiation, which affects the service safety and stability of the track system. This is an important challenge faced during the service process of ballastless tracks. The photovoltaic system converts solar energy into electrical energy through solar panels. Laying the photovoltaic system using the space of ballastless tracks can improve land and space utilization rates and realize the conversion of rich solar energy resources into electrical energy for use. At the same time, after the photovoltaic system absorbs solar energy, it can reduce the sunlight irradiating on the track slabs, thereby alleviating the problem of buckling deformation of the track slabs, which has significant benefits. Since the power generation efficiency of the photovoltaic system is affected by factors such as solar radiation intensity, illumination time, and the installation angle of photovoltaic modules, currently, the traditional fixed support type photovoltaic system cannot be dynamically adjusted according to the change of the sun's position, resulting in limited power generation efficiency.

[0003] In the prior art, there are technical problems that the expected effect cannot be achieved during photovoltaic automatic tracking and the tracking regulation accuracy is low. Summary of the Invention

[0004] This application provides an automatic tracking photovoltaic system for track slabs, which is used to solve the technical problems that the expected effect cannot be achieved during photovoltaic automatic tracking and the tracking regulation accuracy is low in the prior art.

[0005] In view of the above problems, this application provides an automatic tracking photovoltaic system for track slabs, and the system includes: A tracking support set acquisition module, which is used to lay photovoltaic panels on the target ballastless track, and obtain K rotating shafts after laying and K tracking support sets respectively connected by the K rotating shafts, where K is a positive integer; A reliability evaluation module, which is used to obtain the historical synchronous tracking data of the K tracking support sets and the corresponding timestamps to evaluate the tracking reliability of each tracking support, and obtain a set of K tracking reliability evaluation results; A driven rotating shaft determination module, which is used to determine the main rotating shaft and K - 1 driven rotating shafts among the K rotating shafts based on the set of K tracking reliability evaluation results; A tracking regulation plan acquisition module, which is used to collect the sun position information at the current moment, and combine the information captured by the sensor components arranged on each tracking support connected to the main rotating shaft to perform tracking adjustment analysis, and obtain a tracking regulation plan for the main rotating shaft; An automatic tracking control scheme acquisition module is configured to perform co-axis analysis on the same axis by combining the K sets of tracking reliability evaluation results and the main rotating shaft tracking control scheme, obtain K - 1 driven rotating shaft tracking control schemes for controlling the K - 1 driven rotating shafts, and summarize the K - 1 driven rotating shaft tracking control schemes and the main rotating shaft tracking control scheme to obtain an automatic tracking control scheme.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: In this application, by laying photovoltaic panels on the target ballastless track, K rotating shafts after laying are obtained, and K sets of tracking brackets respectively connected by the K rotating shafts are obtained, where K is a positive integer. Then, historical synchronous tracking data of the K sets of tracking brackets and corresponding timestamps are obtained to evaluate the tracking reliability of each tracking bracket, and K sets of tracking reliability evaluation results are obtained. Furthermore, based on the K sets of tracking reliability evaluation results, the main rotating shaft and K - 1 driven rotating shafts among the K rotating shafts are determined. Then, the solar position information at the current moment is collected, and combined with the information captured by the sensor components arranged on each tracking bracket connected to the main rotating shaft, tracking adjustment analysis is performed to obtain a main rotating shaft tracking control scheme. By combining the K sets of tracking reliability evaluation results and the main rotating shaft tracking control scheme for co-axis analysis on the same axis, K - 1 driven rotating shaft tracking control schemes for controlling the K - 1 driven rotating shafts are obtained, and the K - 1 driven rotating shaft tracking control schemes and the main rotating shaft tracking control scheme are summarized to obtain an automatic tracking control scheme. The technical effect of providing automatic tracking reliability according to the photovoltaic is achieved. Description of the Drawings

[0007] Figure 1 It is a schematic structural diagram of an automatic tracking photovoltaic system for a track slab provided by an embodiment of this application; Figure 2 It is a schematic flowchart of obtaining K sets of tracking reliability evaluation results in an automatic tracking photovoltaic system for a track slab provided by an embodiment of this application; Description of the reference numerals: Tracking bracket set acquisition module 11, reliability evaluation module 12, driven rotating shaft determination module 13, tracking control scheme acquisition module 14, automatic tracking control scheme acquisition module 15. Detailed Embodiments

[0008] This application provides an automatic tracking photovoltaic system for a track slab to solve the technical problems that the photovoltaic automatic tracking in the prior art cannot achieve the expected effect and the tracking control accuracy is low.

