Wind power large parts slicing drawing method and system based on digital twin

Abstract

The present application provides a method and system for slicing and drawing large wind power parts based on digital twins, which relates to the field of parts maintenance technology. The method includes: collecting wind speed detection values ​​and wind direction monitoring values ​​through wind turbine sensors, then optimizing large parts of the wind turbine, and then obtaining monitoring direction and position information, outputting the digital twin model according to the optimization information, obtaining the expected PDF drawing, and then collecting images of the unit to obtain the PDF drawing of the parts, and sending the expected image and the part drawing to the user end. The present application mainly solves the problem that the existing technology has high cost, poor objectivity of monitoring results, and cannot monitor and predict the performance of large parts in real time with high efficiency. Through the digital twin model, the large parts of the wind turbine are sliced ​​and drawn, and their internal information is obtained, and then performance evaluation and fault prediction are performed. Improve the equipment operation efficiency and reduce maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of parts maintenance, and in particular to a method and system for slicing and drawing large wind power parts based on digital twins. Background Art

[0002] With the continuous development and popularization of wind power technology, wind power has become an important pillar in the field of renewable energy. However, the maintenance and overhaul of wind power equipment has always been a difficult problem, especially for large parts in large wind turbines, such as blades and gearboxes. Therefore, using digital twin models to monitor and predict the performance of large parts of wind turbines in real time is of great significance for improving equipment operation efficiency and reducing maintenance costs.

[0003] The existing technology is to maintain and detect the operating efficiency of the equipment by having experts perform periodic observations of wind turbines at different locations.

[0004] The existing technology has the problems of high cost, poor objectivity of monitoring results, and inability to efficiently monitor and predict the performance of large parts in real time. Summary of the invention

[0005] The present application mainly solves the problems that the prior art has high cost, poor objectivity of monitoring results, and cannot efficiently monitor and predict the performance of large parts in real time.

[0006] In view of the above problems, the present application provides a method and system for slicing and drawing large wind power parts based on digital twins. In the first aspect, the embodiment of the present application provides a method for slicing and drawing large wind power parts based on digital twins, and the method includes: collecting wind speed monitoring values ​​and wind direction monitoring values ​​through wind turbine sensors. According to the wind speed monitoring values ​​and the wind direction monitoring values, the operation of large parts of the wind turbine is optimized to generate the expected operation state of the parts. Based on the user-side display interface, the monitoring direction information and the monitoring position information are obtained. According to the expected operation state of the parts, the digital twin model of the wind turbine is initialized, and the digital twin model of the wind turbine is sliced ​​and drawn based on the monitoring direction information and the monitoring position information to generate the expected PDF output of the parts. Based on the monitoring direction information and the monitoring position information, the wind turbine is subjected to physical image acquisition to generate a part monitoring PDF output. The expected PDF output of the parts and the monitoring PDF output of the parts are sent to the user-side display interface for display.

[0007] In the second aspect, the present application provides a wind power large parts slicing and drawing system based on digital twins, the system comprising: a monitoring value acquisition module, the monitoring value acquisition module is used to collect wind speed monitoring values ​​and wind direction monitoring values ​​through wind turbine sensors. A part expected operating state generation module, the part expected operating state generation module is used to optimize the operation of large parts of wind turbines according to the wind speed monitoring values ​​and the wind direction monitoring values, and generate the expected operating state of the parts. A direction and position information monitoring module, the direction and position information monitoring module is based on the user-side display interface, to obtain monitoring direction information and monitoring position information. A part expected PDF drawing generation module, the part expected PDF drawing generation module is used to initialize the digital twin model of the wind turbine according to the expected operating state of the part, and slice and draw the digital twin model of the wind turbine based on the monitoring direction information and the monitoring position information, and generate the expected PDF drawing of the part. A part monitoring PDF drawing generation module, the part monitoring PDF drawing generation module performs entity image acquisition of the wind turbine based on the monitoring direction information and the monitoring position information, and generates a part monitoring PDF drawing. The output sending module sends the expected PDF output of the part and the monitored PDF output of the part to the user-side display interface for display.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The present application provides a method and system for slicing and drawing large wind power parts based on digital twins, which relates to the field of parts maintenance technology. The method includes: collecting wind speed detection values ​​and wind direction monitoring values ​​through wind turbine sensors, then optimizing large parts of the wind turbine, and then obtaining monitoring direction and position information, setting the digital twin model for output according to the optimization information, obtaining the expected PDF drawing, then collecting images of the unit, obtaining the PDF drawing of the parts, and sending the expected image and the part drawing to the user end.

[0010] This application mainly solves the problem that the existing technology has high cost, poor objectivity of monitoring results, and cannot monitor and predict the performance of large parts in real time efficiently. Through the digital twin model, large parts of wind turbines are sliced ​​and mapped to obtain their internal information, and then performance evaluation and fault prediction are carried out. The equipment operation efficiency is improved and the maintenance cost is reduced.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present disclosure or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A schematic flow chart of a method for slicing and drawing large wind power parts based on digital twins is provided for the embodiment of the present application;

[0014] Figure 2 A schematic flow chart of a method for generating operation record data of large parts of a wind turbine generator set in a method for slicing and drawing large parts of a wind turbine generator set based on digital twins is provided for an embodiment of the present application;

[0015] Figure 3 A schematic flow chart of a method for generating expected PDF drawings of parts in a method for slicing and drawing large wind power parts based on digital twins is provided for an embodiment of the present application;

[0016] Figure 4 A structural schematic diagram of a wind power large parts slicing and drawing system based on digital twin is provided for an embodiment of the present application.

