A method for detecting a fault of a converter of an offshore wind turbine and a device therefor
By using data-driven fault prediction of offshore wind turbine converters to generate maintenance plans, the problems of resource waste and untimely detection of potential faults in traditional maintenance methods are solved, thus achieving stable equipment operation and cost optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUANENG CLEAN ENERGY RES INST
- Filing Date
- 2024-12-30
- Publication Date
- 2026-06-05
Smart Images
Figure CN119778193B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of offshore power generation technology, and in particular to a fault detection method and apparatus for an offshore wind turbine converter. Background Technology
[0002] Offshore wind power, as an important renewable energy source, relies heavily on converters in its power systems. Converters are the core equipment connecting wind turbines to the power grid, responsible for converting the direct current (DC) generated by the wind turbines into alternating current (AC) suitable for grid use. With the continuous development and maturation of offshore wind power technology, the scale of wind turbine units is increasing, placing higher demands on the performance and stability of converters. The reliable operation of converters directly affects the power generation efficiency of the wind power system and the stability of the power grid; therefore, the maintenance and management of converters are particularly important.
[0003] However, as offshore wind power projects expand in scale, converter maintenance costs account for a significant proportion of total operating costs. Traditional maintenance methods mainly include scheduled maintenance and post-failure maintenance. Scheduled maintenance typically involves routine inspections and upkeep of the converter based on preset time intervals or operating times. While this method can ensure the basic normal operation of the equipment to a certain extent, it suffers from problems such as a mismatch between maintenance frequency and actual needs, resource waste, and the inability to adjust maintenance plans according to the equipment's health condition. Post-failure maintenance, on the other hand, repairs the converter when it fails. Although it can effectively address equipment failures, the losses are more severe because the equipment can no longer operate normally after a failure. Furthermore, this method cannot detect potential failure risks in a timely manner, resulting in longer equipment downtime and higher repair costs. Summary of the Invention
[0004] This application aims to at least partially address one of the technical problems in the related art.
[0005] Therefore, one objective of this application is to propose a fault detection method for offshore wind turbine converters, comprising: acquiring operating data of the offshore wind turbine converter, the operating data including at least temperature data, current data, vibration data, and voltage data; inputting the operating data into a trained anomaly identification model, performing time-series analysis through the anomaly identification model, and obtaining fault prediction parameters output by the anomaly identification model, the fault prediction parameters including predicted fault type and predicted fault time; and generating a maintenance plan for the offshore wind turbine converter based on the fault prediction parameters.
[0006] The second objective of this application is to provide a fault detection device for offshore wind turbine converters.
[0007] The third objective of this application is to propose an electronic device.
[0008] The fourth objective of this application is to provide a non-transitory computer-readable storage medium.
[0009] The fifth objective of this application is to provide a computer program product.
[0010] To achieve the above objectives, the first aspect of this application proposes a fault detection method for an offshore wind turbine converter, comprising: acquiring operating data of the offshore wind turbine converter, the operating data including at least temperature data, current data, vibration data, and voltage data; inputting the operating data into a trained anomaly identification model, performing time-series analysis through the anomaly identification model, and acquiring fault prediction parameters output by the anomaly identification model, the fault prediction parameters including predicted fault type and predicted fault time; and generating a maintenance plan for the offshore wind turbine converter based on the fault prediction parameters.
[0011] According to one embodiment of this application, the fault detection method for offshore wind turbine converters further includes: generating fault alarm information based on fault prediction parameters; and sending the fault alarm information and maintenance plan to the terminal equipment corresponding to the maintenance personnel.
[0012] According to one embodiment of this application, obtaining operating data of an offshore wind turbine converter includes: obtaining operating data of the offshore wind turbine converter via wireless communication, wherein the operating data is collected by relevant sensors installed on the offshore wind turbine converter.
[0013] According to one embodiment of this application, a training method for an anomaly recognition model includes: acquiring a training sample set, wherein each training sample in the training sample set includes historical operating data of the offshore wind turbine converter within a preset time window and historical fault information of the offshore wind turbine converter, wherein the historical fault information includes historical fault type and historical fault time; and training the anomaly recognition model to be trained based on the training sample set to obtain a trained anomaly recognition model.