[0009] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0010] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion. For example, a process, system, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, systems, products, or devices.

[0011] Embodiment, such as Figure 1 As shown, the present application provides an automatic tracking photovoltaic system for track slabs. Among them, the system includes: A tracking bracket set acquisition module 11, which is used to lay photovoltaic panels on the target ballastless track, and obtain K rotating shafts that have been laid and K tracking bracket sets respectively connected by the K rotating shafts, where K is a positive integer.

[0012] In a possible embodiment, the target ballastless track is any track that requires photovoltaic panels to be laid on the track slab for photovoltaic tracking. Exemplarily, the specific process of laying the tracking brackets and rotating shafts is as follows: Assume that the longitudinal direction of the target ballastless track, that is, the longitudinal direction, is the length, and the transverse direction is the width. Thus, the following parameters are set: the length of the track slab is a, the width is b, the length of the photovoltaic panel is c, the width is d, the inner distance between the left and right rails is e, the height from the rail top to the upper surface of the track slab is f, the longitudinal distance between the photovoltaic panels is g, the safety distance from the top surface of the photovoltaic panel to the top surface of the rail is h, the left and right safety distances between the photovoltaic panel and the rail are i, the length of the sleeper is j, the transverse sleeper spacing is k, and the installation height of the photovoltaic panel is L. Among them, a, b, c, d, e, f, g, h, i, j, k, and L are all positive integers set by those skilled in the art according to the actual situation.

[0013] Among them, the length c of the photovoltaic panel outside the rail should be selected to be less than or equal to 2k + 2j - g. The width d of the photovoltaic panel outside the rail can be arbitrarily selected, but it should maintain a safety distance i from the rail. Each photovoltaic tracking bracket is installed on the symmetry axis of two adjacent transverse sleepers in the "install one every other two" manner. The installation position of the hinge base of the photovoltaic tracking bracket is at a distance A from the outer edge of the track slab, where A is a positive integer. Among them, the "install one every other two" means installing one photovoltaic tracking bracket every two sleepers. Then the center distance between two adjacent photovoltaic tracking brackets is 2j + 2k, and the required number of photovoltaic tracking brackets is the number of sleepers / 2.

[0014] Between the left and right rails, the width d of the photovoltaic panel should be selected to be less than or equal to e - 2i, and the width of the hinge base of the photovoltaic tracking bracket shall not exceed the distance between the left and right sleepers. Each photovoltaic tracking bracket is installed on the symmetry axis between the left and right sleepers longitudinally. The center distance between adjacent two photovoltaic brackets is c + g. With such a spacing, the photovoltaic tracking brackets are evenly arranged. Then the number of required photovoltaic tracking brackets is a / (c + g), so as to realize the laying of photovoltaic tracking brackets on the target ballastless track. Furthermore, the photovoltaic panel is installed on the top of the tracking bracket, and the sensor assembly is installed on the tracking bracket to complete the laying of the photovoltaic panel.

[0015] The rotating shaft is a mechanical component used to drive multiple tracking brackets to rotate. It is usually laid at a certain interval along the track direction. Each rotating shaft is connected to a group of photovoltaic brackets through a connecting structure to form K sets of tracking brackets. After the photovoltaic components are laid on the target ballastless track, the laying structure is identified and grouped to determine K independent rotating shafts and the K sets of tracking brackets connected to them. Each rotating shaft and a group of tracking brackets form a relatively independent control unit, laying the foundation for the subsequent regulation process.

[0016] The reliability evaluation module 12 is used to obtain the historical synchronous tracking data and the corresponding timestamps of the K sets of tracking brackets to evaluate the tracking reliability of each tracking bracket, and obtain a set of K tracking reliability evaluation results.

[0017] Furthermore, as Figure 2 shown, the reliability evaluation module 12 is used to execute the following steps: Compare the K sets of historical synchronous tracking data sets of the K sets of tracking brackets with the corresponding historical automatic tracking regulation schemes to obtain K sets of historical synchronous tracking deviation data sets; conduct heuristic screening on the K sets of historical synchronous tracking deviation data sets to determine K sets of first historical synchronous tracking deviation coefficient sets; conduct forward and backward sequential iteration trend analysis on the K sets of historical synchronous tracking deviation data sets based on timestamps to determine K sets of second historical synchronous tracking deviation coefficient sets; evaluate the tracking reliability of the K sets of first historical synchronous tracking deviation coefficient sets and the K sets of second historical synchronous tracking deviation coefficient sets to obtain the K tracking reliability evaluation results.

