Photovoltaic module intelligent installation method and device based on application requirements

Abstract

The present invention discloses a method and device for intelligent installation of photovoltaic components based on application requirements, and relates to the field of intelligent control technology, including: performing application requirement analysis to obtain multiple installation requirement information; determining multiple installation methods; performing combined optimization on multiple installation methods according to the installation process of photovoltaic components, and formulating installation strategies according to the optimization results; performing installation application evaluation on the installation strategies, and feeding back the application evaluation results to the installation execution unit to generate adjustment instructions; executing the adjustment instructions to dynamically adjust the installation strategies, and performing intelligent installation. The present invention solves the technical problems of low installation efficiency and poor adaptability in the prior art when installing photovoltaic components, and performs application requirement analysis by retrieving the installation scenario information set of photovoltaic components, matching multiple installation methods, combining and optimizing to formulate installation strategies, performing installation application evaluation and generating adjustment instructions, and dynamically adjusting and updating the installation strategies, thereby achieving the technical effect of improving installation efficiency and adaptability.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent installation method and device for photovoltaic components based on application requirements. Background Art

[0002] With the widespread application of photovoltaic technology, the installation requirements of photovoltaic modules are becoming increasingly diversified. Different installation methods, installation scenarios and installation locations pose different challenges to the installation of photovoltaic modules. Traditional installation methods are often difficult to adapt to these complex and changing requirements, resulting in low installation efficiency and poor adaptability of existing photovoltaic module installation methods. Summary of the invention

[0003] The present application provides a method and device for intelligent installation of photovoltaic components based on application requirements, which is used to solve the technical problems of low installation efficiency and poor adaptability in the prior art when installing photovoltaic components.

[0004] In view of the above problems, the present application provides a method and device for intelligent installation of photovoltaic components based on application requirements.

[0005] In a first aspect of the present application, a method for intelligently installing photovoltaic components based on application requirements is provided, the method comprising:

[0006] Retrieve the installation scenario information set of the photovoltaic component to perform application demand analysis and obtain multiple installation demand information; determine multiple installation methods, and the multiple installation methods are obtained by traversing the historical installation information library of the photovoltaic component based on the multiple installation demand information for matching; combine and optimize the multiple installation methods according to the installation process of the photovoltaic component, and formulate an installation strategy based on the optimization result; perform installation application evaluation on the installation strategy, and feed back the application evaluation result to the installation execution unit to generate an adjustment instruction; execute the adjustment instruction to dynamically adjust the installation strategy, and update the installation strategy to perform intelligent installation of the photovoltaic component.

[0007] The second aspect of the present application provides a photovoltaic module intelligent installation device based on application requirements, the device comprising:

[0008] An application requirement analysis module, wherein the application requirement analysis module retrieves the installation scenario information set of the photovoltaic component to perform application requirement analysis and obtain multiple installation requirement information; an installation method determination module, wherein the installation method determination module determines multiple installation methods, wherein the multiple installation methods are obtained by matching the historical installation information base of the photovoltaic component based on the multiple installation requirement information; a combination optimization module, wherein the combination optimization module performs combination optimization on the multiple installation methods according to the installation process of the photovoltaic component, and formulates an installation strategy based on the optimization result; an application evaluation module, wherein the application evaluation module performs installation application evaluation on the installation strategy, and feeds back the application evaluation result to the installation execution unit to generate an adjustment instruction; an installation strategy update module, wherein the installation strategy update module executes the adjustment instruction to dynamically adjust the installation strategy, and updates the installation strategy to perform intelligent installation of the photovoltaic component.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application retrieves the installation scenario information set of the photovoltaic component to perform application demand analysis, and obtains multiple installation demand information; determines multiple installation methods, and the multiple installation methods are obtained by matching the historical installation information base of the photovoltaic component based on the multiple installation demand information; combines and optimizes the multiple installation methods according to the installation process of the photovoltaic component, and formulates the installation strategy according to the optimization result; performs installation application evaluation on the installation strategy, and feeds back the application evaluation result to the installation execution unit to generate adjustment instructions; executes the adjustment instruction to dynamically adjust the installation strategy, and updates the installation strategy to intelligently install the photovoltaic component. The present invention solves the technical problems of low installation efficiency and poor adaptability in the prior art when installing photovoltaic components, and achieves the technical effect of improving installation efficiency and adaptability by retrieving the installation scenario information set of the photovoltaic component to perform application demand analysis, matching multiple installation methods, combining and optimizing to formulate the installation strategy, performing installation application evaluation and generating adjustment instructions, and dynamically adjusting and updating the installation strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a process flow of a photovoltaic module intelligent installation method based on application requirements provided in an embodiment of the present application;

[0013] Figure 2A schematic diagram of the structure of a photovoltaic module intelligent installation device based on application requirements provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: application requirement analysis module 11 , installation mode determination module 12 , combination optimization module 13 , application evaluation module 14 , installation strategy update module 15 . DETAILED DESCRIPTION

[0015] The present application provides an intelligent installation method and device for photovoltaic components based on application requirements, aiming to solve the technical problems of low installation efficiency and poor adaptability in the prior art when installing photovoltaic components. By retrieving the installation scenario information set of the photovoltaic components, application demand analysis is performed, multiple installation methods are matched, and installation strategies are formulated through combined optimization. Installation application evaluation is performed and adjustment instructions are generated, and the installation strategy is dynamically adjusted and updated to achieve the technical effect of improving installation efficiency and adaptability.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a method for intelligent installation of photovoltaic components based on application requirements, the method comprising:

[0019] Step S100: Retrieving the installation scenario information set of the photovoltaic components to perform application demand analysis and obtain multiple installation demand information.

[0020] In the embodiment of the present application, the installation scene information set of the photovoltaic module is first retrieved from the historical database to obtain relevant environmental data, location parameters and other necessary information. Such information sets include but are not limited to the geographical location, climate conditions, building characteristics, and distribution of obstructions at the photovoltaic module installation site.

