Monitoring method and monitoring system of wind turbine generator and wind turbine generator

Abstract

The invention provides a monitoring method and a monitoring system for a wind turbine generator and the wind turbine generator. The monitoring method comprises the following steps: acquiring monitoring data of a monitoring object in a marine environment where the wind turbine generator is located; determining the current state of the monitoring object based on the monitoring data; according to the current state of the monitored object, carrying out early warning on the load of the monitored object, and determining a current unit control strategy corresponding to the current state of the monitored object; obtaining vibration data of the wind turbine generator after the current unit control strategy is executed; and according to the vibration data, updating a unit control strategy of the wind turbine unit so as to control the wind turbine unit based on the updated unit control strategy. According to the monitoring method and monitoring system of the wind turbine generator and the wind turbine generator, the problems that in an offshore load coping scheme, a physical structure is high in cost, difficult to maintain and poor in vibration suppression effect are solved, active control can be used for replacing traditional structure passive load resistance, and load vibration generated by an offshore object is avoided or relieved in advance.

Description

Technical Field

[0001] The present disclosure relates to the field of wind power generation, and more specifically, to a monitoring method and a monitoring system for a wind turbine generator set, and a wind turbine generator set. Background Art

[0002] For offshore wind turbines, offshore objects such as sea ice, waves, and scouring may generate loads on the supporting structure of the turbine. Taking sea ice as an example, when a wind turbine is in an ice area, sea ice may act on the supporting structure of the turbine, causing severe ice-induced vibrations in the structure, endangering the safety and stability of the offshore wind turbine and its supporting structure. Therefore, the loads generated by offshore objects such as sea ice become the controlling loads of the offshore wind turbine supporting structure.

[0003] In the relevant technology, such offshore loads are usually dealt with by changing the physical structure of the wind turbine or the supporting structure. However, in these solutions, on the one hand, the load vibration problem cannot be avoided, but the impact of load vibration is reduced as much as possible by adding physical support structures after the load vibration occurs, which may result in poor vibration suppression effect; on the other hand, adding physical support structures will bring different degrees of construction work and structural costs. In addition, the processing, anti-corrosion and post-maintenance of the physical structure have their own problems, which may make the physical structure unable to meet the load response requirements of the unit throughout the entire cycle. Summary of the invention

[0004] In view of the problems of high physical structure cost, difficult maintenance and poor vibration suppression effect in existing offshore load response solutions, the present disclosure provides a monitoring method and a monitoring system for a wind turbine generator set, and a wind turbine generator set.

[0005] A first aspect of the present disclosure provides a monitoring method for a wind turbine group, the monitoring method comprising: acquiring monitoring data of a monitoring object in an offshore environment where the wind turbine group is located, wherein the monitoring object is an offshore object that can generate a load on a supporting structure of the wind turbine group; determining a current state of the monitoring object based on the monitoring data; issuing an early warning for the load of the monitoring object according to the current state of the monitoring object, and determining a current unit control strategy corresponding to the current state of the monitoring object; acquiring vibration data of the wind turbine group after executing the current unit control strategy; and updating the unit control strategy of the wind turbine group according to the vibration data, so as to control the wind turbine group based on the updated unit control strategy.

[0006] Optionally, the monitoring data includes marine video data containing the monitored object acquired by a video capture device, wherein the current state of the monitored object is determined by: inputting the marine video data into a pre-trained machine vision analysis model, identifying the marine video data by the machine vision analysis model, and obtaining the current state of the monitored object.

[0007] Optionally, the monitoring data includes monitoring data obtained by monitoring the monitoring object through an environmental monitoring device, wherein the current state of the monitoring object is determined by extracting the current state of the monitoring object from the monitoring data.

[0008] Optionally, the current state of the monitored object is represented by an object state parameter, wherein the step of determining a current unit control strategy corresponding to the current state of the monitored object based on the current state of the monitored object includes: based on a parameter range satisfied by the object state parameter, selecting a unit control strategy corresponding to the parameter range from a plurality of preset unit control strategies as the current unit control strategy.

