Wind turbine generator data cleaning method based on support vector single classification and related device

Abstract

The invention belongs to the technical field of data cleaning, and discloses a wind turbine generator data cleaning method based on support vector single classification and a related device. The wind turbine generator data cleaning method based on support vector single classification comprises the following steps: acquiring multi-source heterogeneous data of a wind turbine generator, preprocessing the multi-source heterogeneous data to obtain normal data and abnormal data, and constructing a support vector single classification data cleaning model according to the normal data, training the support vector single-classification data cleaning model according to the normal data and the abnormal data, and cleaning the multi-source heterogeneous data of the wind turbine generator by using the trained support vector single-classification data cleaning model; according to the method, normal data and abnormal data can be accurately identified, misjudgment and omission in a traditional data cleaning method are effectively avoided, the accuracy and efficiency of data cleaning are remarkably improved, a more reliable basis is provided for data processing and analysis, and improvement of data quality is greatly promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of data cleaning, and in particular to a wind turbine generator set data cleaning method based on support vector single classification and a related device. Background Art

[0002] In today's data-driven era, data has become a crucial foundation for business decision-making and academic research. However, during the actual data collection and processing process, data often contains various errors and omissions, such as input errors, inconsistent formats, missing values, and outliers. These problems can seriously affect the reliability and validity of the data. Therefore, to ensure data accuracy and credibility, data cleaning has become an essential step.

[0003] However, the current problems faced by data cleaning are mainly reflected in two aspects: accuracy and efficiency. In terms of accuracy, due to imperfect algorithms or human errors in the data cleaning process, erroneous data may not be accurately identified or corrected, which in turn affects the accuracy of subsequent data analysis and decision-making. In addition, the setting of data cleaning rules may also be biased and unable to fully adapt to the actual situation of the data, resulting in inaccurate cleaning results; in terms of efficiency, with the rapid growth of data volume, traditional manual data cleaning methods can no longer meet the needs of efficient processing. Although automated data cleaning tools have emerged, they still face performance bottlenecks when processing complex data types and large-scale data sets, resulting in low data cleaning efficiency.

[0004] Therefore, it is necessary to continuously improve data cleaning algorithms and technologies to improve the accuracy and efficiency of data cleaning in order to better adapt to the development needs of the big data era. Summary of the Invention

[0005] The purpose of the present invention is to provide a wind turbine data cleaning method and related devices based on support vector single classification to overcome the problems existing in the prior art. The present invention can accurately identify normal data and abnormal data, effectively avoid misjudgments and omissions in traditional data cleaning methods, and significantly improve the accuracy and efficiency of data cleaning, providing a more reliable basis for data processing and analysis, and greatly promoting the improvement of data quality.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a wind turbine data cleaning method based on support vector single classification, comprising the following steps: Step 1: Acquire multi-source heterogeneous data of wind turbines, pre-process the multi-source heterogeneous data, and obtain normal data and abnormal data; Step 2: Construct a support vector single classification data cleaning model based on normal data; Step 3: Train the support vector single classification data cleaning model based on normal data and abnormal data; Step 4: Use the trained support vector single classification data cleaning model to clean the multi-source heterogeneous data of the wind turbine; Furthermore, the multi-source heterogeneous data specifically includes: Wind speed data, power data, temperature data, vibration data and speed data; Furthermore, the preprocessing of multi-source heterogeneous data to obtain normal data and abnormal data specifically includes: Perform standardization and missing value processing on multi-source heterogeneous data in turn to obtain normal data and abnormal data; Furthermore, the standardization process specifically includes: scaling the multi-source heterogeneous data to a unified scale range; The missing value processing specifically includes: using a time series-based interpolation algorithm to fill the missing values ​​of the multi-source heterogeneous data after standardization processing, marking the multi-source heterogeneous data whose missing values ​​do not exceed a preset threshold as normal data, and marking the multi-source heterogeneous data whose missing values ​​exceed a preset threshold as abnormal data; Furthermore, the support vector single classification data cleaning model is trained based on normal data and abnormal data, specifically including: Normal data and abnormal data are used as prepared data, the prepared data are divided into a training set and a test set, various parameters of the support vector single classification data cleaning model are set, the support vector single classification data cleaning model is trained using the training set, and then various indicators of the support vector single classification data cleaning model are calculated using the test set. The trained support vector single classification data cleaning model is evaluated according to the various indicators, and then the parameters and data volume of the support vector single classification data cleaning model are tuned according to the evaluation results to obtain a trained support vector single classification data cleaning model; Furthermore, the cleaning of the multi-source heterogeneous data of the wind turbine generator system specifically includes: Input the multi-source heterogeneous data into the trained support vector single classification data cleaning model, and use the support vector single classification data cleaning model to identify the multi-source heterogeneous data. If it is identified as normal data, the normal data is directly output; if it is identified as abnormal data, the abnormal data is cleaned; Furthermore, the cleaning of abnormal data specifically includes: Use a smoothing correction algorithm based on adjacent data for cleaning, or delete abnormal data.

