Wind power load test data processing method and system for adaptive data compression

Abstract

The present invention discloses a method and system for processing wind power load test data with adaptive data compression, which relates to the field of data processing. The method includes: collecting load test data of a wind turbine using a nested sliding window; respectively performing multi-scale feature extraction on the collected data of the nested sliding window, executing multi-scale feature fusion, and establishing a comprehensive change score for each data point; obtaining the spatial distribution of the acquisition sensors, configuring the sensor adjacency coefficient according to the spatial distribution and sensor functions, performing spatial consistency detection of data points, and locating key frames; synchronizing the key frames to an adaptive compression channel, constructing a data compression strategy, and executing compression management. It solves the technical problems existing in the existing data processing, such as insufficient acquisition flexibility and difficulty in accurately capturing dynamic features, resulting in insufficient compression efficiency and accuracy, and achieves the technical effect of improving the acquisition flexibility, accurately capturing the dynamic change features of data, and further improving the efficiency and accuracy of data compression.

Description

Technical Field

[0001] This application relates to the field of data processing, and particularly to a method and system for processing wind power load test data with adaptive data compression. Background Art

[0002] In the wind power industry, the processing of wind turbine load test data is crucial for ensuring the safety of wind turbines, optimizing operation and maintenance strategies. Traditional data acquisition methods often sample at fixed time intervals or with a fixed amount of data. This method is not flexible enough to handle complex and variable load conditions. In terms of data processing, existing methods usually perform simple statistical analysis or filtering on the collected data, making it difficult to comprehensively capture the dynamic change characteristics of the data. In terms of data compression, most existing methods use fixed compression algorithms and parameters, lacking the ability to adapt to data characteristics. This results in the possible loss of important information during the data compression process, or low compression efficiency, unable to meet the requirements of real-time processing.

[0003] In the related technologies at the present stage, there are technical problems in the processing of wind power load test data, such as insufficient flexibility in data acquisition, difficulty in accurately capturing the dynamic characteristics of data, resulting in insufficient efficiency and accuracy of data compression. Summary of the Invention

[0004] This application provides a method and system for processing wind power load test data with adaptive data compression. By using nested sliding windows to collect data, performing multi-scale feature extraction and fusion on the collected data, establishing a comprehensive change score for each data point, conducting spatial consistency detection based on the sensor adjacency coefficient, locating key frames according to the results of spatial consistency detection and the comprehensive change score, and constructing an adaptive compression strategy and other technical means, it achieves the technical effects of improving the flexibility of data acquisition, accurately capturing the dynamic change characteristics of data, and further improving the efficiency and accuracy of data compression.

[0005] The present application provides a method for processing wind power load test data with adaptive data compression, including: collecting load test data of a wind turbine using a nested sliding window, where the nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window. The load test data includes stress data, vibration data, torque data, and wind speed data; performing multi-scale feature extraction on the collected data of the nested sliding window respectively, and executing multi-scale feature fusion to establish a comprehensive change score for each data point; obtaining the spatial distribution of the acquisition sensors, configuring a sensor adjacency coefficient according to the spatial distribution and sensor functions, performing spatial consistency detection of data points based on the sensor adjacency coefficient, and positioning key frames according to the spatial consistency detection results and the comprehensive change score; synchronizing the key frames to an adaptive compression channel, constructing a data compression strategy, and using the data compression strategy to perform compression management of the load test data.

[0006] In a possible implementation, when configuring the sensor adjacency coefficient according to the spatial distribution and sensor functions, the following processing is performed: calculating the adjacency distance of the sensors based on the spatial distribution, and determining whether the adjacency distance is less than a preset distance threshold; if the adjacency distance is less than the preset distance threshold, generating a first authentication pass result; configuring a function vector according to the sensor functions, calculating the function similarity through the cosine similarity and the function vector, and if the function similarity is higher than a preset function threshold, generating a second authentication pass result; when both the first authentication pass result and the second authentication pass result exist, calculating the sensor adjacency coefficient.

[0007] In a possible implementation, when calculating the sensor adjacency coefficient, the following processing is performed: calculating the sensor adjacency coefficient through the following formula: ; where represents the sensor adjacency coefficient of sensor and sensor , and the value range is [0, 1], represents the adjacency distance between sensor and sensor , represents the spatial attenuation factor, represents the function similarity between sensor and sensor .

[0008] In a possible implementation, after calculating the sensor adjacency coefficient, the following processing is performed: calculating the differential deviation of the sensor data through the formula: ; where represents sensor and sensor at time The data difference degree at characterizes the sensor at time the measured value at characterizes the sensor at time the measured value at; Calculate the consistency score based on the differential deviation and the sensor adjacency coefficient: ; where characterizes at time the consistency score of the sensor at characterizes the set of sensors with the sensor adjacency coefficient with the sensor ; is the data difference sensitivity coefficient.