[0009] Optionally, when the monitored object includes sea ice, the object state parameters include at least one of sea ice thickness data, sea ice speed data, sea ice direction data and sea ice coverage; and / or, when the monitored object includes waves, the object state parameters include at least one of wave height, wave length, wave direction and wave period; and / or, when the monitored object includes seabed scour, the object state parameters include scour depth.

[0010] Optionally, the step of updating the unit control strategy of the wind turbine set according to the vibration data includes: in response to the vibration data satisfying a preset vibration condition, combining the current unit control strategy with at least one other unit control strategy as an updated unit control strategy, wherein the preset vibration condition indicates that the vibration data exceeds the design safety boundary of the wind turbine set.

[0011] Optionally, the monitoring method also includes: in response to the current state of the monitored object satisfying a preset state condition, executing the step of determining a current unit control strategy corresponding to the current state of the monitored object; in response to the current state of the monitored object not satisfying the preset state condition, notifying external measures outside the wind turbine to destroy the current state of the monitored object, wherein the preset state condition indicates that the current state of the monitored object is within the design safety boundary of the wind turbine.

[0012] Optionally, the vibration data of the wind turbine group includes vibration data at different heights on the tower of the wind turbine group, wherein the vibration data includes at least one of vibration velocity, vibration acceleration and vibration displacement, wherein the wind turbine group is a wind turbine group at the edge of a wind farm, wherein the unit control strategy is used to increase the damping of the wind turbine group, and the unit control strategy includes at least one of the following items: increasing the damping of the transmission chain of the wind turbine group during the operation of the wind turbine group, controlling the side of the nacelle of the wind turbine group to face the wind when the wind turbine group is in a stopped state, and adjusting the retraction angle of the blades of the wind turbine group when the wind turbine group is in a stopped state.

[0013] A second aspect of the present disclosure provides a monitoring system for a wind turbine, the monitoring system comprising: an object monitoring system for acquiring monitoring data of a monitoring object in an offshore environment where the wind turbine is located, and determining a current state of the monitoring object based on the monitoring data; a unit control system for issuing an early warning for a load of the monitoring object according to the current state of the monitoring object, and determining a current unit control strategy corresponding to the current state of the monitoring object; and a vibration monitoring system for acquiring vibration data of the wind turbine after executing a current unit control strategy, wherein the unit control system is further used to update a unit control strategy for the wind turbine according to the vibration data, so as to control the wind turbine based on the updated unit control strategy.

[0014] Optionally, the object monitoring system includes a video capture device and a pre-trained machine vision analysis model, wherein the video capture device is used to obtain marine video data containing the monitored object, and the machine vision analysis model receives the marine video data, identifies the marine video data, and outputs the current status of the monitored object.

[0015] Optionally, the object monitoring system includes an environment monitoring device, and the environment monitoring device is used to monitor the monitored object to obtain the monitoring data.

[0016] Optionally, the current state of the monitored object is represented by an object state parameter, wherein the unit control system is also used to: select a unit control strategy corresponding to the parameter interval from a plurality of preset unit control strategies according to a parameter interval satisfied by the object state parameter, as the current unit control strategy.

[0017] Optionally, when the monitored object includes sea ice, the object state parameters include at least one of sea ice thickness data, sea ice speed data, sea ice direction data and sea ice coverage; and / or, when the monitored object includes waves, the object state parameters include at least one of wave height, wave length, wave direction and wave period; and / or, when the monitored object includes seabed scour, the object state parameters include scour depth.

[0018] Optionally, the unit control system is further used to: in response to the vibration data satisfying a preset vibration condition, combine the current unit control strategy with at least one other unit control strategy as an updated unit control strategy.