[0021] When conducting application demand analysis, the various parameters in the installation scenario information set are classified and sorted, and the key factors affecting the installation effect are analyzed in combination with the technical specifications and installation standards of photovoltaic modules. For example, the solar radiation intensity, wind speed, rainfall, etc. in the climate conditions will directly affect the power generation efficiency and installation firmness of photovoltaic modules; the roof inclination angle, load-bearing capacity, material type, etc. in the building characteristics will determine the installation method and tool selection; the distribution of obstructions needs to consider the layout and arrangement of photovoltaic modules to minimize shadow obstruction. Through the above application demand analysis, multiple installation demand information is finally obtained.

[0022] Furthermore, in the method provided in the embodiment of the application, the installation scenario information set of the photovoltaic component is retrieved to perform application demand analysis to obtain multiple installation demand information, including:

[0023] Based on the historical installation data record log of the photovoltaic components, the installation scope and installation target are set; information is collected according to the installation target in combination with the installation scope to obtain the installation scenario information set; a demand analysis framework is constructed based on the installation characteristics of the photovoltaic components; a multi-dimensional analysis is performed using the demand analysis framework in combination with the installation scenario information set to obtain a multi-dimensional installation demand analysis result; the multi-dimensional installation demand analysis result is traversed to perform weight allocation, and an installation demand list is constructed based on the weight allocation results; and the installation demand list is added to the multiple installation demand information.

[0024] In the embodiment of the present application, based on the historical installation data log of the photovoltaic components, the installation scope and installation target are first set by analyzing and sorting out the past installation records. The installation scope includes the specific geographical location, environmental conditions and building characteristics, while the installation target clarifies the performance indicators and quality standards that the photovoltaic system should achieve, such as power generation efficiency, service life and safety.

[0025] According to the set installation goals, information is collected in combination with the above installation scope. Specifically, geographic location data is obtained through the geographic information system; climate condition information is obtained using a weather station or meteorological data service; and building inspections are carried out through field measurements and architectural drawing analysis to obtain structural and material information of the building. Through these steps, the installation scenario information set is obtained.

[0026] Next, based on the installation characteristics of PV modules, a demand analysis framework is constructed. This framework uses big data analysis technology from technical experts to classify and organize the various parameters in the installation scenario information set, and evaluate their impact on the installation and operation of the PV system. For example, simulation analysis software is used to calculate the optimal installation angle and direction under different climatic conditions; structural analysis software is used to evaluate the load-bearing capacity of the building and select the appropriate mounting bracket and fixing method. The demand analysis framework is then used to conduct multidimensional analysis in combination with the collected installation scenario information set. Specifically, data mining technology is used to analyze the interaction of various parameters; simulation tools are used to predict system performance under different installation conditions; and detailed multidimensional installation demand analysis results are generated. These results show the optimal installation scheme and necessary adjustment measures under various conditions.

[0027] Next, we traverse the multi-dimensional installation requirement analysis results and assign weights to each requirement item. When assigning weights, we use the analytic hierarchy process to determine the importance of each requirement item to the overall installation effect; through expert scoring and data analysis, we calculate the weight value of each requirement item. In this way, we integrate the weight assignment results into an installation requirement list. Finally, we add the constructed installation requirement list to multiple installation requirement information.

[0028] Step S200: determining a plurality of installation methods, wherein the plurality of installation methods are obtained by traversing a historical installation information base of photovoltaic components for matching based on the plurality of installation requirement information.

[0029] In the embodiment of the present application, in order to determine multiple installation methods, based on the aforementioned multiple installation requirement information, the historical installation information library of photovoltaic components is traversed for matching. Specifically, using database query technology, the historical installation information library is searched according to key parameters in the installation requirement information, such as geographical location, climate conditions, building characteristics, etc., to filter out installation records that meet the conditions. The filtered installation records contain installation projects that have been successfully implemented under similar conditions and the corresponding installation methods.

[0030] Through the above process, the installation methods corresponding to the installation projects successfully implemented under similar conditions are taken as multiple installation methods that meet the current requirements.

[0031] Step S300: performing combination optimization on the multiple installation methods according to the installation process of the photovoltaic module, and formulating an installation strategy according to the optimization result.

[0032] In an embodiment of the present application, after determining multiple installation methods, these installation methods are combined according to the standard installation process of photovoltaic modules. The installation process includes stages such as preparation, installation, commissioning and acceptance. Then, the combination optimization technology is used to optimize different installation methods. Combination optimization refers to finding the overall optimal installation solution by arranging and combining different installation methods in a given installation process. In the combination optimization process, heuristic algorithms, such as greedy algorithms, are used to simplify the optimization process. Specifically, for each installation stage, the installation method that performs best under similar conditions is given priority, and these methods are gradually combined into a complete installation strategy. By comparing the effects of different combinations, the combination with the lowest total cost, the shortest construction time and meeting the quality requirements is selected. Finally, an installation strategy is formulated based on the results of the combination optimization.

[0033] Furthermore, in the method provided in the embodiment of the application, the plurality of installation methods are combined and optimized according to the installation process of the photovoltaic module, including:

[0034] The installation process of the photovoltaic component is retrieved based on the historical installation data record log of the photovoltaic component; the historical installation layout information set of the photovoltaic component is retrieved, and the historical installation layout information set includes multiple installation angle information and multiple installation direction information; the multiple installation methods are traversed according to the installation process for iterative configuration, and a first installation method group and a second installation method group are randomly selected; the installation optimization direction is determined based on the multiple installation angle information and the multiple installation direction information in combination with the installation process; according to the installation optimization direction, the first installation angle information and the first installation direction information of the first installation method group are cross-validated with the second installation angle information and the second installation direction information of the second installation method group, and the installation optimization variable is determined according to the cross-validation result; the installation constraint condition is introduced, and the third installation method group is generated according to the installation optimization direction based on the installation optimization variable. The third installation method group is added to the candidate solution set, and it is iterated until a preset number of iterations is reached; the candidate solution set is traversed for weight division according to the installation process, the candidate solution set is sorted in descending order according to the weight division result, and the first-order installation method group is selected according to the candidate solution sequence and added to the optimization result.

