Wind turbine simulation data analysis method, device, terminal and storage medium

Abstract

The present invention provides a method, device, terminal and storage medium for analyzing wind turbine simulation data. The method comprises: obtaining a selected task representing a certain wind turbine simulation data analysis and a selected algorithm template corresponding to the selected task; screening the corresponding wind turbine simulation data according to each selected algorithm template, generating an initial algorithm instance corresponding to each selected algorithm template; splitting the corresponding initial algorithm instance according to a splitting parameter body including a splitting method and a splitting size in each selected algorithm template, obtaining a minimum algorithm instance list corresponding to each selected algorithm template; generating a priority counter according to a priority parameter in each selected algorithm template and the number of minimum algorithm instances in the corresponding minimum algorithm instance list; obtaining a data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter. The present invention can improve the working efficiency of wind turbine simulation data analysis and quickly obtain multiple data analysis results.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, terminal and storage medium for analyzing wind turbine simulation data. Background Art

[0002] During the wind turbine simulation design stage, a large amount of variable time series data (i.e., wind turbine simulation data) can be obtained through simulation calculations, and different types of data analysis can be performed on each key variable of each component of the wind turbine based on the variable time series data, so as to optimize the wind turbine parameter configuration based on the analysis results and improve the reliability of the wind turbine design.

[0003] However, the inventors discovered in the process of implementing the present invention that since fan simulation involves multiple working conditions, up to more than 6,000 working conditions, and some fan components need to be analyzed independently according to different working conditions at different positions. For example, for fan blades, since the blades are very long, some key variables of the blades, such as force conditions, torque, etc., have different values ​​in different section sections at different positions of the blades, so it is necessary to analyze each section of the blade at each position independently. However, some fan components, such as the fan hub, can be analyzed as a whole. Moreover, when the key variables targeted by the fan simulation data analysis are different, the analysis algorithms used may also be different. Therefore, when the fan simulation data analysis targets different fan components and different analysis purposes, it is usually necessary to rewrite the data analysis code, which has low work efficiency.

[0004] On this basis, there may still be dependencies between the key variables of the analysis or between the analysis algorithms, which makes it inconvenient for parallel processing, affects the processing speed, and makes it difficult to obtain multiple data analysis results in a short period of time. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, terminal and storage medium for analyzing wind turbine simulation data to solve the problems of low working efficiency of wind turbine simulation data analysis and difficulty in obtaining multiple data analysis results in a short time.

[0006] In a first aspect, an embodiment of the present invention provides a method for analyzing wind turbine simulation data, comprising:

[0007] A task of performing data analysis on a certain wind turbine simulation data is obtained, which is recorded as a selected task, and an algorithm template required for performing data analysis on the selected task is obtained, which is recorded as a selected algorithm template;

[0008] Screening the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates, and generating an initial algorithm instance corresponding to each of the selected algorithm templates;

[0009] Splitting the corresponding initial algorithm instance according to the splitting parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template; the splitting parameter body includes parameters characterizing the splitting method and the splitting size;

[0010] generating a priority counter according to the priority parameter in each of the selected algorithm templates and the number of the minimum algorithm instances in the corresponding minimum algorithm instance list;

[0011] A data analysis result corresponding to the selected task is obtained based on the minimum algorithm instance list and the priority counter.

[0012] In a possible implementation, the selected algorithm template includes applicable operating condition parameters and simulated wind turbine component type parameters;

[0013] Screening the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates to generate an initial algorithm instance corresponding to each of the selected algorithm templates includes:

[0014] Filter the file names of the wind turbine simulation data corresponding to the selected task according to the applicable operating condition parameters in each of the selected algorithm templates to obtain a list of operating condition files corresponding to each of the selected algorithm templates;

[0015] According to the simulated wind turbine component type parameters in each selected algorithm template, the simulated wind turbine components contained in the wind turbine simulation data corresponding to the selected task are screened to obtain a list of simulated wind turbine components corresponding to each selected algorithm template, and to obtain an initial algorithm instance corresponding to each selected algorithm template.

[0016] In a possible implementation, the corresponding initial algorithm instance is split according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template, including:

[0017] According to the splitting method included in the splitting parameter body in each of the selected algorithm templates, the operating condition file list or the simulated wind turbine component list is determined as a splitting target;

[0018] The split target is split according to the split size included in the split parameter body in each of the selected algorithm templates to obtain a minimum algorithm instance list corresponding to each of the selected algorithm templates.

[0019] In a possible implementation, obtaining the data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter includes:

[0020] Step a: based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, the minimum algorithm instance with the current highest priority in the minimum algorithm instance list is processed in parallel, and the count value of the counter corresponding to the current highest priority in the priority counter is updated;

[0021] Step b: When the count value of the counter corresponding to the current highest priority is updated to zero, delete the counter corresponding to the current highest priority in the priority counter, and re-execute step a and its subsequent steps until the current highest priority in the priority counter is the lowest priority and the count value of the counter corresponding to the current highest priority is updated to zero, delete the priority counter, and obtain the data analysis result corresponding to the selected task.

