Control method and device for variable pitch system of offshore wind turbine generator

Abstract

The invention provides a control method and device for a variable pitch system of an offshore wind turbine generator, and relates to the technical field of offshore power generation. The method comprises the following steps: acquiring real-time related data corresponding to an offshore wind turbine generator, wherein the real-time related data at least comprises wind speed data, wind direction data and pitch angle data; processing the real-time related data to obtain a control instruction of a variable pitch system of the offshore wind turbine generator; the control instruction is sent to a driving unit corresponding to the variable pitch system; and blade variable-pitch control is executed on the variable-pitch system based on the driving unit. According to the method, the pitch angle is adjusted by collecting data in real time and combining with the control algorithm, so that the fan can keep optimal power output when running at different wind speeds and wind directions, and the power generation efficiency of the fan is improved; the precise control of the variable pitch system can effectively avoid the overload or overspeed of the fan.

Description

Technical Field

[0001] The present application relates to the field of offshore power generation technology, and in particular to a control method and device for a variable pitch system of an offshore wind turbine. Background Art

[0002] As the global demand for renewable energy increases, offshore wind power has developed rapidly as an important form of clean energy. Offshore wind turbines are usually deployed in complex marine environments and face many challenges such as large wind speed changes, rough waves, and difficult offshore equipment maintenance. In this context, the performance and reliability requirements of wind turbines are becoming increasingly higher, especially the design and operation of variable pitch systems.

[0003] The pitch system is the core component of the wind turbine, responsible for adjusting the angle of the wind turbine blades to optimize the wind energy conversion efficiency and ensure the safe operation of the unit at different wind speeds. The pitch system can effectively control the speed and power output of the unit by adjusting the windward angle of the blades in real time, thereby improving power generation efficiency, preventing overload, and reducing the risk of failure. Since offshore wind turbines are in harsh marine environments for a long time, the pitch system must have a high degree of precision control capability and reliability. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, one purpose of the present application is to propose a control method for a variable pitch system of an offshore wind turbine, comprising: collecting real-time relevant data corresponding to the offshore wind turbine, the real-time relevant data including at least wind speed data, wind direction data and pitch angle data; processing the real-time relevant data to obtain control instructions for the variable pitch system of the offshore wind turbine; sending the control instructions to a drive unit corresponding to the variable pitch system; and performing blade pitch control on the variable pitch system based on the drive unit.

[0006] The second objective of the present application is to provide a control device for a variable pitch system of an offshore wind turbine.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first aspect of the embodiment of the present application proposes a control method for a pitch control system of an offshore wind turbine, including: collecting real-time relevant data corresponding to the offshore wind turbine, the real-time relevant data at least including wind speed data, wind direction data and pitch angle data; processing the real-time relevant data to obtain control instructions for the pitch control system of the offshore wind turbine; sending the control instructions to the drive unit corresponding to the pitch control system; and performing blade pitch control on the pitch control system based on the drive unit.

[0011] According to an embodiment of the present application, real-time relevant data is processed to obtain control instructions for a variable pitch system of an offshore wind turbine, including: inputting the real-time relevant data into a target control model to obtain control instructions output by the target control model.

[0012] According to one embodiment of the present application, the target control model is generated based on a control algorithm, and the control algorithm is any one of a neural network algorithm, a fuzzy control algorithm, a genetic algorithm, and a particle swarm algorithm.

[0013] According to one embodiment of the present application, a training method for a target control model includes: obtaining a first training sample set, each first training sample in the first training sample set includes historical relevant data of an offshore wind turbine and historical control instructions corresponding to a pitch system under the historical relevant data; iteratively training a control model to be trained based on the first training sample set to obtain a target control model.

[0014] According to one embodiment of the present application, the control method of the variable pitch system of an offshore wind turbine also includes: inputting real-time relevant data into a target abnormality detection model to obtain a first abnormality identification result of the offshore wind turbine; comparing the real-time relevant data with a critical threshold corresponding to the real-time relevant data to obtain a second abnormality identification result of the offshore wind turbine; and generating a target abnormality identification result of the offshore wind turbine based on the first abnormality identification result and the second abnormality identification result.