[0035] In an embodiment of the present application, detailed information of the installation process is first accurately extracted from the historical installation data record log of the photovoltaic module through database query technology. This information includes the specific steps of each installation method group, the materials used, the debugging process during installation, and the final acceptance criteria. At the same time, the historical installation layout information set of the photovoltaic module is retrieved, and the historical installation layout information set contains multiple installation angle information and multiple installation direction information. These data include not only the layout of the photovoltaic module at different angles, but also the actual performance data corresponding to each layout, such as power generation efficiency, cost-effectiveness, etc.

[0036] Next, according to the standard installation process of photovoltaic modules, two different installation methods are randomly selected as the initial first installation method group and the second installation method group. Based on the multiple installation angles and installation direction information in the historical installation layout information set, matching analysis is performed to determine which installation strategies perform well under specific conditions. Specifically, data mining technology is used to find the installation optimization direction with the greatest potential for improving performance by comparing the characteristics of the installation conditions (such as geographical location, surrounding environment, building structure, etc.).

[0037] After the installation optimization direction is determined, cross-validation is further performed to combine a specific installation angle and direction of the first installation mode group with another specific installation angle and direction of the second installation mode group for verification. The expected performance of each installation combination, such as the expected power generation efficiency and cost-effectiveness, is analyzed through the quantitative evaluation model. These evaluations are based on the existing performance trends and correlations in the historical data, as well as the application of the prediction model to the new combination. According to the results of cross-validation, the optimal installation optimization variables are determined, that is, the installation angle and direction parameters that can achieve the best comprehensive performance under the current conditions. Among them, the quantitative evaluation model is pre-established. When establishing the quantitative evaluation model, the performance indicators are first determined according to the actual needs and application scenarios, including power generation efficiency, installation cost, construction time and system stability. Next, the installation angle and direction information extracted from the historical data is integrated and pre-processed with the corresponding performance data, such as power generation, cost, etc. Then, the mathematical mapping relationship between the installation angle and direction and the performance indicators is established through statistical analysis or correlation analysis. For example, the degree of influence of the installation angle on the power generation efficiency is explored using techniques such as regression analysis. Then, an evaluation model suitable for the characteristics of the problem is selected. Here, a linear model based on statistical analysis is used. Next, the established evaluation model is verified and tuned, using part of the historical data set as the training set and the other part as the test set. The prediction ability and accuracy of the model are evaluated by comparing the difference between the model prediction value and the actual observation value. Finally, the established quantitative evaluation model is applied to evaluate various installation angles and directions of each installation method group.

[0038] Then, the installation constraint condition is introduced, and iterative calculation is performed according to the installation optimization direction based on the installation optimization variable, and a new installation mode group, i.e., the third installation mode group, is generated by using iterative calculation technology, such as genetic algorithm, simulated annealing algorithm, etc. These newly generated installation mode groups are added to the candidate solution set and updated through multiple iterations until a preset number of iterations is reached or other stop conditions are met.

[0039] Next, we traverse the candidate solution set and use multi-attribute decision analysis methods, such as the analytic hierarchy process, to divide the weights according to the performance of each installation method group on different performance indicators, such as power generation and cost. Technical experts will then adjust the weights to ensure the rationality of the weights. According to the weight division results, the candidate solution set is sorted in descending order to generate a candidate solution sequence. Finally, the installation method group with the highest comprehensive score in the candidate solution sequence is selected as the final optimization result, that is, the optimal installation solution.

[0040] Furthermore, in the method provided in the application embodiment, the installation constraint conditions include:

[0041] Based on the installation scenario information set, a structural safety assessment of the photovoltaic assembly is performed to determine the installation complexity; based on the multiple installation angle information combined with the power generation efficiency of the photovoltaic assembly, a simulation calculation is performed to obtain multiple power generation data, and the multiple power generation data have a first correlation coefficient with the multiple installation angle information; based on the first correlation coefficient and the multiple power generation data, an installation angle constraint is determined; based on the multiple installation direction information combined with the sunshine duration of the photovoltaic assembly, a simulation calculation is performed to obtain multiple illumination data, and the multiple illumination data have a second correlation coefficient with the multiple installation direction information, and the multiple illumination data include illumination duration and illumination intensity; based on the second correlation coefficient and the illumination duration and the illumination intensity, an installation direction constraint is determined; based on the integration of the installation complexity, the installation angle constraint and the installation direction constraint, the installation constraint condition is formulated.

[0042] In the embodiment of the present application, a structural safety assessment of the photovoltaic module is first performed based on the installation scenario information set to determine the installation complexity. The installation scenario information set includes data such as geographical location, climate conditions, and building characteristics. In the structural safety assessment, the finite element analysis method is used to analyze factors such as the building's load-bearing capacity, roof inclination angle, and material type to ensure that the photovoltaic module can operate safely and stably after installation. This information is integrated and analyzed to determine the installation complexity, that is, the difficulty and potential risks of the installation task.

[0043] Next, we simulate and calculate the power generation efficiency of photovoltaic modules based on multiple installation angle information. Installation angle information refers to the installation method of photovoltaic modules at different tilt angles. By using photovoltaic performance simulation software to simulate the power generation efficiency of photovoltaic modules at different angles, multiple power generation data are obtained. These data are calculated with the first correlation coefficient between the installation angle information through regression analysis. The first correlation coefficient represents the correlation between the installation angle and the power generation efficiency. Based on these calculation results, we use multi-objective optimization algorithms, such as genetic algorithms, to determine the installation angle constraints to ensure that the selected installation angle can achieve the best power generation efficiency.