[0007] In a second aspect, the present invention provides a wind turbine data cleaning system based on support vector single classification, comprising: The data acquisition and preprocessing module is used to obtain multi-source heterogeneous data of wind turbines, preprocess the multi-source heterogeneous data, and obtain normal data and abnormal data; Model building module, used to build a support vector single classification data cleaning model based on normal data; Model training module, used to train the support vector single classification data cleaning model based on normal data and abnormal data; The data cleaning module is used to clean the multi-source heterogeneous data of wind turbines using the trained support vector single classification data cleaning model.

[0008] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0009] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0010] The above technical solution has the following advantages or beneficial effects: In the first aspect, the present invention provides a wind turbine data cleaning method based on support vector single classification. The multi-source heterogeneous data generated by the operation of wind turbines often contain a large amount of noise and outliers. Through this method, abnormal data can be accurately identified and eliminated, and normal data can be retained, thereby significantly improving data quality. High-quality data provides a reliable basis for subsequent data analysis, fault diagnosis and performance evaluation, making data-based decisions more accurate and effective; after constructing and training a support vector single classification data cleaning model, the model can learn the distribution characteristics and patterns of normal data. Using the trained model for data cleaning can effectively avoid the interference of abnormal data, help improve the accuracy and stability of the model, and enable the model to better capture the operation of wind turbines. Regularity can improve the model's predictive ability and decision-making level; accurate data cleaning can help to timely discover potential problems and hidden faults of wind turbines. By analyzing the cleaned data, operation and maintenance personnel can take targeted maintenance measures in advance to avoid further deterioration of equipment failures, reduce downtime and maintenance costs. At the same time, the operation and maintenance plan formulated based on reliable data is more scientific and reasonable, which can optimize resource allocation, improve operation and maintenance efficiency, and thus reduce overall operation and maintenance costs; high-quality data and accurate models can provide strong support for the operation and management of wind farms. By reasonably arranging power generation plans and optimizing equipment operating parameters, the power generation efficiency and reliability of wind turbines can be improved, the power generation of wind farms can be increased, and the economic and social benefits of wind farms can be improved.

[0011] Furthermore, wind speed, power, temperature, vibration and speed data comprehensively cover the key parameters of wind turbine operation. For example, accurate wind speed data helps to evaluate the power generation performance of wind turbines under different wind speed conditions; power data without abnormalities can clearly show the changes in the power generation capacity of the unit, providing a reliable basis for subsequent performance analysis and optimization.

[0012] Furthermore, multi-source heterogeneous data usually contain features of different dimensions (such as temperature, speed, power, etc.). Standardization processing can scale the data to a uniform range to avoid model training bias caused by dimensional differences. If missing values ​​are not processed, it may cause the model to predict incomplete samples. After processing, the model's fitting accuracy for normal data can be improved. Reasonable missing value processing can help the model identify abnormal patterns, such as systematic missing values ​​caused by certain sensor failures.

[0013] Furthermore, scaling multi-source heterogeneous data to a unified scale can avoid model bias caused by differences in feature dimensions; using time series interpolation algorithms (such as linear interpolation, spline interpolation, or weighted average based on previous and next moments) to fill missing values ​​can retain the temporal correlation of the data. For example, when wind turbine sensor data is missing, interpolating data from adjacent moments can more realistically restore the missing values ​​and avoid the loss of temporal information caused by simple filling.

[0014] Furthermore, the prepared data is divided into training and test sets to avoid the risk of overfitting. The training set is used to help the model learn the distribution patterns of normal data, while the test set is used to verify the model's generalization ability to unseen data, ensuring that the model can stably identify abnormal data in real-world applications. Based on the evaluation results, the model parameters and data volume are tuned to gradually optimize model performance. The trained model can quickly and accurately identify outliers in wind turbine data, reducing the workload of manual investigation. Furthermore, accurate anomaly detection can promptly identify potential equipment failures, avoid significant losses, and significantly reduce operation and maintenance costs.