[0014] According to one embodiment of this application, the anomaly detection model is generated based on a machine learning algorithm.
[0015] To achieve the above objectives, a second aspect of this application proposes a fault detection device for an offshore wind turbine converter, comprising: an acquisition module for acquiring operating data of the offshore wind turbine converter, the operating data including at least temperature data, current data, vibration data, and voltage data; a prediction module for inputting the operating data into a trained anomaly identification model, performing time-series analysis through the anomaly identification model, and acquiring fault prediction parameters output by the anomaly identification model, the fault prediction parameters including predicted fault type and predicted fault time; and a generation module for generating a maintenance plan for the offshore wind turbine converter based on the fault prediction parameters.
[0016] According to one embodiment of this application, the generation module is further configured to: generate fault alarm information based on fault prediction parameters; and send the fault alarm information and maintenance plan to the terminal device corresponding to the maintenance personnel.
[0017] According to one embodiment of this application, the acquisition module is further configured to: acquire operating data of the offshore wind turbine converter via wireless communication, wherein the operating data is collected by relevant sensors installed on the offshore wind turbine converter.
[0018] According to one embodiment of this application, the fault detection device for offshore wind turbine converters further includes a training module for acquiring a training sample set. Each training sample in the training sample set includes historical operating data of the offshore wind turbine converter within a preset time window and historical fault information of the offshore wind turbine converter. The historical fault information includes historical fault type and historical fault time. The anomaly recognition model to be trained is trained based on the training sample set to obtain a trained anomaly recognition model.
[0019] According to one embodiment of this application, the anomaly detection model is generated based on a machine learning algorithm.
[0020] To achieve the above objectives, a third aspect of this application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to implement the fault detection method for offshore wind turbine converters as described in the first aspect of this application.
[0021] To achieve the above objectives, a fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the fault detection method for offshore wind turbine converters as described in the first aspect of this application.
[0022] To achieve the above objectives, a fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the fault detection method for offshore wind turbine converters as described in the first aspect of this application.
[0023] This application achieves at least the following beneficial effects: By using an anomaly identification model, this application can accurately predict the faults of wind turbine converters based on historical and real-time data, thereby avoiding the occurrence of sudden faults; traditional wind turbine converter maintenance often relies on periodic inspections or human judgment, while data-driven solutions can improve the accuracy of fault early warning, thereby reducing unplanned downtime; through real-time monitoring and fault prediction of offshore wind turbine converters, the operational risks of the equipment can be effectively reduced, ensuring long-term stable operation of the equipment; by predicting faults in advance, the costs of emergency repairs and equipment replacements are reduced, while production interruptions caused by equipment failures can be avoided, increasing the availability of wind turbines. Attached Figure Description
[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:
[0025] Figure 1 This is an exemplary schematic diagram illustrating a fault detection method for an offshore wind turbine converter, as shown in one embodiment of this application.
[0026] Figure 2 This is a schematic diagram of a fault detection device for an offshore wind turbine converter, as shown in one embodiment of this application.
[0027] Figure 3 This is a schematic diagram of an electronic device according to one embodiment of this application. Detailed Implementation
[0028] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0029] Figure 1 This is an exemplary schematic diagram of a fault detection method for an offshore wind turbine converter shown in this application, such as... Figure 1 As shown, the fault detection method for the converter of this offshore wind turbine includes the following steps:
[0030] S101, acquire the operating data of the offshore wind turbine converter, including at least temperature data, current data, vibration data and voltage data.
[0031] Preferably, the operating data of the offshore wind turbine converter is acquired through wireless communication, and the operating data is collected by relevant sensors installed on the offshore wind turbine converter.
[0032] Optionally, operating data of the offshore wind turbine converter can be obtained via a relevant data transmission cable.
[0033] S102, input the running data into the trained anomaly identification model, perform time series analysis through the anomaly identification model, and obtain the fault prediction parameters output by the anomaly identification model. The fault prediction parameters include the predicted fault type and the predicted fault time.
[0034] Among them, the predicted fault type refers to what type of fault is predicted (e.g., overheating, short circuit, abnormal vibration, etc.).