[0044] Subsequently, simulation calculations are performed based on multiple installation direction information combined with the sunshine duration of photovoltaic modules. Installation direction information refers to the installation method of photovoltaic modules in different directions. Use the sunshine simulation tool to perform simulation calculations to obtain multiple lighting data, which include information such as lighting duration and light intensity. The second correlation coefficient between these lighting data and the installation direction information is calculated using the correlation analysis method to evaluate the impact of different directions on the lighting effect. The second correlation coefficient represents the correlation between the installation direction and the lighting duration and light intensity, which helps to determine the optimal installation direction. Based on these simulation calculation results, a linear regression model is used to determine the installation direction constraints to ensure that the photovoltaic modules can operate under optimal lighting conditions.

[0045] Finally, the installation complexity, installation angle constraints and installation direction constraints are integrated to formulate installation constraint conditions. The installation constraint conditions combine the results of structural safety assessment, power generation efficiency simulation calculation results and illumination data simulation calculation results.

[0046] Step S400: performing installation application evaluation on the installation strategy, and feeding back the application evaluation result to the installation execution unit to generate an adjustment instruction.

[0047] In an embodiment of the present application, a simulation environment is first constructed to perform a detailed installation application evaluation on the installation strategy. A simulation verification is performed on the installation strategy based on the simulation environment to generate a first simulation installation result. During the simulation verification process, the performance of the installation strategy under different conditions, such as power generation efficiency, installation cost, structural stability, etc., is evaluated. Next, it is determined whether the first simulation installation result achieves the expected installation effect. The expected installation effect is based on previously determined installation goals and performance indicators, such as power generation reaching a certain standard, installation costs being within the budget, and structural safety meeting requirements. If the first simulation installation result achieves the expected installation effect, an installation application evaluation is performed on the installation strategy to generate an application evaluation result. The application evaluation result includes a detailed evaluation of various aspects of the installation strategy, such as performance, cost-effectiveness, safety, etc.

[0048] If the first simulated installation result does not achieve the expected installation effect, the second-order installation method group is selected based on the candidate solution sequence to replace the first-order installation method group in the installation strategy. The candidate solution sequence is generated through the previous combinatorial optimization process and contains multiple possible installation method combinations. The replaced installation strategy is simulated and verified again to obtain the second simulated installation result. Through multiple iterations and verifications, the simulated installation results that achieve the expected installation effect are extracted, and the installation strategy is finally evaluated for installation application to generate an application evaluation result. Once the application evaluation result is obtained, it is fed back to the installation execution unit to generate an adjustment instruction.

[0049] Furthermore, in the method provided in the embodiment of the application, the installation strategy is evaluated for installation application, including:

[0050] Construct a simulation environment, perform simulation verification on the installation strategy based on the simulation environment, and generate a first simulation installation result; determine whether the first simulation installation result achieves the expected installation effect; if the first simulation installation result achieves the expected installation effect, perform installation application evaluation on the installation strategy to generate the application evaluation result; if the first simulation installation result does not achieve the expected installation effect, select a second-order installation method group based on the candidate solution sequence to replace the first-order installation method group in the installation strategy, perform simulation verification based on the replacement result, and obtain a second simulation installation result, thereby iterating, extracting the simulation installation result that achieves the expected installation effect, performing installation application evaluation on the installation strategy, and generating the application evaluation result.

[0051] In the embodiment of the present application, a simulation environment is first created by computer simulation software, such as Simulink in MATLAB, to simulate the actual photovoltaic system installation scenario, including environmental conditions, installation structure, lighting conditions, etc. In this simulation environment, based on the installation strategy, simulation verification is performed to generate a first simulation installation result.

[0052] Next, determine whether the first simulated installation result achieves the expected installation effect. The expected installation effect is based on the previously determined installation goals and performance indicators, such as power generation reaching a certain standard and installation costs within the budget. If the first simulated installation result achieves the expected installation effect, the installation strategy is evaluated for installation application and an application evaluation result is generated. The application evaluation result contains a detailed evaluation of various aspects of the installation strategy, such as performance, cost-effectiveness, safety, etc. When conducting an installation application evaluation, for example, photovoltaic performance simulation software such as PVsyst is used to evaluate the power generation of photovoltaic modules under different conditions. Calculate the material cost, labor cost and other related expenses during the installation process. Use the finite element analysis (FEA) method to evaluate the safety and stability of the installation structure. Based on the above evaluation content, generate an application evaluation result.

[0053] If the first simulated installation result does not achieve the expected installation effect, the second-order installation method group is selected based on the candidate solution sequence to replace the first-order installation method group in the installation strategy. The candidate solution sequence is generated through the previous combinatorial optimization process and contains multiple possible installation method combinations. The position of each installation method group in the candidate solution sequence is ranked based on its performance in the initial simulation verification. The top few percent, such as the top 10%, of the installation method groups are selected from the candidate solution sequence for iterative verification. During the iterative process, simulation verification is performed again after each replacement to obtain a new simulated installation result. Through multiple iterations and verifications, the installation strategy is gradually optimized. Specifically, each time the simulation result does not achieve the expected effect, it is replaced by the pre-selected suboptimal installation method group in the candidate solution sequence, and the simulation verification is performed again. This process is similar to the iterative optimization in the genetic algorithm. The optimal installation strategy is found through continuous trial and improvement. When a round of simulation verification results achieves the expected installation effect, it is used as the current optimal solution and a detailed installation application evaluation is performed to obtain the application evaluation result.

[0054] Furthermore, in the method provided in the embodiment of the application, the application evaluation result is fed back to the installation execution unit to generate an adjustment instruction, including:

[0055] The application evaluation result is fed back to the installation execution unit to perform application scoring on the installation strategy to obtain an installation application scoring result; the application fitness of the installation strategy is calculated according to the installation application scoring result; the installation strategy is traversed based on the application fitness to perform correction identification and determine multiple correction identification results; installation adjustment suggestions are formulated according to the multiple correction identification results; and the installation adjustment suggestions are added to the adjustment instructions.