[0015] According to one embodiment of the present application, a training method for a target anomaly detection model includes: obtaining a second training sample set, each second training sample in the second training sample set including historical relevant data of an offshore wind turbine and historical fault information of an offshore wind turbine; iteratively training an anomaly detection model to be trained based on the second training sample set to obtain a target anomaly detection model.

[0016] To achieve the above-mentioned purpose, the second aspect of the present application proposes a control device for a pitch control system of an offshore wind turbine, comprising: an acquisition module, used to collect real-time relevant data corresponding to the offshore wind turbine, the real-time relevant data including at least wind speed data, wind direction data and pitch angle data; a processing module, used to process the real-time relevant data and obtain control instructions for the pitch control system of the offshore wind turbine; a sending module, used to send the control instructions to the drive unit corresponding to the pitch control system; and a control module, used to perform blade pitch control on the pitch control system based on the drive unit.

[0017] According to one embodiment of the present application, the processing module is further used to: input the real-time related data into the target control model, and obtain the control instructions output by the target control model.

[0018] According to one embodiment of the present application, the target control model is generated based on a control algorithm, and the control algorithm is any one of a neural network algorithm, a fuzzy control algorithm, a genetic algorithm, and a particle swarm algorithm.

[0019] According to one embodiment of the present application, the control device of the variable pitch system of an offshore wind turbine also includes a first training module, which is used to: obtain a first training sample set, each first training sample in the first training sample set includes historical relevant data of the offshore wind turbine and historical control instructions corresponding to the variable pitch system under the historical relevant data; iteratively train the control model to be trained based on the first training sample set to obtain a target control model.

[0020] According to one embodiment of the present application, the control device of the variable pitch system of an offshore wind turbine also includes an abnormality detection module, which is used to: input real-time relevant data into a target abnormality detection model to obtain a first abnormality identification result of the offshore wind turbine; compare the real-time relevant data with a critical threshold corresponding to the real-time relevant data to obtain a second abnormality identification result of the offshore wind turbine; and generate a target abnormality identification result of the offshore wind turbine based on the first abnormality identification result and the second abnormality identification result.

[0021] According to one embodiment of the present application, the control device of the offshore wind turbine variable pitch system also includes a second training module, which is used to: obtain a second training sample set, each second training sample in the second training sample set includes historical relevant data of the offshore wind turbine and historical fault information of the offshore wind turbine; iteratively train the anomaly detection model to be trained based on the second training sample set to obtain a target anomaly detection model.

[0022] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes 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, and the instructions are executed by the at least one processor to implement the control method of the variable pitch system of an offshore wind turbine as described in the first aspect embodiment of the present application.

[0023] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the control method of the offshore wind turbine variable pitch system as described in the first aspect embodiment of the present application.

[0024] To achieve the above-mentioned purpose, the fifth aspect embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the control method of the offshore wind turbine variable pitch system as described in the first aspect embodiment of the present application.

[0025] The present application achieves at least the following beneficial effects: the present application collects data in real time and adjusts the pitch angle in combination with a control algorithm, so that the wind turbine can maintain optimal power output when operating at different wind speeds and wind directions, thereby improving the power generation efficiency of the wind turbine; precise control of the variable pitch system can effectively avoid wind turbine overload or overspeed, especially in extreme weather conditions (such as strong winds or gusts), and the wind turbine load can be reduced by adjusting the pitch angle to reduce the risk of equipment damage; control instructions can prevent frequent wear and tear of blades and variable pitch systems, reduce the probability of failures, and extend the service life of wind turbines; the pitch angle is adjusted according to real-time data such as wind speed and wind direction, so that the wind turbine can capture wind energy more efficiently and avoid energy waste due to excessively high or low wind speeds. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1 It is a schematic diagram of an exemplary implementation of a control method for a variable pitch system of an offshore wind turbine set shown in an embodiment of the present application.