[0035] The predicted failure time refers to the expected time period or critical point during which a failure is expected to occur.
[0036] Among them, the fault prediction parameters output by the anomaly identification model can identify potential faults in advance, thus avoiding sudden equipment shutdowns or large-scale equipment damage.
[0037] The training method for the anomaly identification model includes: acquiring a training sample set, where each training sample in the training sample set includes historical operating data of the offshore wind turbine converter within a preset time window and historical fault information of the offshore wind turbine converter, including historical fault type and historical fault time; training the anomaly identification model to be trained based on the training sample set to obtain the trained anomaly identification model.
[0038] The anomaly detection model is built and generated based on machine learning algorithms (such as neural networks, support vector machines, decision trees, etc.).
[0039] S103, Generate maintenance plans for offshore wind turbine converters based on fault prediction parameters.
[0040] The maintenance plan can be understood as follows: based on the predicted fault types and predicted fault times, the necessary maintenance resources, personnel scheduling and spare parts preparation can be arranged in advance, thereby optimizing maintenance work.
[0041] This application proposes a fault detection method for offshore wind turbine converters, comprising: acquiring operating data of the offshore wind turbine converter, including at least temperature data, current data, vibration data, and voltage data; inputting the operating data into a trained anomaly identification model, performing time-series analysis through the anomaly identification model, and obtaining fault prediction parameters output by the anomaly identification model, including predicted fault type and predicted fault time; and generating a maintenance plan for the offshore wind turbine converter based on the fault prediction parameters. This application, by using an anomaly identification model, can accurately predict faults in wind turbine converters based on historical and real-time data, thereby avoiding sudden faults. Traditional wind turbine converter maintenance often relies on periodic inspections or human judgment, while a data-driven approach can improve the accuracy of fault early warning, thereby reducing unplanned downtime. Real-time monitoring and fault prediction of offshore wind turbine converters can effectively reduce equipment operating risks and ensure long-term stable operation. Early fault prediction reduces the cost of emergency repairs and equipment replacement, while also avoiding production interruptions caused by equipment failures, increasing the availability of wind turbines.
[0042] Furthermore, fault alarm information is generated based on fault prediction parameters; the fault alarm information and maintenance plan are sent to the terminal devices (such as mobile terminals, tablets, smartphones, or dedicated terminals) of maintenance personnel. By generating fault alarms in real time and sending them to the terminal devices of maintenance personnel, the operation and maintenance team can be notified immediately. In this way, when a potential fault occurs in the wind turbine converter, maintenance personnel can respond immediately, preventing the fault from developing into a more serious situation. This can effectively reduce equipment downtime and reduce production capacity loss caused by equipment failure.
[0043] Alarm information can also be conveyed to maintenance personnel through instant messaging (such as SMS, APP notifications, emails, etc.), sound alerts, or visual interfaces.
[0044] The maintenance plan may include detailed inspection items for the converter, repair steps, spare parts requirements, technical requirements, and scheduled maintenance time.
[0045] Figure 2 This is a schematic diagram of a fault detection device for an offshore wind turbine converter shown in this application, as follows: Figure 2 As shown, the fault detection device 200 for the offshore wind turbine converter includes: an acquisition module 201, a prediction module 202, and a generation module 203, wherein:
[0046] The acquisition module 201 is used to acquire the operating data of the offshore wind turbine converter. The operating data includes at least temperature data, current data, vibration data and voltage data.
[0047] The prediction module 202 is used to input the running data into the trained anomaly identification model, perform time series analysis through the anomaly identification model, and obtain the fault prediction parameters output by the anomaly identification model. The fault prediction parameters include the predicted fault type and the predicted fault time.
[0048] The generation module 203 is used to generate a maintenance plan for the offshore wind turbine converter based on fault prediction parameters.
[0049] This device, through the use of anomaly identification models, can accurately predict faults in wind turbine converters based on historical and real-time data, thereby avoiding sudden failures. Traditional wind turbine converter maintenance often relies on periodic inspections or human judgment, while data-driven solutions can improve the accuracy of fault early warning, thereby reducing unplanned downtime. By monitoring and predicting faults in offshore wind turbine converters in real time, operational risks can be effectively reduced, ensuring long-term stable operation of the equipment. By predicting faults in advance, the costs of emergency repairs and equipment replacements are reduced, while production interruptions caused by equipment failures can be avoided, increasing the availability of wind turbines.