[0056] In an embodiment of the present application, the application evaluation result is first fed back to the installation execution unit. The application evaluation result contains detailed analysis and data on different aspects of the installation strategy, including performance, cost-effectiveness, safety, etc. During the evaluation process, multi-criteria decision analysis methods, such as the analytic hierarchy process, are used to evaluate and score different performance indicators. Through these detailed evaluation results, the pros and cons of the current installation strategy can be understood. Next, the installation execution unit performs an application score on the installation strategy. In this process, a scoring model, such as the analytic hierarchy process, is used to comprehensively evaluate and score different performance indicators. Specifically, based on the pre-defined scoring criteria for each performance indicator and the pre-assigned weights based on the importance of each indicator to the overall goal, a comprehensive score for each installation strategy, i.e., the installation application scoring result, is calculated.

[0057] Next, the application fitness of the installation strategy is calculated based on the installation application scoring results. Application fitness is a comprehensive indicator that reflects the overall performance of the installation strategy in actual applications. When calculating application fitness, the scores of each performance indicator are weighted and summed according to their weights to obtain a comprehensive score. Specifically, the score of each performance indicator is multiplied by the corresponding weight, and then summed to normalize the comprehensive score. The weights are pre-set.

[0058] Then, based on the application fitness, all installation strategies are traversed for correction identification. Correction identification refers to identifying the parts that need to be adjusted by analyzing the various steps and parameters of the installation strategy. Using data analysis, such as statistical analysis, regression analysis, and expert review methods, the correction items for each strategy are determined to form multiple correction identification results. Specifically, each parameter of the installation strategy is analyzed in detail to find out the key factors affecting performance, and the expert team reviews the data analysis results to determine the specific parts that need to be corrected. Finally, based on the expert opinions, a specific correction identification result is formed.

[0059] Then, based on these correction identification results, installation adjustment suggestions are formulated. The installation adjustment suggestions include specific adjustment steps and parameters, such as adjusting the installation angle, direction, position, etc., to optimize the installation strategy. Specifically, optimization algorithms such as genetic algorithms and particle swarm optimization are used to optimize the installation parameters. The adjustment suggestions are simulated and verified to ensure that the adjusted strategy performs well in the simulation environment. Based on the optimization results, specific installation adjustment suggestions are generated.

[0060] Finally, the installation adjustment suggestions are added to the adjustment instructions. The adjustment instructions list the specific adjustment steps, parameter modifications and implementation plans in detail to guide the actual installation adjustment process.

[0061] Step S500: executing the adjustment instruction to dynamically adjust the installation strategy, and updating the installation strategy to perform intelligent installation of photovoltaic components.

[0062] Furthermore, in the method provided in the embodiment of the application, executing the adjustment instruction to dynamically adjust the installation strategy, updating the installation strategy to intelligently install the photovoltaic components, includes:

[0063] The installation adjustment suggestion is used as a data index, and the installation strategy is traversed for matching to generate matching information; the installation strategy is dynamically adjusted according to the matching information to generate an installation adjustment result; based on the installation adjustment result, verification is performed through the installation execution unit, and when the verification passes, the installation strategy is updated to perform intelligent installation of photovoltaic components.

[0064] In an embodiment of the present application, the installation adjustment suggestion is first used as a data index to traverse all installation strategies for matching and generate matching information. The installation adjustment suggestion is formulated based on the previous evaluation and correction identification results, and includes specific adjustment steps and parameters. To ensure the effectiveness of the adjustment suggestion, the installation strategy is quickly matched using database indexing technology. Specifically, the installation adjustment suggestion is used as a data index item to establish an index database. Next, all installation strategies are traversed, and the adjustment suggestion is matched with the existing strategy through the index database to generate matching information. The matching information includes the strategy that needs to be adjusted and the corresponding adjustment parameters. This process uses efficient search algorithms, such as binary search or hash search, to improve matching speed and accuracy.

[0065] Next, according to the generated matching information, the installation strategy is dynamically adjusted to generate the installation adjustment results. The dynamic adjustment process is implemented through optimization algorithms, such as genetic algorithms and particle swarm optimization, to adjust the strategy in real time according to the matching information. Specifically, the optimization algorithm is used to adjust the strategy in the matching information and optimize the adjustment parameters. The optimization algorithm uses the historical data and performance indicators of the installation strategy to find the optimal adjustment plan through iterative calculation. Based on the output of the adjustment algorithm, a new installation strategy is generated and the adjustment results are recorded. The adjustment results include new installation parameter settings and expected performance improvements.