[0017] Explanation of the accompanying drawings: monitoring value acquisition module 10, part expected operating state generation module 20, direction and position information monitoring module 30, part expected PDF output generation module 40, part monitoring PDF output generation module 50, output sending module 60. DETAILED DESCRIPTION

[0018] This application mainly solves the problem that the existing technology has high cost, poor objectivity of monitoring results, and cannot monitor and predict the performance of large parts in real time efficiently. Through the digital twin model, large parts of wind turbines are sliced ​​and mapped to obtain their internal information, and then performance evaluation and fault prediction are carried out. The equipment operation efficiency is improved and the maintenance cost is reduced.

[0019] In order to better understand the above technical solution, the above solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification: Example 1

[0020] like Figure 1 The method for slicing and drawing large wind power parts based on digital twins is shown, and the method includes:

[0021] Collect wind speed monitoring values ​​and wind direction monitoring values ​​through wind turbine sensors;

[0022] Specifically, the wind turbine includes a wind speed sensor and a wind direction sensor. The method of collecting wind speed monitoring values ​​and wind direction monitoring values ​​is to use a wind speed sensor and a wind direction sensor. Wind speed sensor: A wind speed sensor is usually installed on the top of the nacelle of the wind turbine to capture and measure wind speed. These sensors usually measure wind speed in real time and transmit the data to the data acquisition system of the wind turbine. Wind direction sensor: A wind direction sensor is used to measure wind direction and is usually also installed on the top of the nacelle. These sensors determine the wind direction by capturing the deviation of the wind. When wind blows through a device, it generates a thrust, the magnitude and direction of which is related to the direction and speed of the wind. By measuring this thrust, the direction of the wind can be determined. In this way, the monitoring value is obtained.

[0023] According to the wind speed monitoring value and the wind direction monitoring value, the operation of the large parts of the wind turbine generator set is optimized to generate the expected operation state of the parts;

[0024] Specifically, according to the wind speed monitoring value and the wind direction monitoring value, the operation of the large parts of the wind turbine can be optimized to generate the expected operating state of the parts. The wind energy distribution is calculated using the wind speed monitoring value and the wind direction monitoring value, and the wind energy distribution can be expressed by wind energy density or wind energy flow density. According to the wind energy distribution, the large parts of the wind turbine are optimized to operate under the best wind energy conditions. For example, the shape and structure of the wind rotor blades are optimized to improve their performance under the best wind energy conditions. According to the results of the optimized design, the expected operating state of the parts is generated. This includes determining the best operating parameters, such as the best speed, the best power output, etc. The wind turbine is controlled and adjusted according to the expected operating state of the parts so that it operates according to the best operating state. For example, the wind turbine can always be in the best operating state by controlling the angle of the wind rotor blades and the yaw control system.

[0025] Based on the user terminal display interface, obtain monitoring direction information and monitoring location information;

[0026] Specifically, based on the user-side display interface, monitoring direction information and monitoring location information can be obtained. User-side display interface: The user-side display interface is an interactive interface for displaying monitoring data of wind turbines. The operating status, sensor data and other information of the wind turbine can be displayed to the user through the interface, so that the user can intuitively understand the operation of the wind turbine. Monitoring direction information: The monitoring direction information can be obtained through a wind direction sensor. A wind direction sensor is a device for measuring wind direction, which can monitor and output the current wind direction data in real time. In the user-side display interface, a wind rose diagram can be drawn to visually display the distribution of the current wind direction. At the same time, the wind direction information can also be combined with other sensor data, such as wind speed sensor data, to determine the situation of wind energy resources. Monitoring location information: The monitoring location information can be obtained through positioning technologies such as GPS. A GPS receiver is installed on the wind turbine and connected to the control system, so that the location information of the wind turbine can be transmitted to the user-side display interface in real time. In the interface, you can draw a Geographic Information System (GIS) of a wind farm, mark the location of each wind turbine on the map, and combine other sensor data, such as temperature sensors and vibration sensors, to evaluate the performance and maintenance management of wind power equipment. Based on the user-side display interface, you can intuitively display the monitoring data of wind turbines, including monitoring direction information and monitoring location information.

[0027] Initializing the digital twin model of the wind turbine generator set according to the expected operating state of the part, and slicing and plotting the digital twin model of the wind turbine generator set based on the monitoring direction information and the monitoring position information to generate an expected PDF plot of the part;

[0028] Specifically, according to the expected operating state of the part, the digital twin model of the wind turbine can be initialized, and the digital twin model of the wind turbine can be sliced ​​and plotted based on the monitoring direction information and the monitoring position information to generate the expected PDF plot of the part. Initialization of the digital twin model of the wind turbine: The digital twin model is a digital representation based on a physical model that can simulate the operating state and behavior of the actual equipment. According to the expected operating state of the part, initial parameters and conditions such as the shape, angle, and rotation speed of the wind rotor blade can be set in the digital twin model. Slicing plot based on monitoring direction information and monitoring position information: In the digital twin model, the model can be sliced ​​and processed in combination with the monitoring direction information and the monitoring position information, and cut into multiple slices. These slices can represent, for example, the operating conditions under different wind directions and wind speeds. Generate the expected PDF plot of the part: After slicing the digital twin model, the corresponding PDF plot can be generated. These plots can represent the performance and stress conditions of the parts under different operating conditions, such as the force distribution diagram of the wind rotor blade under different wind directions and wind speeds. Users can simulate and analyze the operating status of large parts of wind turbines in the digital twin model, predict their performance and stress conditions, etc., to provide support for equipment optimization design, operation control and maintenance management. It can be used for comparison with actual parts.