[0015] Furthermore, multi-source heterogeneous data can be directly input into the trained model to realize automatic identification and cleaning of abnormal data, eliminating the need for manual investigation one by one. The automated process greatly improves the efficiency of data cleaning, which is especially suitable for the massive and high-frequency data scenarios of wind turbines, reducing labor costs and time consumption. The model only cleans data identified as abnormal, and directly outputs normal data, ensuring the integrity and availability of the data.

[0016] Furthermore, the smoothing correction algorithm maintains the temporal continuity of the data by utilizing the information of adjacent data, avoiding time series breaks caused by deleting data; if abnormal data is directly input into the model without being processed, it may cause the model to overfit or learn incorrect patterns. Through cleaning, the model training set is purer, and can more accurately learn normal data features, thereby improving generalization capabilities.

[0017] Secondly, the present invention provides a wind turbine data cleaning system based on support vector single classification. The system automatically acquires and cleans multi-source heterogeneous data through the data acquisition and preprocessing module, quickly distinguishes normal data from abnormal data, and greatly improves the efficiency of data processing; the model construction module constructs a support vector single classification model based on normal data, accurately defines the normal behavior boundary, and is highly sensitive to abnormal data that deviates from the boundary; the model training module combines normal data and abnormal data for training, and evaluates the model performance through quantitative indicators to achieve dynamic parameter tuning; the data cleaning module uses the trained model to clean the input data in real time, supporting two strategies: smooth correction or deletion; the high-quality data after cleaning provides a reliable basis for wind turbine status monitoring, fault prediction, etc., reducing the risk of misjudgment; the system can accurately identify normal data and abnormal data, effectively avoid misjudgment and omissions in traditional data cleaning methods, and significantly improve the accuracy and efficiency of data cleaning, providing a more reliable basis for data processing and analysis, and greatly promoting the improvement of data quality.

[0018] In a third aspect, the present invention provides a computer device that can efficiently implement the steps of the method of the present invention by executing a specific computer program through a processor. When performing data processing tasks, the computer device can accurately perform numerical calculations and logical judgments, avoiding errors caused by human factors; at the same time, since the computer program has a high degree of stability and reliability, the accuracy and consistency of the data processing results can be ensured.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium. By programming the steps of the method of the present invention into a computer program and storing it on a computer-readable storage medium, users can easily load these programs onto any compatible computer device and execute them without rewriting or converting the code, thereby greatly improving the convenience and flexibility of program execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of a wind turbine data cleaning method based on support vector single classification according to the present invention; Figure 2 Schematic diagram of the structure of the computer device of the present invention. DETAILED DESCRIPTION

[0021] The present invention will be further described in detail below with reference to specific embodiments, which are intended to explain the present invention rather than to limit it. In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention. It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] Example: See also Figure 1 The present invention provides a wind turbine data cleaning method based on support vector single classification, comprising the following steps: Step 1: Acquire multi-source heterogeneous data of wind turbines, pre-process the multi-source heterogeneous data, and obtain normal data and abnormal data; Preferably, the multi-source heterogeneous data specifically includes: wind speed data, power data, temperature data, vibration data and rotation speed data; Specifically, preprocessing the multi-source heterogeneous data to obtain normal data and abnormal data specifically includes: performing standardization processing and missing value processing on the multi-source heterogeneous data in sequence to obtain normal data and abnormal data; the standardization processing includes: scaling the multi-source heterogeneous data to a unified scale range; the missing value processing includes: using a time series-based interpolation algorithm to fill the missing values ​​of the multi-source heterogeneous data after standardization processing, marking the multi-source heterogeneous data whose missing values ​​do not exceed a preset threshold as normal data, and marking the multi-source heterogeneous data whose missing values ​​exceed the preset threshold as abnormal data; Step 2: Construct a support vector single classification data cleaning model based on normal data; Step 3: Train the support vector single classification data cleaning model based on normal data and abnormal data; Specifically, normal data and abnormal data are used as prepared data, the prepared data are divided into a training set and a test set, various parameters of a support vector single classification data cleaning model are set, the support vector single classification data cleaning model is trained using the training set, and then various indicators of the support vector single classification data cleaning model are calculated using the test set, and the trained support vector single classification data cleaning model is evaluated according to the various indicators. Then, according to the evaluation results, the parameters and data amount of the support vector single classification data cleaning model are tuned to obtain a trained support vector single classification data cleaning model; Step 4: Use the trained support vector single classification data cleaning model to clean the multi-source heterogeneous data of the wind turbine; Specifically, cleaning the multi-source heterogeneous data of wind turbines includes: inputting the multi-source heterogeneous data into a trained support vector single classification data cleaning model, identifying the multi-source heterogeneous data through the support vector single classification data cleaning model, and directly outputting the normal data if it is identified as normal data; if it is identified as abnormal data, cleaning the abnormal data; cleaning the abnormal data includes: using a smoothing correction algorithm based on adjacent data for cleaning, or deleting the abnormal data.

