A method and system for analyzing the operating state of a wind turbine based on rotational speed monitoring

Abstract

The present invention discloses a method and system for analyzing the operating state of a wind turbine based on rotational speed monitoring, which relates to the technical field of wind power generation and includes: collecting the data of the wind turbine and the historical data of the wind turbine data, and preprocessing the collected wind turbine data; performing rotational speed monitoring verification based on fault tree analysis, training a machine learning model in combination with the historical data, and using the rotational speed monitoring verification result for fault diagnosis; automatically generating a repair plan based on the fault diagnosis result, executing the repair plan, and restoring the normal operating state of the wind turbine. The method for analyzing the operating state of a wind turbine based on rotational speed monitoring provided by the present invention uses the optimal features of the wind turbine for data modeling, captures the correlation between each feature through a multi-dimensional Gaussian model, calculates the fault probability of each component, improves the accuracy of fault diagnosis, and overcomes the limitation of only relying on a single data source in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and particularly to a method and system for analyzing the operating state of a wind turbine based on rotational speed monitoring. Background Art

[0002] As the core equipment of a wind power generation station, the operating state of a wind turbine directly affects the operating efficiency and safety of the wind power generation station. With the rapid development of the wind power industry, the number and scale of wind turbines are constantly expanding, and their fault problems have gradually become an important factor restricting the development efficiency of wind power. In order to ensure the reliability and safety of wind turbines during operation, the research and application of wind turbine fault diagnosis technology have become particularly important.

[0003] Existing wind turbine fault diagnosis methods mainly include methods based on vibration signal analysis, monitoring of physical parameters such as oil temperature and oil pressure, and pattern recognition based on artificial intelligence and machine learning. Although these methods can provide certain fault diagnosis functions, there are still some deficiencies, which are mainly reflected in the following aspects:

[0004] Many existing fault diagnosis technologies mainly rely on data during the operation of wind turbines for real-time monitoring and analysis. However, due to the complex working environment of wind turbines, diverse fault types, and the fact that the occurrence of faults is often a gradual process, traditional diagnosis methods are difficult to fully consider the mutual influence between various components of wind turbines, resulting in insufficient accuracy of fault diagnosis.

[0005] Traditional fault diagnosis methods mostly ignore the influence of environmental factors (such as wind speed, temperature, humidity, etc.) and the operating state of wind turbines (such as load, power factor, etc.) on wind turbine faults. The environment and operating state have a significant impact on wind turbine faults, and ignoring these factors may lead to deviations in the diagnosis results.

[0006] Most existing wind turbine fault diagnosis technologies lack systematic and comprehensive analysis. Especially in a multi-component system, simply relying on a single monitoring index is difficult to comprehensively evaluate the fault path of a wind turbine. There are complex mutual relationships between different fault paths, and these mutual relationships need to be evaluated through a more systematic analysis method in order to identify potential high-risk paths in advance for targeted prevention and repair.

[0007] Currently, the application of machine learning methods in wind turbine fault diagnosis is gradually increasing. However, due to the unreasonable quality and feature selection of data, the accuracy and generalization ability of the model are often poor, making it difficult to handle complex wind turbine fault types.

[0008] In view of the above problems, there is an urgent need in the prior art for a multi-dimensional fault diagnosis method that can better combine the operating status of wind turbines, environmental impacts, and the mutual relationships among various components to improve the accuracy of fault diagnosis, timely identify high-risk fault paths, and be able to automatically generate targeted repair plans based on the diagnosis results to reduce the downtime and maintenance costs of wind turbines. Summary of the Invention

[0009] In view of the existing problems above, the present invention is proposed.

[0010] Therefore, the technical problem to be solved by the present invention is that the existing fault diagnosis methods for wind turbines rely on a single data source, ignoring the correlation between data. The occurrence of wind turbine faults is usually related to multiple factors, and traditional fault diagnosis methods are difficult to handle the mutual influence among various characteristics of wind turbines, resulting in low diagnosis accuracy.

[0011] The connection between the fault diagnosis results and the repair plan in the prior art is not tight enough. Usually, fault diagnosis and the repair plan are carried out separately, lacking a comprehensive assessment of fault risks, resulting in low efficiency in the fault handling process and inability to achieve real-time and automated repair.

