Method, device and equipment for determining design parameters of fan blade
By using deep learning models and second-generation genetic algorithms to optimize wind turbine blade parameters in parallel, the problems of low efficiency and misoperation in traditional design were solved, and efficient and accurate blade design was achieved.
Patent Information
- Application Number
- CN202511031612.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-25
- Publication Date
- 2025-11-07
AI Technical Summary
Traditional wind turbine blade design methods are inefficient and require collaboration between different scientific teams, which carries the risk of human error and waste of resources.
By employing a deep learning model combined with a second-generation genetic algorithm, the weight coefficients for classifying various parameters of the wind turbine blades are determined in parallel through modeling, automatically optimizing design parameters and reducing manual coordination steps.
It improved the efficiency of wind turbine blade design, reduced human error in coordination, improved the accuracy of design parameters, and reduced resource waste.
Smart Images
Figure CN120911026A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the field of wind power generation, in particular to the technical field of determining design parameters of wind turbine blades. BACKGROUND
[0002] The design of wind turbine blades is a highly complex multi-disciplinary coupling engineering, which needs to integrate multiple fields of professional knowledge such as aerodynamics, structural mechanics, composite materials, control engineering, and overall system matching. The traditional design method adopts a linear iterative process: aerodynamic shape design is completed first, then structural topology optimization, material selection, control strategy formulation, and overall verification, and manual coordination and feedback are performed between each link. Each design step corresponds to a blade parameter classification (for example, the blade parameter classification corresponding to aerodynamic shape design is obviously aerodynamic design classification, and the design parameters to be optimized under this aerodynamic design classification include chord length distribution and angle of attack distribution), so the existing design method obviously determines the design parameters in the next blade parameter classification after the design parameters in the previous blade parameter classification are determined. This serial blade design parameter determination method leads to low design efficiency of wind turbine blades, and requires mutual cooperation of different scientific teams, which inevitably leads to the risk of human error in the process of manual coordination, further exacerbating resource waste. SUMMARY
[0003] The present disclosure provides a method, device, equipment and storage medium for determining design parameters of wind turbine blades.
[0004] According to a first aspect of the present disclosure, a method for determining design parameters of wind turbine blades is provided. The method comprises:
[0005] obtaining a target performance parameter of the blade;
[0006] inputting the target performance parameter of the blade into a target deep learning model to determine weight coefficients of a plurality of blade parameter classifications corresponding to the target performance parameter;
[0007] determining optimal solutions of each design parameter of the blade under each blade parameter classification according to the weight coefficients of the plurality of blade parameter classifications corresponding to the target performance parameter.
[0008] According to any possible implementation of the above-mentioned aspect, a further implementation is provided, wherein the target performance parameter comprises a plurality of parameters, and before inputting the target performance parameter of the blade into the target deep learning model, the method further comprises:
[0009] standardizing the plurality of parameters;
[0010] normalizing the plurality of parameters after standardization.
[0011] According to the weight coefficient of each blade parameter category corresponding to the target performance parameter, the optimal solution of each design parameter of the blade under each blade parameter category is determined, including:
[0012] According to the weight coefficient of each blade parameter category corresponding to the target performance parameter and the second-generation genetic algorithm, the initialization of each design parameter of the blade under each blade parameter category is performed, and a plurality of initialization values of the design parameters are obtained.
[0013] The optimal solution of each design parameter is selected from the plurality of initialization values of the design parameters.
[0014] According to the weight coefficient of each blade parameter category corresponding to the target performance parameter, the optimal solution of each design parameter of the blade under each blade parameter category is determined, including:
[0015] The weight coefficient threshold of each blade parameter category is obtained.
[0016] It is judged whether the weight coefficient of each blade parameter category corresponding to the target performance parameter is greater than the minimum weight coefficient of each blade parameter category.
[0017] From the plurality of blade parameter categories corresponding to the target performance parameter, the blade parameter category whose weight coefficient is greater than the minimum weight coefficient is determined.
