Intelligent health diagnosis method for offshore wind turbine generator equipment and related device

Abstract

The invention discloses an intelligent health diagnosis method for offshore wind turbine generator equipment and a related device, and belongs to the technical field of wind turbine generators. The method comprises the steps of obtaining multi-dimensional data of offshore wind turbine generator operation; performing feature extraction on the multi-dimensional data through a least square method to obtain feature data; inputting the feature data into a trained wind turbine generator health early warning model to obtain a predicted value; and finally, calculating a health coefficient according to the predicted value and giving out early warning. The unit fault is represented through the health coefficient, and the greater the health coefficient is, the more serious the fault is. Faults are identified according to the early warning signals, the operation state of the unit can be controlled in time, the management efficiency and management level of the wind turbine unit are improved, and the purposes of improving the wind resource utilization rate, improving the power generation capacity, improving the production management efficiency, reducing the electricity loss, innovating the management mode and comprehensively improving the economic benefits are achieved.

Description

Technical Field

[0001] This invention belongs to the field of wind turbine technology and relates to a method and related device for intelligent health diagnosis of offshore wind turbine equipment. Background Technology

[0002] The current trend of offshore wind turbines is towards larger single-unit capacity, larger rotor diameter, and deeper installation water depth. In addition, the marine environment in which offshore wind turbines are located is complex and changeable, with high humidity, high salt spray, and long hours of sunshine in the atmospheric zone, frequent dry and wet transitions in the splash zone, and prolonged immersion in seawater and severe attachment of aquatic organisms in the underwater zone. All of these factors pose serious challenges to the long-term safe and stable operation of offshore wind power equipment.

[0003] Fault diagnosis and predictive control are crucial aspects of offshore wind farm operation and maintenance. They ensure the normal operation of wind turbine generators, improve power generation efficiency, and reduce maintenance costs. Accurate fault diagnosis allows for the timely detection and assessment of abnormal operating conditions of power generation equipment, reducing downtime caused by faults and improving the reliability and utilization rate of offshore wind farms. Condition monitoring technology, through real-time online monitoring of equipment operating status and health, can detect signs of faults before they occur, thus reducing the probability of actual failures. This facilitates the development of preventative maintenance mechanisms, improves equipment operational reliability, and reduces downtime and maintenance costs due to equipment failures.

[0004] Current methods for fault diagnosis of offshore wind turbines are primarily offline, meaning fault diagnosis generally occurs after a fault has occurred or during routine maintenance. This results in a significant lag in fault detection and diagnosis, further increasing maintenance costs. Due to the harsh offshore operating environment, real-time fault diagnosis is crucial for offshore wind turbines. Consequently, fault early warning is receiving increasing attention. Effective fault early warning can provide warnings before faults occur and allow for preventative measures.

[0005] Offshore wind turbines' built-in SCADA (Supervisory Control and Data Acquisition) systems record dozens of operating parameters collected by various sensors. However, while existing fault diagnosis studies consider the correlation between these parameters, they only retain input parameters above a set correlation threshold. This threshold setting relies on expert experience, introducing significant subjectivity. Furthermore, retaining only a subset of input parameters leads to the loss of parameter correlation information, resulting in reduced accuracy in normal behavior modeling. The selection of input parameters for fault diagnosis and early warning models suffers from subjective limitations, heavily relying on experience. Moreover, the sampling of early fault samples for fault diagnosis and early warning is insufficient, affecting prediction accuracy. Summary of the Invention

[0006] This invention provides a method and related device for intelligent health diagnosis of offshore wind turbine equipment, in order to solve the technical problem that insufficient input parameters for model prediction in the prior art affect the prediction accuracy.

[0007] To achieve the above objectives, the present invention employs the following technical solution:

[0008] In a first aspect, the present invention provides a method for intelligent health diagnosis of offshore wind turbine equipment, comprising the following steps:

[0009] Acquire multidimensional data on the operation of offshore wind turbines;

[0010] Feature data is obtained by extracting features from the multidimensional data using the least squares method.