[0018] In one embodiment, the set of K historical synchronous tracking data groups refers to the tracking execution data recorded by K sets of tracking brackets within the same time period, including parameters such as rotation angle, execution time, response delay, energy consumption, error value, etc. The historical automatic tracking regulation scheme is data describing the situations where the tracking brackets need to be adjusted during historical time. Timestamps are used to identify the specific time points of each data collection, and are used for time-series data modeling and trend analysis. The tracking reliability evaluation refers to quantitatively evaluating the ability of each bracket to stably track the sun's trajectory during past operations, so as to output a set of reliability scores. The set of K tracking reliability evaluation results is the historical performance scoring results corresponding to each set of tracking brackets, and will be used as the basis for the determination of the master and slave rotating shafts in the future.

[0019] In a possible embodiment, by analyzing the historical tracking situations of the K sets of tracking brackets, the tracking reliability degree of each tracking bracket is determined. This is mainly to identify the reliability of the regulation response of the tracking brackets due to factors such as dust accumulation, rain and snow. The tracking angles in the set of K historical synchronous tracking data groups are compared with the regulation angles in the corresponding historical automatic tracking regulation scheme, and the difference between the two is used as the historical synchronous tracking deviation data, so as to obtain the set of K historical synchronous tracking deviation data groups. Furthermore, from two dimensions of determining the generally representative data deviation degree and the development trend of the deviation data, heuristic screening and forward and backward time-series iterative trend analysis are performed on the set of K historical synchronous tracking deviation data groups, so as to obtain the corresponding set of K first historical synchronous tracking deviation coefficients and the set of K second historical synchronous tracking deviation coefficients. Among them, each first historical synchronous tracking deviation coefficient reflects the general deviation situation of the corresponding historical synchronous tracking deviation data group. Each set of second historical synchronous tracking deviation coefficients reflects the deviation trend situation of the corresponding historical synchronous tracking deviation data group.

[0020] Call the pre-constructed tracking reliability evaluation network layer to perform tracking reliability evaluation on the set of K first historical synchronous tracking deviation coefficients and the set of K second historical synchronous tracking deviation coefficients, and obtain the set of K tracking reliability evaluation results. Preferably, obtain multiple sample sets of first historical synchronous tracking deviation coefficients, multiple sample sets of second historical synchronous tracking deviation coefficients and the corresponding multiple sample tracking reliability evaluation results as training data, and use the training data to perform supervised training on the framework constructed based on the feedforward neural network. During the training, the network parameters of the framework are adjusted and updated until the training converges, and the trained tracking reliability evaluation network layer is obtained. By obtaining the set of K tracking reliability evaluation results, the technical effect of providing a basis for distinguishing the master rotating shaft and the slave rotating shaft in the future is achieved.

[0021] Furthermore, the reliability evaluation module 12 is used to perform the following steps: Randomly select one data from each of the K historical synchronous tracking deviation data group sets as the K heuristic data sets; use the K heuristic data sets as the screening starting point, and construct a heuristic neighborhood in the K historical synchronous tracking deviation data group sets according to a preset radius to obtain K heuristic neighborhood sets; determine the heuristic direction based on the K heuristic neighborhood sets, and iterate the K heuristic data sets according to the K heuristic directions to determine K iterative heuristic data sets. After multiple iterations, until the difference between the neighborhood densities of two adjacent iterations is less than or equal to the preset neighborhood density difference threshold, obtain K target heuristic data sets; compare the K target heuristic data sets with a preset deviation tolerance threshold to obtain the K first historical synchronous tracking deviation coefficient sets.

[0022] Further, the reliability evaluation module 12 is used to perform the following steps: Based on a preset neighborhood center search function, search for neighborhood dense centers in the K heuristic neighborhood sets to determine K neighborhood dense center sets; respectively use the directions from the K heuristic data sets to the K neighborhood dense center sets as the K heuristic direction sets.