[0028] Figure 2 It is a schematic diagram of an exemplary implementation of a control method for a variable pitch system of an offshore wind turbine set shown in an embodiment of the present application.

[0029] Figure 3 It is a schematic diagram of an exemplary implementation of a control method for a variable pitch system of an offshore wind turbine set shown in an embodiment of the present application.

[0030] Figure 4It is a schematic diagram of a control device for a variable pitch system of an offshore wind turbine shown in one embodiment of the present application.

[0031] Figure 5 It is a schematic diagram of an electronic device shown in one embodiment of the present application. DETAILED DESCRIPTION

[0032] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0033] Figure 1 is a schematic diagram of an exemplary implementation of a control method for a variable pitch system of an offshore wind turbine generator system shown in the present application, such as Figure 1 As shown, a control method for a variable pitch system of an offshore wind turbine generator system comprises the following steps:

[0034] S101, collecting real-time relevant data corresponding to the offshore wind turbine, where the real-time relevant data at least includes wind speed data, wind direction data and pitch angle data.

[0035] Among them, wind speed is one of the most important indicators of wind turbine operation, which affects the power output of the generator and the pitch angle of the blades. Therefore, wind speed data needs to be obtained in this application.

[0036] Among them, wind direction data helps to determine the blade orientation of the wind turbine and the pitch control strategy, so it is necessary to obtain wind direction data in this application.

[0037] Among them, the pitch angle is the relative angle between the wind turbine blades and the wind.

[0038] S102, processing the real-time relevant data to obtain control instructions for the variable pitch system of the offshore wind turbine.

[0039] Since data such as wind speed and wind direction may be affected by environmental noise or equipment errors, preprocessing steps such as filtering and denoising are required to ensure the accuracy of the data.

[0040] By establishing mathematical models and control algorithms, the relationship between the current wind speed, wind direction and pitch angle is analyzed. Based on the data analysis results, corresponding control instructions are generated.

[0041] The control command is adjustment data based on the current pitch angle, for example, increasing the pitch angle or decreasing the pitch angle.

[0042] S103, sending the control instruction to the drive unit corresponding to the pitch control system.

[0043] Among them, the drive unit is an important component of the variable pitch system, responsible for receiving control instructions and performing related operations.

[0044] S104, performing blade pitch control on the pitch system based on the drive unit.

[0045] After receiving the control command, the drive unit will adjust the action of the pitch system according to the command, thereby changing the pitch angle of the wind turbine blades. The pitch system usually includes hydraulic or electric actuators, and the drive unit adjusts the blade angle through these actuators.

[0046] The embodiment of the present application proposes a control method for a variable pitch system of an offshore wind turbine, comprising: collecting real-time relevant data corresponding to the offshore wind turbine, the real-time relevant data at least including wind speed data, wind direction data and pitch angle data; processing the real-time relevant data to obtain a control instruction for the variable pitch system of the offshore wind turbine; sending the control instruction to the drive unit corresponding to the variable pitch system; and performing blade variable pitch control on the variable pitch system based on the drive unit. The present application can maintain the best power output when the wind turbine is running at different wind speeds and wind directions by collecting data in real time and adjusting the pitch angle in combination with a control algorithm, thereby improving the power generation efficiency of the wind turbine; the precise control of the variable pitch system can effectively avoid overloading or overspeeding of the wind turbine, especially under extreme weather conditions (such as strong winds or gusts), and the load of the wind turbine can be reduced by adjusting the pitch angle to reduce the risk of equipment damage; the control instruction can prevent frequent loss of blades and variable pitch systems, reduce the probability of failure, and extend the service life of the wind turbine; the pitch angle is adjusted according to real-time data such as wind speed and wind direction, so that the wind turbine can capture wind energy more efficiently and avoid energy waste caused by excessively high or low wind speeds.