[0009] In a possible implementation, the method for collecting the load test data of the wind turbine by using the nested sliding window performs the following processing: Configure the default window value of the basic sliding window within the nested sliding window, and call the basic sliding window according to the default window value to perform data pre-collection of the load test data, and establish a pre-collected data set; Perform data stability analysis on the pre-collected data set, and generate reconstruction parameters according to the data stability analysis results, where the reconstruction parameters include the window value of the basic sliding window and the extension value of the extended sliding window; After reconstructing the nested sliding window according to the window value and the extension value, collect the load test data of the wind turbine.

[0010] In a possible implementation, the method for reconstructing the nested sliding window according to the window value and the extension value performs the following processing: Perform data fluctuation analysis on the pre-collected data set, and establish an extension bias according to the data fluctuation analysis results; After reconstructing the basic sliding window with the window value, take the reconstructed basic sliding window as the center, and reconstruct the extended sliding window based on the extension bias and the extension value; After collecting the load test data of the wind turbine by using the reconstructed nested sliding window, obtain the window data set corresponding to the reconstructed extended sliding window; After uniformly dividing the window data set, calculate the fluctuation amplitude under the uniformly divided window; Configure the adaptive sliding step according to the fluctuation amplitude and the sensitivity coefficient.

[0011] In a possible implementation, the method for synchronizing the key frame to the adaptive compression channel and constructing a data compression strategy performs the following processing: Perform the quantity analysis of the key frame; If the quantity analysis result is higher than the preset quantity threshold, divide the key frame into a main key frame and a secondary key frame; Keep the original data compression for the main key frame, perform reference low-loss compression based on the main key frame for the secondary key frame, and perform lossy compression on the non-key frame to construct a data compression strategy.

[0012] The present application also provides a wind power load test data processing system with adaptive data compression, including: a load test data acquisition module for collecting load test data of a wind turbine using a nested sliding window, where the nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window, and the load test data includes stress data, vibration data, torque data, and wind speed data; a multi-scale feature extraction and fusion module for performing multi-scale feature extraction on the collected data of the nested sliding window respectively, and performing multi-scale feature fusion to establish a comprehensive change score for each data point; a key frame positioning module for obtaining the spatial distribution of the acquisition sensors, configuring a sensor adjacency coefficient according to the spatial distribution and sensor functions, performing spatial consistency detection of data points based on the sensor adjacency coefficient, and positioning key frames according to the spatial consistency detection results and the comprehensive change score; a data compression module for synchronizing the key frames to an adaptive compression channel, constructing a data compression strategy, and using the data compression strategy to perform compression management of the load test data.

[0013] It is intended to first collect the load test data of the wind turbine using a nested sliding window through the wind power load test data processing method and system with adaptive data compression proposed in the present application. The nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window. The load test data includes stress data, vibration data, torque data, and wind speed data. Then, perform multi-scale feature extraction on the collected data of the nested sliding window respectively, and perform multi-scale feature fusion to establish a comprehensive change score for each data point. Next, obtain the spatial distribution of the acquisition sensors, configure a sensor adjacency coefficient according to the spatial distribution and sensor functions, perform spatial consistency detection of data points based on the sensor adjacency coefficient, and position key frames according to the spatial consistency detection results and the comprehensive change score. Finally, synchronize the key frames to an adaptive compression channel, construct a data compression strategy, and use the data compression strategy to perform compression management of the load test data. The technical effects of improving the flexibility of data acquisition, accurately capturing the dynamic change characteristics of data, and further improving the efficiency and accuracy of data compression are achieved. Description of the Drawings

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 It is a schematic flow chart of the wind power load test data processing method with adaptive data compression provided by the embodiments of the present application.

[0016] Figure 2 It is a schematic structural diagram of the wind power load test data processing system with adaptive data compression provided by the embodiments of the present application.

[0017] Explanation of reference numerals: Load test data acquisition module 10, multi-scale feature extraction and fusion module 20, key frame positioning module 30, data compression module 40. Detailed implementation manners

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0020] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily limit to those clearly listed steps or units, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] The embodiments of the present application provide a wind power load test data processing method with adaptive data compression, as Figure 1 shown, the method includes:

[0022] Step S100: Collect load test data of the wind turbine using a nested sliding window. The nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window. The load test data includes stress data, vibration data, torque data, and wind speed data.