[0029] Based on the monitoring direction information and the monitoring position information, a physical image of the wind turbine is collected to generate a PDF output of the parts monitoring;

[0030] Specifically, based on the monitoring direction information and the monitoring position information, the wind turbine can be subjected to physical image acquisition to generate a part monitoring PDF output. Physical image acquisition: Physical image acquisition is the process of photographing and recording objects through high-precision cameras and sensors. Installing high-precision cameras and sensors on the wind turbine and connecting them to the control system can perform physical image acquisition on the operating status of the wind turbine under different wind directions and wind speeds. Physical image acquisition: First, install high-precision cameras and sensors on the wind turbine and connect them to the control system to perform physical image acquisition on the operating status of the wind turbine under different wind directions and wind speeds. Processing image data: Processing and analyzing the data collected by the physical image, including image preprocessing, feature extraction, and data encoding. These processing processes can convert the physical image data into an analyzable data format and save it as a digital file. Generate PDF output: Use drawing software, such as Adobe Acrobat or a similar tool, to open the digital file obtained in the previous step. Then, draw the operating status diagram of the parts of the wind turbine under different wind directions and wind speeds as needed. These images may include the rotation speed, force distribution, vibration conditions, etc. of the wind rotor blades. Through this method, users can comprehensively observe and analyze wind turbines through physical image acquisition, and understand their operating status and performance under different wind directions and wind speeds. At the same time, the generated parts monitoring PDF output can be easily exported and shared, providing convenience for other personnel to understand and analyze the operation of wind turbines.

[0031] The expected PDF output of the part and the monitored PDF output of the part are sent to the user-side display interface for display.

[0032] Specifically, the expected PDF output of the part and the monitored PDF output of the part are sent to the user-side display interface for display. Data transmission: The generated expected PDF output of the part and the monitored PDF output of the part are saved in a server or a data center, and then sent to the device where the user-side display interface is located through a data transmission network. Display interface parsing: The user-side display interface is opened on the device, and the PDF output data from the server or the data center is received and parsed. This process can be implemented through a front-end development framework and a back-end API interface. Display PDF output: The parsed PDF output data is rendered and displayed on the user-side display interface. These outputs can be displayed on the interface in the form of charts, curves, animations, etc., and users can observe and analyze the operating status and performance of large parts of the wind turbine through the interface. Based on the expected output, the deviation of the entity is analyzed, and when it is abnormal, it is repaired on site. Sending the PDF output to the user-side display interface for display requires ensuring the security and reliability of the data. Therefore, in actual operation, necessary data encryption, identity authentication and other measures are required to ensure that the data is not leaked or tampered with.

[0033] Furthermore, the method of the present application optimizes the operation of large parts of the wind turbine generator set according to the wind speed monitoring value and the wind direction monitoring value to generate the expected operation state of the parts, including:

[0034] Based on the wind speed monitoring value and the wind direction monitoring value, collecting operation record data of large parts of the wind turbine set from the wind turbine set operation big data;

[0035] Extracting the ith operation record data of the large parts operation record data of the wind turbine generator set, wherein the ith operation record data includes the ith operation state record value, the ith wind turbine generator set power generation record value and the ith fault frequency record value;

[0036] Counting the proportion of the recorded power generation value of the i-th wind turbine group in the sum of the recorded power generation values, and setting it as a first optimization index;

[0037] Counting the proportion of the i-th fault frequency record value in the sum of the fault frequency record values, and setting it as a second optimization index;

[0038] Weighting the first optimization index with a first preset weight, weighting the inverse of the second optimization index with a second preset weight, adding them together, and generating a quality coefficient of the i-th running state record value;

[0039] The i-th running state record value quality coefficient is added into the running state record value quality coefficient set, and the running state record value quality coefficient set is sorted for maximum value to generate the expected running state of the part.

[0040] Specifically, the operation record data of the large parts of the wind turbine are collected: these data include the status of each operation, power generation, fault frequency, etc. These data are recorded and collected in real time during the operation of the wind turbine. Extract the i-th operation record data: select the i-th operation record data from the collected operation record data. The i-th operation record data includes the i-th operation status record value, the i-th wind turbine power generation record value and the i-th fault frequency record value. Count the proportion of the i-th wind turbine power generation record value in the sum of the power generation record values: this step is to obtain the proportion of power generation in the total power generation. Count the proportion of the i-th fault frequency record value in the sum of the fault frequency record values: this step is to obtain the proportion of the fault frequency in the total fault frequency. Weight the first optimization index and the second optimization index with preset weights: the preset weights are set according to the actual situation, for example, the first preset weight may represent the importance of power generation, and the second preset weight may represent the importance of fault frequency. Generate the i-th operation status record value quality coefficient: add the reciprocals of the weighted first optimization index and the second optimization index to obtain the quality coefficient of the i-th operation status record value. Add the i-th running state record value quality coefficient to the running state record value quality coefficient set: add the state record value quality coefficient of each operation to this set. Perform maximum value sorting on the running state record value quality coefficient set: select the maximum value from the set, and this maximum value is the expected running state. This method can help us better understand the operation of wind turbines, predict future operating states, and optimize the operating states of large parts.