[0047] Figure 2 is a schematic diagram of an exemplary implementation of a control method for a variable pitch system of an offshore wind turbine generator system shown in the present application, such as Figure 2 As shown, a control method for a variable pitch system of an offshore wind turbine generator system comprises the following steps:

[0048] S201, collecting real-time relevant data corresponding to the offshore wind turbine generator set, where the real-time relevant data at least includes wind speed data, wind direction data and pitch angle data.

[0049] S202, inputting the real-time related data into the target control model, and obtaining the control instructions output by the target control model.

[0050] The target control model is generated based on a control algorithm, and the control algorithm is any one of a neural network algorithm, a fuzzy control algorithm, a genetic algorithm and a particle swarm algorithm.

[0051] Among them, the training method of the target control model includes: obtaining a first training sample set, each first training sample in the first training sample set includes historical relevant data of the offshore wind turbine and historical control instructions corresponding to the variable pitch system under the historical relevant data; based on the first training sample set, iteratively training the control model to be trained to obtain the target control model.

[0052] S203: Send the control instruction to the drive unit corresponding to the pitch control system.

[0053] S204, performing blade pitch control on the pitch system based on the drive unit.

[0054] The embodiment of the present application collects data in real time and adjusts the pitch angle in combination with a control algorithm, so that the wind turbine can maintain optimal power output when operating at different wind speeds and wind directions, thereby improving the power generation efficiency of the wind turbine; precise control of the variable pitch system can effectively avoid wind turbine overload or overspeed, especially in extreme weather conditions (such as strong winds or gusts), and the wind turbine load can be reduced by adjusting the pitch angle to reduce the risk of equipment damage; control instructions can prevent frequent wear and tear of blades and variable pitch systems, reduce the probability of failures, and extend the service life of wind turbines; the pitch angle is adjusted according to real-time data such as wind speed and wind direction, so that the wind turbine can capture wind energy more efficiently and avoid energy waste due to excessively high or low wind speeds.

[0055] Figure 3 is a schematic diagram of an exemplary implementation of a control method for a variable pitch system of an offshore wind turbine generator system shown in the present application, such as Figure 3 As shown, a control method for a variable pitch system of an offshore wind turbine generator system comprises the following steps:

[0056] S301, collecting real-time relevant data corresponding to the offshore wind turbine, where the real-time relevant data at least includes wind speed data, wind direction data and pitch angle data.

[0057] S302, inputting the real-time related data into the target control model, and obtaining the control instructions output by the target control model.

[0058] S303: Send the control instruction to the drive unit corresponding to the pitch control system.

[0059] S304, performing blade pitch control on the pitch system based on the drive unit.

[0060] Regarding the specific implementation of steps S301 to S304, reference may be made to the specific introduction of the relevant parts in the above embodiments, which will not be elaborated here.

[0061] S305, inputting the real-time related data into a target anomaly detection model to obtain a first anomaly recognition result of the offshore wind turbine.

[0062] The training method of the target anomaly detection model includes: obtaining a second training sample set, each second training sample in the second training sample set includes historical relevant data of an offshore wind turbine and historical fault information of an offshore wind turbine; iteratively training an anomaly detection model to be trained based on the second training sample set to obtain a target anomaly detection model.

[0063] Optionally, the target anomaly detection model can select a model based on machine learning or deep learning algorithms (e.g., support vector machine (SVM), decision tree, neural network, etc.). The target anomaly detection model is trained with a large amount of historical relevant data and historical fault information, and can learn the difference between normal operation mode and abnormal mode. During the training process, the target anomaly detection model learns the distribution pattern of the data, the relationship between the features, and various potential fault modes.

[0064] S306: Compare the real-time related data with a critical threshold corresponding to the real-time related data to obtain a second abnormality identification result of the offshore wind turbine.

[0065] Among them, the critical threshold is usually a predetermined value set based on experience, historical data or industry standards. For example, the wind speed range of the wind turbine, the maximum and minimum values ​​of the pitch angle, the safe operating range of current and voltage, etc. Exceeding these critical values ​​may indicate that the equipment is abnormal.