[0022] In a possible implementation, based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, the minimum algorithm instance with the highest current priority in the minimum algorithm instance list is processed in parallel, including:

[0023] Determine in turn whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter;

[0024] If the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter, moving the minimum algorithm instance to the work queue;

[0025] When there is a minimum algorithm instance in the work queue, the minimum algorithm instance is used as an input parameter of the corresponding algorithm program process, and according to the number of minimum algorithm instances existing in the work queue or the parallel number of the algorithm program processes, a corresponding number of algorithm program processes are started for parallel processing.

[0026] In a possible implementation manner, after sequentially determining whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter, the method further includes:

[0027] If the priority corresponding to the minimum algorithm instance is not the current highest priority in the priority counter, moving the minimum algorithm instance to a waiting queue;

[0028] When the waiting time of the minimum algorithm instance in the waiting queue exceeds a set threshold, it is re-determined whether the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter.

[0029] In a possible implementation manner, updating the count value of the counter corresponding to the current highest priority in the priority counters includes:

[0030] After the algorithm program process outputs the execution result, the count value of the counter corresponding to the corresponding priority in the priority counter is decremented according to the priority of the minimum algorithm instance corresponding to the algorithm program process.

[0031] In a second aspect, an embodiment of the present invention provides a wind turbine simulation data analysis device, comprising:

[0032] An acquisition module is used to acquire a task of performing data analysis on a certain wind turbine simulation data, recorded as a selected task, and acquire an algorithm template required for performing data analysis on the selected task, recorded as a selected algorithm template;

[0033] A first processing module, configured to screen the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates, and generate an initial algorithm instance corresponding to each of the selected algorithm templates;

[0034] A second processing module is used to split the corresponding initial algorithm instance according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template; the split parameter body includes parameters characterizing the split method and split size;

[0035] A third processing module, configured to generate a priority counter according to the priority parameter in each of the selected algorithm templates and the number of minimum algorithm instances in the corresponding minimum algorithm instance list;

[0036] An analysis module is used to obtain a data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter.

[0037] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0038] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0039] The embodiment of the present invention provides a method, device, terminal and storage medium for analyzing wind turbine simulation data. By distinguishing selected tasks and selected algorithm templates corresponding to the selected tasks in the wind turbine simulation data analysis process, the wind turbine simulation data analysis can be applied to different analysis purposes or analysis components. When the key variables to be analyzed are different or the wind turbine components are different, it is only necessary to reselect the algorithm template to be used, which has no effect on the overall analysis process and does not require rewriting the code, thereby effectively improving the work efficiency of wind turbine simulation data analysis. Moreover, for a selected task, the split parameter body including the split method and the split size in the corresponding selected algorithm template can be split into the minimum execution unit, that is, the minimum algorithm instance. And the priority in the corresponding selected algorithm template can also meet the dependency relationship between different analysis algorithms, so that the minimum algorithm instances of the same priority can be processed in parallel, and the minimum algorithm instances of different priorities with dependencies are processed according to the priority, thereby realizing parallel processing on the basis of satisfying the dependency relationship, improving the data analysis speed, and thus helping to quickly obtain multiple data analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative labor.

[0041] Figure 1 is a flow chart of the implementation of the wind turbine simulation data analysis method provided by an embodiment of the present invention;

[0042] Figure 2 is a schematic diagram of a channel merging algorithm template provided by an embodiment of the present invention;

[0043] Figure 3 is a schematic diagram of an extreme algorithm template provided by an embodiment of the present invention;

[0044] Figure 4 is a flow chart of an implementation of a wind turbine simulation data analysis method provided by another embodiment of the present invention;

[0045] Figure 5 is a structural schematic diagram of a wind turbine simulation data analysis device provided by an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0048] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0049] See also Figure 1 , which shows a flow chart of the implementation of the wind turbine simulation data analysis method provided by an embodiment of the present invention, which is described in detail as follows:

[0050] In step 101, a task of performing data analysis on certain wind turbine simulation data is obtained, which is recorded as a selected task, and an algorithm template required for performing data analysis on the selected task is obtained, which is recorded as a selected algorithm template.

[0051] In this embodiment, in order to use the timing files of different variables of different fan components obtained by fan simulation (ie, fan simulation data) to determine the most suitable parameter configuration of the fan under a certain environment or working condition, it is necessary to perform data analysis on the timing files.

[0052] For example, assuming that a fan needs to be established at position A or position B, the operation of the fan can be simulated according to the environmental conditions at position A or position B, thereby obtaining a timing file of different variables of different fan components when the fan is running as fan simulation data.

[0053] When analyzing wind turbine simulation data, in some cases it is necessary to directly analyze the stress conditions or maximum or minimum torque of a certain component of the wind turbine, such as blades, towers or hubs. In some cases, it is necessary to group the wind turbine simulation data before analysis, or it may be necessary to merge some wind turbine simulation data before analysis.

[0054] In order to avoid the problem of having to rewrite code when performing data analysis in different situations, this embodiment uses selected tasks and selected algorithm templates required for data analysis of selected tasks to distinguish wind turbine simulation data analysis in different situations, so that when the data analysis purposes and components are different, it is only necessary to select the corresponding algorithm template. Even if the adopted algorithm needs to be modified or updated, it is only necessary to expand or modify the implemented algorithm template without rewriting the code.