[0019] Optionally, the unit control system is also used to: in response to the current state of the monitored object satisfying a preset state condition, execute the step of determining a current unit control strategy corresponding to the current state of the monitored object; in response to the current state of the monitored object not satisfying the preset state condition, notify external measures outside the wind turbine to destroy the current state of the monitored object, wherein the preset state condition indicates that the current state of the monitored object is within the design safety boundary of the wind turbine.

[0020] Optionally, the vibration data of the wind turbine group includes vibration data at different heights on the tower of the wind turbine group, wherein the vibration data includes at least one of vibration velocity, vibration acceleration and vibration displacement, wherein the wind turbine group is a wind turbine group at the edge of a wind farm, wherein the unit control strategy is used to increase the damping of the wind turbine group, and the unit control strategy includes at least one of the following items: increasing the damping of the transmission chain of the wind turbine group during the operation of the wind turbine group, controlling the side of the nacelle of the wind turbine group to face the wind when the wind turbine group is in a shutdown state, and adjusting the retraction angle of the blades of the wind turbine group when the wind turbine group is in a shutdown state.

[0021] A third aspect of the present disclosure provides a wind turbine group, wherein the wind turbine group includes a monitoring system for the wind turbine group according to an exemplary embodiment of the present disclosure.

[0022] According to the monitoring method, monitoring system and wind turbine of the wind turbine disclosed in the present invention, the current state of the monitoring object can be determined based on the monitoring data of the monitoring object in the offshore environment to determine the unit control strategy corresponding to the current state, so that the load impact that the object may have on the unit can be estimated according to the state of the monitoring object, so as to take the corresponding unit control strategy in time, and the vibration data of the unit can be obtained after taking the unit control strategy, so that the unit control strategy can be updated according to the vibration condition of the unit to further avoid the load vibration caused by the offshore monitoring object. Compared with the scheme of using physical structure to deal with offshore load vibration in the related art, according to the scheme disclosed in the present invention, the unit control strategy can be taken in advance according to the monitoring data of the offshore object, and active control can be used to replace the traditional passive load resistance of the structure to avoid or alleviate the load vibration generated by the offshore object in advance, and the unit control strategy can be updated according to the vibration data of the unit to further suppress the vibration. In addition, the scheme does not need to add physical structure, saving the relevant construction engineering and production maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The diagram is a schematic diagram showing a wind power support structure provided with a flexible upright column foundation according to the related art.

[0024] Figure 2 The diagram is a schematic diagram showing a wind power support structure provided with an anti-ice cone structure according to the related art.

[0025] Figure 3 is a schematic flow chart showing a method for monitoring a wind turbine according to an exemplary embodiment of the present disclosure.

[0026] Figure 4 is a schematic diagram showing the direction of sea ice obtained through monitoring data according to an exemplary embodiment of the present disclosure.

[0027] Figure 5 FIG. 4 is a schematic diagram illustrating acquiring monitoring data through a radar according to an exemplary embodiment of the present disclosure.

[0028] Figure 6 is a schematic diagram illustrating a machine vision analysis model according to an exemplary embodiment of the present disclosure.

[0029] Figure 7 is a schematic architecture diagram showing a method for implementing a monitoring method of a wind turbine generator system according to an exemplary embodiment of the present disclosure.

[0030] Figure 8 is a schematic block diagram showing a monitoring system for a wind turbine according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following specific embodiments are provided to help the reader obtain a comprehensive understanding of the methods, devices and / or systems described herein. However, after understanding the disclosure of the present application, various changes, modifications and equivalents of the methods, devices and / or systems described herein will be clear. For example, the order of operations described herein is only an example and is not limited to those orders set forth herein, but can be changed as will be clear after understanding the disclosure of the present application, except for operations that must occur in a specific order. In addition, for greater clarity and simplicity, the description of features known in the art may be omitted.