[0011] The feature data is input into the trained wind turbine health early warning model to obtain the predicted value;

[0012] A health coefficient is calculated based on the predicted values, and an early warning is issued.

[0013] Furthermore, the multidimensional data includes SCADA data, unit status parameters, and environmental parameters.

[0014] Furthermore, the SCADA data includes wind conditions, power, current, and operating conditions.

[0015] Furthermore, the unit's status parameters include vibration, temperature, load, strain, sway, and settlement.

[0016] Furthermore, the environmental parameters include wind speed, wind direction, wave height, wave direction, and seabed topography.

[0017] Furthermore, the wind turbine health early warning model is an early warning model based on a Gaussian mixture model.

[0018] Furthermore, the step of calculating the health coefficient based on the predicted value and issuing an early warning specifically includes:

[0019] The deviation between the predicted value and the preset threshold is calculated to obtain the health coefficient;

[0020] If the health coefficient is 0, it means that the wind turbine is operating normally; if the health coefficient is >0, it means that the wind turbine is malfunctioning and an early warning will be issued.

[0021] Secondly, the present invention provides an intelligent health diagnosis system for offshore wind turbine equipment, characterized in that it includes:

[0022] The data acquisition module is used to acquire multi-dimensional data on the operation of offshore wind turbines;

[0023] The feature extraction module is used to extract features from the multidimensional data using the least squares method to obtain feature data;

[0024] The prediction module is used to input the feature data into the trained wind turbine health early warning model to obtain the predicted value;

[0025] The early warning module is used to calculate the health coefficient based on the predicted value and issue an early warning.

[0026] Thirdly, the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0027] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described above.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] This invention discloses an intelligent health diagnosis method and related device for offshore wind turbine equipment. Based on the operational characteristics of different components of the wind turbine, it extracts characteristic parameters such as time-domain, frequency-domain, and nonlinear time-frequency-domain signals of different types, fuses multi-dimensional data, and performs feature extraction using the least squares method. These features are then input into an early warning model to obtain predicted values. Furthermore, this invention characterizes turbine faults using a health coefficient; a higher health coefficient indicates a more severe fault. Identifying faults based on early warning signals allows for timely control of the turbine's operating status, ensuring normal operation of the wind turbine, improving power generation efficiency, and reducing maintenance costs. Accurate fault diagnosis enables timely detection and assessment of abnormal operating conditions of the power generation equipment, reducing downtime caused by faults and improving the reliability and utilization rate of offshore wind farms. This facilitates the development of preventative maintenance mechanisms, improves equipment operational reliability, and reduces downtime and maintenance costs due to equipment failures. Accurately identifying the type and location of power generation equipment faults provides timely maintenance guidance and decision-making for maintenance personnel, reducing unnecessary on-site maintenance frequency and costs. Therefore, this invention can improve the management efficiency and level of wind turbine units, thereby achieving the goals of increasing wind resource utilization, increasing power generation capacity, improving production management efficiency, reducing power loss, and comprehensively improving economic benefits through innovative management models. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a flowchart of a method for intelligent health diagnosis of offshore wind turbine equipment according to the present invention;

[0032] Figure 2 This is a schematic diagram of a smart health diagnosis system for offshore wind turbine equipment according to the present invention.

[0033] Figure 3 This is a multi-dimensional data fusion diagram according to an embodiment of the present invention;

[0034] Figure 4 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0036] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0037] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0038] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0039] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0040] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0041] The present invention will now be described in further detail with reference to the accompanying drawings:

[0042] See Figure 1 This invention discloses an intelligent health diagnosis method for offshore wind turbine equipment, comprising the following steps:

[0043] S1, acquire multi-dimensional data on the operation of offshore wind turbines;

[0044] S2, feature data is obtained by extracting features from the multidimensional data using the least squares method;

[0045] S3, input the feature data into the trained wind turbine health early warning model to obtain the predicted value;

[0046] S4 calculates the health coefficient based on the predicted value and issues an early warning.