[0041] Furthermore, the method of the present application collects operation record data of large parts of the wind turbine generator set from the wind turbine generator set operation big data based on the wind speed monitoring value and the wind direction monitoring value, including:

[0042] Collecting initial operation record data from the wind turbine operation big data according to the wind speed monitoring value and the wind direction monitoring value;

[0043] Obtaining a first operation status record value of a first initial operation record data of the initial operation record data;

[0044] Obtain a second operation status record value of second initial operation record data of the initial operation record data;

[0045] Traverse the running status indicators and set the running status indicator consistency deviation threshold;

[0046] When the first operation status record value and the second operation status record value meet the operation status indicator consistency deviation threshold, the first initial operation record data and the second initial operation record data are aggregated into one group;

[0047] Repeatedly clustering the initial operation record data to generate multiple groups of initial operation record data;

[0048] The plurality of groups of initial operation record data are traversed to perform characteristic value fitting to generate the operation record data of the large parts of the wind turbine generator set.

[0049] Specifically, collect initial operation record data: collect initial operation record data in the wind turbine operation big data according to the wind speed monitoring value and the wind direction monitoring value. Including the state of each operation, power generation, fault frequency, etc. Obtain the first operation state record value of the first initial operation record data: select the first operation record data from the collected initial operation record data, and obtain its operation state record value. Obtain the second operation state record value of the second initial operation record data: select the second operation record data, and obtain its operation state record value. Traverse the operation state indicators and set the consistent deviation threshold: these operation state indicators can be power generation, fault frequency, etc. Set the consistent deviation threshold of each indicator, which represents the maximum deviation allowed for the operation state record value on this indicator. Determine whether the first operation state record value and the second operation state record value meet the consistent deviation threshold: compare the consistency of the first operation state record value and the second operation state record value on each operation state indicator. If the consistent deviation threshold is met, it means that the two groups of data can be clustered into one category. Cluster the first initial operation record data and the second initial operation record data into one group: If the first operation status record value and the second operation status record value meet the consistent deviation threshold, cluster the two groups of data into one group as a group of initial operation record data. Repeat the clustering of the initial operation record data to generate multiple groups of initial operation record data: Repeat the above steps to cluster each new group of initial operation record data until all the initial operation record data are clustered to generate multiple groups of initial operation record data. Traverse multiple groups of initial operation record data to perform feature value fitting to generate large parts operation record data of wind turbines: Perform feature extraction and fitting on each group of initial operation record data to generate large parts operation record data of wind turbines for each group. Clustering these data together will obtain complete large parts operation record data of wind turbines.

[0050] Furthermore, if Figure 2 As shown, the method of the present application traverses the multiple groups of initial operation record data to perform characteristic value fitting to generate the operation record data of the large parts of the wind turbine generator set, including:

[0051] Extracting a plurality of operation status record values, a plurality of wind turbine generator set power generation record values ​​and a plurality of fault frequency record values ​​of a first group of initial operation record data of the plurality of groups of initial operation record data;

[0052] Performing centralized value evaluation on the power generation record values ​​of the plurality of wind turbines to generate a wind turbine power generation characteristic value;

[0053] Performing centralized value evaluation on the plurality of fault frequency record values ​​to generate a fault frequency characteristic value;

[0054] The plurality of operation status record values ​​are identified by using the wind turbine generator set power generation characteristic value and the fault frequency characteristic value, and the operation record data of the major parts of the wind turbine generator set are generated.

[0055] Specifically, extract multiple operating status record values, multiple wind turbine power generation record values, and multiple fault frequency record values ​​of the first group of initial operating record data: select the first group of initial operating record data from the multiple initial operating record data generated previously, and extract its operating status record values, wind turbine power generation record values, and fault frequency record values. Perform centralized value evaluation on multiple wind turbine power generation record values: obtain the characteristic value of wind turbine power generation by calculating the average value, median, standard deviation, and other statistics of these power generation record values. Perform centralized value evaluation on multiple fault frequency record values: obtain the characteristic value of fault frequency by calculating the average value, median, standard deviation, and other statistics of these fault frequency record values. Identify multiple operating status record values ​​by wind turbine power generation characteristic value and fault frequency characteristic value: classify and identify each operating status record value according to the wind turbine power generation characteristic value and fault frequency characteristic value. Generate wind turbine large parts operating record data: merge the identified operating status record value with other data extracted previously to generate the operating record data of wind turbine large parts.

[0056] This approach can help us better understand the operation of wind turbines, predict future operating conditions, and optimize the operating conditions of large components.

[0057] Furthermore, the method of the present application initializes the digital twin model of the wind turbine according to the expected operating state of the part, slices and plots the digital twin model of the wind turbine based on the monitoring direction information and the monitoring position information, and generates an expected PDF plot of the part, including:

[0058] When the wind turbine digital twin model generates an initialization completion signal, a first slice section, a second slice section and a first viewing angle section are constructed based on the monitoring direction information and the monitoring position information, wherein the first slice section coincides with the direction of the monitoring direction information through the monitoring position information, the second slice section coincides with the direction of the monitoring direction information through the monitoring position information, the first slice section and the second slice section are perpendicular to each other, and the first viewing angle section is perpendicular to the direction of the monitoring direction information through the monitoring position information;

[0059] Extending the first slice section and the second slice section along the monitoring direction information, slicing the digital twin model of the wind turbine generator set, and obtaining a first expected PDF drawing of a part and a second expected PDF drawing of a part;

[0060] Capturing images of the wind turbine digital twin model at a preset viewing angle through the first viewing angle section to generate a third expected PDF output of the parts;

[0061] The first expected PDF drawing of the part, the second expected PDF drawing of the part and the third expected PDF drawing of the part are added to the expected PDF drawing of the part.