[0018] According to the weight coefficient of the blade parameter category whose weight coefficient is greater than the minimum weight coefficient, the optimal solution of each design parameter of the blade under each blade parameter category is determined.
[0019] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, and the method further includes:
[0020] The SHAP value of the optimal solution of each design parameter is calculated.
[0021] According to the SHAP value of the optimal solution of each design parameter, it is judged whether the weight coefficient of each blade parameter category is abnormal.
[0022] If the weight coefficient of any blade parameter category of the plurality of blade parameter categories is abnormal, the weight coefficient of the any blade parameter category is modified, and the optimal solution of each design parameter is re-determined according to the modified weight coefficient.
[0023] According to the SHAP value of the optimal solution of each design parameter, it is determined whether the weight coefficient occupied by each of the plurality of blade parameter categories is abnormal.
[0024] According to the SHAP value of the optimal solution of each design parameter, the SHAP value of each of the plurality of blade parameter categories is calculated.
[0025] If the SHAP value of any blade parameter category in the plurality of blade parameter categories is lower than the lowest SHAP threshold value or higher than the highest SHAP threshold value, it is determined that the weight coefficient occupied by the any blade parameter category is abnormal.
[0026] If the weight coefficient occupied by any blade parameter category in the plurality of blade parameter categories is abnormal, the weight coefficient occupied by the any blade parameter category is modified, including:
[0027] If the SHAP value of the any blade parameter category is lower than the lowest SHAP threshold value, the weight coefficient occupied by the any blade parameter category is modified to the corresponding lowest weight coefficient.
[0028] If the SHAP value of the any blade parameter category is higher than the highest SHAP threshold value, the weight coefficient occupied by the any blade parameter category is modified to the corresponding highest weight coefficient.
[0029] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, and the method further includes:
[0030] Determining a performance parameter expected to be optimized by the blade;
[0031] According to the performance parameter expected to be optimized by the blade, adjusting the weight coefficient occupied by each of the plurality of blade parameter categories;
[0032] According to the adjusted weight coefficient, re-determining the optimal solution of each design parameter.
[0033] According to a second aspect of the present disclosure, a determination device for a wind turbine blade design parameter is provided. The device includes:
[0034] An acquisition module is configured to acquire a target performance parameter of the blade;
[0035] A first determination module is configured to input the target performance parameter of the blade into a target deep learning model, and determine a weight coefficient occupied by each of a plurality of blade parameter categories corresponding to the target performance parameter;
[0036] The second determining module is configured to determine the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category corresponding to the target performance parameter.
[0037] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device comprises a memory and a processor, the memory having stored thereon a computer program, the processor implementing the method as described above when executing the program.
[0038] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, the program being executed by a processor to implement the method according to the first aspect of the present disclosure.
[0039] In the present disclosure, the optimal solution of each design parameter under different blade parameter categories can be obtained through model parallelism, which can obviously improve the design efficiency of the fan blade compared to the prior art which needs to determine the design parameters in different blade parameter categories in series, and does not need the mutual cooperation of different teams, reduces the misoperation caused by manual coordination in the design of blade parameters, and is beneficial to improve the accuracy of the design parameters and reduce resource waste.
[0040] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS
[0041] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The attached drawings are intended to better understand the present disclosure and do not limit the present disclosure. In the drawings, the same or similar elements are denoted by the same or similar reference numerals, and:
[0042] Figure 1 A flowchart of a method for determining fan blade design parameters according to an embodiment of the present disclosure is shown;
[0043] Figure 2 A block diagram of a device for determining fan blade design parameters according to an embodiment of the present disclosure is shown;
[0044] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION
[0045] In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.
[0046] In addition, the term "and / or" in this paper is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents an "or" relationship between the front and rear associated objects.