[0055] For example, if you need to analyze the stress condition of a wind turbine blade section or the extreme value of the moment, you can create a new task and select the channel merging algorithm template, the limit algorithm template, etc. If you need to analyze the stress condition of a tower or the extreme value of the moment, you can create a new task, update the limit algorithm template, and select the updated limit algorithm template. These processes only involve configuration changes without rewriting the code.

[0056] In step 102, the wind turbine simulation data corresponding to the selected task is screened according to each selected algorithm template, and an initial algorithm instance corresponding to each selected algorithm template is generated.

[0057] For example, Figure 2 or Figure 3 As shown, the selected algorithm template may be a channel merging algorithm template or an extreme algorithm template, etc. According to actual conditions, the selected algorithm template may also include a standard extreme algorithm template, an improved extreme algorithm template, etc., which is not limited in this embodiment.

[0058] Among them, the selected algorithm template may include parameters such as algorithm name, algorithm type, applicable working condition, simulated wind turbine component type, variable list, priority, split parameter body, algorithm parameter body, etc. In this embodiment, by setting parameters such as algorithm name, algorithm type, applicable working condition, simulated wind turbine component type, variable list, priority, split parameter body, algorithm parameter body, etc. in the algorithm template, it is convenient to expand or modify the implemented algorithm template and generate batches of algorithm templates. For example, after implementing the algorithm template related to the fan blade, by modifying the values ​​of the parameters such as algorithm name, algorithm type, applicable working condition, simulated wind turbine component type, variable list, priority, split parameter body, algorithm parameter body, etc. in the algorithm template, the algorithm template related to the fan tower or fan hub can be obtained, so as to more conveniently realize the fan simulation data analysis.

[0059] For example, Figure 2 and Figure 3 As shown, post_name can be used to represent the algorithm name parameter. The specific value of the algorithm name parameter can be determined according to actual conditions, such as Combine-Blade-E8 or Ultimate-Blade-E8.

[0060] Exemplarily, post_type may be used to represent an algorithm type parameter, and a specific value of the algorithm type may be determined according to actual conditions, such as combine (ie, channel merging algorithm) or ultimate (ie, extreme algorithm).

[0061] For example, dlc_type can be used to characterize the applicable working condition parameter, and the specific value of the applicable working condition can be determined according to the actual situation, such as ultimate, dlc1*, etc. Among them, ultimate can represent the extreme working condition, dlc1* can represent the working condition starting with dlc1, and the value of the applicable working condition parameter can also be fatigue, which represents the fatigue working condition.

[0062] Exemplarily, corresponding to different wind turbine components, stations_type can be used to characterize the type parameters of the simulated wind turbine components, such as using BladeStations to characterize all blade section types, or using TowerStations to characterize all tower section types, or using ConcreteTowerStations to characterize concrete tower section types, or using NoStations to characterize no section type.

[0063] Exemplarily, variables can be used to represent the variable list parameters. The variable list may include parameters such as variable name (e.g., variable), file suffix where the variable is located (e.g., extension), and variable unit (e.g., unit). The value of the variable list may be determined based on the key variables that actually need to be analyzed. Exemplarily, the variable name may be Blade 1Mx (Principal axes), Blade 2Mx (Principal axes), Blade 3Mx (Principal axes), etc., the file suffix where the variable is located may be %15, %16, %17, etc., and the variable unit may be kNm, etc.

[0064] Exemplarily, priority can be used to represent the priority parameter. The specific value of the priority parameter can be determined according to the dependency relationship between the algorithms used in the actual data analysis. If there is no dependency relationship between the algorithm corresponding to the selected algorithm template A and the algorithm corresponding to the selected algorithm template B, the value of the priority parameter of the selected algorithm template A and the selected algorithm template B can be set to the same value. If the algorithm corresponding to the selected algorithm template A needs to rely on the result of the algorithm corresponding to the selected algorithm template B, the value of the priority parameter of the selected algorithm template B can be set higher than the value of the priority parameter of the selected algorithm template A, so as to satisfy the dependency relationship between the algorithm corresponding to the selected algorithm template A and the algorithm corresponding to the selected algorithm template B when the data analysis is subsequently performed. Exemplarily, the priority parameter can be a value between 1-5.

[0065] Exemplarily, partition can be used to represent the parameters of the splitting parameter body, which may include parameters such as splitting method (such as method) and splitting size (such as size). For example, the splitting method may take values ​​of dlc, station, etc., and the splitting size may take values ​​of 10, 1, etc., wherein the splitting method taking dlc and the splitting size taking 10 can represent splitting according to working conditions, and there are at most 10 elements in the working condition list in the minimum algorithm instance after splitting; the splitting method taking station and the splitting size taking 1 can represent splitting according to sections, and there is only 1 section in the section list in the minimum algorithm instance after splitting.

[0066] For example, custom_data can be used to represent the algorithm parameter body parameters, which can include the control parameters of the algorithm itself, as shown in the following example: Figure 2 and Figure 3 As shown, this embodiment does not limit this.

[0067] Optionally, the selected algorithm template may also include other parameters such as a seed value, which may be specifically determined according to actual conditions and is not limited in this embodiment.

[0068] Combination Figure 2 and Figure 3 As shown, the selected algorithm template mainly includes some static parameters and control parameters of the algorithm corresponding to the selected algorithm template. In order to realize the wind turbine simulation data analysis based on the selected algorithm template, the selected algorithm template also needs to be instantiated.