[0012] To solve the above technical problems, the present invention provides the following technical solution: A method for analyzing the operating status of a wind turbine based on rotational speed monitoring, including:

[0013] Collecting the data of the wind turbine and the historical data of the wind turbine data, and preprocessing the collected wind turbine data;

[0014] Verifying the rotational speed monitoring based on fault tree analysis, training a machine learning model in combination with historical data, and using the rotational speed monitoring verification results for fault diagnosis;

[0015] Automatically generating a repair plan based on the fault diagnosis results, executing the repair plan, and restoring the normal operating state of the wind turbine;

[0016] Before verifying the rotational speed monitoring based on fault tree analysis, extracting the characteristics of the wind turbine using the preprocessed data;

[0017] The characteristics of the wind turbine include a load index, a power factor, a mechanical stress coefficient, and an environmental impact coefficient;

[0018] The load index is expressed as

[0019] ,

[0020] ,

[0021] ,

[0022] ,

[0023] Among them, represents the load index, represents the actual power output, represents the maximum power, represents the power coefficient, represents the air density, is the atmospheric pressure, is the gas constant, is the air temperature represents the swept area of the wind turbine, is the blade radius of the wind turbine, represents the wind speed;

[0024] The power factor is expressed as,

[0025] ,

[0026] ,

[0027] ,

[0028] Among them, represents the power factor, represents the actual power, represents the voltage, represents the current, represents the phase angle between the current and the voltage, represents the apparent power;

[0029] The mechanical stress coefficient is expressed as,

[0030] ,

[0031] Among them, represents the mechanical stress coefficient, represents the rotational speed of the current wind turbine, represents the maximum rotational speed of the wind turbine, represents the vibration speed of the wind turbine, represents the maximum allowable vibration speed of the wind turbine;

[0032] The environmental impact coefficient is expressed as,

[0033] ,

[0034] Among them, represents the environmental impact coefficient, represents the current wind speed, represents the rated wind speed of the wind turbine, represents the current environmental temperature.

[0035] As a preferred solution of the wind turbine operating state analysis method based on rotational speed monitoring according to the present invention, wherein: the wind turbine data includes wind turbine operating state data, environmental data, and electrical system data;

[0036] The preprocessing includes denoising, missing value filling, and normalization of the data.

[0037] As a preferred solution of the wind turbine operating state analysis method based on rotational speed monitoring according to the present invention, wherein: the rotational speed monitoring verification includes using a multi-dimensional Gaussian model to model the characteristics of the wind turbine, and obtaining the failure probability of each component through the probability density function of the multi-dimensional Gaussian distribution in combination with the covariance matrix.

[0038] As a preferred solution of the wind turbine operating state analysis method based on rotational speed monitoring according to the present invention, wherein: the failure probability calculates the probability density of each feature combination through the multi-dimensional Gaussian distribution model, given the feature vector , and the probability density function is expressed as

[0039] ,

[0040] ,

[0041] wherein represents the mean vector, represents the failure probability, represents the dimension of the feature, represents the covariance matrix of the determinant, represents the covariance matrix of the inverse matrix, represents the deviation of each feature from its mean, represents the transpose operation, represents the exponential function, represents the mean of the load index, represents the mean of the power factor, represents the mean of the mechanical stress coefficient, represents the mean of the environmental impact coefficient;

[0042] Based on the logical gates in the fault tree model combined with the failure probability, evaluate the risk level of each fault path and determine the potential fault path.

[0043] As a preferred solution of the wind turbine operating state analysis method based on rotational speed monitoring according to the present invention, wherein: the determination of the potential fault path includes combining the failure probabilities of each component through the logical gates in the fault tree analysis model to obtain the overall failure probability of the wind turbine;

[0044] When using an AND gate, the probability of the overall failure of the wind turbine is the product of the failure probabilities of each sub-component; when using an OR gate, the probability of the overall failure of the wind turbine is the weighted sum of the failure probabilities of each sub-component; when using a NOT gate, calculate the probability that the component does not fail.