[0047] Figure 1 A flow chart of a method 100 for determining fan blade design parameters according to an embodiment of the present disclosure is shown. The method 100 can include:
[0048] Step 110, obtaining a target performance parameter of the blade;
[0049] The target performance parameter includes but is not limited to: Cp value (aerodynamic efficiency of the blade, wind energy utilization coefficient), blade root thrust, safety factor, modal frequency, total cost of the blade, fatigue life, blade load, power generation, noise, etc.
[0050] For example: the target performance parameter can be: maximum Cp value ≥ 0.48, total cost of the blade ≤ 12 million yuan.
[0051] Step 120, inputting the target performance parameter of the blade into a target deep learning model to determine the weight coefficient of each blade parameter classification corresponding to the target performance parameter;
[0052] The target deep learning model can be a Transformer model.
[0053] The target performance parameter can have multiple performance parameters, and different performance parameters correspond to different blade parameter classifications, and each blade parameter classification corresponds to different design parameters.
[0054] The blade parameter classification can be: aerodynamic design classification, structural design classification, material design classification, and whole machine matching classification.
[0055] The target performance parameter and the design parameter corresponding to each blade parameter classification are shown in Table 1:
[0056] Table 1
[0057]
[0058] For example, when the target performance parameter is Cp value and total blade cost, according to Table 1, the corresponding blade parameter categories are aerodynamic design category and material design category (wherein the Cp value corresponds to the aerodynamic design category, and the total blade cost corresponds to the material design category), and the design parameters under the aerodynamic design category are chord length distribution, angle of attack distribution and other shape design parameters, and the design parameters under the material design category are material properties and material cost.
[0059] Step 130, determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category corresponding to the target performance parameter.
[0060] By obtaining the target performance parameter of the blade, and then inputting the target performance parameter of the blade into the target deep learning model, the weight coefficient of each blade parameter category corresponding to the target performance parameter can be determined, and then according to the weight coefficient of each blade parameter category corresponding to the target performance parameter, the optimal solution of each design parameter of the blade under each blade parameter category can be determined. In this way, the optimal solution of each design parameter under different blade parameter categories can be obtained in parallel through the model, which obviously improves the design efficiency of the fan blade compared to the existing technology which needs to determine the design parameters in different blade parameter categories in series, and does not require the mutual cooperation of different teams, reduces the misoperation caused by manual coordination in blade parameter design, and is beneficial to improving the accuracy of the design parameters and reducing resource waste.
[0061] In some embodiments, the target performance parameter includes multiple parameters, and before inputting the target performance parameter of the blade into the target deep learning model, the method further includes:
[0062] standardizing the multiple parameters;
[0063] normalizing the multiple parameters after standardization, such as mapping different parameters to the interval [0, 1].
[0064] Since the target performance parameter can include multiple parameters, and the unit or writing method of the same parameter in each target performance parameter can also not be uniform, the multiple parameters can be standardized to ensure the standardization of the parameters, and the orders of magnitude of the parameters can also differ greatly, such as when the target performance parameter is maximum Cp value ≥ 0.48 and total blade cost ≤ 12 million yuan, the orders of magnitude of 0.48 and 12 million yuan differ greatly. Therefore, the multiple parameters after standardization can be normalized to map the multiple parameters to the same numerical interval, so as to ensure the accuracy of each design parameter.
[0065] In some embodiments, determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category corresponding to the target performance parameter comprises:
[0066] Initializing each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category corresponding to the target performance parameter and the NSGA-II algorithm, to obtain a plurality of initialized values of each design parameter.
[0067] The NSGA-II algorithm is a second-generation genetic algorithm.
[0068] Selecting the optimal solution of each design parameter from the plurality of initialized values of each design parameter.
[0069] By inputting the weight coefficient of each blade parameter category corresponding to the target performance parameter into the NSGA-II algorithm, the NSGA-II algorithm can initialize each design parameter to obtain a plurality of initialized values of each design parameter, and then find the optimal Pareto front solution set by searching for the optimal solution of each design parameter from the plurality of initialized values of each design parameter.