[0047] Based on association rules and feature data early warning models of SCADA data, this invention can detect potential faults in wind turbines in advance and monitor catastrophic failures before accidents occur, thus preventing losses caused by emergency shutdowns.

[0048] In one feasible embodiment of the present invention, see [link to relevant documentation]. Figure 3 The multidimensional data includes SCADA data, unit status parameters, and environmental parameters. SCADA data includes, but is not limited to, wind conditions, power, current, and operating conditions. Unit status parameters include, but are not limited to, vibration, temperature, load, strain, sloshing, and settlement. Environmental parameters include, but are not limited to, wind speed, wind direction, wave height, wave direction, and seabed topography.

[0049] In one feasible embodiment of the present invention, the wind turbine health early warning model is an early warning model based on a Gaussian Mixture Model. A Gaussian Mixture Model (GMM) is a widely used clustering algorithm that uses a Gaussian distribution as its parametric model and is trained using the Expectation Maximization (EM) algorithm. This model uses a Gaussian probability density function (normal distribution curve) to quantify phenomena, decomposing phenomena into several models based on this function.

[0050] In one feasible embodiment of the present invention, the step of calculating the health coefficient based on the predicted value and issuing an early warning specifically includes:

[0051] S401, calculate the deviation between the predicted value and the preset threshold to obtain the health coefficient;

[0052] S402, if the health coefficient = 0, it means that the wind turbine is operating normally; if the health coefficient > 0, it means that the wind turbine is malfunctioning and an early warning will be issued.

[0053] It should be noted that the higher the health coefficient, the more serious the malfunction.

[0054] See Figure 2 This invention discloses an intelligent health diagnosis system for offshore wind turbine equipment, comprising: a data acquisition module, a feature extraction module, a prediction module, and an early warning module.

[0055] The data acquisition module is used to acquire multi-dimensional data such as SCADA data, unit status parameters, and environmental parameters of the offshore wind turbine operation; the feature extraction module is used to extract features from the multi-dimensional data using the least squares method to obtain feature data; the prediction module is used to input the feature data into a trained wind turbine health early warning model to obtain predicted values; the early warning module is used to calculate the deviation between the predicted values ​​and a preset threshold to obtain a health coefficient; if the health coefficient = 0, it indicates that the wind turbine is operating normally; if the health coefficient > 0, it indicates that the wind turbine is malfunctioning, and an early warning is issued.

[0056] See Figure 4This invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the intelligent health diagnosis method for offshore wind turbine equipment as described above.

[0057] It should be noted that the aforementioned intelligent health diagnosis method for offshore wind turbine equipment specifically includes the following steps:

[0058] S1, acquire multi-dimensional data on the operation of offshore wind turbines;

[0059] S2, feature data is obtained by extracting features from the multidimensional data using the least squares method;

[0060] S3, input the feature data into the trained wind turbine health early warning model to obtain the predicted value;

[0061] S4 calculates the health coefficient based on the predicted value and issues an early warning.

[0062] This invention discloses a computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the intelligent health diagnosis method for offshore wind turbine equipment.

[0063] It should be noted that the aforementioned intelligent health diagnosis method for offshore wind turbine equipment specifically includes the following steps:

[0064] S1, acquire multi-dimensional data on the operation of offshore wind turbines;

[0065] S2, feature data is obtained by extracting features from the multidimensional data using the least squares method;

[0066] S3, input the feature data into the trained wind turbine health early warning model to obtain the predicted value;

[0067] S4 calculates the health coefficient based on the predicted value and issues an early warning.

[0068] This invention extracts characteristic parameters from different types of signals in the time domain, frequency domain, and nonlinear time-frequency domain based on the operational characteristics of different components of wind turbines. It integrates multi-dimensional data and performs feature extraction using the least squares method, then inputs these parameters into an early warning model to obtain predicted values. Furthermore, this invention characterizes turbine faults using a health coefficient; a higher health coefficient indicates a more severe fault. By identifying faults based on early warning signals, the operating status of the turbine can be controlled in a timely manner, improving wind turbine management efficiency and level. This ultimately aims to increase wind resource utilization, enhance power generation capacity, improve production management efficiency, reduce power loss, and comprehensively improve economic benefits through innovative management models.