[0045] Through the combination of logic gates, evaluate the failure probability of each failure path and conduct risk level classification. If the failure probability is greater than the preset threshold, it is judged as a high-risk path; if the failure probability is less than or equal to the preset threshold, it is judged as a low-risk path.

[0046] As a preferred embodiment of the method for analyzing the operating state of a wind turbine based on rotational speed monitoring according to the present invention, wherein: the failure diagnosis includes inputting the characteristic data of the high-risk path into a machine learning model for training. The training uses historical failure data and combines the failure probability information of each high-risk path. The historical failure data is used to learn the failure modes of the wind turbine; during the training process, feature selection is performed by evaluating the correlation between each feature and the failure probability to remove redundant features; the model is optimized through cross-validation and hyperparameter tuning methods.

[0047] The machine learning model is trained through a supervised learning method. The model learns the failure modes and path characteristics in the historical data. After the model training is completed, input the characteristic data of the current high-risk path, diagnose each path, and output the failure type, failure component, and the location of the failure component of each path.

[0048] As a preferred embodiment of the method for analyzing the operating state of a wind turbine based on rotational speed monitoring according to the present invention, wherein: the execution of the repair plan includes generating a repair plan according to the failure type, failure component, and the location of the failure component output by the machine learning model. The repair plan includes repair steps, required tools, personnel arrangements, and time scheduling. The repair sequence and urgency in the repair plan are optimized based on the priority of the failure components.

[0049] Another object of the present invention is to provide a rotational speed monitoring test system, which can solve the problem that the existing method for analyzing the operating state of a wind turbine based on rotational speed monitoring usually relies on a large amount of prior knowledge and is difficult to adapt to the dynamically changing operating environment of the wind turbine by constructing a rotational speed monitoring test system. At the same time, there are certain limitations in dealing with multi-dimensional data by traditional methods, and it is difficult to accurately evaluate the association between components and the failure paths in a complex system.

[0050] To solve the above technical problems, the present invention provides the following technical solutions: A rotational speed monitoring and testing system, comprising: a data acquisition module, a fault diagnosis module, and a fault repair module; the data acquisition module is used to collect wind turbine data and historical data of wind turbine data, and preprocess the collected wind turbine data; the fault diagnosis module is used to perform rotational speed monitoring verification based on fault tree analysis, train a machine learning model in combination with historical data, and perform fault diagnosis using the rotational speed monitoring verification results; the fault repair module is used to automatically generate a repair plan based on the fault diagnosis results, execute the repair plan, and restore the normal operating state of the wind turbine.

[0051] A computer device, comprising a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for analyzing the operating state of a wind turbine based on rotational speed monitoring are implemented.

[0052] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for analyzing the operating state of a wind turbine based on rotational speed monitoring are implemented.

[0053] The beneficial effects of the present invention: The method for analyzing the operating state of a wind turbine based on rotational speed monitoring provided by the present invention uses the preferred features of the wind turbine to perform data modeling, captures the correlation between each feature through a multi-dimensional Gaussian model, calculates the failure probability of each component, improves the accuracy of fault diagnosis, and overcomes the limitation of only relying on a single data source in the prior art; through the failure probability calculated by combining fault tree analysis with a multi-dimensional Gaussian model, high-risk paths can be automatically identified, and fault diagnosis can be performed through a machine learning model, and a repair plan can be automatically generated. The obtained repair plan not only has higher accuracy, but also can optimize the repair order and urgency, and improve the operation and maintenance efficiency of the wind turbine; combined with the logic gates in the fault tree analysis, the risk level of each component or fault path can be accurately evaluated, high-risk fault paths can be obtained through reasonable probability calculation, and effective sorting can be performed. Description of the Drawings

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is the overall flowchart of a method for analyzing the operating state of a wind turbine based on rotational speed monitoring provided by an embodiment of the present invention. Detailed Embodiments

[0056] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0058] Example 1, referring to Figure 1 , which is an embodiment of the present invention, provides a method for analyzing the operating state of a wind turbine based on rotational speed monitoring, including:

[0059] Collect the data of the wind turbine and the historical data of the wind turbine data, and preprocess the collected wind turbine data;

[0060] Based on fault tree analysis, conduct rotational speed monitoring verification, train a machine learning model in combination with historical data, and use the rotational speed monitoring verification results for fault diagnosis;

[0061] Automatically generate a repair plan based on the fault diagnosis results, execute the repair plan, and restore the normal operating state of the wind turbine.