[0023] In an embodiment of the present application, the historical synchronous tracking deviation data group set refers to a set of deviation data records of the actual angle and the set target angle of each tracking bracket during the historical control process. The K heuristic data sets are initial samples randomly selected from the K historical synchronous tracking deviation data group sets, and are used to guide the subsequent data clustering and optimization search process. The heuristic neighborhood refers to a data subset constructed with the heuristic sample as the center and within a preset radius, representing the similar group of the initial sample in the local space. Among them, the preset radius is the distance that can be classified into the same neighborhood preset by those skilled in the art, and the distance can be the Euclidean distance between the historical synchronous tracking deviation data and the heuristic data corresponding to the screening starting point.

[0024] By respectively counting the amount of data contained in the K heuristic neighborhood sets and dividing the statistical result by twice the preset radius, the neighborhood density is obtained. The preset neighborhood density difference threshold is the maximum difference between the heuristic neighborhood densities after two adjacent iterations set by those skilled in the art when stopping the iteration, and is the condition for controlling the iteration convergence. The heuristic direction is the vector direction from the current heuristic data set to the neighborhood dense center, which guides the iterative update. The K target heuristic data sets are representative deviation data sets obtained after iterative optimization and convergence. The first historical synchronous tracking deviation coefficient set is the reliability performance index of the tracking bracket in the spatial deviation dimension.

[0025] Preferably, a preset neighborhood center search function is used to perform neighborhood dense center search within the K heuristic neighborhood sets, determine the historical synchronous tracking deviation data that is more representative and has a denser distribution around in each heuristic neighborhood, and use it as the neighborhood dense center to obtain the K neighborhood dense center sets. Furthermore, the directions from the K heuristic data sets to the K neighborhood dense center sets are used as the K heuristic direction sets.

[0026] Preferably, the preset neighborhood center search function is: , where is the neighborhood dense center, is the Gaussian kernel function, is the i-th historical synchronous tracking deviation data within the heuristic domain, is the heuristic data corresponding to the screening starting point.

[0027] In one embodiment, after determining the K heuristic directions, the K heuristic data sets are moved by the preset radius in the K heuristic directions to obtain K iterative heuristic data sets, and based on the same construction principle as the K heuristic neighborhood sets, K iterative heuristic neighborhoods are constructed. It is judged whether the difference in neighborhood density between the K iterative heuristic neighborhoods and the K heuristic neighborhoods is less than or equal to a preset neighborhood density difference threshold. If not, based on the same principle as determining the K heuristic directions, K iterative heuristic directions are determined, and the K iterative heuristic data sets are iterated until the difference in neighborhood density between two adjacent iterations is less than or equal to the preset neighborhood density difference threshold, and the data obtained in the last iteration is used as the K target heuristic data sets.

[0028] Preferably, the preset deviation tolerance threshold is a tolerance interval for data deviation in the corresponding historical automatic tracking control scheme preset by those skilled in the art. The K target heuristic data sets are divided by the preset deviation tolerance threshold to obtain the K first historical synchronous tracking deviation coefficient sets. Thus, by analyzing the density within the neighborhood, calling the neighborhood center search function, determining the dense center in each neighborhood, and constructing the heuristic direction set based on this. Then move the initial heuristic point along this direction to achieve the next round of iteration. After each round of iteration, judge the change in neighborhood density before and after. If the density is less than the set threshold, it is considered convergent, and the final target heuristic data set is formed. It achieves the technical effect of improving the data processing quality and providing high-quality data for determining the reliability of the tracking bracket.

[0029] Furthermore, the reliability evaluation module 12 is used to perform the following steps: Activate multiple adaptive encoders to separately perform adaptive data trend feature extraction on each historical synchronous tracking deviation data group in the set of the K historical synchronous tracking deviation data groups in the order of time stamps from front to back, and obtain K sets of deviation trend feature groups; separately integrate the K sets of deviation trend feature groups to determine K sets of fused deviation trend features; perform deviation scoring on the K sets of fused deviation trend features to obtain the K sets of second historical synchronous tracking deviation coefficients.

[0030] Further, the reliability evaluation module 12 is used to perform the following steps: Randomly extract two deviation trend feature groups from the K sets of deviation trend feature groups for similarity comparison to determine the comparison similarity. When the comparison similarity is greater than or equal to the preset similarity threshold, perform an association identification on these two deviation trend features to obtain K sets of associated deviation trend feature groups and K sets of isolated deviation trend feature groups; calculate the feature similarity between any two associated deviation trend features with association identification in the K sets of associated deviation trend feature groups, and normalize the calculation results to obtain an association matrix. Use a convolutional network to calculate the convolution analysis results of the two associated deviation trend features and the association matrix respectively to obtain the corresponding two associated fused deviation trend features, and construct K sets of associated fused deviation trend feature groups; calculate the means of the K sets of associated fused deviation trend feature groups and the K sets of isolated deviation trend feature groups to obtain the K sets of fused deviation trend features.