[0023] Specifically, the nested sliding window is a data processing method that slides windows of different sizes over time series data to capture data changes at different scales. The basic sliding window is a fixed time length (e.g., 1 second) for data collection. It slides over the data stream to continuously capture data segments for initially capturing local changes in the data. The extended sliding window is a longer time length (e.g., 10 seconds) that covers multiple slides of the basic sliding window and is used to capture broader data change trends. Through a sensor network connected to the wind turbine, load test data such as stress data, vibration data, torque data, and wind speed data are collected in real time. The load test data are various physical quantity data generated when the wind turbine is operating and are used to evaluate the load status and performance of the unit. The data are stored in time series, and each time point corresponds to a complete set of load test data. The basic sliding window slides over the time series, moving one data point at a time and recording the data within the window. Within the extended sliding window, the basic sliding window can slide multiple times, thus collecting richer data samples.

[0024] In a possible implementation, for the step S100 of collecting load test data of the wind turbine using a nested sliding window, step S100 further includes step S110: Configure the default window value of the basic sliding window within the nested sliding window, and call the basic sliding window according to the default window value to perform pre - collection of load test data and establish a pre - collection data set. Specifically, set an initial or default window size for the basic sliding window. This window size is determined based on empirical values or previous data analysis results and is used to cover a reasonable time range or number of data points so as to effectively capture the local characteristics of the data. Subsequently, use this configured basic sliding window to slide over the load test data stream to collect data. Each time the window slides into place, the data within the window are extracted to form a pre - collection data set. This process is carried out continuously until a predetermined amount or time of pre - collected data is reached.

[0025] Step S120: Perform data stability analysis on the pre - collected dataset, and generate reconstruction parameters according to the data stability analysis results. The reconstruction parameters include the window value of the basic sliding window and the expansion value of the extended sliding window. Specifically, analyze the pre - collected dataset to evaluate the stability and consistency of the data over time. By calculating indicators such as variance, standard deviation, and autocorrelation coefficient of the data, determine whether there are obvious fluctuations or trends in the data. According to the results of the data stability analysis, adjust the window value of the basic sliding window and the expansion value of the extended sliding window. If the data fluctuates greatly, it is necessary to increase the window value to include more data points to smooth the fluctuations; if the data is relatively stable, the window value can be appropriately reduced to improve the efficiency of data processing. The expansion value of the extended sliding window is used to expand the data collection range when needed.

[0026] Step S130: After reconstructing the nested sliding window according to the window value and the expansion value, collect the load test data of the wind turbine. Specifically, according to the reconstruction parameters generated in step S120, modify the relevant variables or configurations in the program, adjust the sizes of the basic sliding window and the extended sliding window, and ensure that the subsequent data collection meets the requirements of the new window sizes. Use the reconstructed nested sliding window to slide on the load test data stream to collect data. At this time, the basic sliding window is used to capture the local characteristics of the data, and the extended sliding window provides the ability to expand the data collection range when needed. This implementation method improves the efficiency and accuracy of data collection and processing by gradually adjusting and optimizing the sizes of the nested sliding window to adapt to different data characteristics.

[0027] In a possible implementation, for the step of reconstructing the nested sliding window according to the window value and the expansion value, step S130 further includes step S131: Perform data fluctuation analysis on the pre - collected dataset, and establish an expansion bias according to the data fluctuation analysis results. Specifically, perform fluctuation analysis on the pre - collected dataset by calculating the standard deviation, coefficient of variation, or other statistics of the data. Based on these statistics, identify trends, periodic changes, or outliers in the data. The expansion bias refers to determining the bias or expansion direction of the extended sliding window relative to the basic sliding window based on the data fluctuation characteristics. For example, if the data fluctuates greatly on one side, the extended sliding window will expand more to that side to capture more change information.

[0028] Step S132: After reconstructing the basic sliding window with the window value, taking the reconstructed basic sliding window as the center, reconstruct the extended sliding window based on the extended bias and the extended value. Specifically, according to the reconstruction parameters (including the window value and the extended value of the basic sliding window) generated in step S120, first reconstruct the basic sliding window. Then, taking this reconstructed basic sliding window as the center, combine the extended bias and the extended value determined in step S131 to reconstruct the extended sliding window, that is, the extended sliding window surrounds the basic sliding window and is dynamically adjusted according to the fluctuation characteristics of the data.

[0029] Step S133: After collecting the load test data of the wind turbine using the reconstructed nested sliding window, obtain the window data set corresponding to the reconstructed extended sliding window. Specifically, once the nested sliding window is reconstructed, use this window to collect the load test data of the wind turbine. During the collection process, record the data within each extended sliding window to form a window data set.

[0030] Step S134: After evenly dividing the window data set, calculate the fluctuation amplitude under the evenly divided window. Specifically, evenly divide the window data set into multiple small windows. Then, calculate the fluctuation amplitude of the data within each small window, including calculating the difference between the maximum value and the minimum value of the data, the standard deviation, or other statistics.