[0062] The wind turbine data includes the operating state data of the wind turbine, environmental data, and electrical system data;

[0063] The operating state data of the wind turbine includes the rotational speed of the wind turbine, power output, and blade angle;

[0064] The environmental data includes wind speed, wind direction, and air temperature;

[0065] The electrical system data includes current, voltage, and frequency data;

[0066] The preprocessing includes denoising, missing value filling, and normalization processing of the data;

[0067] The denoising process removes noise data through methods such as low-pass filters and moving averages to ensure that the input data is smoother and more reliable.

[0068] The missing value filling fills the missing values through interpolation methods (linear interpolation, Lagrange interpolation, etc.) to ensure that each data point is complete.

[0069] Standardize the data to eliminate the difference in measurement units and ensure that data in different dimensions have the same weight in the model.

[0070] Before verifying the rotational speed monitoring based on fault tree analysis, extract the characteristics of the wind turbine using the preprocessed data;

[0071] The characteristics of the wind turbine include a load index, a power factor, a mechanical stress coefficient, and an environmental impact coefficient;

[0072] The load index is expressed as

[0073] ,

[0074] ,

[0075] ,

[0076] ,

[0077] where represents the load index, represents the actual power output, represents the maximum power, represents the power coefficient, represents the air density, is the atmospheric pressure, is the gas constant, is the air temperature represents the swept area of the wind turbine, is the blade radius of the wind turbine, represents the wind speed;

[0078] The power factor is expressed as

[0079] ,

[0080] ,

[0081] ,

[0082] where represents the power factor, represents the actual power, represents the voltage, represents the current, represents the phase angle between the current and the voltage, represents the apparent power;

[0083] The mechanical stress coefficient is expressed as

[0084] ,

[0085] wherein, represents the mechanical stress coefficient, represents the rotational speed of the current wind turbine unit, represents the maximum rotational speed of the wind turbine unit, represents the vibration speed of the wind turbine unit, represents the maximum allowable vibration speed of the wind turbine unit;

[0086] The environmental impact coefficient is expressed as

[0087] ,

[0088] wherein, represents the environmental impact coefficient, represents the current wind speed, represents the rated wind speed of the wind turbine unit, represents the current environmental temperature.

[0089] The rotational speed monitoring and verification includes modeling the characteristics of the wind turbine unit using a multi-dimensional Gaussian model, and obtaining the failure probability of each component through the probability density function of the multi-dimensional Gaussian distribution in combination with the covariance matrix;

[0090] The failure probability calculates the probability density of each characteristic combination through the multi-dimensional Gaussian distribution model, given the characteristic vector , and the probability density function is expressed as

[0091] ,

[0092] ,

[0093] ,

[0094] wherein, represents the mean vector, represents the failure probability, represents the dimension of the characteristic, which is 4, represents the covariance matrix of the determinant, represents the covariance matrix of the inverse matrix, represents the deviation of each characteristic from its mean, represents the transpose operation, represents the exponential function, represents the mean of the load index, represents the mean of the power factor, represents the mean of the mechanical stress coefficient, represents the mean of the environmental impact coefficient, represents the variance of the load index, represents the variance of the power factor, represents the variance of the mechanical stress coefficient, represents the variance of the environmental impact coefficient, is the covariance between different features, reflecting the correlation between them;

[0095] It should be noted that the load index, power factor, mechanical stress coefficient, and environmental impact coefficient are four key features that describe the operating state of a wind turbine. They can reflect the working health status of the wind turbine from different aspects. These four features reveal various aspects of the operating state of the wind turbine from different dimensions and can comprehensively and accurately describe the potential risks of wind turbine faults. Therefore, they are preferably selected as the key features for wind turbine fault diagnosis.

[0096] Moreover, these four features are not only independent but also have complex correlations with each other. For example, an increase in the load index may lead to an increase in mechanical stress, a decrease in the power factor may exacerbate the wear of mechanical components, and changes in environmental temperature and wind speed will affect the load and mechanical stress. The interaction between these features indicates that considering the failure probability of each feature alone is not sufficient to comprehensively describe the overall failure risk of the wind turbine.