[0070] In some embodiments, determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category corresponding to the target performance parameter comprises:
[0071] Obtaining the weight coefficient threshold of each blade parameter category;
[0072] Determining whether the weight coefficient of each blade parameter category corresponding to the target performance parameter is greater than the minimum weight coefficient of each blade parameter category;
[0073] Determining the blade parameter category whose weight coefficient is greater than the minimum weight coefficient from the plurality of blade parameter categories corresponding to the target performance parameter;
[0074] Determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category whose weight coefficient is greater than the minimum weight coefficient.
[0075] After obtaining the weight coefficient threshold of each blade parameter classification, it can be determined whether the weight coefficient of each blade parameter classification corresponding to the target performance parameter is greater than the minimum weight coefficient. If the weight coefficient of any blade parameter classification is lower than the minimum weight coefficient, the blade parameter classification can be selected to be ignored or inactivated to reduce the consumption of computing resources (e.g., only the blade parameter classification with a weight coefficient greater than 0.1 is retained to participate in the calculation, thereby reducing the consumption of computing resources). Then, the optimal solution of each design parameter of the blade under each blade parameter classification is determined according to the weight coefficient of the blade parameter classification with a weight coefficient greater than the minimum weight coefficient. In this way, the optimal solution of each design parameter can be accurately obtained while reducing the consumption of computing resources.
[0076] In some embodiments, the method further comprises:
[0077] calculating the SHAP value of the optimal solution of each design parameter;
[0078] SHAP value stands for SHapley Additive exPlanations.
[0079] According to the SHAP value of the optimal solution of each design parameter, it can be determined whether the weight coefficient of each blade parameter classification is abnormal.
[0080] The SHAP value of the optimal solution of each design parameter under each blade parameter classification is averaged or weighted summed to obtain the SHAP value corresponding to each blade parameter classification.
[0081] Each blade parameter classification has a corresponding SHAP value threshold range. If the SHAP value corresponding to a blade parameter classification exceeds the corresponding SHAP value threshold range, it is determined that the weight coefficient of the blade parameter classification is abnormal.
[0082] If the weight coefficient of any blade parameter classification in the plurality of blade parameter classifications is abnormal, the weight coefficient of the blade parameter classification is modified, and the optimal solution of each design parameter is re-determined according to the modified weight coefficient.
[0083] After calculating the SHAP value of the optimal solution of each design parameter, it can be determined whether the weight coefficient of each blade parameter classification is abnormal. If the weight coefficient of any blade parameter classification in the plurality of blade parameter classifications is abnormal, it indicates that the weight coefficient of the blade parameter classification is not appropriate. Therefore, the weight coefficient of the blade parameter classification can be modified, and the optimal solution of each design parameter can be re-determined automatically according to the modified weight coefficient to ensure the accuracy of each design parameter.
[0084] In some embodiments, determining whether the weight coefficient of each of the plurality of blade parameter categories is abnormal according to the SHAP value of the optimal solution of each design parameter comprises:
[0085] calculating the SHAP value of each of the plurality of blade parameter categories according to the SHAP value of the optimal solution of each design parameter;
[0086] if the SHAP value of any of the plurality of blade parameter categories is lower than the lowest SHAP threshold value or higher than the highest SHAP threshold value, determining that the weight coefficient of the any of the plurality of blade parameter categories is abnormal;
[0087] if the weight coefficient of any of the plurality of blade parameter categories is abnormal, modifying the weight coefficient of the any of the plurality of blade parameter categories comprises:
[0088] if the SHAP value of the any of the plurality of blade parameter categories is lower than the lowest SHAP threshold value, modifying the weight coefficient of the any of the plurality of blade parameter categories to the corresponding lowest weight coefficient;
[0089] if the SHAP value of the any of the plurality of blade parameter categories is higher than the highest SHAP threshold value, modifying the weight coefficient of the any of the plurality of blade parameter categories to the corresponding highest weight coefficient.