[0031] Step S135: Configure the adaptive sliding step according to the fluctuation amplitude and the sensitivity coefficient. Specifically, based on the fluctuation amplitude calculated in step S134 and the preset sensitivity coefficient, dynamically adjust the sliding step. The sensitivity coefficient is a preset parameter used to control the influence degree of the fluctuation amplitude on the adjustment of the sliding step. If the fluctuation amplitude is large and the sensitivity coefficient is high, then reduce the sliding step to capture the data change more precisely. On the contrary, if the fluctuation amplitude is small and the sensitivity coefficient is low, then increase the sliding step to reduce the data volume. This implementation method can flexibly adapt to the change characteristics of the data by dynamically adjusting the size and step of the nested sliding window. In the area where the data fluctuates greatly, reducing the sliding step can capture more detailed information; in the area where the data fluctuates slightly, increasing the sliding step can reduce unnecessary data redundancy. This can not only reduce the data volume, lower the storage and transmission costs, but also retain the important change information in the data, thereby improving the efficiency and accuracy of data compression.

[0032] Step S200: Perform multi-scale feature extraction on the collected data of the nested sliding window respectively, and execute multi-scale feature fusion to establish a comprehensive change score for each data point.

[0033] Specifically, for the data within each basic sliding window, basic features such as the average value, standard deviation, maximum value, minimum value, etc. are extracted to reflect the overall distribution and dispersion degree of the data. Within the extended sliding window, in addition to extracting basic features, more macroscopic features such as trend features (such as linear regression coefficients) and periodic features (such as Fourier transform results) are also extracted to reflect the change trend and periodicity of the data over a longer time period. Combining the feature extraction results of the basic window and the extended window forms a multi-scale feature set. These features contain both local detailed information and global macroscopic information of the data.

[0034] According to the characteristics of the data and the analysis requirements, through feature importance evaluation methods (such as information gain, Gini coefficient, etc.), key features are selected from the multi-scale feature set for fusion, and methods such as linear combination and non-linear mapping are used to fuse the selected features. For example, the weighted summation method can be used to linearly combine features at different scales, or non-linear models such as neural networks can be used for feature fusion.

[0035] Based on the fused feature vector, through distance metrics (such as Euclidean distance, Manhattan distance, etc.), similarity metrics (such as cosine similarity, Pearson correlation coefficient, etc.) or a custom scoring function, etc., the comprehensive change score of each data point is calculated to represent the degree of change of each data point relative to its surrounding data points. To make the comprehensive change scores comparable, they are standardized. For example, the score values can be mapped to the range from 0 to 1 so that the score values of different data points have the same scale.

[0036] In step S300, obtain the spatial distribution of the acquisition sensors, configure the sensor adjacency coefficient according to the spatial distribution and the sensor functions, perform spatial consistency detection of the data points based on the sensor adjacency coefficient, and locate the key frames according to the spatial consistency detection results and the comprehensive change scores.

[0037] Specifically, obtain the spatial distribution information of the sensors on the wind turbine through a configuration file or a database, including longitude, latitude, and altitude. Using the spatial distribution data, calculate the physical distance between each pair of sensors using Euclidean distance, Manhattan distance, etc. According to the functional descriptions of the sensors (such as measurement type, accuracy, range, etc.), evaluate the functional similarity between sensors by comparing the cosine similarity, Jaccard similarity, etc. of the functional vectors. Combining the adjacency distance and functional similarity, assign an adjacency coefficient to each sensor pair through weighted summation, multiplication, or other combination methods. This coefficient can be a value between 0 and 1, indicating the degree of association between sensors. Using the adjacency coefficient, evaluate the consistency between adjacent sensor data points by comparing the values of the data points, the rate of change, or other statistical features. Combining the spatial consistency detection results and the comprehensive change score, identify those data points that are spatially consistent and have significant changes as key frames.

[0038] In a possible implementation, the step of configuring the sensor adjacency coefficient according to the spatial distribution and sensor functions, step S300 further includes step S310 of calculating the adjacency distance of the sensors based on the spatial distribution and determining whether the adjacency distance is less than a preset distance threshold. Specifically, collect the position information of all sensors through GPS or other positioning technologies to form a coordinate data set. For each pair of sensors, calculate the distance between them using a distance formula (Euclidean distance formula or other distance measurement methods). Compare the calculated distance with a preset distance threshold (determined according to the actual situation of the wind farm and the characteristics of the sensors, used to determine whether two sensors are close enough to be considered adjacent). If the distance is less than the threshold, it is considered that these two sensors are physically close.

[0039] Step S320, if the adjacency distance is less than the preset distance threshold, generate a first authentication passed result. Specifically, check the comparison results of each distance calculated in step S310 with the preset distance threshold. For all distances less than the threshold, mark the corresponding sensor pairs as "adjacent" and generate a first authentication passed result.