[0066] The relevant data collected in real time is compared with the corresponding critical thresholds. For example, if the wind speed exceeds the safe range, or the pitch angle changes beyond the set limit, these will be regarded as potential abnormal signals, the corresponding data will be marked as abnormal, and the second abnormality identification result will be output.

[0067] S307: Generate a target abnormality recognition result for the offshore wind turbine according to the first abnormality recognition result and the second abnormality recognition result.

[0068] Optionally, if both the first abnormality identification result and the second abnormality identification result indicate abnormality, the offshore wind turbine is judged to be operating abnormally, and a serious alarm signal is issued. The offshore wind turbine may also automatically take measures (such as shutting down, adjusting operating parameters, etc.).

[0069] Optionally, if one of the first abnormality identification result and the second abnormality identification result indicates an abnormality and the other does not indicate an abnormality, a low-level alarm signal is triggered to remind maintenance personnel to intervene.

[0070] Optionally, if both the first abnormality identification result and the second abnormality identification result indicate normal, it is determined that the offshore wind turbine is operating normally.

[0071] The embodiments of the present application can evaluate the operating status of a wind turbine from multiple perspectives by combining an anomaly detection model based on machine learning and a traditional threshold-based method. The first method focuses on model self-learning to identify potential complex abnormal patterns, while the second method uses physical or empirical thresholds to identify direct and significant anomalies. This multi-dimensional anomaly detection method can improve the accuracy and comprehensiveness of anomaly identification. Through real-time anomaly detection and analysis, rapid feedback can be provided when a wind turbine fails or its performance degrades, helping operation and maintenance personnel to discover problems in advance and avoid economic losses caused by wind turbine shutdowns or reduced operating efficiency.

[0072] Figure 4 is a schematic diagram of a control device for a variable pitch system of an offshore wind turbine set shown in the present application, such as Figure 4 As shown, the control device 400 of the offshore wind turbine variable pitch system includes a collection module 401, a processing module 402, a sending module 403 and a control module 404, wherein:

[0073] The acquisition module 401 is used to acquire real-time relevant data corresponding to the offshore wind turbines, and the real-time relevant data at least includes wind speed data, wind direction data and pitch angle data.

[0074] The processing module 402 is used to process the real-time related data and obtain the control instructions of the variable pitch system of the offshore wind turbine.

[0075] The sending module 403 is used to send the control instruction to the drive unit corresponding to the pitch system.

[0076] The control module 404 is configured to perform blade pitch control on the pitch system based on the drive unit.

[0077] This device collects data in real time and adjusts the pitch angle in combination with a control algorithm, so that the wind turbine can maintain optimal power output when operating at different wind speeds and wind directions, thereby improving the power generation efficiency of the wind turbine; the precise control of the variable pitch system can effectively avoid wind turbine overload or overspeed, especially in extreme weather conditions (such as strong winds or gusts), and the wind turbine load can be reduced by adjusting the pitch angle to reduce the risk of equipment damage; control instructions can prevent frequent wear and tear of blades and variable pitch systems, reduce the probability of failure, and extend the service life of wind turbines; the pitch angle is adjusted according to real-time data such as wind speed and wind direction, so that the wind turbine can capture wind energy more efficiently and avoid energy waste caused by excessively high or low wind speeds.

[0078] Furthermore, the processing module 402 is also used to: input the real-time related data into the target control model, and obtain the control instructions output by the target control model.

[0079] Furthermore, the target control model is constructed and generated based on a control algorithm, and the control algorithm is any one of a neural network algorithm, a fuzzy control algorithm, a genetic algorithm and a particle swarm algorithm.

[0080] Furthermore, the control device 400 of the variable pitch system of the offshore wind turbine also includes a first training module, which is used to: obtain a first training sample set, each first training sample in the first training sample set includes historical relevant data of the offshore wind turbine and historical control instructions corresponding to the variable pitch system under the historical relevant data; iteratively train the control model to be trained based on the first training sample set to obtain a target control model.