[0090] The SHAP value is proportional to the weight coefficient. After the SHAP value of each of the plurality of blade parameter categories is calculated, if the SHAP value of the any of the plurality of blade parameter categories is lower than the lowest SHAP threshold value or higher than the highest SHAP threshold value, it is determined that the weight coefficient of the any of the plurality of blade parameter categories is abnormal. Specifically, if the SHAP value of the any of the plurality of blade parameter categories is lower than the lowest SHAP threshold value, it indicates that the weight coefficient of the any of the plurality of blade parameter categories is lower than the corresponding lowest weight coefficient, and thus the weight coefficient of the any of the plurality of blade parameter categories can be forcibly modified to the corresponding lowest weight coefficient. If the SHAP value of the any of the plurality of blade parameter categories is higher than the highest SHAP threshold value, it indicates that the weight coefficient of the any of the plurality of blade parameter categories is higher than the corresponding highest weight coefficient, and thus the weight coefficient of the any of the plurality of blade parameter categories can be forcibly modified to the corresponding highest weight coefficient, thereby avoiding that the weight coefficient of the blade parameter category is too low or too high.
[0091] In some embodiments, the method further comprises:
[0092] determining a performance parameter of the blade expected to be optimized;
[0093] The performance parameter of the blade expected to be optimized can be a Cp value, a blade cost, a blade load, etc.
[0094] According to the performance parameter expected to be optimized by the blade, the weight coefficient of each of the plurality of blade parameter categories is adjusted;
[0095] For example, the expected power generation efficiency improvement can increase the weight of the corresponding aerodynamic design category by 0.1, and the expected material cost reduction can reduce the weight of the corresponding material design category by 0.2.
[0096] According to the adjusted weight coefficient, the optimal solution of each design parameter is determined again.
[0097] By determining the performance parameter expected to be optimized by the blade, the weight coefficient of each of the plurality of blade parameter categories can be automatically adjusted according to the performance parameter expected to be optimized by the blade, and then the optimal solution of each design parameter is automatically determined again according to the adjusted weight coefficient, to ensure the accuracy of each design parameter.
[0098] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the disclosure is not limited by the order of the described actions, because according to the disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the disclosure.
[0099] The above is the introduction of the method embodiment, and the scheme of the disclosure will be further described through the device embodiment.
[0100] Figure 2 A block diagram of a fan blade design parameter determination device 200 according to an embodiment of the disclosure is shown. As shown in Figure 2 The device 200 includes:
[0101] The acquisition module 210 is configured to acquire the target performance parameter of the blade.
[0102] The first determination module 220 is configured to input the target performance parameter of the blade into a target deep learning model, and determine the weight coefficient of each of the plurality of blade parameter categories corresponding to the target performance parameter.
[0103] The second determination module 230 is configured to determine the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each of the plurality of blade parameter categories corresponding to the target performance parameter.
[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, and will not be described here.
[0105] According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium having computer instructions stored therein.
[0106] Figure 3 A schematic block diagram of an electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.
[0107] The device 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0108] Various components in the device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc., an output unit 807, such as various types of displays, speakers, etc., a storage unit 808, such as a magnetic disk, an optical disk, etc., and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.
[0109] The computing unit 801 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs various methods and processes described above, such as the method 100. For example, in some embodiments, the method 100 can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded onto the RAM 803 and executed by the computing unit 801, one or more steps of the method 100 described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the method 100 by any other suitable means, such as by means of firmware.
[0110] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.
[0111] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.
[0112] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0113] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.
[0114] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.
[0115] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0116] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology described in the present disclosure are achieved.
[0117] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method of determining design parameters of a wind turbine blade, characterized by, The method comprises the following steps: obtaining a target performance parameter of the blade; inputting the target performance parameter of the blade into a target deep learning model to determine the weight coefficients of each blade parameter category corresponding to the target performance parameter; determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficients of each blade parameter category corresponding to the target performance parameter.