[0050] Furthermore, the generation module 203 is also used to: generate fault alarm information based on fault prediction parameters; and send the fault alarm information and maintenance plan to the terminal equipment corresponding to the maintenance personnel.
[0051] Furthermore, the acquisition module 201 is also used to: acquire the operating data of the offshore wind turbine converter based on wireless communication, wherein the operating data is collected by relevant sensors installed on the offshore wind turbine converter.
[0052] Furthermore, the fault detection device 200 for offshore wind turbine converters also includes a training module for acquiring a training sample set. Each training sample in the training sample set includes historical operating data of the offshore wind turbine converter within a preset time window and historical fault information of the offshore wind turbine converter. The historical fault information includes historical fault type and historical fault time. Based on the training sample set, the anomaly recognition model to be trained is trained to obtain a trained anomaly recognition model.
[0053] Furthermore, the anomaly detection model is built and generated based on machine learning algorithms.
[0054] To implement the above embodiments, this application also proposes an electronic device 300, such as... Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 communicatively connected to the processor. The memory 302 stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor 301 to implement the fault detection method for offshore wind turbine converters as shown in the above embodiment.
[0055] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to implement the fault detection method for offshore wind turbine converters as shown in the above embodiments.
[0056] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the fault detection method for offshore wind turbine converters as shown in the above embodiments.
[0057] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application 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 this application.
[0058] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.
[0059] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0060] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.
Claims
1. A fault detection method for an offshore wind turbine converter, characterized in that, include: Obtain operating data of the offshore wind turbine converter, wherein the operating data includes at least temperature data, current data, vibration data and voltage data; The operational data is input into the trained anomaly identification model, and time-series analysis is performed through the anomaly identification model to obtain fault prediction parameters output by the anomaly identification model. The fault prediction parameters include predicted fault type and predicted fault time. The training method of the anomaly identification model includes: obtaining a training sample set, wherein each training sample in the training sample set includes historical operational data of the offshore wind turbine converter within a preset time window and historical fault information of the offshore wind turbine converter, wherein the historical fault information includes historical fault type and historical fault time; and training the anomaly identification model to be trained based on the training sample set to obtain a trained anomaly identification model. A maintenance plan for the offshore wind turbine converter is generated based on the fault prediction parameters. The method further includes: Fault alarm information is generated based on the fault prediction parameters; The fault alarm information and the maintenance plan are sent to the terminal device corresponding to the maintenance personnel.
2. The method according to claim 1, characterized in that, The acquisition of operating data from offshore wind turbine converters includes: The operating data of the offshore wind turbine converter is acquired via wireless communication, and the operating data is collected by relevant sensors installed on the offshore wind turbine converter.
3. The method according to claim 1, characterized in that, The anomaly detection model is built and generated based on machine learning algorithms.
4. A fault detection device for an offshore wind turbine converter, characterized in that, include: The acquisition module is used to acquire the operating data of the offshore wind turbine converter, and the operating data includes at least temperature data, current data, vibration data and voltage data; The prediction module is used to input the operating data into a trained anomaly identification model, perform time-series analysis through the anomaly identification model, and obtain fault prediction parameters output by the anomaly identification model. The fault prediction parameters include the predicted fault type and the predicted fault time. The training method of the anomaly identification model includes: obtaining a training sample set, wherein each training sample in the training sample set includes historical operating data of the offshore wind turbine converter within a preset time window and historical fault information of the offshore wind turbine converter, wherein the historical fault information includes historical fault type and historical fault time; and training the anomaly identification model to be trained based on the training sample set to obtain a trained anomaly identification model. The generation module is used to generate a maintenance plan for the offshore wind turbine converter based on the fault prediction parameters, and is also used to: generate fault alarm information based on the fault prediction parameters; and send the fault alarm information and the maintenance plan to the terminal equipment corresponding to the maintenance personnel.
5. An electronic device, comprising: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.
6. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.
7. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-3.