[0040] Step S330: Configure a function vector according to the sensor function, calculate the function similarity through the cosine similarity and the function vector. If the function similarity is higher than the preset function threshold, generate a second authentication passed result. Specifically, generate a function vector for each sensor according to its function configuration (obtained from the technical specification or database of the sensor, such as measurement type, accuracy, sampling rate, etc.). For each pair of sensors, use the cosine similarity formula to calculate the similarity between their function vectors. The value range is [-1, 1], and the larger the value, the closer the directions are. Compare the calculated similarity with the preset function threshold (a value set in advance, used to determine whether the functional similarity between two sensors is high enough, determined according to the data processing requirements of the wind farm and the functional characteristics of the sensors). If the similarity is higher than the threshold, it is considered that these two sensors are functionally similar.

[0041] Step S340: When both the first authentication passed result and the second authentication passed result exist, calculate the sensor adjacency coefficient. Specifically, check whether each pair of sensors simultaneously satisfies the first authentication passed result (physical adjacency) and the second authentication passed result (functionally similar). For the pair of sensors that meet the conditions, use the formula to calculate the adjacency coefficient. The adjacency coefficient can be a value between 0 and 1, indicating the degree of adjacency between sensors. This implementation method combines the physical location and function configuration of the sensors, can more accurately evaluate the adjacency between sensors, helps to more reasonably utilize sensor data in subsequent key frame positioning and data compression strategy construction, ensures that important information will not be lost during the data compression process, and at the same time reduces unnecessary data redundancy.

[0042] In a possible implementation, the step of calculating the sensor adjacency coefficient, step S340 further includes step S341: calculate the sensor adjacency coefficient through the following formula:

[0043] ;

[0044] where represents the sensor adjacency coefficient of sensor and sensor , and the value range is [0, 1], represents the adjacency distance between sensor and sensor , represents the spatial attenuation factor, represents the functional similarity between sensor and sensor .

[0045] Specifically, obtain the adjacent distance between sensors from step S310 and the functional similarity between sensors from step S330. The spatial attenuation factor is a parameter used to adjust the influence of the adjacent distance on the adjacency coefficient, which determines how the adjacency coefficient decays as the physical distance increases. The value of the spatial attenuation factor is determined according to the actual situation of the wind farm and the data processing requirements. For example, a suitable value can be set through experiments or expert experience. Calculate the adjacency coefficient between sensors using a formula, and the calculated adjacency coefficient is within the range of [0, 1], where 1 represents complete adjacency and 0 represents complete non - adjacency. This implementation provides a method for comprehensively evaluating the adjacency degree between sensors. By considering the physical and functional characteristics of sensors, key frames and data redundancy can be more accurately identified, thereby improving the efficiency and quality of data compression.

[0046] In a possible implementation, after calculating the sensor adjacency coefficient, step S300 further includes step S350, calculating the differential deviation of sensor data through the formula:

[0047] ;

[0048] where, represents the degree of data difference between sensor and sensor at time . represents the measured value of sensor at time . represents the measured value of sensor at time . Specifically, collect the measured values at the same time point (e.g., each time step) from each sensor. For each pair of sensors ( and ), calculate their degree of data difference at the same time point , and the degree of data difference is calculated by the absolute difference between the measured values of the two sensors.

[0049] Step S360, calculate the consistency score based on the differential deviation and the sensor adjacency coefficient:

[0050] ;

[0051] where, represents the consistency score of sensor at time , represents the set of sensors that have a sensor adjacency coefficient with sensor , is the data difference sensitivity coefficient. Specifically, for time the consistency score of the sensor is calculated by considering all sensors with an adjacency coefficient to the sensor The data difference degree and the adjacency coefficient. The data difference sensitivity coefficient is an adjustment factor used to control the weight of the data difference degree in the consistency score. This implementation provides a method for evaluating the data space consistency, which considers both the physical and functional characteristics between sensors (through the adjacency coefficient) and the differences in their measured values at the same time point (through the differential deviation). It can accurately identify anomalies and inconsistencies in the data. By preferentially retaining data frames with high consistency, data can be compressed more effectively while retaining key information.

[0052] Step S400: Synchronize the key frames to the adaptive compression channel, construct a data compression strategy, and use the data compression strategy to perform compression management on the load test data.

[0053] Specifically, synchronize the located key frames to a channel or module dedicated to data compression. The adaptive compression channel can automatically adjust the compression strategy according to the data characteristics. According to the distribution of the key frames and the data characteristics, construct a suitable data compression strategy, such as key frame-based compression, lossy compression, lossless compression, etc. Use the constructed data compression strategy to compress the load test data to reduce the data storage space, while maintaining the availability and accuracy of the data, and improving the data processing efficiency. Store and manage the compressed data to ensure the integrity and availability of the data. The embodiments of the present application use techniques such as collecting data using nested sliding windows, performing multi-scale feature extraction and fusion on the collected data, establishing a comprehensive change score for each data point, performing spatial consistency detection based on the sensor adjacency coefficient, locating key frames according to the spatial consistency detection results and the comprehensive change score, and constructing an adaptive compression strategy, etc., to achieve the technical effects of improving the flexibility of data collection, accurately capturing the dynamic change characteristics of the data, and further improving the efficiency and accuracy of data compression.