[0069] Exemplarily, a list of operating condition files can be obtained by filtering the applicable operating condition parameters in the selected algorithm template, a list of simulated fan components can be obtained by filtering the simulated fan component types in the selected algorithm template, and some custom dynamic parameters required for the algorithm corresponding to the selected algorithm template can be loaded through the placeholders in the selected algorithm template, thereby completing the initial instantiation of the selected algorithm template and generating an initial algorithm instance corresponding to the selected algorithm template.

[0070] In step 103, the corresponding initial algorithm instance is split according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template.

[0071] The splitting parameter body includes parameters that characterize the splitting method and splitting size.

[0072] In this embodiment, taking into account the need to analyze multiple key variables simultaneously during data analysis, in order to improve the processing speed, split parameter body parameters are defined in the selected algorithm template for wind turbine simulation data analysis to facilitate splitting the task of wind turbine simulation data analysis into smaller sub-tasks of the same type, and then processing each sub-task in parallel, thereby improving the processing speed of wind turbine simulation data analysis.

[0073] For example, the working condition file list or the simulated fan component section list after initial instantiation may be a heavy calculation process with a loop. According to the different algorithms corresponding to the selected algorithm template, it may be a working condition list loop or a fan component list loop (such as a blade section list loop). The initial algorithm instance after initial instantiation can be split according to the splitting method and splitting size corresponding to the split parameter body in the selected algorithm template to obtain several smaller and more specific subtasks of the same type.

[0074] In step 104, a priority counter is generated according to the priority parameter in each selected algorithm template and the number of minimum algorithm instances in the corresponding minimum algorithm instance list.

[0075] In step 105, a data analysis result corresponding to the selected task is obtained based on the minimum algorithm instance list and the priority counter.

[0076] In this embodiment, considering that there may be dependencies between the algorithms required for data analysis in the selected task, it is difficult to satisfy the corresponding dependencies by directly processing each minimum algorithm instance in the list of split minimum algorithm instances in parallel. Therefore, the dependencies between algorithms are simplified to priorities, and when the selected task requires the use of multiple analysis algorithms, analysis algorithms of the same priority can be executed in parallel, and analysis algorithms of different priorities with dependencies can be executed according to the priority, thereby achieving parallel processing on the basis of satisfying the dependencies, improving the speed of data analysis, and thus helping to quickly obtain multiple data analysis results.

[0077] The embodiment of the present invention distinguishes between the selected task and the selected algorithm template corresponding to the selected task in the wind turbine simulation data analysis process, so that the wind turbine simulation data analysis can be applied to different analysis purposes or analysis components. When the key variables to be analyzed are different or the wind turbine components are different, it is only necessary to reselect the algorithm template to be used, which has no impact on the overall analysis process and does not require rewriting the code, thereby effectively improving the work efficiency of the wind turbine simulation data analysis. Moreover, for a selected task, it can be split into the minimum execution unit, that is, the minimum algorithm instance, through the split parameter body including the split method and the split size in the corresponding selected algorithm template. And through the priority in the corresponding selected algorithm template, the dependency relationship between different analysis algorithms can also be met, so that the minimum algorithm instances of the same priority can be processed in parallel, and the minimum algorithm instances of different priorities with dependencies are processed according to the priority, thereby realizing parallel processing on the basis of satisfying the dependency relationship, improving the data analysis speed, and thus helping to quickly obtain multiple data analysis results.

[0078] Optionally, the selected algorithm template includes applicable operating condition parameters and simulated wind turbine component type parameters.

[0079] Accordingly, the wind turbine simulation data corresponding to the selected task is screened according to each selected algorithm template, and an initial algorithm instance corresponding to each selected algorithm template is generated, which may include:

[0080] The file names of the wind turbine simulation data corresponding to the selected task are screened according to the applicable operating condition parameters in each selected algorithm template to obtain a list of operating condition files corresponding to each selected algorithm template.

[0081] According to the simulated fan component type parameters in each selected algorithm template, the simulated fan components contained in the fan simulation data corresponding to the selected task are screened, a simulated fan component list corresponding to each selected algorithm template is obtained, and an initial algorithm instance corresponding to each selected algorithm template is obtained.

[0082] For example, if the total number of working conditions of a wind turbine simulation task is 3016, the distribution of various working conditions is shown in Table 1, and each blade has 120 blade sections.

[0083] Table 1

[0084]

[0085] Figure 4 Another implementation flow chart of the wind turbine simulation data analysis method provided in this embodiment is as follows: Figure 4 Based on Figure 2 and Figure 3As shown, the applicable working condition parameters in the channel merging algorithm template or the limit algorithm template include ultimate and dlc1*. Where ultimate = {dlc1.3, dlc2.1}, dlc1* = {dlc1.2, dlc1.3}, then:

[0086] ultimate∪dlc1*={dlc1.3,dlc2.1}∪{dlc1.2,dlc1.3}, that is, ultimate∪dlc1*=501+1503+505=2509, and a list of working condition files containing 2509 working conditions is obtained, which can be expressed as [0,1,2…2508] for example.