[0097] The multi-dimensional Gaussian model can handle the correlation between multiple variables and can comprehensively consider the mutual influence between these features. By constructing a multi-dimensional Gaussian distribution, we can not only calculate the independent failure probability of each feature but also reveal the relationship between features through the covariance matrix, and then accurately estimate the overall failure probability of the wind turbine. In this way, the multi-dimensional Gaussian model is very suitable for analyzing these features because it can handle the complex dependence relationship between features and improve the accuracy of fault diagnosis.

[0098] Combining these four features with the multi-dimensional Gaussian model can significantly improve the accuracy and robustness of fault diagnosis. First, this combination can reveal the complex interaction relationship between features and avoid the practice of simply relying on a single feature or simple weighted summation. For example, although the load index is closely related to the failure risk, if the influence of the power factor of the electrical system and environmental factors is ignored, it may lead to diagnostic deviation. Through the multi-dimensional Gaussian model, the method of the present invention can comprehensively consider the interaction between these features and obtain a more accurate failure probability. Second, it can automatically discover the implicit correlation between features without the need for manual explicit setting of the relationship between features. The covariance matrix can capture these potential dependence relationships, thereby calculating the failure probability more accurately, avoiding the interference of redundant features, and improving the efficiency of the model. At the same time, the model can be optimized in a high-dimensional space to reduce the influence of irrelevant features on the results.

[0099] Based on the logical gates in the fault tree model and combined with the fault probabilities, evaluate the risk level of each fault path and determine the potential fault paths.

[0100] A potential fault path refers to a fault chain formed by connecting the faults of each component through logical relationships, which may lead to the failure of the wind turbine system.

[0101] The determination of the potential fault paths includes combining the fault probabilities of each component through the logical gates in the fault tree analysis model to obtain the overall fault probability of the wind turbine.

[0102] When using an AND gate, the probability of the overall failure of the wind turbine is the product of the fault probabilities of each sub-component; when using an OR gate, the probability of the overall failure of the wind turbine is the weighted sum of the fault probabilities of each sub-component; when using a NOT gate, calculate the probability that the component does not fail.

[0103] Through the combination of logical gates, evaluate the fault probability of each fault path and conduct risk level classification. If the fault probability is greater than the preset threshold, it is judged as a high-risk path; if the fault probability is less than or equal to the preset threshold, it is judged as a low-risk path.

[0104] A path refers to a fault chain in the wind turbine composed of multiple components and the fault propagation relationships between them (such as components connected by logical gates). Each path consists of a series of components and their fault probabilities, and may form more complex paths through the combination of logical gates such as AND gates and OR gates.

[0105] A high-risk path refers to a fault path of the wind turbine obtained through the combination of different logical gates (such as AND gates and OR gates) in the fault tree model, whose fault probability is greater than the preset threshold, meaning that these paths may lead to major failures or shutdowns of the wind turbine.

[0106] The fault tree model of the wind turbine determines the fault propagation relationships between components through engineering analysis. Define the fault modes of each component and their mutual relationships with other components according to the wind turbine system structure. These relationships include: which components are critical components and must fail simultaneously to cause the overall failure of the wind turbine, and use an AND gate. Which components are redundant or backup, and the failure of any one of them will cause the overall failure of the wind turbine, and use an OR gate. Which components' normal operation is redundant, and the system can continue to operate as long as there are redundant components, and use a NOT gate.

[0107] The AND gate is represented as

[0108] ,

[0109] where represents the total fault probability of the fault path, Indicates each component that makes up the fault path The probability of failure

[0110] The OR gate is represented as

[0111] ,

[0112] Wherein Represents the total failure probability of the fault path Indicates each component that makes up the fault path The probability of failure

[0113] The NOT gate is represented as

[0114] ,

[0115] Wherein Represents the probability that component Does not fail Represents component The probability of failure

[0116] The fault diagnosis described above includes inputting the characteristic data of the high-risk path into a machine learning model for training. The training uses historical fault data and combines the fault probability information of each high-risk path. The historical fault data is used to learn the fault modes of the wind turbine generator set; during the training process, feature selection is performed by evaluating the correlation between each feature and the fault probability, and redundant features are removed; the model is optimized through cross-validation and hyperparameter tuning methods;

[0117] The machine learning model is trained through a supervised learning method. The model learns the fault modes and path characteristics in the historical data. After the model training is completed, the characteristic data of the current high-risk path is input, and each path is diagnosed, and the fault type, fault component, and location of the fault component of each path are output.