[0031] In a possible embodiment, the adaptive encoder is a neural network structure that can dynamically extract features according to the changing laws of the data itself, including different data processing scales, and is commonly used to process the trend changes and periodic fluctuations in time series data. Using the multiple adaptive encoders to perform convolution analysis on the set of K historical synchronous tracking deviation data groups at different scales can extract the deviation trends of the regulation response reliability of the tracking bracket changing with time. The K sets of deviation trend feature groups are used to reflect the offset trend features of the K tracking brackets in the time dimension. The set of fused deviation trend features is a comprehensive representation after fusing the deviation trend feature groups belonging to the same tracking bracket, which is convenient for subsequent unified scoring. By quantitatively evaluating the fused trend features, K sets of second historical synchronous tracking deviation coefficients are generated, which are used to measure the stability of the long-term dynamic behavior of the bracket.

[0032] Preferably, after obtaining a plurality of sample synchronous tracking deviation data groups and analyzing them according to the convolution scale of an adaptive encoder, a plurality of sample deviation trend feature groups are obtained. The framework constructed based on the feedforward neural network is supervised and trained using the plurality of sample synchronous tracking deviation data groups and the plurality of sample deviation trend feature groups until the training converges, and a trained adaptive encoder is obtained. Based on the same construction principle, a plurality of trained adaptive encoders are obtained.

[0033] In one embodiment, each historical synchronous tracking deviation data group in the set of K historical synchronous tracking deviation data groups is sorted in ascending order of the timestamp to obtain a set of K historical synchronous tracking deviation data sequences. The plurality of adaptive encoders are respectively used to perform convolution feature extraction on the set of K historical synchronous tracking deviation data sequences to obtain the set of K deviation trend feature groups. Furthermore, by integrating the features of each deviation trend feature group, the set of K fused deviation trend features is obtained. A person skilled in the art performs deviation scoring based on the set of K fused deviation trend features and a preset feature-deviation scoring table to obtain a corresponding set of K second historical synchronous tracking deviation coefficients. Wherein, the preset feature-deviation scoring table is a table constructed by a person skilled in the art according to the mapping relationship between historical trend features and corresponding historical deviation scores.

[0034] In one embodiment, the process of integrating the set of K deviation trend feature groups is as follows: Two deviation trend feature groups are randomly extracted from the set of K deviation trend feature groups for similarity comparison, and the cosine similarity calculation formula is used to analyze the similarity between the two deviation trend feature groups to obtain a comparison similarity. When the comparison similarity is greater than or equal to a preset similarity threshold (the minimum similarity when features are associated as preset by a person skilled in the art), the two deviations are marked with an association identifier to obtain a set of K associated deviation trend feature groups. The features in the set of K deviation trend feature groups that are not marked with an association identifier are used as a set of K isolated deviation trend feature groups.

[0035] Preferably, for any two associated deviation trend features with an association identifier in the set of K associated deviation trend feature groups, the cosine similarity calculation formula is used to calculate the feature similarity, and the calculation result is normalized. Optionally, the softmax formula is used for normalization, and the processed result is added to an initially empty matrix to obtain an association matrix. Furthermore, the convolution analysis results of the two associated deviation trend features and the association matrix are calculated using a convolution network to enhance the features of the two associated deviation trend features, and the corresponding two associated fused deviation trend features are obtained, thereby constructing a set of K associated fused deviation trend feature groups.

[0036] Preferably, multiple associated deviation trend features and corresponding association matrices, as well as multiple associated fusion deviation trend features after enhanced association analysis, are obtained as training data to perform supervised training on the convolutional network until the training converges. Furthermore, an associated deviation trend feature and an association matrix are input into the convolutional network, and the corresponding associated fusion deviation trend feature is output. Furthermore, mean calculations are performed on the K sets of associated fusion deviation trend feature sets and the corresponding K sets of isolated deviation trend feature sets to obtain the K sets of fusion deviation trend features.