[0087] The blade section type parameter in the channel merging algorithm template or the limit algorithm template is BladeStations, which represents all blade sections, and a blade section list including 120 blade sections can be obtained, which can be expressed as [0, 1, 2…119]. At this point, the initial instantiation of the selected algorithm template is completed.

[0088] Optionally, the corresponding initial algorithm instance is split according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template, which may include:

[0089] According to the splitting method included in the splitting parameter body in each selected algorithm template, the operating condition file list or the simulated wind turbine component list is determined as the splitting target.

[0090] The split target is split according to the split size included in the split parameter body in each selected algorithm template, and a minimum algorithm instance list corresponding to each selected algorithm template is obtained.

[0091] Continue to combine Figure 4 as well as Figure 2 and Figure 3 When the split method is dlc and the split size is 10, the working condition file list [0,1,2…2508] is split to obtain the minimum algorithm instance list [0…9], [10…19], [20…29]…[2500…2508], totaling 251 minimum algorithm instances. The number of working condition elements in each minimum algorithm instance is 10, 10, 10…9. When the split method is station and the split size is 1, the blade section list [0,1,2…119] is split to obtain the minimum algorithm instance list [0], [1], [2]…

[119] , totaling 120 minimum algorithm instances, and the number of section elements in each minimum algorithm instance is 1.

[0092] On this basis, in order to facilitate data processing, if the selected algorithm template corresponding to the selected task only includes the extreme algorithm template, that is, the priority of the algorithm corresponding to the selected algorithm template is 1, and the number of minimum algorithm instances in the minimum algorithm instance list is 120, then a priority counter of {1:120} can be obtained. If the selected task is recorded as batch01, the task mark of batch01 can also be added to the priority counter and each minimum algorithm instance, so as to distinguish the minimum execution unit of the processing during subsequent parallel processing. Exemplarily, the priority counter after adding the task mark can be recorded as Counter = (batch01, {1:120}).

[0093] Exemplarily, if the selected algorithm template corresponding to the selected task includes a channel merging algorithm template and an extreme algorithm template, the priority of the algorithm corresponding to the channel merging algorithm template is 2, and the number of minimum algorithm instances in the minimum algorithm instance list is 251, the priority of the algorithm corresponding to the extreme algorithm template is 1, and the number of minimum algorithm instances in the minimum algorithm instance list is 120, if the selected task is recorded as batch02, then the priority counter after adding the task mark can be recorded as Counter = (batch02, {1:120,2:251}).

[0094] On this basis, the data analysis results corresponding to the selected tasks are obtained based on each minimum algorithm instance after adding the task mark and the priority counter Counter = (batch01, {1:120}) or Counter = (batch02, {1:120, 2:251}).

[0095] Optional, continue combining Figure 4 , based on the minimum algorithm instance list and priority counter, the data analysis results corresponding to the selected task can include:

[0096] Step a: Based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, the minimum algorithm instance with the current highest priority in the minimum algorithm instance list is processed in parallel, and the count value of the counter corresponding to the current highest priority in the priority counter is updated.

[0097] Step b: When the count value of the counter corresponding to the current highest priority is updated to zero, delete the counter corresponding to the current highest priority in the priority counter, and re-execute step a and its subsequent steps until the current highest priority in the priority counter is the lowest priority and the count value of the counter corresponding to the current highest priority is updated to zero, delete the priority counter, and obtain the data analysis result corresponding to the selected task.

[0098] In this embodiment, after obtaining the minimum algorithm instance list consisting of the minimum algorithm instances after adding the task mark, and after obtaining the priority counter after adding the task mark, it can be sent as a message to the distribution queue of the scheduling service. For a large number of minimum algorithm instances submitted in the same batch, the distribution queue combines the corresponding task marks and the count value of the priority counter for the minimum algorithm instance of each priority, so that the high-priority minimum algorithm instance is executed first. When all the high-priority minimum algorithm instances are executed, the lower-level minimum algorithm instance is executed, and so on, until all the minimum algorithm instances with the lowest priority are executed, and the data analysis results corresponding to the selected task are obtained.

[0099] Optional, combined Figure 4 , based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, parallel processing of the minimum algorithm instance with the highest current priority in the minimum algorithm instance list may include:

[0100] It is determined in turn whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter.

[0101] If the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter, the minimum algorithm instance is moved to the work queue.

[0102] When there is a minimum algorithm instance in the work queue, the minimum algorithm instance is used as an input parameter of the corresponding algorithm program process, and according to the number of minimum algorithm instances or the parallel number of algorithm program processes in the work queue, a corresponding number of algorithm program processes are started for parallel processing.

[0103] In this embodiment, the priority of the received message can be read through the distribution queue of the scheduling service first, and then it is determined whether the read priority is the highest priority in the corresponding priority counter. If the read priority is the highest priority in the corresponding priority counter, the message is moved to the work queue.

[0104] For example, after getting a message tagged with batch01, its priority is 1. Find the priority counter tagged with batch01 and determine that the highest priority is 1, then move the message to the work queue.

[0105] Then set up a resident background Agent service to monitor the work queue. When it detects that there is a message or a minimum algorithm instance in the work queue, it pulls the message and calls the corresponding algorithm program process. After the algorithm program process is started, it can continue to pull messages until the parallel number of algorithm program processes is reached or there are no messages waiting in the work queue.