[0118] The execution of the repair plan includes generating a repair plan according to the fault type, fault component, and location of the fault component output by the machine learning model. The repair plan includes repair steps, required tools, personnel arrangements, and time scheduling. The repair order and urgency in the repair plan are optimized based on the priority of the fault component.

[0119] Embodiment 2, an embodiment of the present invention, provides a rotational speed monitoring and testing system, including:

[0120] A data acquisition module, a fault diagnosis module, and a fault repair module;

[0121] The data acquisition module is used to acquire the wind turbine data and the historical data of the wind turbine data, and preprocess the acquired wind turbine data;

[0122] The fault diagnosis module is used to perform speed monitoring verification based on fault tree analysis, train a machine learning model in combination with historical data, and perform fault diagnosis by using the speed monitoring verification result;

[0123] The fault repair module is used to automatically generate a repair plan based on the fault diagnosis result, execute the repair plan, and restore the normal working state of the wind turbine.

[0124] Embodiment 3, an embodiment of the present invention, which is different from the previous two embodiments in that:

[0125] If the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0126] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0127] More specific examples (nonexhaustive list) of computer-readable media include the following: electrical connections (electronic devices) having one or more wirings, portable computer disk cartridges (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0128] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0129] Embodiment 4, an embodiment of the present invention, provides a method for analyzing the operating state of a wind turbine based on rotational speed monitoring. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0130] The experiment uses 10 wind turbines. The operating state and fault data of each wind turbine are collected in real time by a wind turbine monitoring system, including data such as wind speed, rotational speed, voltage, current, ambient temperature, vibration speed, load, etc. Each wind turbine has different types of potential faults, and each fault path is labeled through empirical rules and historical data. The experiment is divided into two parts. The first part uses traditional wind turbine fault diagnosis methods, and the second part uses the multifunctional method for analyzing the operating state of a wind turbine based on rotational speed monitoring of the present invention.

[0131] In the experiments of traditional methods, the collected data of each wind turbine generator set is first preprocessed by standardization and analyzed according to the traditional fault tree model. In the fault tree model, the risk assessment of the fault path is only based on the rules set by experience, and the identification of high-risk paths is carried out using simple threshold judgments. The fault probabilities of each component of each wind turbine generator set are combined through logic gates to obtain the overall fault probability. For each path, if the fault probability exceeds the preset threshold, it is judged as a high-risk path; if it is lower than the threshold, it is a low-risk path. Finally, based on the high-risk paths, corresponding repair plans are generated. The generation of the repair plan depends on preset rules, usually based on the fault type and the severity of the component, and general repair steps are adopted.

[0132] In the experiments of the method of the present invention, first, the collected data of the wind turbine generator set is denoised, missing value filled, and standardized. Then, four features in the present invention are used to extract features of the wind turbine generator set. Based on these features, a multi-dimensional Gaussian model is combined for modeling, the fault probability of each component is calculated, and the covariance matrix is used to describe the mutual relationship between the features. Through the probability density function of the multi-dimensional Gaussian distribution, the fault probability of each feature combination is obtained, and then the overall fault probability of the wind turbine generator set is calculated. Then, the high-risk paths are evaluated through the logic gates in the fault tree analysis model. Different from the traditional method, the method of the present invention uses the probability obtained by combining multi-dimensional features and fault tree analysis to accurately identify potential high-risk paths. Finally, based on the data of the high-risk paths, the machine learning model is trained to optimize the repair plan. The repair plan is automatically generated, considering the location of the faulty component, repair steps, required tools, and personnel arrangement, and the repair order and urgency are intelligently adjusted according to historical data. The experimental results are shown in Table 1.