[0081] Furthermore, the control device 400 of the offshore wind turbine variable pitch system also includes an abnormality detection module, which is used to: input real-time related data into a target abnormality detection model to obtain a first abnormality identification result of the offshore wind turbine; compare the real-time related data with a critical threshold corresponding to the real-time related data to obtain a second abnormality identification result of the offshore wind turbine; and generate a target abnormality identification result of the offshore wind turbine based on the first abnormality identification result and the second abnormality identification result.

[0082] Furthermore, the control device 400 of the offshore wind turbine variable pitch system also includes a second training module, which is used to: obtain a second training sample set, each second training sample in the second training sample set includes historical relevant data of the offshore wind turbine and historical fault information of the offshore wind turbine; iteratively train the anomaly detection model to be trained based on the second training sample set to obtain a target anomaly detection model.

[0083] In order to implement the above embodiment, the present application embodiment also proposes an electronic device 500, such as Figure 5 As shown, the electronic device 500 includes: a processor 501 and a memory 502 that is communicatively connected to the processor, the memory 502 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 501 to implement the control method of the offshore wind turbine variable pitch system as shown in the above embodiment.

[0084] In order to implement the above embodiments, the embodiments of the present application also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to implement the control method of the offshore wind turbine variable pitch system as shown in the above embodiments.

[0085] In order to implement the above embodiments, the embodiments of the present application also propose a computer program product, including a computer program, which, when executed by a processor, implements the control method of the offshore wind turbine variable pitch system as shown in the above embodiments.

[0086] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0087] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0088] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0089] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A control method for a variable pitch system of an offshore wind turbine, characterized in that: include: Collecting real-time relevant data corresponding to the offshore wind turbine, wherein the real-time relevant data at least includes wind speed data, wind direction data and pitch angle data; Processing the real-time relevant data to obtain control instructions for the variable pitch system of the offshore wind turbine; Sending the control instruction to the drive unit corresponding to the pitch system; The blade pitch control is performed on the pitch system based on the drive unit.

2. The method according to claim 1, characterized in that The processing of the real-time related data to obtain control instructions for the variable pitch system of the offshore wind turbine generator system includes: The real-time related data is input into a target control model to obtain a control instruction output by the target control model.

3. The method according to claim 2, characterized in that The target control model is generated based on a control algorithm, and the control algorithm is any one of a neural network algorithm, a fuzzy control algorithm, a genetic algorithm and a particle swarm algorithm.

4. The method according to claim 3, characterized in that The training method of the target control model comprises: Acquire a first training sample set, wherein each first training sample in the first training sample set includes historical relevant data of the offshore wind turbine generator set and historical control instructions of the variable pitch system corresponding to the historical relevant data; The control model to be trained is iteratively trained based on the first training sample set to obtain a target control model.

5. The method according to claim 4, characterized in that The method further comprises: Inputting the real-time related data into a target anomaly detection model to obtain a first anomaly recognition result of the offshore wind turbine; Comparing the real-time related data with a critical threshold value corresponding to the real-time related data to obtain a second abnormality identification result of the offshore wind turbine generator set; A target abnormality identification result of the offshore wind turbine group is generated according to the first abnormality identification result and the second abnormality identification result.

6. The method according to claim 5, characterized in that The training method of the target anomaly detection model includes: Acquire a second training sample set, wherein each second training sample in the second training sample set includes historical relevant data of the offshore wind turbine generator set and historical fault information of the offshore wind turbine generator set; The anomaly detection model to be trained is iteratively trained based on the second training sample set to obtain a target anomaly detection model.

7. A control device for a variable pitch system of an offshore wind turbine, characterized in that: include: A collection module, used to collect real-time relevant data corresponding to the offshore wind turbine, wherein the real-time relevant data at least includes wind speed data, wind direction data and pitch angle data; A processing module, used to process the real-time related data and obtain control instructions for the variable pitch system of the offshore wind turbine; A sending module, used for sending the control instruction to a drive unit corresponding to the pitch system; A control module is used to perform blade pitch control on the pitch system based on the drive unit.

8. 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images