[0032] The features described herein can be implemented in different forms and should not be construed as being limited to the examples described herein. Rather, the examples described herein have been provided to illustrate only some of the many possible ways to implement the methods, devices, and / or systems described herein, which will be clear after understanding the disclosure of the present application.

[0033] As used herein, the term "and / or" includes any one of the associated listed items and any combination of any two or more.

[0034] Although terms such as "first", "second", and "third" may be used herein to describe various members, components, regions, layers, or portions, these members, components, regions, layers, or portions should not be limited by these terms. Instead, these terms are only used to distinguish one member, component, region, layer, or portion from another member, component, region, layer, or portion. Therefore, without departing from the teachings of the examples described herein, the first member, first component, first region, first layer, or first portion referred to in the examples may also be referred to as the second member, second component, second region, second layer, or second portion.

[0035] In the specification, when an element (such as a layer, a region, or a substrate) is described as being “on”, “connected to”, or “coupled to” another element, the element may be directly “on”, “connected to”, or “coupled to” another element, or one or more other elements may be present therebetween. Conversely, when an element is described as being “directly on”, “directly connected to”, or “directly coupled to” another element, there may be no other elements present therebetween.

[0036] The terms used herein are only used to describe various examples and are not intended to limit the disclosure. Unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. The terms "comprise", "include" and "have" indicate the presence of the described features, quantities, operations, components, elements and / or combinations thereof, but do not exclude the presence or addition of one or more other features, quantities, operations, components, elements and / or combinations thereof.

[0037] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by a person of ordinary skill in the art to which the present disclosure belongs after understanding the present disclosure. Unless explicitly defined as such herein, terms (such as those defined in a general dictionary) should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and should not be interpreted in an idealized or overly formal manner.

[0038] Furthermore, in the description of examples, when it is considered that a detailed description of a well-known related structure or function would cause vague interpretation of the present disclosure, such a detailed description will be omitted.

[0039] As mentioned above, for offshore wind turbines, the impact of offshore loads is usually dealt with by changing the physical structure of the wind turbine or the supporting structure. However, these physical structure-based response solutions have many problems.

[0040] Here, taking sea ice as an example, there are three main ways to design support structures in sea ice areas. One way is to directly design flexible vertical column foundations (such as Figure 1 As shown in the figure, the influence of ice-induced vibration is fully considered in the structural design, and the stiffness and strength of the foundation itself are relied on to resist the effect of sea ice. Here, ice-induced vibration refers to the structural vibration caused by the impact of sea ice on the structure. Another way is to adopt anti-ice cone structure (such as Figure 2 As shown in the figure, the sea ice crushing mode is changed from extrusion crushing to complete crushing, thereby reducing the sea ice load and avoiding resonance. Here, the anti-ice cone structure is a cone structure, which can be installed near the water surface to change the sea ice crushing mode. In addition, other special anti-ice devices can also be used to destroy the sea ice structure and avoid resonance caused by direct contact between the sea ice and the supporting structure.

[0041] However, there are some shortcomings in these support structure design solutions.

[0042] Specifically, the flexible vertical column foundation solution relies on its own rigidity and strength to directly resist the sea ice load, so it needs to be strengthened compared to the non-sea ice state, resulting in an increase in the amount of engineering work. In addition, this solution does not avoid the problem of ice-induced vibration, and still has an adverse effect on the offshore wind power support structure and the stability of unit operation. Therefore, this solution is only suitable for areas with weak ice conditions, not for areas with severe ice conditions.

[0043] Regarding the solution of using anti-ice cone structure to resist ice, although this solution can effectively solve the problem of sea ice load, the structure increases the diameter of the structure near the water surface, resulting in a significant increase in wave load, which in turn increases the amount of support structure engineering, and the anti-ice cone itself has a large amount of engineering, further increasing the cost of the structure. In addition, in the construction plan, due to the large buoyancy of the anti-ice cone structure, the sinking construction of the anti-ice cone structure in the water during the offshore construction process also brings difficulties to the construction process.