[0133] Table 1 Comparison table of experimental results

[0134] ,

[0135] First, in terms of the accuracy of fault diagnosis, the present invention uses a multi-dimensional Gaussian model to model multiple features (load index, power factor, mechanical stress coefficient, and environmental impact coefficient) of the wind turbine generator set. Traditional methods often make fault judgments based on simplified empirical rules or single features, ignoring the complex correlations between features and reacting slowly to changes in the operating environment of the wind turbine generator set. In contrast, the present invention considers the covariance relationship between each feature through the multi-dimensional Gaussian model, can comprehensively integrate the operating state of the wind turbine generator set and environmental impacts, thereby improving the accuracy of fault diagnosis. Specifically, the multi-dimensional Gaussian distribution calculates the fault probability of the feature combination through the probability density function. This refined modeling method enables the fault type and location of the wind turbine generator set to be more accurately identified, avoiding the phenomenon of missed diagnosis or misdiagnosis in traditional methods.

[0136] Secondly, in terms of the accuracy of risk assessment, the present invention combines a multi-dimensional Gaussian model and fault tree analysis to comprehensively calculate the failure probabilities of various components and then conduct risk assessment. Traditional methods generally use simple logic gates (such as AND gates, OR gates, etc.) for combining failure probabilities, but this method cannot accurately consider the correlations between components and the complexity of the failure chain. In contrast, the present invention can more accurately evaluate the risks of each failure path by combining a fault tree model with a multi-dimensional Gaussian distribution. Specifically, the failure probabilities calculated based on the covariance matrix between various features can more realistically reflect the chain reaction of failure occurrence, thereby more accurately determining which components or paths are of high risk and which are of low risk. Through this accurate risk assessment, the present invention can effectively identify potential high-risk paths, reducing the problem in traditional methods that the risks of failure paths cannot be comprehensively evaluated.

[0137] Finally, in terms of optimizing the repair plan, the present invention automatically learns historical failure data through a machine learning model and trains it in combination with the feature data of high-risk paths, thereby generating an intelligent repair plan. The generation of repair plans in traditional methods usually relies on manual experience or simple rules, which are prone to problems of inefficiency and inaccuracy. However, the present invention optimizes the repair sequence and urgency according to the characteristics and historical data of the failure paths of the wind turbine generator set through a machine learning model, making the repair plan more accurate and efficient. Specifically, the machine learning model can not only determine the type and location of the failure, but also dynamically adjust the details of the repair plan according to the current operating state and historical failure data of the wind turbine generator set, thereby improving the accuracy and efficiency of the repair, and reducing the repair time and cost.

[0138] Generally speaking, by adopting a multi-dimensional Gaussian model and machine learning optimization techniques, the present invention can fully consider the complex interactions between various components of the wind turbine generator set and intelligently generate an optimized repair plan. These technical features have greatly improved the accuracy of fault diagnosis, risk assessment, and repair plan generation for wind turbine generator sets, solving the problems of missed diagnosis, misdiagnosis, and inefficient repair plans existing in traditional methods, thereby providing a more reliable guarantee for the reliability and safety of wind turbine generator sets.

[0139] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring, characterized in that: include: Collect wind turbine data and historical data of wind turbine data, and pre-process the collected wind turbine data; Speed ​​monitoring verification is performed based on fault tree analysis, and the machine learning model is trained with historical data, and fault diagnosis is performed using the speed monitoring verification results; Automatically generate a repair plan based on the fault diagnosis results, execute the repair plan, and restore the normal working state of the wind turbine; Before speed monitoring verification based on fault tree analysis, the preprocessed data is used to extract wind turbine characteristics; The wind turbine characteristics include load index, power factor, mechanical stress coefficient and environmental impact coefficient; The load index is expressed as, ， ， ， ， in, represents the load index, Indicates the actual power output, Indicates the maximum power, represents the power factor, represents the air density, is the atmospheric pressure, is the gas constant, It is the temperature It represents the wind swept area of ​​the wind turbine. is the blade radius of the wind turbine, Indicates wind speed; The power factor is expressed as, ， ， ， in, Indicates the power factor, Indicates the actual power, Indicates voltage, represents the current, represents the phase angle between current and voltage, Indicates apparent power; The mechanical stress coefficient is expressed as, ， in, represents the mechanical stress coefficient, Indicates the current speed of the wind turbine. Indicates the maximum speed of the wind turbine. Indicates the vibration speed of the wind turbine. Indicates the maximum allowable vibration speed of the wind turbine; The environmental impact coefficient is expressed as, ， in, represents the environmental impact coefficient, Indicates the current wind speed. Indicates the rated wind speed of the wind turbine. Indicates the current ambient temperature.