2. The method of claim 1, wherein, The target performance parameter comprises a plurality of parameters, and before the target performance parameter of the blade is input into the target deep learning model, the method further comprises: standardizing the plurality of parameters; normalizing the plurality of parameters after standardization.
3. The method of claim 1, wherein the determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficients of each blade parameter category corresponding to the target performance parameter comprises: initializing each design parameter of the blade under each blade parameter category according to the weight coefficients of each blade parameter category corresponding to the target performance parameter and a second-generation genetic algorithm to obtain a plurality of initialization values of the design parameters; selecting the optimal solution of each design parameter from the plurality of initialization values of the design parameters.
4. The method of claim 1, wherein the determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficients of each blade parameter category corresponding to the target performance parameter comprises: obtaining a weight coefficient threshold of each blade parameter category; determining whether the weight coefficients of each blade parameter category corresponding to the target performance parameter are greater than the minimum weight coefficient of each blade parameter category; determining the blade parameter category whose weight coefficient is greater than the minimum weight coefficient from the plurality of blade parameter categories corresponding to the target performance parameter; determining the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of the blade parameter category whose weight coefficient is greater than the minimum weight coefficient. The method further comprises: calculating the SHAP value of the optimal solution of each design parameter; 5. The method of claim 1, wherein, determining whether the weight coefficients of each blade parameter category are abnormal according to the SHAP value of the optimal solution of each design parameter; if the weight coefficient of any blade parameter category is abnormal, modifying the weight coefficient of the blade parameter category and determining the optimal solution of each design parameter according to the modified weight coefficient.
6. The method of claim 5, wherein the determining whether the weight coefficients of each blade parameter category are abnormal according to the SHAP value of the optimal solution of each design parameter comprises: calculating the SHAP value of each blade parameter category according to the SHAP value of the optimal solution of each design parameter; if the SHAP value of any blade parameter category is lower than a minimum SHAP threshold or higher than a maximum SHAP threshold, confirming that the weight coefficient of the blade parameter category is abnormal. If the weight coefficient of any blade parameter category in the plurality of blade parameter categories is abnormal, the weight coefficient of the any blade parameter category is modified, including: If the SHAP value of any blade parameter category in the plurality of blade parameter categories is lower than the lowest SHAP threshold, the weight coefficient of the any blade parameter category is modified to the corresponding lowest weight coefficient; If the SHAP value of the any blade parameter category is higher than the highest SHAP threshold, the weight coefficient of the any blade parameter category is modified to the corresponding highest weight coefficient.
7. The method of any one of claims 1 to 6, wherein, The method further includes: determining the performance parameter that the blade is expected to optimize; adjusting the weight coefficient of each blade parameter category in the plurality of blade parameter categories according to the performance parameter that the blade is expected to optimize; re-determining the optimal solution of each design parameter according to the adjusted weight coefficient.
8. An apparatus for determining design parameters of a wind turbine blade, characterized by It includes: an acquisition module configured to acquire the target performance parameter of the blade; a first determination module configured to input the target performance parameter of the blade into a target deep learning model and determine the weight coefficient of each blade parameter category in the plurality of blade parameter categories corresponding to the target performance parameter; a second determination module configured to determine the optimal solution of each design parameter of the blade under each blade parameter category according to the weight coefficient of each blade parameter category in the plurality of blade parameter categories corresponding to the target performance parameter.
9. An electronic device, comprising: It includes: a memory and a processor, the memory stores a computer program, and the processor implements the method of any one of claims 1-7 when executing the program.
10. A computer readable storage medium, characterized in that, when the instructions in the storage medium are executed by the processor corresponding to the electronic device, the electronic device can implement the determination method of the fan blade design parameter as claimed in any one of claims 1-7.