[0062] Specifically, when the digital twin model of the wind turbine generates an initialization completion signal, based on the monitoring direction information and the monitoring position information, a first slice section, a second slice section and a first viewing angle section are constructed, wherein the first slice section coincides with the direction of the monitoring direction information through the monitoring position information, the second slice section coincides with the direction of the monitoring direction information through the monitoring position information, the first slice section and the second slice section are perpendicular to each other, and the first viewing angle section is perpendicular to the direction of the monitoring position information and the monitoring direction information. Three directions, one is a slice diagram directly seen from the monitoring position. The other two are diagrams obtained by cutting the parts along the viewing angle direction. Select a slice position: Select the slice position of the digital twin model as needed, and determine the appropriate position through the monitoring direction information and the monitoring position information. For example, a position perpendicular to the monitoring direction information can be selected for slicing. Construct a slice section: According to the selected slice position, construct a section that intersects with the digital twin model as a slice section. The construction of this section can be completed by determining its intersection with the monitoring position information and the monitoring direction information and its intersection with the digital twin model. Slice the digital twin model: slice the slice section along the contour of the digital twin model to obtain slice data representing the first expected PDF output of the part and the second expected PDF output of the part. Determine the preset perspective: determine the preset perspective based on the monitoring direction information and the monitoring position information, and observe from the front, side, top and other angles. Construct the first perspective section: construct a section perpendicular to the preset perspective based on the monitoring direction information and the monitoring position information as the first perspective section. The construction of this section can be completed by determining its intersection with the monitoring position information and the monitoring direction information and its intersection with the digital twin model. Slice the digital twin model of the wind turbine: slice the first perspective section along the contour of the digital twin model to obtain slice data representing the first expected PDF output of the part. Collect image data: collect images of the digital twin model of the wind turbine through the first perspective section to obtain image data representing the third expected PDF output of the part. These image data can be collected through the intersection of the section and the digital twin model, and can be further processed and optimized as needed. Initialize the expected PDF output of the part: Before you start adding, you first need to initialize an empty PDF document as the expected PDF output of the part. This document can be blank, or it can contain some necessary information, such as title, summary, header and footer, etc. Add the first expected PDF output to the PDF output: Add the generated first expected PDF output of the part to the expected PDF output of the part. This can be done by inserting the first expected PDF output into the appropriate position of the PDF document. For example, you can add the first expected PDF output at the beginning or end of the document, or add it to a specific chapter or page.Add the second expected PDF plot to the PDF plot: A similar method is used to add the second expected PDF plot of the part to the expected PDF plot of the part. It can be added to the same or different position as the first expected PDF plot as needed. Add the third expected PDF plot to the PDF plot: A similar method is used to add the third expected PDF plot of the part to the expected PDF plot of the part. This can be added to the same or different position as the first expected PDF plot and the second expected PDF plot as needed. In this way, the generated first expected PDF plot of the part, the second expected PDF plot of the part, and the third expected PDF plot of the part can be added to the expected PDF plot of the part to generate the final expected PDF plot of the part.

[0063] Furthermore, the method of the present application extends the first slice section and the second slice section along the monitoring direction information, slices the digital twin model of the wind turbine, and obtains a first expected PDF drawing of a part and a second expected PDF drawing of a part, including:

[0064] Determine whether the slice section passes through the large part digital twin model, wherein the slice section is the first slice section or the second slice section;

[0065] When the slice section passes through the digital twin model of the large part, the cross-section drawing parameters of the large part are obtained;

[0066] When the slice section does not pass through the large part digital twin model, obtaining the section viewing angle drawing parameters;

[0067] According to the large part section drawing parameters or the cross-sectional view drawing parameters, the first expected PDF drawing of the part or the second expected PDF drawing of the part is constructed.

[0068] Specifically, it is determined whether the slice section passes through the digital twin model of the wind turbine. This step determines whether the slice section intersects with the digital twin model by analyzing the geometric shape of the digital twin model. If they intersect, it means that the slice section passes through the digital twin model of the large part. Otherwise, it means that the slice section does not pass through. If the slice section passes through the digital twin model of the large part, the cross-sectional drawing parameters of the large part can be obtained. These parameters are obtained by analyzing the intersection line, intersection point and other information of the slice section and the digital twin model, such as the position, length, angle and the size and shape of the intersection point. If the slice section does not pass through the digital twin model of the wind turbine, the cross-sectional view drawing parameters can be obtained. These parameters are determined by analyzing the relationship between the slice section and the digital twin model, such as the closest distance and relative angle between the slice section and the digital twin model. According to the obtained cross-sectional drawing parameters of the large part or the cross-sectional view drawing parameters, the expected PDF drawing can be constructed. This step is completed by drawing software or algorithms, and these parameters are used to generate corresponding PDF drawings, including the first expected PDF drawing of the part or the second expected PDF drawing of the part.

[0069] Furthermore, if Figure 3 As shown, the method of the present application adds the first expected PDF output of the part, the second expected PDF output of the part and the third expected PDF output of the part into the expected PDF output of the part, and further includes:

[0070] Get the non-visual status indicator type;

[0071] Based on the digital twin model of the wind turbine generator set, assigning a value to the non-visualization status indicator type, generating a non-visualization status indicator assignment result and a non-visualization status indicator assignment result associated position;

[0072] According to the associated position of the non-visual status indicator assignment result, character identification of the non-visual status indicator assignment result is performed on the first expected PDF drawing of the part, the second expected PDF drawing of the part and the third expected PDF drawing of the part to generate the expected PDF drawing of the part.