[0037] By obtaining the second historical synchronous tracking deviation coefficient set, that is, the coefficient used to characterize the deviation stability of each group of tracking brackets in the time dimension, and summarizing it with the spatial deviation coefficient, the technical effect of providing two-dimensional support for the subsequent selection of the master and slave rotating shafts is achieved.

[0038] The slave rotating shaft determination module 13 is used to determine the master rotating shaft and K - 1 slave rotating shafts among the K rotating shafts based on the K sets of tracking reliability evaluation result sets.

[0039] Furthermore, the slave rotating shaft determination module 13 is used to perform the following steps: Calculate the difference between the maximum value and the minimum value in the K sets of tracking reliability evaluation result sets to determine K first evaluation factors; calculate the fluctuation variance of the K sets of tracking reliability evaluation result sets to obtain K second evaluation factors; perform weighted analysis on the K first evaluation factors and the K second evaluation factors to obtain K rotating shaft evaluation factors; use the rotating shaft corresponding to the maximum value among the K rotating shaft evaluation factors as the master rotating shaft, and use the remaining rotating shafts as the K - 1 slave rotating shafts.

[0040] In a possible embodiment, by screening the K rotating shafts according to the obtained K sets of tracking reliability evaluation result sets, that is, the running stability scores of the tracking brackets corresponding to each rotating shaft, the master rotating shaft and K - 1 slave rotating shafts are determined. The first evaluation factor refers to the running performance discrimination degree obtained from the range (maximum value - minimum value) of the evaluation value of this rotating shaft, and the second evaluation factor is the statistical fluctuation degree (variance) calculated based on the reliability score, reflecting the consistency of the running stability of this rotating shaft. Weighted analysis is to fuse these two factors into a comprehensive rotating shaft evaluation factor for the final master-slave division. Finally, the rotating shaft with the highest score is selected as the master rotating shaft, and the rest are slave rotating shafts to participate in collaborative tracking execution.

[0041] Among them, the master rotating shaft is the rotating shaft with the optimal comprehensive stability and the highest reliability, and is used to undertake the core tracking regulation responsibility. The remaining K - 1 rotating shafts are classified as slave rotating shafts, and will be coordinately adjusted under the guidance of the master rotating shaft driving scheme. Thus, the technical effect of laying a foundation for improving the reliability of photovoltaic tracking in the future is achieved.

[0042] The tracking control scheme acquisition module 14 is configured to collect the solar position information at the current moment, and perform tracking adjustment analysis by combining the information captured by the sensor components arranged on each tracking bracket connected to the main rotating shaft, so as to obtain the tracking control scheme for the main rotating shaft.

[0043] The automatic tracking control scheme acquisition module 15 is configured to perform co - analysis of the same rotating shaft by combining the K tracking reliability evaluation result sets and the tracking control scheme for the main rotating shaft, so as to obtain K - 1 tracking control schemes for the K - 1 driven rotating shafts for regulation, and summarize the K - 1 tracking control schemes for the driven rotating shafts and the tracking control scheme for the main rotating shaft to obtain the automatic tracking control scheme.

[0044] Furthermore, the automatic tracking control scheme acquisition module 15 is configured to execute the following steps: Extract the minimum values except the tracking reliability evaluation result set corresponding to the main rotating shaft from the K tracking reliability evaluation result sets respectively to obtain K - 1 minimum tracking reliability evaluation results; use the control scheme coordinator to identify the K - 1 minimum tracking reliability evaluation results and the tracking control scheme for the main rotating shaft to obtain K - 1 tracking control schemes for the driven rotating shafts.

[0045] In a possible embodiment, the tracking control scheme for the main rotating shaft is combined with the control logic of the driven rotating shafts to achieve synchronous and efficient adjustment of the K tracking bracket sets. The control scheme coordinator is a decision - making unit responsible for formulating corresponding following strategies for each driven rotating shaft according to the action plan of the main rotating shaft and the operation ability differences of the driven rotating shafts. The minimum tracking reliability evaluation result refers to the one with the lowest evaluation value selected from the tracking bracket set corresponding to the driven rotating shaft, representing the potential "weak response" unit, which is used to set the boundary of the most conservative adjustment scheme. The finally output automatic tracking control scheme is the tracking adjustment strategy after integrating the control instructions of the main rotating shaft and the K - 1 driven rotating shafts.