[0106] The algorithm program process is a computer program that implements the corresponding algorithm content and saves the calculation results. After the algorithm program process is started, the message content can be read. Figure 2 For the channel merging algorithm template shown, 10 working condition files and 120 blade sections are read, and the %15, %16, and %17 files in the cache are downloaded or read in sequence according to the working condition sequence, and the 3 variable data of the 120 section positions are read, and the calculation is performed, and the results are saved in the database, and the algorithm program process is waited for to exit and the calculation is completed. Figure 3 The limit algorithm template shown reads a list of 2509 working condition files and 1 blade section, downloads or reads the %15, %16, and %17 files in the cache in sequence according to the working condition sequence, reads the 3 variable data of 1 section position, performs calculations, saves the results to the database, waits for the algorithm program process to exit, and completes the calculation.

[0107] Among them, in order to reduce the use of network resources and prevent excessive cache growth, a multi-process cache module can be set up. When the source of the sequential files read by multiple algorithm program processes is the same, it can be used to cache the downloaded files between multiple algorithm program processes to avoid repeated downloads.

[0108] Among them, after the algorithm program process completes the calculation, the message completion information can be fed back to the scheduling service, and the scheduling service can move the message to the completion queue to facilitate updating the count value in the priority counter.

[0109] Optionally, updating the count value of the counter corresponding to the current highest priority in the priority counter may include:

[0110] After the algorithm program process outputs the execution result, the count value of the counter corresponding to the corresponding priority in the priority counter is decremented according to the priority of the minimum algorithm instance corresponding to the algorithm program process.

[0111] For example, after the algorithm program process completes the calculation, it feeds back the message completion information to the scheduling service, and the scheduling service moves the message to the completion queue. The completion queue reads the priority of the message therein, and then decrements the count value of the counter corresponding to the corresponding priority in the priority counter, thereby updating the count value of the corresponding priority in the priority counter. For example, when a task is marked as batch02 and the minimum algorithm instance with a priority of 2 is executed, the priority counter Counter = (batch02, {1:120, 2:251}) can be updated to Counter = (batch02, {1:120, 2:250}) until the count value of the priority 2 is reduced to 0.

[0112] When the count value of a higher priority level is reduced to 0, the counter corresponding to the priority level can be deleted. For example, when Counter = (batch02, {1:120, 2:0}), the counter with a priority level of 2 can be deleted to obtain Counter = (batch02, {1:120}).

[0113] After the priority counter is updated based on the messages in the completion queue, the completed messages may be deleted.

[0114] Optionally, a multi-process log module can be set up to write the local log of the algorithm program process to multiple processes safely to prevent damage to the log file.

[0115] Optional, combined Figure 4 , after successively determining whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter, the method may further include:

[0116] If the priority corresponding to the minimum algorithm instance is not the current highest priority in the priority counter, the minimum algorithm instance is moved to the waiting queue.

[0117] When the waiting time of the minimum algorithm instance in the waiting queue exceeds a set threshold, it is re-determined whether the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter.

[0118] In this embodiment, if the message received by the dispatch queue of the scheduling service is not the highest priority in the priority counter, the message can be moved to the waiting queue to meet the dependency relationship between different algorithms.

[0119] If a message with batch02 tag is obtained, its priority is 1, the priority counter with batch02 tag is found and the highest priority is determined to be 2, then the message is moved to the waiting queue.

[0120] After a short waiting period, the messages in the waiting queue can be moved back to the distribution queue so that the execution of the lower-level messages can be started in time after all the higher-level messages are executed.

[0121] In the process of wind turbine simulation data analysis, the embodiments of the present invention can facilitate the expansion or modification of different algorithms through algorithm templating, thereby improving the work efficiency and generalization ability of wind turbine simulation data analysis. By splitting the algorithm instance, the wind turbine simulation data analysis task can be split into the minimum granularity of parallelization. On this basis, by setting the priority for message scheduling processing, the dependency relationship between different algorithms can be satisfied. Through multi-process caching, the reuse rate of time series file data (that is, wind turbine simulation data) can be increased. The algorithm instance is atomized by the method of disassembling the algorithm instance, message scheduling processing and multi-process caching, thereby reducing the dispersion of the time series file and the computing node, so that the time series file can be significantly reused in parallelization, thereby achieving the effect of improving the overall computing speed.

[0122] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0123] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0124] Figure 5 The structural schematic diagram of the wind turbine simulation data analysis device provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0125] like Figure 5 As shown, the wind turbine simulation data analysis device includes: an acquisition module 51 , a first processing module 52 , a second processing module 53 , a third processing module 54 and an analysis module 55 .

[0126] The acquisition module 51 is used to acquire a task of performing data analysis on a certain wind turbine simulation data, which is recorded as a selected task, and acquire an algorithm template required for performing data analysis on the selected task, which is recorded as a selected algorithm template;

[0127] A first processing module 52 is used to screen the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates, and generate an initial algorithm instance corresponding to each of the selected algorithm templates;

[0128] The second processing module 53 is used to split the corresponding initial algorithm instance according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template; the split parameter body includes parameters characterizing the split method and split size;

[0129] A third processing module 54 is used to generate a priority counter according to the priority parameter in each of the selected algorithm templates and the number of minimum algorithm instances in the corresponding minimum algorithm instance list;

[0130] The analysis module 55 is used to obtain the data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter.