[0073] Specifically, obtain non-visual status indicator types: these indicator types are usually not directly observable or presentable visually, and may include performance parameters, health status, temperature, humidity, output power, etc. Assign values ​​to non-visual status indicator types based on the digital twin model of the wind turbine: through the digital twin model, the operation and status of the wind turbine can be simulated, and non-visual status indicator types can be assigned and calculated. The specific assignment method and calculation method depend on the nature and requirements of the non-visual status indicator type, including statistical analysis, data processing, model calculation and other steps. Generate non-visual status indicator assignment results and non-visual status indicator assignment result associated positions: after completing the assignment, the assignment results of the non-visual status indicators can be obtained, and the positions or associated positions of these assignment results in the digital twin model need to be determined. Character identification is performed according to the associated positions of the non-visual status indicator assignment results: according to the associated positions of the non-visual status indicator assignment results, character identification is performed in the first expected PDF output of the part, the second expected PDF output of the part and the third expected PDF output of the part. Character identification can be an intuitive way to display the assignment results of non-visual status indicators in the PDF output, so that users can quickly understand and evaluate the operating status and performance of the wind turbine. Through the above steps, the non-visual status indicator type can be obtained based on the digital twin model of the wind turbine, and the non-visual status indicator assignment results and the associated positions of the non-visual status indicator assignment results can be generated. Finally, character identification is performed on the expected PDF output of the part according to these associated positions to generate the final expected PDF output of the part. Example 2

[0074] Based on the same inventive concept as the method for slicing and drawing large wind power parts based on digital twins in the aforementioned embodiment, Figure 4 As shown, the present application provides a wind power large parts slicing and drawing system based on digital twins, the system comprising:

[0075] A monitoring value acquisition module 10, wherein the monitoring value acquisition module 10 is used to acquire wind speed monitoring values ​​and wind direction monitoring values ​​through wind turbine sensors;

[0076] A component expected operating state generating module 20, wherein the component expected operating state generating module 20 is used to optimize the operation of large components of the wind turbine generator set according to the wind speed monitoring value and the wind direction monitoring value, and generate the component expected operating state;

[0077] A direction and position information monitoring module 30, wherein the direction and position information monitoring module 30 obtains monitoring direction information and monitoring position information based on a user terminal display interface;

[0078] A part expected PDF drawing generation module 40, wherein the part expected PDF drawing generation module 40 is used to initialize the wind turbine digital twin model according to the expected operating state of the part, and to slice and draw the wind turbine digital twin model based on the monitoring direction information and the monitoring position information to generate the part expected PDF drawing;

[0079] A parts monitoring PDF output generation module 50, wherein the parts monitoring PDF output generation module 50 collects entity images of the wind turbine generator system based on the monitoring direction information and the monitoring position information to generate a parts monitoring PDF output;

[0080] The output sending module 60 sends the expected PDF output of the part and the monitored PDF output of the part to the user-side display interface for display.

[0081] Furthermore, the system also includes:

[0082] The operation record collection module collects the operation record data of the large parts of the wind turbine generator set from the wind turbine generator set operation big data based on the wind speed monitoring value and the wind direction monitoring value;

[0083] The i-th operation record data extraction module is used to extract the i-th operation record data of the large parts operation record data of the wind turbine generator set, wherein the i-th operation record data includes the i-th operation state record value, the i-th wind turbine generator set power generation record value and the i-th fault frequency record value;

[0084] A first optimization index setting module, used for counting the proportion of the power generation record value of the i-th wind turbine group in the sum of the power generation record values, and setting it as a first optimization index;

[0085] A second optimization index setting module, used for counting the proportion of the i-th fault frequency record value in the sum of the fault frequency record values, and setting it as a second optimization index;

[0086] A reciprocal weighting module, used to weight the first optimization index with a first preset weight, and weight the reciprocal of the second optimization index with a second preset weight, and add them together to generate a quality coefficient of the i-th running state record value;

[0087] The expected operating state generating module is used to add the i-th operating state record value quality coefficient into the operating state record value quality coefficient set, perform maximum value sorting on the operating state record value quality coefficient set, and generate the expected operating state of the part.

[0088] Furthermore, the system also includes:

[0089] An initial operation record data collection module is used to collect initial operation record data from the wind turbine operation big data according to the wind speed monitoring value and the wind direction monitoring value;

[0090] A first operation status record value acquisition module, used to obtain a first operation status record value of a first initial operation record data of the initial operation record data;

[0091] A second operation status record value acquisition module, used to obtain a second operation status record value of a second initial operation record data of the initial operation record data;

[0092] Deviation threshold setting module, used to traverse the operation status indicators and set the consistent deviation threshold of the operation status indicators;

[0093] a data aggregation module, configured to aggregate the first initial operation record data and the second initial operation record data into one group when the first operation state record value and the second operation state record value meet the operation state indicator consistency deviation threshold;

[0094] A record data generating module, used for repeatedly clustering the initial operation record data to generate multiple groups of initial operation record data;

[0095] The characteristic value fitting module is used to traverse the multiple groups of initial operation record data to perform characteristic value fitting and generate the operation record data of the large parts of the wind turbine generator set.

[0096] Furthermore, the system also includes:

[0097] A data extraction module, used to extract a plurality of operation status record values, a plurality of wind turbine generator set power generation record values ​​and a plurality of fault frequency record values ​​of a first group of initial operation record data of the plurality of groups of initial operation record data;

[0098] A wind turbine generator set power generation characteristic value generation module, used for performing centralized value evaluation on the power generation record values ​​of the plurality of wind turbine generator sets to generate a wind turbine generator set power generation characteristic value;

[0099] A fault frequency characteristic value generating module, used for performing centralized value evaluation on the plurality of fault frequency record values ​​to generate a fault frequency characteristic value;

[0100] The record value identification module is used to identify the multiple operation status record values ​​through the wind turbine generator set power generation characteristic value and the fault frequency characteristic value, and generate the operation record data of the major parts of the wind turbine generator set.