[0066] Then, based on the generated installation adjustment results, the installation execution unit is used for verification. In the simulation environment, the new installation strategy is simulated and verified to evaluate its performance. The simulation verification uses simulation software, such as Simulink in MATLAB, to simulate the execution of the strategy under actual environmental conditions. The installation strategy is simulated and verified in the simulation environment, and the data of various performance indicators are recorded. These data include power generation efficiency, installation cost, structural stability, etc. Then, the collected data is preprocessed, including data cleaning, removal of outliers, processing of missing data, etc., to ensure the integrity and accuracy of the data. In addition, data of different dimensions need to be standardized so that they can be compared on the same scale. By using standardization methods such as Z-score standardization, the data is converted into standardized data with a mean of 0 and a standard deviation of 1. Next, the regression analysis method is used to build an evaluation model to analyze the performance of the adjusted strategy. According to the characteristics of the performance data and the relationship between the installation parameters, a suitable regression model is selected. A linear regression model is usually used, but if the data shows a nonlinear relationship, a polynomial regression or other nonlinear regression model can be selected. Regression modeling is performed using regression analysis software or library. Input the preprocessed performance data and installation parameters, train the regression model, and obtain the regression equation. The goodness of fit and explanatory power of the model are evaluated by regression coefficient and determination coefficient. The determination coefficient is used to measure the degree to which the explanatory variables of the model explain the variation of the dependent variable. The closer the value is to 1, the better the model fit is. When evaluating the performance of the adjusted strategy, the constructed regression model is used to analyze the data of the simulation verification to evaluate the performance of the adjusted strategy. The adjusted strategy is predicted using the regression model to obtain the predicted value. The predicted value is compared with the actual value to evaluate the prediction accuracy and reliability of the model. The difference between the predicted value and the actual value (i.e., the residual) is analyzed to check whether the distribution of the residual conforms to the normal distribution and whether there is heteroscedasticity or autocorrelation. The residual plot and statistical tests are used for evaluation. The performance of the adjusted strategy in various performance indicators is evaluated by the prediction results of the regression model and the actual performance data. For example, the improvement in power generation efficiency, the change in installation cost, the improvement in structural stability, etc. Then, a data analysis report is generated, which contains the detailed results, charts and explanations of the regression analysis. Finally, by summarizing the analysis results, it is judged whether the adjusted strategy has achieved the expected effect. Specifically, whether the power generation efficiency is significantly improved, whether the installation cost is controlled within the budget, whether the structural stability meets the safety requirements, etc. If the adjusted strategy does not achieve the expected effect, return to step 1, readjust the installation strategy, and conduct a new round of simulation verification and data analysis.

[0067] When the verification is passed, the installation strategy is updated and the PV panels are intelligently installed.

[0068] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0069] The present application retrieves the installation scenario information set of the photovoltaic component to perform application demand analysis, and obtains multiple installation demand information; determines multiple installation methods, and the multiple installation methods are obtained by matching the historical installation information base of the photovoltaic component based on the multiple installation demand information; combines and optimizes the multiple installation methods according to the installation process of the photovoltaic component, and formulates the installation strategy according to the optimization result; performs installation application evaluation on the installation strategy, and feeds back the application evaluation result to the installation execution unit to generate adjustment instructions; executes the adjustment instruction to dynamically adjust the installation strategy, and updates the installation strategy to intelligently install the photovoltaic component. The present invention solves the technical problems of low installation efficiency and poor adaptability in the prior art when installing photovoltaic components, and achieves the technical effect of improving installation efficiency and adaptability by retrieving the installation scenario information set of the photovoltaic component to perform application demand analysis, matching multiple installation methods, combining and optimizing to formulate the installation strategy, performing installation application evaluation and generating adjustment instructions, and dynamically adjusting and updating the installation strategy.

[0070] Embodiment 2 is based on the same inventive concept as the photovoltaic module intelligent installation method based on application requirements in the above embodiments. Figure 2 As shown, the present application provides a photovoltaic module intelligent installation device based on application requirements, and the device and method embodiments in the present application embodiments are based on the same inventive concept. Among them, the device includes:

[0071] An application requirement analysis module 11, wherein the application requirement analysis module 11 retrieves the installation scenario information set of the photovoltaic component to perform application requirement analysis and obtain multiple installation requirement information; an installation method determination module 12, wherein the installation method determination module 12 determines multiple installation methods, wherein the multiple installation methods are obtained by matching the historical installation information base of the photovoltaic component based on the multiple installation requirement information; a combination optimization module 13, wherein the combination optimization module 13 performs combination optimization on the multiple installation methods according to the installation process of the photovoltaic component, and formulates an installation strategy based on the optimization result; an application evaluation module 14, wherein the application evaluation module 14 performs installation application evaluation on the installation strategy, and feeds back the application evaluation result to the installation execution unit to generate an adjustment instruction; an installation strategy update module 15, wherein the installation strategy update module 15 executes the adjustment instruction to dynamically adjust the installation strategy, and updates the installation strategy to perform intelligent installation of the photovoltaic component.

[0072] Furthermore, the device is also used to achieve the following functions:

[0073] Based on the historical installation data record log of the photovoltaic components, the installation scope and installation target are set; information is collected according to the installation target in combination with the installation scope to obtain the installation scenario information set; a demand analysis framework is constructed based on the installation characteristics of the photovoltaic components; a multi-dimensional analysis is performed using the demand analysis framework in combination with the installation scenario information set to obtain a multi-dimensional installation demand analysis result; the multi-dimensional installation demand analysis result is traversed to perform weight allocation, and an installation demand list is constructed based on the weight allocation results; and the installation demand list is added to the multiple installation demand information.

[0074] Furthermore, the device is also used to achieve the following functions:

[0075] The installation process of the photovoltaic component is retrieved based on the historical installation data record log of the photovoltaic component; the historical installation layout information set of the photovoltaic component is retrieved, and the historical installation layout information set includes multiple installation angle information and multiple installation direction information; the multiple installation methods are traversed according to the installation process for iterative configuration, and a first installation method group and a second installation method group are randomly selected; the installation optimization direction is determined based on the multiple installation angle information and the multiple installation direction information in combination with the installation process; according to the installation optimization direction, the first installation angle information and the first installation direction information of the first installation method group are cross-validated with the second installation angle information and the second installation direction information of the second installation method group, and the installation optimization variable is determined according to the cross-validation result; the installation constraint condition is introduced, and the third installation method group is generated according to the installation optimization direction based on the installation optimization variable. The third installation method group is added to the candidate solution set, and it is iterated until a preset number of iterations is reached; the candidate solution set is traversed for weight division according to the installation process, the candidate solution set is sorted in descending order according to the weight division result, and the first-order installation method group is selected according to the candidate solution sequence and added to the optimization result.