[0131] The embodiment of the present invention distinguishes between the selected task and the selected algorithm template corresponding to the selected task in the wind turbine simulation data analysis process, so that the wind turbine simulation data analysis can be applied to different analysis purposes or analysis components. When the key variables to be analyzed are different or the wind turbine components are different, it is only necessary to reselect the algorithm template to be used, which has no impact on the overall analysis process and does not require rewriting the code, thereby effectively improving the work efficiency of the wind turbine simulation data analysis. Moreover, for a selected task, it can be split into the minimum execution unit, that is, the minimum algorithm instance, through the split parameter body including the split method and the split size in the corresponding selected algorithm template. And through the priority in the corresponding selected algorithm template, the dependency relationship between different analysis algorithms can also be met, so that the minimum algorithm instances of the same priority can be processed in parallel, and the minimum algorithm instances of different priorities with dependencies are processed according to the priority, thereby realizing parallel processing on the basis of satisfying the dependency relationship, improving the data analysis speed, and thus helping to quickly obtain multiple data analysis results.

[0132] In a possible implementation, the selected algorithm template includes applicable operating condition parameters and simulated wind turbine component type parameters; the first processing module 52 can be used to filter the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates, and generate an initial algorithm instance corresponding to each of the selected algorithm templates, including:

[0133] Filter the file names of the wind turbine simulation data corresponding to the selected task according to the applicable operating condition parameters in each of the selected algorithm templates to obtain a list of operating condition files corresponding to each of the selected algorithm templates;

[0134] According to the simulated wind turbine component type parameters in each selected algorithm template, the simulated wind turbine components contained in the wind turbine simulation data corresponding to the selected task are screened to obtain a list of simulated wind turbine components corresponding to each selected algorithm template, and to obtain an initial algorithm instance corresponding to each selected algorithm template.

[0135] In a possible implementation, the first processing module 52 may be configured to determine the operating condition file list or the simulated wind turbine component list as a split target according to the split method included in the split parameter body in each selected algorithm template;

[0136] The split target is split according to the split size included in the split parameter body in each of the selected algorithm templates to obtain a minimum algorithm instance list corresponding to each of the selected algorithm templates.

[0137] In a possible implementation, the analysis module 55 may be used in step a: based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, parallelly process the minimum algorithm instance with the current highest priority in the minimum algorithm instance list, and update the count value of the counter corresponding to the current highest priority in the priority counter;

[0138] Step b: When the count value of the counter corresponding to the current highest priority is updated to zero, delete the counter corresponding to the current highest priority in the priority counter, and re-execute step a and its subsequent steps until the current highest priority in the priority counter is the lowest priority and the count value of the counter corresponding to the current highest priority is updated to zero, delete the priority counter, and obtain the data analysis result corresponding to the selected task.

[0139] In a possible implementation, the analysis module 55 may be used to sequentially determine whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter;

[0140] If the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter, moving the minimum algorithm instance to the work queue;

[0141] When there is a minimum algorithm instance in the work queue, the minimum algorithm instance is used as an input parameter of the corresponding algorithm program process, and according to the number of minimum algorithm instances existing in the work queue or the parallel number of the algorithm program processes, a corresponding number of algorithm program processes are started for parallel processing.

[0142] In a possible implementation, the analysis module 55 may also be configured to move the minimum algorithm instance to a waiting queue if the priority corresponding to the minimum algorithm instance is not the current highest priority in the priority counter;

[0143] When the waiting time of the minimum algorithm instance in the waiting queue exceeds a set threshold, it is re-determined whether the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter.

[0144] In a possible implementation, the analysis module 55 may be used to decrement the count value of the counter corresponding to the corresponding priority in the priority counter according to the priority of the minimum algorithm instance corresponding to the algorithm program process after the algorithm program process outputs the execution result.

[0145] Figure 6 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 6 As shown, the terminal 6 of this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program 62, the steps in the above-mentioned various wind turbine simulation data analysis method embodiments are implemented, for example Figure 1 Alternatively, when the processor 60 executes the computer program 62, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 5 Functions of the modules / units 51 to 55 are shown.

[0146] Exemplarily, the computer program 62 may be divided into one or more modules / units, one or more modules / units are stored in the memory 61 and executed by the processor 60 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the terminal 6. For example, the computer program 62 may be divided into Figure 5 Modules / units 51 to 55 are shown.