[0101] Furthermore, the system also includes:

[0102] The first and second expected output acquisition modules are used to construct a first slice section, a second slice section and a first viewing angle section based on the monitoring direction information and the monitoring position information when the digital twin model of the wind turbine generator generates an initialization completion signal, wherein the first slice section coincides with the direction of the monitoring direction information through the monitoring position information, the second slice section coincides with the direction of the monitoring direction information through the monitoring position information, the first slice section and the second slice section are perpendicular to each other, and the first viewing angle section is perpendicular to the direction of the monitoring direction information through the monitoring position information. The first slice section and the second slice section are extended along the monitoring direction information, and the digital twin model of the wind turbine generator is sliced ​​to obtain the first expected PDF output of the part and the second expected PDF output of the part;

[0103] A third expected output image acquisition module is used to collect images of the wind turbine digital twin model at a preset viewing angle through the first viewing angle section to generate a third expected PDF output image of the parts;

[0104] The drawing adding module is used to add the first expected PDF drawing of the part, the second expected PDF drawing of the part and the third expected PDF drawing of the part into the expected PDF drawing of the part.

[0105] Furthermore, the system also includes:

[0106] A judgment module, used to judge whether a slice section passes through the large part digital twin model, wherein the slice section is the first slice section or the second slice section;

[0107] A section drawing parameter acquisition module, used to acquire the section drawing parameters of the large part when the slice section passes through the large part digital twin model;

[0108] A cross-sectional view angle drawing parameter acquisition module, used for acquiring cross-sectional view angle drawing parameters when the slice section does not pass through the large part digital twin model;

[0109] The drawing construction module is used to construct the first expected PDF drawing of the part or the second expected PDF drawing of the part according to the large part section drawing parameters or the cross-sectional view drawing parameters.

[0110] Furthermore, the system also includes:

[0111] A non-visual status indicator type acquisition module is used to obtain the non-visual status indicator type;

[0112] A result association module is used to assign values ​​to the non-visual status indicator types based on the digital twin model of the wind turbine generator set, and to generate non-visual status indicator assignment results and non-visual status indicator assignment result association positions;

[0113] The expected PDF output generation module is used to perform character identification of the non-visual status indicator assignment result on the first expected PDF output of the part, the second expected PDF output of the part and the third expected PDF output of the part according to the associated position of the non-visual status indicator assignment result, and generate the expected PDF output of the part.

[0114] Through the detailed description of the aforementioned wind power large parts slicing and drawing method based on digital twins, technical personnel in this field can clearly understand the wind power large parts slicing and drawing system based on digital twins in this embodiment. For the system disclosed in the embodiment, since it corresponds to the device disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0115] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wind power large parts slicing and drawing method based on digital twins is characterized by: include: Collect wind speed monitoring values ​​and wind direction monitoring values ​​through wind turbine sensors; Optimizing the operation of large parts of the wind turbine generator set according to the wind speed monitoring value and the wind direction monitoring value to generate an expected operating state of the parts; Based on the user terminal display interface, obtain monitoring direction information and monitoring location information; Initializing the digital twin model of the wind turbine generator set according to the expected operating state of the part, and slicing and drawing the digital twin model of the wind turbine generator set based on the monitoring direction information and the monitoring position information to generate an expected PDF drawing of the part; Based on the monitoring direction information and the monitoring position information, a physical image of the wind turbine is collected to generate a PDF output of the parts monitoring; Sending the expected PDF output of the part and the monitored PDF output of the part to the user terminal display interface for display; Based on the wind speed monitoring value and the wind direction monitoring value, the operation of the large parts of the wind turbine is optimized to generate the expected operating state of the parts, including: Based on the wind speed monitoring value and the wind direction monitoring value, collecting operation record data of large parts of the wind turbine generator set from the wind turbine generator set operation big data; Extracting the i-th operation record data of the large parts operation record data of the wind turbine generator set, wherein the i-th operation record data includes the i-th operation state record value, the i-th wind turbine generator set power generation record value and the i-th fault frequency record value; Counting the proportion of the recorded power generation value of the i-th wind turbine in the sum of the recorded power generation values, and setting it as a first optimization index; Counting the proportion of the i-th fault frequency record value in the sum of the fault frequency record values, and setting it as a second optimization index; Weighting the first optimization index with a first preset weight, weighting the inverse of the second optimization index with a second preset weight, adding the two, and generating a quality coefficient of the i-th running state record value; The i-th running state record value quality coefficient is added to the running state record value quality coefficient set, and the running state record value quality coefficient set is sorted for maximum value to generate the expected running state of the part.

2. The method according to claim 1, wherein Based on the wind speed monitoring value and the wind direction monitoring value, the wind turbine generator set large parts operation record data is collected from the wind turbine generator set operation big data, including: Collecting initial operation record data from the wind turbine operation big data based on the wind speed monitoring value and the wind direction monitoring value; Obtain a first operation status record value of a first initial operation record data of the initial operation record data; Obtaining a second operation status record value of second initial operation record data of the initial operation record data; Traverse the running status indicators and set the running status indicator consistency deviation threshold; When the first operating status record value and the second operating status record value meet the operating status indicator consistency deviation threshold, aggregating the first initial operating record data and the second initial operating record data into a group; Repeatedly clustering the initial operation record data to generate multiple groups of initial operation record data; The plurality of groups of initial operation record data are traversed to perform characteristic value fitting to generate operation record data of large parts of the wind turbine generator set.