[0076] Furthermore, the device is also used to achieve the following functions:

[0077] Based on the installation scenario information set, a structural safety assessment of the photovoltaic assembly is performed to determine the installation complexity; based on the multiple installation angle information combined with the power generation efficiency of the photovoltaic assembly, a simulation calculation is performed to obtain multiple power generation data, and the multiple power generation data have a first correlation coefficient with the multiple installation angle information; based on the first correlation coefficient and the multiple power generation data, an installation angle constraint is determined; based on the multiple installation direction information combined with the sunshine duration of the photovoltaic assembly, a simulation calculation is performed to obtain multiple illumination data, and the multiple illumination data have a second correlation coefficient with the multiple installation direction information, and the multiple illumination data include illumination duration and illumination intensity; based on the second correlation coefficient and the illumination duration and the illumination intensity, an installation direction constraint is determined; based on the integration of the installation complexity, the installation angle constraint and the installation direction constraint, the installation constraint condition is formulated.

[0078] Furthermore, the device is also used to achieve the following functions:

[0079] Construct a simulation environment, perform simulation verification on the installation strategy based on the simulation environment, and generate a first simulation installation result; determine whether the first simulation installation result achieves the expected installation effect; if the first simulation installation result achieves the expected installation effect, perform installation application evaluation on the installation strategy to generate the application evaluation result; if the first simulation installation result does not achieve the expected installation effect, select a second-order installation method group based on the candidate solution sequence to replace the first-order installation method group in the installation strategy, perform simulation verification based on the replacement result, and obtain a second simulation installation result, thereby iterating, extracting the simulation installation result that achieves the expected installation effect, performing installation application evaluation on the installation strategy, and generating the application evaluation result.

[0080] Furthermore, the device is also used to achieve the following functions:

[0081] The application evaluation result is fed back to the installation execution unit to perform application scoring on the installation strategy to obtain an installation application scoring result; the application fitness of the installation strategy is calculated according to the installation application scoring result; the installation strategy is traversed based on the application fitness to perform correction identification and determine multiple correction identification results; installation adjustment suggestions are formulated according to the multiple correction identification results; and the installation adjustment suggestions are added to the adjustment instructions.

[0082] Furthermore, the device is also used to achieve the following functions:

[0083] The installation adjustment suggestion is used as a data index, and the installation strategy is traversed for matching to generate matching information; the installation strategy is dynamically adjusted according to the matching information to generate an installation adjustment result; based on the installation adjustment result, verification is performed through the installation execution unit, and when the verification passes, the installation strategy is updated to perform intelligent installation of photovoltaic components.

[0084] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0086] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations 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 equivalents, the present application intends to include these modifications and variations.

Claims

1. A photovoltaic module intelligent installation method based on application requirements, characterized in that: The method comprises: Retrieve the installation scenario information set of photovoltaic components to perform application demand analysis and obtain multiple installation demand information; Determine a plurality of installation methods, wherein the plurality of installation methods are obtained by traversing a historical installation information base of photovoltaic components for matching based on the plurality of installation requirement information; Combining and optimizing the multiple installation methods according to the installation process of the photovoltaic components, and formulating an installation strategy according to the optimization result; Performing installation application evaluation on the installation strategy, and feeding back the application evaluation result to the installation execution unit to generate an adjustment instruction; Executing the adjustment instruction to dynamically adjust the installation strategy, and updating the installation strategy to perform intelligent installation of photovoltaic components; Retrieving the installation scenario information set of the photovoltaic components to perform application demand analysis and obtain multiple installation demand information, the method includes: Set installation scope and installation goals based on historical installation data logs of PV modules; Collecting information according to the installation target and the installation scope to obtain the installation scenario information set; Construct a demand analysis framework based on the installation characteristics of PV panels; Performing a multi-dimensional analysis using the demand analysis framework in combination with the installation scenario information set to obtain a multi-dimensional installation demand analysis result; Traversing the multi-dimensional installation requirement analysis results to perform weight distribution, and constructing an installation requirement list based on the weight distribution results; Adding the installation requirement list to the plurality of installation requirement information; The multiple installation methods are combined and optimized according to the installation process of the photovoltaic components, and the method includes: Retrieving the installation process of the photovoltaic component based on the historical installation data record log of the photovoltaic component; Retrieving a historical installation layout information set of photovoltaic components, wherein the historical installation layout information set includes a plurality of installation angle information and a plurality of installation direction information; Traversing the multiple installation methods according to the installation process to perform iterative configuration, and randomly selecting a first installation method group and a second installation method group; Determine the installation optimization direction based on the multiple installation angle information and the multiple installation direction information in combination with the installation process; According to the installation optimization direction, cross-validate the first installation angle information and the first installation direction information of the first installation mode group and the second installation angle information and the second installation direction information of the second installation mode group, and determine the installation optimization variable according to the cross-validation result; Introducing installation constraints, performing iterative calculations based on the installation optimization variables and in the installation optimization direction, generating a third installation mode group, and adding the third installation mode group to the candidate solution set, thereby iterating until a preset number of iterations is reached; Traversing the candidate solution set and dividing the weights according to the installation process, sorting the candidate solution set in descending order according to the weight division result, and selecting the first-ranked installation method group according to the candidate solution sequence to add to the optimization result; Performing an installation application evaluation on the installation strategy, the method comprising: Constructing a simulation environment, performing simulation verification on the installation strategy based on the simulation environment, and generating a first simulation installation result; Determining whether the first simulated installation result achieves the expected installation effect; If the first simulated installation result achieves the expected installation effect, performing installation application evaluation on the installation strategy to generate the application evaluation result; If the first simulated installation result does not achieve the expected installation effect, then select a second-order installation method group based on the candidate solution sequence to replace the first-order installation method group in the installation strategy, perform simulation verification according to the replacement result, and obtain a second simulated installation result, thereby iterating, extracting the simulated installation result that achieves the expected installation effect, performing installation application evaluation on the installation strategy, and generating the application evaluation result; Feeding back the application evaluation result to the installation execution unit to generate adjustment instructions, the method includes: Feeding back the application evaluation result to the installation execution unit to perform application scoring on the installation strategy to obtain an installation application scoring result; Calculating the application fitness of the installation strategy according to the installed application scoring result; Based on the application fitness, the installation strategy is traversed to perform correction identification, and multiple correction identification results are determined; formulating installation adjustment suggestions based on the multiple correction identification results; adding the installation adjustment suggestion to the adjustment instruction; Executing the adjustment instruction to dynamically adjust the installation strategy, updating the installation strategy to intelligently install the photovoltaic components, the method includes: Using the installation adjustment suggestion as a data index, traversing the installation strategy for matching, and generating matching information; Dynamically adjusting the installation strategy according to the matching information to generate an installation adjustment result; The installation execution unit verifies the installation adjustment result, and when the verification is passed, the installation strategy is updated to perform intelligent installation on the photovoltaic components.