[0147] The terminal 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that Figure 6 It is only an example of terminal 6 and does not constitute a limitation on terminal 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0148] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0149] The memory 61 may be an internal storage unit of the terminal 6, such as a hard disk or memory of the terminal 6. The memory 61 may also be an external storage device of the terminal 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal 6. Further, the memory 61 may also include both an internal storage unit of the terminal 6 and an external storage device. The memory 61 is used to store computer programs and other programs and data required by the terminal. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0150] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0151] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0152] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0153] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various wind turbine simulation data analysis method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media can include: any entity or device that can carry computer program code, recording media, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0157] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for analyzing wind turbine simulation data, characterized in that: include: A task of performing data analysis on a certain wind turbine simulation data is obtained, which is recorded as a selected task, and an algorithm template required for performing data analysis on the selected task is obtained, which is recorded as a selected algorithm template; Screening the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates, and generating an initial algorithm instance corresponding to each of the selected algorithm templates; Splitting the corresponding initial algorithm instance according to the splitting parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template; the splitting parameter body includes parameters characterizing the splitting method and the splitting size; generating a priority counter according to the priority parameter in each of the selected algorithm templates and the number of the minimum algorithm instances in the corresponding minimum algorithm instance list; Obtaining a data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter; The selected algorithm template includes applicable operating condition parameters and simulated wind turbine component type parameters; Screening the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates to generate an initial algorithm instance corresponding to each of the selected algorithm templates includes: Filter the file names of the wind turbine simulation data corresponding to the selected task according to the applicable operating condition parameters in each of the selected algorithm templates to obtain a list of operating condition files corresponding to each of the selected algorithm templates; According to the simulated wind turbine component type parameters in each selected algorithm template, the simulated wind turbine components contained in the wind turbine simulation data corresponding to the selected task are screened to obtain a list of simulated wind turbine components corresponding to each selected algorithm template, and to obtain an initial algorithm instance corresponding to each selected algorithm template.

2. The wind turbine simulation data analysis method according to claim 1, characterized in that: The corresponding initial algorithm instance is split according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template, including: According to the splitting method included in the splitting parameter body in each of the selected algorithm templates, the operating condition file list or the simulated wind turbine component list is determined as a splitting target; The split target is split according to the split size included in the split parameter body in each of the selected algorithm templates to obtain a minimum algorithm instance list corresponding to each of the selected algorithm templates.

3. The wind turbine simulation data analysis method according to claim 1, characterized in that: Obtaining a data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter includes: Step a: based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, the minimum algorithm instance with the current highest priority in the minimum algorithm instance list is processed in parallel, and the count value of the counter corresponding to the current highest priority in the priority counter is updated; Step b: When the count value of the counter corresponding to the current highest priority is updated to zero, delete the counter corresponding to the current highest priority in the priority counter, and re-execute step a and its subsequent steps until the current highest priority in the priority counter is the lowest priority and the count value of the counter corresponding to the current highest priority is updated to zero, delete the priority counter, and obtain the data analysis result corresponding to the selected task.

4. The wind turbine simulation data analysis method according to claim 3, characterized in that: Based on the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list, the minimum algorithm instance with the highest current priority in the minimum algorithm instance list is processed in parallel, including: Determine in turn whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter; If the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter, moving the minimum algorithm instance to the work queue; When there is a minimum algorithm instance in the work queue, the minimum algorithm instance is used as an input parameter of the corresponding algorithm program process, and according to the number of minimum algorithm instances existing in the work queue or the parallel number of the algorithm program processes, a corresponding number of algorithm program processes are started for parallel processing.

5. The wind turbine simulation data analysis method according to claim 4, characterized in that: After successively determining whether the priority corresponding to each minimum algorithm instance in the minimum algorithm instance list is the current highest priority in the priority counter, the method further includes: If the priority corresponding to the minimum algorithm instance is not the current highest priority in the priority counter, moving the minimum algorithm instance to a waiting queue; When the waiting time of the minimum algorithm instance in the waiting queue exceeds a set threshold, it is re-determined whether the priority corresponding to the minimum algorithm instance is the current highest priority in the priority counter.

6. The wind turbine simulation data analysis method according to claim 4, characterized in that: Updating the count value of the counter corresponding to the current highest priority in the priority counters, including: After the algorithm program process outputs the execution result, the count value of the counter corresponding to the corresponding priority in the priority counter is decremented according to the priority of the minimum algorithm instance corresponding to the algorithm program process.

7. A wind turbine simulation data analysis device, characterized in that: include: An acquisition module is used to acquire a task of performing data analysis on a certain wind turbine simulation data, which is recorded as a selected task, and acquire an algorithm template required for performing data analysis on the selected task, which is recorded as a selected algorithm template; A first processing module, configured to screen the wind turbine simulation data corresponding to the selected task according to each of the selected algorithm templates, and generate an initial algorithm instance corresponding to each of the selected algorithm templates; A second processing module is used to split the corresponding initial algorithm instance according to the split parameter body in each selected algorithm template to obtain a minimum algorithm instance list corresponding to each selected algorithm template; the split parameter body includes parameters characterizing the split method and split size; A third processing module, configured to generate a priority counter according to the priority parameter in each of the selected algorithm templates and the number of minimum algorithm instances in the corresponding minimum algorithm instance list; An analysis module, configured to obtain a data analysis result corresponding to the selected task based on the minimum algorithm instance list and the priority counter; The selected algorithm template includes applicable operating condition parameters and simulated wind turbine component type parameters; The first processing module is specifically used for: Filter the file names of the wind turbine simulation data corresponding to the selected task according to the applicable operating condition parameters in each of the selected algorithm templates to obtain a list of operating condition files corresponding to each of the selected algorithm templates; According to the simulated wind turbine component type parameters in each selected algorithm template, the simulated wind turbine components contained in the wind turbine simulation data corresponding to the selected task are screened to obtain a list of simulated wind turbine components corresponding to each selected algorithm template, and to obtain an initial algorithm instance corresponding to each selected algorithm template.

8. A terminal, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images