3. The method according to claim 2, wherein Traversing the multiple groups of initial operation record data to perform characteristic value fitting to generate the operation record data of the large parts of the wind turbine generator, including: Extracting a plurality of operation status record values, a plurality of wind turbine generator set power generation record values ​​and a plurality of fault frequency record values ​​from a first group of initial operation record data of the plurality of groups of initial operation record data; Performing centralized value evaluation on the power generation record values ​​of the plurality of wind turbine generator sets to generate a wind turbine generator power generation characteristic value; Performing centralized value evaluation on the plurality of fault frequency record values ​​to generate a fault frequency characteristic value; The plurality of operation status record values ​​are identified by using the wind turbine generator set power generation characteristic value and the fault frequency characteristic value to generate the operation record data of the major parts of the wind turbine generator set.

4. The method according to claim 1, wherein Initializing the digital twin model of the wind turbine generator set according to the expected operating state of the part, and slicing and drawing the digital twin model of the wind turbine generator set based on the monitoring direction information and the monitoring position information to generate an expected PDF drawing of the part, including: When the digital twin model of the wind turbine generates an initialization completion signal, a first slice section, a second slice section, and a first viewing angle section are constructed based on the monitoring direction information and the monitoring position information, wherein the first slice section coincides with the direction of the monitoring direction information through the monitoring position information, the second slice section coincides with the direction of the monitoring direction information through the monitoring position information, the first slice section and the second slice section are perpendicular to each other, and the first viewing angle section coincides with the direction of the monitoring direction information through the monitoring position information; Extending the first slice section and the second slice section along the monitoring direction information, slicing the digital twin model of the wind turbine generator set, and obtaining a first expected PDF drawing of the part and a second expected PDF drawing of the part; Capturing a preset perspective image of the wind turbine digital twin model through the first perspective section to generate a third expected PDF output of the part; The first expected PDF drawing of the part, the second expected PDF drawing of the part and the third expected PDF drawing of the part are added to the expected PDF drawing of the part.

5. The method according to claim 4, wherein Extending the first slice section and the second slice section along the monitoring direction information, slicing the wind turbine digital twin model, and obtaining a first expected PDF drawing of a part and a second expected PDF drawing of a part, including: Determining whether a slice section passes through the large part digital twin model, wherein the slice section is the first slice section or the second slice section; When the slice section passes through the digital twin model of the large part, the cross-sectional drawing parameters of the large part are obtained; When the slice section does not pass through the large part digital twin model, obtaining the cross-sectional view angle drawing parameters; According to the large part section drawing parameters or the cross-sectional view drawing parameters, the first expected PDF drawing of the part or the second expected PDF drawing of the part is constructed.

6. The method according to claim 4, wherein Adding the first expected PDF drawing of the part, the second expected PDF drawing of the part, and the third expected PDF drawing of the part into the expected PDF drawing of the part further includes: Get the non-visual status indicator type; Based on the digital twin model of the wind turbine generator set, assigning a value to the non-visualization status indicator type, and generating a non-visualization status indicator assignment result and an associated position of the non-visualization status indicator assignment result; According to the associated position of the non-visual status indicator assignment result, the character identification of the non-visual status indicator assignment result is performed on the first expected PDF drawing of the part, the second expected PDF drawing of the part, and the third expected PDF drawing of the part to generate the expected PDF drawing of the part.

7. The wind power large parts slicing and drawing system based on digital twin is characterized by: include: A monitoring value acquisition module, wherein the monitoring value acquisition module is used to collect wind speed monitoring values ​​and wind direction monitoring values ​​through wind turbine sensors; A component expected operating state generation module, the component expected operating state generation module is used to optimize the operation of large components of the wind turbine generator set according to the wind speed monitoring value and the wind direction monitoring value, and generate the component expected operating state; A direction and position information monitoring module, which obtains monitoring direction information and monitoring position information based on a user terminal display interface; A part expected PDF output generation module, wherein the part expected PDF output generation module is used to initialize the wind turbine digital twin model according to the expected operating state of the part, and slice and draw the wind turbine digital twin model based on the monitoring direction information and the monitoring position information to generate the part expected PDF output; A parts monitoring PDF output generation module, wherein the parts monitoring PDF output generation module collects a physical image of the wind turbine based on the monitoring direction information and the monitoring position information, and generates a parts monitoring PDF output; A drawing sending module is used to send the expected PDF drawing of the part and the monitored PDF drawing of the part to the user terminal display interface for display; The module for generating the expected operating state of parts includes: An operation record collection module collects operation record data of large parts of the wind turbine generator set from the wind turbine generator set operation big data based on the wind speed monitoring value and the wind direction monitoring value; An i-th operation record data extraction module is used to extract the i-th operation record data of the large parts operation record data of the wind turbine generator set, wherein the i-th operation record data includes the i-th operation status record value, the i-th wind turbine generator set power generation record value and the i-th fault frequency record value; A first optimization index setting module is used to calculate the proportion of the power generation record value of the i-th wind turbine in the sum of the power generation record values, and set it as a first optimization index; A second optimization index setting module is used to calculate the proportion of the i-th fault frequency record value in the sum of the fault frequency record values ​​and set it as a second optimization index; an inverse weighting module, configured to weight the first optimization index with a first preset weight, and weight the inverse of the second optimization index with a second preset weight, and add the sums to generate a quality coefficient of the i-th operating state record value; The expected operating state generating module is used to add the i-th operating state record value quality coefficient to the operating state record value quality coefficient set, perform maximum value sorting on the operating state record value quality coefficient set, and generate the expected operating state of the part.

Images