2. The method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to claim 1, characterized in that: The wind turbine data includes wind turbine operation status data, environmental data and electrical system data; The preprocessing includes denoising, filling missing values ​​and standardizing the data.

3. The method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to claim 2, characterized in that: The speed monitoring verification includes using a multi-dimensional Gaussian model to model the characteristics of the wind turbine generator set, and obtaining the failure probability of each component through the probability density function of the multi-dimensional Gaussian distribution combined with the covariance matrix.

4. The method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to claim 3, characterized in that: The failure probability is calculated through the multi-dimensional Gaussian distribution model for each feature combination. Given the feature vector , the probability density function is expressed as, ， ， in, represents the mean vector, represents the probability of failure, Represents the dimension of the feature, Represents the covariance matrix The determinant of Represents the covariance matrix The inverse matrix of represents the deviation of each feature from its mean, represents the transpose operation, represents the exponential function, represents the mean value of the load index, represents the mean value of the power factor, represents the mean value of the mechanical stress coefficient, represents the mean value of environmental impact coefficient; Based on the logic gates in the fault tree model and the failure probability, the risk level of each fault path is evaluated and the potential fault paths are determined.

5. The method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to claim 4, characterized in that: Determining the potential fault path includes combining the fault probabilities of the various components through logic gates in the fault tree analysis model to obtain the overall fault probability of the wind turbine; When the AND gate is used, the probability of overall failure of the wind turbine is the product of the failure probabilities of each subcomponent; when the OR gate is used, the probability of overall failure of the wind turbine is the weighted sum of the failure probabilities of each subcomponent; when the NOT gate is used, the probability of no failure of the component is calculated; Through the combination of logic gates, the failure probability of each fault path is evaluated and classified into risk levels. If the failure probability is greater than the preset threshold, it is judged as a high-risk path; If the failure probability is less than or equal to the preset threshold, it is judged as a low-risk path.

6. The method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to claim 5, characterized in that: The fault diagnosis includes inputting the characteristic data of the high-risk path into the machine learning model for training, the training uses historical fault data and combines the fault probability information of each high-risk path, and the historical fault data is used to learn the fault mode of the wind turbine; during the training process, by evaluating the correlation between each feature and the fault probability, feature selection is performed to remove redundant features; the model is optimized by cross-validation and hyperparameter tuning methods; The machine learning model is trained using a supervised learning method. The model learns the failure modes and path characteristics in historical data. When the model training is completed, the characteristic data of the current high-risk path is input, each path is diagnosed, and the fault type, faulty component and location of the faulty component of each path are output.

7. The method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to claim 6, characterized in that: The execution of the repair plan includes generating a repair plan based on the fault type, faulty component and location of the faulty component output by the machine learning model. The repair plan includes repair steps, required tools, personnel arrangements and time scheduling. The repair order and urgency in the repair plan are optimized based on the priority of the faulty component.

8. A system using the wind turbine operating status analysis method based on speed monitoring as described in any one of claims 1 to 7, characterized in that: include: Data acquisition module, fault diagnosis module and fault repair module; The data acquisition module is used to collect wind turbine data and historical data of wind turbine data, and pre-process the collected wind turbine data; The fault diagnosis module is used to perform speed monitoring verification based on fault tree analysis, train a machine learning model in combination with historical data, and perform fault diagnosis using the speed monitoring verification results; The fault repair module is used to automatically generate a repair plan based on the fault diagnosis result, execute the repair plan, and restore the normal working state of the wind turbine generator set.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for analyzing the operating status of a wind turbine set based on rotational speed monitoring according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for analyzing the operating status of a wind turbine generator system based on rotation speed monitoring according to any one of claims 1 to 7 are implemented.

Images