[0046] Preferably, the main rotating shaft is excluded from the K tracking reliability evaluation results to obtain K - 1 tracking reliability evaluation result sets for the K - 1 driven rotating shafts. Extract the minimum values from the K - 1 tracking reliability evaluation result sets to form K - 1 minimum tracking reliability evaluation results. This step ensures that each set of control strategies can cover the tracking brackets under the weakest performance.

[0047] Call the regulation plan coordinator to match and analyze the main rotating shaft tracking regulation plan with each minimum tracking reliability evaluation result, and identify the control tolerance range and synchronization method of each driven rotating shaft from them. For example, if the main rotating shaft is planned to rotate by 12°, and a certain driven rotating shaft can only tolerate an adjustment range of 8° due to slow response, the regulation plan coordinator is used to set the driven rotating shaft to adjust step by step with a small step size, or introduce a compensation mechanism (such as starting in advance, delaying response). Through this personalized regulation strategy, the coordinator forms K - 1 driven rotating shaft tracking regulation plans. Preferably, obtain multiple sample main rotating shaft tracking regulation plans, multiple sample minimum tracking reliability evaluation results, and the corresponding multiple sample driven rotating shaft tracking regulation plans as the training data of the coordinator. Divide the coordinator training data into a training set and a validation set according to a preset ratio (usually 3:2). Use the training set to perform supervised training on the framework constructed based on the convolutional neural network. Input multiple sample main rotating shaft tracking regulation plans and multiple sample minimum tracking reliability evaluation results in the validation set into the framework, and obtain the output multiple verified driven rotating shaft tracking regulation plans. Count the number of identical ones between the multiple verified driven rotating shaft tracking regulation plans and the multiple sample driven rotating shaft tracking regulation plans in the validation set. When the statistical result is less than the preset required number, update the network parameters of the framework until the verification passes, and obtain the trained regulation plan coordinator.

[0048] By summarizing all regulation plans, a complete and directly executable automatic tracking regulation plan is output, ensuring that multiple rotating shafts work together efficiently without interfering with each other, thereby improving the tracking stability and response accuracy of the overall system.

[0049] In summary, the embodiments of the present application at least have the following technical effects: 1. Through the regulation plan coordinator, the present application integrates the regulation strategy of the main rotating shaft with the performance level of the driven rotating shaft, generates K - 1 differentiated driven regulation plans, and combines them with the main plan to generate a complete automatic tracking control instruction, effectively realizing the multi-axis synchronous control of the system and improving the tracking accuracy and response efficiency.

[0050] 2. By combining means such as heuristic clustering, neighborhood density determination, adaptive encoder, and trend similarity convolutional modeling, the present application comprehensively extracts the spatial offset characteristics and time response trends of the tracking bracket, realizes a deep-level and multi-angle evaluation of the operating state, and provides high-trust data support for subsequent control strategies.

[0051] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the above specific embodiments of this specification have been described. Further, the processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0052] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0053] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An automatic tracking photovoltaic system for track plates, characterized in that: The system comprises: A tracking bracket set acquisition module is used to lay photovoltaic panels on the target ballastless track, and obtain K shafts that have been laid and K tracking bracket sets that are connected through the K shafts, where K is a positive integer; A reliability evaluation module is used to obtain the historical synchronous tracking data and corresponding timestamps of a set of K tracking brackets to evaluate the tracking reliability of each tracking bracket, and obtain K tracking reliability evaluation result sets; A driven shaft determination module, used for determining a main shaft and K-1 driven shafts among the K shafts based on the K tracking reliability evaluation result sets; The tracking and control scheme acquisition module is used to collect the sun's position information at the current moment, and combine it with the information captured by the sensor components arranged on each tracking bracket connected to the main shaft to perform tracking adjustment analysis to obtain the main shaft tracking and control scheme; The automatic tracking and control scheme acquisition module is used to combine the K tracking reliability evaluation result sets and the main shaft tracking and control scheme to perform collaborative analysis on the same shaft, obtain K-1 driven shaft tracking and control schemes for controlling the K-1 driven shafts, and summarize the K-1 driven shaft tracking and control schemes and the main shaft tracking and control scheme to obtain an automatic tracking and control scheme.