[0054] In a possible implementation, the step of synchronizing the key frames to the adaptive compression channel and constructing a data compression strategy, step S400 further includes step S410 of performing an analysis of the number of key frames. Specifically, the system maintains a list or database containing all key frames. Traverse the list and count each key frame to finally obtain the total number of key frames. Suppose in a 10-minute wind power load test data, the system locates 200 key frames.

[0055] Step S420: If the quantity analysis result is higher than the preset quantity threshold, divide the key frames into primary key frames and secondary key frames. Specifically, preset a threshold for the number of key frames. When the number of key frames exceeds the preset threshold (such as 100 frames), use clustering algorithms (such as K-means), decision trees, or rule-based methods to divide the key frames into primary key frames and secondary key frames according to factors such as the comprehensive change score and time interval of the key frames. The primary key frame is a data point with the highest importance or priority among the key frames. The frame with the highest comprehensive change score, the longest time interval, or the strongest correlation with other key frames can be selected as the primary key frame. The secondary key frame is a key frame with lower importance or priority relative to the primary key frame. For example, among the above 200 key frames, the system identifies 50 primary key frames and 150 secondary key frames through the classification algorithm.

[0056] Step S430: Retain the original data compression for the primary key frames, perform reference-based low-loss compression based on the primary key frames for the secondary key frames, and perform lossy compression on the non-key frames to construct a data compression strategy. Specifically, according to the classification result of the key frames, different compression strategies are used to compress different types of frames. The primary key frames use lossless compression (such as ZIP, GZIP) to ensure the integrity and accuracy of the data; using the primary key frames as a reference, use a prediction-based compression algorithm (such as inter-frame prediction in H.264) to perform low-loss compression on the secondary key frames to reduce the data volume while maintaining relatively high data quality; the non-key frames use lossy compression (such as JPEG, intra-frame compression in H.264) to minimize the data volume to the greatest extent. For example, through the above compression strategy, the system can compress the original 10-minute wind power load test data from 1GB to 200MB while maintaining relatively high data quality and accuracy. This implementation method can make more efficient use of compression resources, achieve a higher compression ratio, improve the compression efficiency, ensure the data quality, and meet the requirements for data management and storage in the wind power field by distinguishing key frames and non-key frames, and further dividing primary key frames and secondary key frames.

[0057] In the above text, reference is made to Figure 1 a detailed description of the method for processing wind power load test data with adaptive data compression according to an embodiment of the present invention. Next, reference will be made to Figure 2 describe a system for processing wind power load test data with adaptive data compression according to an embodiment of the present invention.

[0058] The wind power load test data processing system with adaptive data compression according to an embodiment of the present invention is used to solve the technical problems existing in the prior art, such as insufficient flexibility in data acquisition, difficulty in accurately capturing the dynamic characteristics of data, resulting in insufficient efficiency and accuracy of data compression. It achieves the technical effects of improving the flexibility of data acquisition, accurately capturing the dynamic change characteristics of data, and further improving the efficiency and accuracy of data compression. The wind power load test data processing system with adaptive data compression includes: a load test data acquisition module 10, a multi-scale feature extraction and fusion module 20, a key frame positioning module 30, and a data compression module 40.

[0059] The load test data acquisition module 10 is used to collect the load test data of the wind turbine using a nested sliding window. The nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window. The load test data includes stress data, vibration data, torque data, and wind speed data. The multi-scale feature extraction and fusion module 20 is used to perform multi-scale feature extraction on the collected data of the nested sliding window respectively, and perform multi-scale feature fusion to establish a comprehensive change score for each data point. The key frame positioning module 30 is used to obtain the spatial distribution of the acquisition sensors, configure the sensor adjacency coefficient according to the spatial distribution and sensor functions, perform spatial consistency detection of data points based on the sensor adjacency coefficient, and locate key frames according to the spatial consistency detection result and the comprehensive change score. The data compression module 40 is used to synchronize the key frames to the adaptive compression channel, construct a data compression strategy, and use the data compression strategy to perform compression management of the load test data.