2. The photovoltaic module intelligent installation method based on application requirements according to claim 1, characterized in that: The installation constraint method includes: Performing a structural safety assessment on the photovoltaic assembly based on the installation scenario information set to determine the installation complexity; Performing simulation calculation based on the plurality of installation angle information in combination with the power generation efficiency of the photovoltaic assembly to obtain a plurality of power generation data, wherein the plurality of power generation data has a first correlation coefficient with the plurality of installation angle information; Determine an installation angle constraint based on the first correlation coefficient and the plurality of power generation data; Based on the multiple installation direction information and the sunshine duration of the photovoltaic components, a simulation calculation is performed to obtain multiple illumination data, wherein the multiple illumination data have a second correlation coefficient with the multiple installation direction information, and the multiple illumination data include illumination duration and illumination intensity; Determine an installation direction constraint based on the second correlation coefficient combined with the illumination duration and the illumination intensity; The installation constraint condition is formulated based on the integration of the installation complexity, the installation angle constraint, and the installation direction constraint.

3. A photovoltaic module intelligent installation device based on application requirements, characterized in that: The device comprises: An application requirement analysis module, wherein the application requirement analysis module retrieves an installation scenario information set of a photovoltaic component to perform application requirement analysis and obtain multiple installation requirement information; An installation method determination module, the installation method determination module determines a plurality of installation methods, the plurality of installation methods are obtained by matching the plurality of installation requirement information through a historical installation information base of photovoltaic components; A combined optimization module, wherein the combined optimization module performs combined optimization on the multiple installation methods according to the installation process of the photovoltaic components, and formulates an installation strategy according to the optimization result; An application evaluation module, wherein the application evaluation module performs installation application evaluation on the installation strategy and feeds back the application evaluation result to the installation execution unit to generate an adjustment instruction; An installation strategy update module, the installation strategy update module executes the adjustment instruction to dynamically adjust the installation strategy, and updates the installation strategy to perform intelligent installation of photovoltaic components; The device is also used to achieve the following functions: Based on the historical installation data record log of the photovoltaic components, set the installation scope and installation target; collect information according to the installation target in combination with the installation scope to obtain the installation scenario information set; build a demand analysis framework based on the installation characteristics of the photovoltaic components; use the demand analysis framework in combination with the installation scenario information set to perform multi-dimensional analysis to obtain a multi-dimensional installation demand analysis result; traverse the multi-dimensional installation demand analysis results to perform weight distribution, and construct an installation demand list based on the weight distribution results; add the installation demand list to the multiple installation demand information; Retrieving the installation process of the photovoltaic component based on the historical installation data record log of the photovoltaic component; retrieving the historical installation layout information set of the photovoltaic component, wherein the historical installation layout information set includes multiple installation angle information and multiple installation direction information; traversing the multiple installation methods according to the installation process for iterative configuration, and randomly selecting the first installation method group and the second installation method group; determining the installation optimization direction based on the multiple installation angle information and the multiple installation direction information in combination with the installation process; cross-validating the first installation angle information and the first installation direction information of the first installation method group with the second installation angle information and the second installation direction information of the second installation method group according to the installation optimization direction, and determining the installation optimization variable according to the cross-validation result; introducing installation constraints, iteratively calculating according to the installation optimization direction based on the installation optimization variables, generating a third installation method group, and adding the third installation method group to the candidate solution set, thereby iterating until a preset number of iterations is reached; traversing the candidate solution set for weight division according to the installation process, sorting the candidate solution set in descending order according to the weight division result, and selecting the first-order installation method group according to the candidate solution sequence to add to the optimization result; Construct a simulation environment, perform simulation verification on the installation strategy based on the simulation environment, and generate a first simulation installation result; determine whether the first simulation installation result achieves the expected installation effect; if the first simulation installation result achieves the expected installation effect, perform installation application evaluation on the installation strategy to generate the application evaluation result; if the first simulation installation result does not achieve the expected installation effect, select a second-order installation method group based on the candidate solution sequence to replace the first-order installation method group in the installation strategy, perform simulation verification according to the replacement result, obtain a second simulation installation result, and iterate accordingly to extract the simulation installation result that achieves the expected installation effect, perform installation application evaluation on the installation strategy, and generate the application evaluation result; Feeding back the application evaluation result to the installation execution unit to score the installation strategy and obtain the installation application scoring result; calculating the application fitness of the installation strategy according to the installation application scoring result; traversing the installation strategy to perform correction identification based on the application fitness and determining multiple correction identification results; formulating installation adjustment suggestions according to the multiple correction identification results; and adding the installation adjustment suggestions to the adjustment instructions; The installation adjustment suggestion is used as a data index, and the installation strategy is traversed for matching to generate matching information; the installation strategy is dynamically adjusted according to the matching information to generate an installation adjustment result; based on the installation adjustment result, verification is performed through the installation execution unit, and when the verification passes, the installation strategy is updated to perform intelligent installation of photovoltaic components.

Images