2. An automatic tracking photovoltaic system for track plates according to claim 1, characterized in that: The reliability evaluation module is used to perform the following steps: Perform deviation comparison between K historical synchronous tracking data group sets of K tracking bracket sets and corresponding historical automatic tracking control schemes to obtain K historical synchronous tracking deviation data group sets; Performing heuristic screening on the K historical synchronization tracking deviation data group sets to determine K first historical synchronization tracking deviation coefficient sets; Performing a forward and backward time series iteration trend analysis on the K historical synchronization tracking deviation data group sets based on the timestamp to determine K second historical synchronization tracking deviation coefficient sets; Tracking reliability evaluation is performed on the K first historical synchronization tracking deviation coefficient sets and the K second historical synchronization tracking deviation coefficient sets to obtain the K tracking reliability evaluation results.

3. An automatic tracking photovoltaic system for track plates according to claim 2, characterized in that: The reliability evaluation module is used to perform the following steps: Randomly select one data from each of the K historical synchronous tracking deviation data sets as K heuristic data sets; Taking the K heuristic data sets as the screening starting point, constructing heuristic neighborhoods in the K historical synchronous tracking deviation data set sets according to a preset radius to obtain K heuristic neighborhood sets; Determine the heuristic direction based on the K heuristic neighborhood sets, iterate the K heuristic data sets according to the K heuristic directions, determine K iterative heuristic data sets, and after multiple iterations, obtain K target heuristic data sets until the difference between the neighborhood densities of two adjacent iterations is less than or equal to a preset neighborhood density difference threshold; The K target heuristic data sets are compared with a preset deviation tolerance threshold to obtain the K first historical synchronization tracking deviation coefficient sets.

4. The automatic tracking photovoltaic system for track plates according to claim 3, characterized in that: The reliability evaluation module is used to perform the following steps: Based on a preset neighborhood center search function, performing a neighborhood dense center search in the K heuristic neighborhood sets to determine K neighborhood dense center sets; The directions from the K heuristic data sets to the K neighborhood dense center sets are respectively used as K heuristic direction sets.

5. The automatic tracking photovoltaic system for track plates according to claim 2, characterized in that: The reliability evaluation module is used to perform the following steps: Activate multiple adaptive encoders to perform adaptive data trend feature extraction on each historical synchronization tracking deviation data group in the K historical synchronization tracking deviation data group sets in a time stamp-to-time order to obtain K deviation trend feature group sets; Integrate the K deviation trend feature group sets respectively to determine K fused deviation trend feature sets; Deviation scores are performed on the K fusion deviation trend feature sets to obtain the K second historical synchronization tracking deviation coefficient sets.

6. An automatic tracking photovoltaic system for track plates as claimed in claim 5, characterized in that: The reliability evaluation module is used to perform the following steps: Randomly extract two deviation trend feature groups from the K deviation trend feature group sets for similarity comparison, determine the comparison similarity, and when the comparison similarity is greater than or equal to a preset similarity threshold, associate the two deviation trend features to obtain K associated deviation trend feature group sets and K isolated deviation trend feature group sets; The feature similarity calculation is performed on any two associated deviation trend features with associated identifiers in the K associated deviation trend feature group sets, and the calculation results are normalized to obtain the association matrix. The convolution network is used to calculate the convolution analysis results of the two associated deviation trend features and the association matrix respectively, and the corresponding two associated fusion deviation trend features are obtained to construct K associated fusion deviation trend feature group sets; The means of the K associated fused deviation trend feature group sets and the K isolated deviation trend feature group sets are calculated to obtain the K fused deviation trend feature sets.

7. The automatic tracking photovoltaic system for track plates according to claim 1, characterized in that: The automatic tracking and control scheme acquisition module is used to perform the following steps: Extracting minimum values ​​from the K tracking reliability evaluation result sets except the tracking reliability evaluation result set corresponding to the main shaft, respectively, to obtain K-1 minimum tracking reliability evaluation results; The control scheme coordinator is used to identify the K-1 minimum tracking reliability evaluation results and the main shaft tracking control scheme to obtain K-1 driven shaft tracking control schemes.

8. The automatic tracking photovoltaic system for track plates according to claim 1, characterized in that: The driven shaft determination module is used to perform the following steps: Calculate the difference between the maximum value and the minimum value in the K tracking reliability evaluation result sets to determine K first evaluation factors; Calculating the fluctuation variance of the K tracking reliability evaluation result sets to obtain K second evaluation factors; Performing weighted analysis on the K first evaluation factors and the K second evaluation factors to obtain K rotation axis evaluation factors; The rotating shaft corresponding to the maximum value of the K rotating shaft evaluation factors is used as the main rotating shaft, and the remaining rotating shafts are used as the K-1 driven rotating shafts.

Images