[0060] Next, the specific configuration of the key frame positioning module 30 will be described in detail. As described above, the sensor adjacency coefficient is configured according to the spatial distribution and sensor functions. The key frame positioning module 30 may further include: an adjacency distance calculation unit for calculating the adjacency distance of the sensors based on the spatial distribution and determining whether the adjacency distance is less than a preset distance threshold; an authentication passed unit for generating a first authentication passed result if the adjacency distance is less than the preset distance threshold; a function similarity calculation unit for configuring a function vector according to the sensor functions and calculating the function similarity through the cosine similarity and the function vector, and generating a second authentication passed result if the function similarity is higher than a preset function threshold; a sensor adjacency coefficient calculation unit for calculating the sensor adjacency coefficient when both the first authentication passed result and the second authentication passed result exist.

[0061] Among them, for the calculation of the sensor adjacency coefficient, the sensor adjacency coefficient calculation unit may further include: a sensor adjacency coefficient formula construction subunit for constructing a sensor adjacency coefficient formula and calculating the sensor adjacency coefficient through the following formula: , where characterizes the sensor and the sensor of the sensor adjacency coefficient, with a value range of [0, 1], characterizes the sensor and the sensor of the adjacency distance, characterizes the spatial attenuation factor, characterizes the sensor and the sensor of the functional similarity.

[0062] Among them, after calculating the sensor adjacency coefficient, the key frame positioning module 30 may further include: a differential deviation calculation unit for calculating the differential deviation of the sensor data through the formula: , where characterizes the sensor and the sensor at time of the data difference degree, characterizes the sensor at time of the measured value, characterizes the sensor at time of the measured value; a consistency score calculation unit for calculating a consistency score based on the differential deviation and the sensor adjacency coefficient: , where characterizes the consistency score of the sensor at time , characterizes the set of sensors with the sensor adjacency coefficient with the sensor , is the data difference sensitivity coefficient.

[0063] Next, the specific configuration of the load test data acquisition module 10 will be described in detail. As described above, the load test data of the wind turbine is collected using a nested sliding window. The load test data acquisition module 10 may further include: a data pre-acquisition unit for configuring the default window value of the basic sliding window within the nested sliding window, calling the basic sliding window according to the default window value for data pre-acquisition of the load test data, and establishing a pre-acquisition data set; a reconstruction parameter generation unit for performing data stability analysis on the pre-acquisition data set and generating reconstruction parameters according to the data stability analysis results, where the reconstruction parameters include the window value of the basic sliding window and the extension value of the extended sliding window; a load test data acquisition unit for reconstructing the nested sliding window according to the window value and the extension value and then collecting the load test data of the wind turbine.

[0064] Among them, for reconstructing the nested sliding window according to the window value and the extension value, the load test data acquisition unit may further include: an extension bias establishment subunit for performing data fluctuation analysis on the pre-acquired data set and establishing an extension bias according to the data fluctuation analysis result; a sliding window extension subunit for reconstructing a basic sliding window with the window value, and then, centered on the reconstructed basic sliding window, reconstructing an extended sliding window based on the extension bias and the extension value; a window data set acquisition subunit for acquiring a window data set corresponding to the reconstructed extended sliding window after collecting the load test data of the wind turbine generator set by using the reconstructed nested sliding window; a fluctuation amplitude calculation subunit for uniformly dividing the window data set and calculating the fluctuation amplitude under the uniformly divided window; and an adaptive sliding step configuration subunit for configuring an adaptive sliding step according to the fluctuation amplitude and the sensitivity coefficient.

[0065] Next, the specific configuration of the data compression module 40 will be described in detail. As described above, synchronizing the key frames to the adaptive compression channel and constructing a data compression strategy, the data compression module 40 may further include: a quantity analysis unit for performing quantity analysis on the key frames; a key frame division unit for dividing the key frames into main key frames and secondary key frames if the quantity analysis result is higher than a preset quantity threshold; and a data compression strategy construction unit for retaining the original data compression for the main key frames, performing reference low-loss compression based on the main key frames on the secondary key frames, and performing lossy compression on the non-key frames to construct a data compression strategy.

[0066] The wind power load test data processing system with adaptive data compression provided by the embodiments of the present invention can execute the method for processing wind power load test data with adaptive data compression provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0067] Although various references are made to certain modules in the systems of the embodiments according to the present application, any number of different modules may be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0068] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps described in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for processing wind power load test data with adaptive data compression, characterized in that, The method includes: Collecting load test data of a wind turbine using a nested sliding window, where the nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window. The load test data includes stress data, vibration data, torque data, and wind speed data. Performing multi-scale feature extraction on the collected data of the nested sliding window respectively, and performing multi-scale feature fusion to establish a comprehensive change score for each data point. Obtaining the spatial distribution of the acquisition sensors, configuring the sensor adjacency coefficient according to the spatial distribution and sensor functions, performing spatial consistency detection of data points based on the sensor adjacency coefficient, and locating key frames according to the spatial consistency detection result and the comprehensive change score. Synchronizing the key frames to an adaptive compression channel, constructing a data compression strategy, and performing compression management of the load test data using the data compression strategy.