[0069] This invention's condition monitoring technology enables real-time online detection of equipment operating status and health, allowing for the discovery of signs of malfunctions before actual failures occur, thus reducing the probability of failures. This facilitates the development of preventative maintenance mechanisms, improves equipment reliability, and reduces downtime and maintenance costs due to equipment failures. Because offshore wind farms are located far from shore, each on-site maintenance requires the deployment of dedicated maintenance vessels or helicopters, which is costly and highly susceptible to weather and sea conditions. Therefore, the application of fault diagnosis technology can accurately determine the type and location of faults in the power generation equipment, providing timely maintenance guidance and decision-making for maintenance personnel, reducing unnecessary on-site maintenance frequency and costs. Wind turbine generators consist of two major integrated systems: mechanical and electrical, involving multiple complex components and systems. A failure in any component or system may affect the normal operation of the entire wind turbine generator and could even lead to safety accidents. Therefore, the application of fault diagnosis technology can promptly identify and address potential safety hazards, ensuring the safe operation of wind turbine generators. Furthermore, this invention can guarantee the normal operation of wind turbine generators, improve power generation efficiency, and reduce operation and maintenance costs. Accurate fault diagnosis can promptly detect and assess abnormal operating conditions of power generation equipment, reduce power plant downtime caused by faults, and improve the power generation reliability and utilization rate of offshore wind farms.

[0070] In the field of equipment health diagnostics, Gaussian mixture models can be applied in various ways, including, but not limited to, cluster analysis of equipment operating status data to identify normal operating conditions, abnormal conditions, and potential failure modes. This cluster analysis helps to promptly detect abnormal equipment behavior, predict potential failures, and thus provide decision support for equipment maintenance and repair.

[0071] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0072] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0073] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent health diagnosis of offshore wind turbine equipment, characterized in that, Includes the following steps: Acquire multidimensional data on the operation of offshore wind turbines; Feature data is obtained by extracting features from the multidimensional data using the least squares method. The feature data is input into the trained wind turbine health early warning model to obtain the predicted value; A health coefficient is calculated based on the predicted values, and an early warning is issued.

2. The intelligent health diagnosis method for offshore wind turbine equipment according to claim 1, characterized in that, The multidimensional data includes SCADA data, unit status parameters, and environmental parameters.

3. The intelligent health diagnosis method for offshore wind turbine equipment according to claim 2, characterized in that, The SCADA data includes wind conditions, power, current, and operating conditions.

4. The intelligent health diagnosis method for offshore wind turbine equipment according to claim 2, characterized in that, The unit's status parameters include vibration, temperature, load, strain, sway, and settlement.

5. The intelligent health diagnosis method for offshore wind turbine equipment according to claim 2, characterized in that, The environmental parameters include wind speed, wind direction, wave height, wave direction, and seabed topography.

6. The intelligent health diagnosis method for offshore wind turbine equipment according to claim 1, characterized in that, The wind turbine health early warning model is an early warning model based on a Gaussian mixture model.

7. The intelligent health diagnosis method for offshore wind turbine equipment according to claim 1, characterized in that, The step of calculating the health coefficient based on the predicted value and issuing an early warning specifically includes: The deviation between the predicted value and the preset threshold is calculated to obtain the health coefficient; If the health coefficient is 0, it means that the wind turbine is operating normally; if the health coefficient is >0, it means that the wind turbine is malfunctioning and an early warning will be issued.

8. A smart health diagnostic system for offshore wind turbine equipment, characterized in that, include: The data acquisition module is used to acquire multi-dimensional data on the operation of offshore wind turbines; The feature extraction module is used to extract features from the multidimensional data using the least squares method to obtain feature data; The prediction module is used to input the feature data into the trained wind turbine health early warning model to obtain the predicted value; The early warning module is used to calculate the health coefficient based on the predicted value and issue an early warning.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images