[0023] In one embodiment of the present invention, a wind turbine data cleaning system based on support vector single classification is provided, comprising: The data acquisition and preprocessing module is used to obtain multi-source heterogeneous data of wind turbines, preprocess the multi-source heterogeneous data, and obtain normal data and abnormal data; Model building module, used to build a support vector single classification data cleaning model based on normal data; Model training module, used to train the support vector single classification data cleaning model based on normal data and abnormal data; The data cleaning module is used to clean the multi-source heterogeneous data of wind turbines using the trained support vector single classification data cleaning model.

[0024] See also Figure 2In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is used to execute the program instructions stored in the computer storage medium; the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a wind turbine data cleaning method based on support vector unit classification.

[0025] In one embodiment of the present invention, a computer-readable storage medium is provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device, used to store programs and data. It is understood that the computer-readable storage medium herein may include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides storage space, which stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for being loaded and executed by a processor. These instructions may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium herein may be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor may load and execute the one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the wind turbine data cleaning method based on support vector unit classification in the embodiment.

[0026] Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0027] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate the instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0028] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0029] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0030] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wind turbine data cleaning method based on support vector single classification, characterized in that: The following steps are involved: Acquire multi-source heterogeneous data of wind turbines, pre-process the multi-source heterogeneous data, and obtain normal data and abnormal data; Construct a support vector single classification data cleaning model based on normal data; Train the support vector single classification data cleaning model based on normal data and abnormal data; The trained support vector single classification data cleaning model is used to clean the multi-source heterogeneous data of wind turbines.

2. The wind turbine data cleaning method based on support vector single classification according to claim 1 is characterized in that: The multi-source heterogeneous data specifically includes: Wind speed data, power data, temperature data, vibration data and speed data.

3. The wind turbine data cleaning method based on support vector single classification according to claim 1 is characterized in that: The preprocessing of multi-source heterogeneous data to obtain normal data and abnormal data specifically includes: Multi-source heterogeneous data are standardized and missing value processed in turn to obtain normal data and abnormal data.

4. The wind turbine data cleaning method based on support vector single classification according to claim 3 is characterized in that: The standardization process specifically includes: scaling multi-source heterogeneous data to a unified scale range; The missing value processing specifically includes: using a time series-based interpolation algorithm to fill the missing values ​​of the multi-source heterogeneous data after standardization processing, marking the multi-source heterogeneous data whose missing values ​​do not exceed a preset threshold as normal data, and marking the multi-source heterogeneous data whose missing values ​​exceed a preset threshold as abnormal data.

5. The wind turbine data cleaning method based on support vector single classification according to claim 1 is characterized in that: The training of the support vector single classification data cleaning model based on normal data and abnormal data specifically includes: Normal data and abnormal data are used as prepared data, and the prepared data are divided into a training set and a test set. The various parameters of the support vector single classification data cleaning model are set, and the support vector single classification data cleaning model is trained using the training set. Then, the various indicators of the support vector single classification data cleaning model are calculated using the test set. The trained support vector single classification data cleaning model is evaluated according to the various indicators. Then, according to the evaluation results, the parameters and data volume of the support vector single classification data cleaning model are tuned to obtain the trained support vector single classification data cleaning model.

6. The wind turbine data cleaning method based on support vector single classification according to claim 5 is characterized in that: The cleaning of multi-source heterogeneous data of wind turbines specifically includes: The multi-source heterogeneous data is input into the trained support vector single classification data cleaning model, and the multi-source heterogeneous data is identified by the support vector single classification data cleaning model. If it is identified as normal data, the normal data is directly output; if it is identified as abnormal data, the abnormal data is cleaned.

7. The wind turbine data cleaning method based on support vector single classification according to claim 6 is characterized in that: The cleaning of abnormal data specifically includes: Use a smoothing correction algorithm based on adjacent data for cleaning, or delete abnormal data.

8. A wind turbine data cleaning system based on support vector single classification, characterized in that: include: The data acquisition and preprocessing module is used to obtain multi-source heterogeneous data of wind turbines, preprocess the multi-source heterogeneous data, and obtain normal data and abnormal data; Model building module, used to build a support vector single classification data cleaning model based on normal data; Model training module, used to train the support vector single classification data cleaning model based on normal data and abnormal data; The data cleaning module is used to clean the multi-source heterogeneous data of wind turbines using the trained support vector single classification data cleaning model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images