2. The method for processing wind power load test data with adaptive data compression according to claim 1, wherein The configuring the sensor adjacency coefficient according to the spatial distribution and sensor functions includes: Calculating the adjacency distance of the sensors based on the spatial distribution, and determining whether the adjacency distance is less than a preset distance threshold. If the adjacency distance is less than the preset distance threshold, generating a first authentication passed result. Configuring a function vector according to the sensor functions, calculating the function similarity through cosine similarity and the function vector, and if the function similarity is higher than a preset function threshold, generating a second authentication passed result. When both the first authentication passed result and the second authentication passed result exist, calculating the sensor adjacency coefficient.

3. The method for processing wind power load test data with adaptive data compression according to claim 2, wherein The calculating the sensor adjacency coefficient includes: Calculating the sensor adjacency coefficient through the following formula: ； Among them, characterize the sensor and the sensor The adjacency coefficient of the sensor has a value range of [0, 1]. characterize the sensor and the sensor The adjacency distance of the sensor characterize the spatial attenuation factor characterize the sensor and the sensor The functional similarity of the sensor 4. The adaptive data compression-based wind power load test data processing method according to claim 3, characterized in that, After the calculating the sensor adjacency coefficient, it includes: Calculating the differential deviation of the sensor data through a formula. ； Among them, characterize the sensor and the sensor at time the data difference degree at this time, characterize the sensor at time the measured value at this time, characterize the sensor at time the measured value at this time; Calculating a consistency score based on the differential deviation and the sensor adjacency coefficient. ； Among them, characterizes the consistency score of the sensor at time , characterizes the set of sensors with a sensor adjacency coefficient to the sensor, is the data difference sensitivity coefficient.

5. The method for processing wind power load test data with adaptive data compression according to claim 1, characterized in that The collecting load test data of a wind turbine using a nested sliding window includes: Configuring the default window value of the basic sliding window within the nested sliding window, calling the basic sliding window for pre-acquisition of load test data according to the default window value, and establishing a pre-acquisition data set. Performing data stability analysis on the pre-acquisition data set, and generating reconstruction parameters according to the data stability analysis result. The reconstruction parameters include the window value of the basic sliding window and the extension value of the extended sliding window. After reconstructing the nested sliding window according to the window value and the extension value, collecting load test data of the wind turbine.

6. The method for processing wind power load test data with adaptive data compression according to claim 5, characterized in that The reconstructing the nested sliding window according to the window value and the extension value includes: Performing data fluctuation analysis on the pre-acquisition data set, and establishing an extension bias according to the data fluctuation analysis result. After reconstructing the basic sliding window with the window value, taking the reconstructed basic sliding window as the center, and reconstructing the extended sliding window based on the extension bias and the extension value. After collecting load test data of the wind turbine using the reconstructed nested sliding window, obtaining the window data set corresponding to the reconstructed extended sliding window. After uniformly dividing the window data set, calculating the fluctuation amplitude under the uniformly divided window. Configuring an adaptive sliding step according to the fluctuation amplitude and the sensitivity coefficient.

7. The method for processing wind power load test data with adaptive data compression according to claim 1, wherein Synchronizing the key frames to an adaptive compression channel and constructing a data compression policy includes: Performing a quantity analysis of the key frames; If the result of the quantity analysis is higher than a preset quantity threshold, dividing the key frames into primary key frames and secondary key frames; Retaining the original data compression for the primary key frames, performing reference low-loss compression based on the primary key frames for the secondary key frames, and performing lossy compression on the non-key frames to construct a data compression policy.

8. A wind power load test data processing system for adaptive data compression, characterized in that, The system is used to implement the method for processing wind power load test data with adaptive data compression according to any one of claims 1-7. The system includes: A load test data acquisition module for acquiring load test data of a wind turbine using a nested sliding window. The nested sliding window includes a basic sliding window and an extended sliding window, and the basic sliding window can slide multiple times within the extended sliding window. The load test data includes stress data, vibration data, torque data, and wind speed data; A multi-scale feature extraction and fusion module for respectively performing multi-scale feature extraction on the acquired data of the nested sliding window, performing multi-scale feature fusion, and establishing a comprehensive change score for each data point; A key frame positioning module for obtaining the spatial distribution of the acquisition sensors, configuring the sensor adjacency coefficient according to the spatial distribution and the sensor functions, performing spatial consistency detection of the data points based on the sensor adjacency coefficient, and positioning the key frames according to the spatial consistency detection result and the comprehensive change score; A data compression module for synchronizing the key frames to an adaptive compression channel, constructing a data compression policy, and performing compression management of the load test data using the data compression policy.

Images