[0044] Although the solution of using other anti-ice devices can reduce the sea ice load to a certain extent, there are certain problems in the processing, manufacturing, corrosion prevention, and sea ice abrasion of the devices, and they cannot meet the anti-ice requirements of offshore wind turbines throughout their life cycle.

[0045] In addition to the sea ice described above, similar problems also exist in existing response plans for marine objects such as sea waves and scours.

[0046] In view of the above problems, a monitoring method for a wind turbine set, a monitoring system for a wind turbine set and a wind turbine set are provided according to exemplary embodiments of the present disclosure to solve or alleviate at least one of the above problems. Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0047] According to a first aspect of the present disclosure, a monitoring method for a wind turbine is provided. The monitoring method may be performed by a monitoring system of the wind turbine, and the monitoring system of the wind turbine may include a device with a computing and analyzing function, and the device may be a terminal device or a server, wherein the terminal device may be a tablet computer, a laptop computer, a digital assistant, etc.; the server may be an independent server, a server cluster, a cloud computing platform, or a virtualization center.

[0048] In an example application scenario, the monitoring system of a wind turbine may include an object monitoring system, a turbine control system, and a vibration monitoring system. The object monitoring system installed at / near the wind turbine may obtain monitoring data of monitoring objects in the offshore environment where the wind turbine is located, wherein the monitoring objects are offshore objects that can generate loads on the supporting structure of the wind turbine.

[0049] The object monitoring system can provide monitoring data to the unit control system of the wind turbine, and the unit control system can determine the current state of the monitored object based on the monitoring data, and determine the current unit control strategy corresponding to the current state of the monitored object according to the current state of the monitored object. Here, the unit control system can be the control system of the wind turbine itself, or it can be a remote control system that is communicatively connected to the control system of the wind turbine itself, such as a control system located on land.

[0050] The vibration monitoring system installed at the wind turbine can obtain the vibration data of the wind turbine after executing the current unit control strategy, and can provide the vibration data to the unit control system of the wind turbine. Thus, the unit control system can update the unit control strategy of the wind turbine according to the vibration data to control the wind turbine based on the updated unit control strategy.

[0051] Here, as an example, the object monitoring system, the unit control system and the vibration monitoring system can all be run on any terminal device such as a server, a portable terminal or a desktop computer terminal, etc. Any two of the object monitoring system, the unit control system and the vibration monitoring system can communicate directly or indirectly through any suitable network, and here, the suitable network can include but is not limited to the Internet, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network such as an optical fiber network and a coaxial cable, and a wireless network such as WIFI, a cellular network and Bluetooth, etc.

[0052] It should be noted that, although the monitoring scheme is mainly described in this article using the sea ice application scenario as an example, the application scenario of the monitoring scheme according to the embodiment of the present disclosure is not limited to this, and it can also be used to deal with application scenarios such as waves and scouring.

[0053] In the above scenario, by using the monitoring method according to the embodiment of the present disclosure, the current state of the monitored object can be determined based on the monitoring data of the monitored object in the offshore environment to determine the unit control strategy corresponding to the current state, so that the load impact that the object may have on the unit can be estimated according to the state of the monitored object, so that the corresponding unit control strategy can be taken in time, and the vibration data of the unit can be obtained after taking the unit control strategy, so that the unit control strategy can be updated according to the vibration condition of the unit to further avoid the load vibration caused by the offshore monitored object. In this way, on the one hand, the load vibration problem caused by the offshore object can be avoided as much as possible, and the unit control strategy can be updated according to the unit vibration data to further suppress the vibration; on the other hand, the solution does not need to add physical structure, saving the relevant construction work and production maintenance costs.

[0054] The following will refer to Figures 3 to 7 A monitoring method for a wind turbine according to a first aspect of an exemplary embodiment of the present disclosure is described in detail. The monitoring method is applicable to various types of offshore wind turbines with different capacities, different technical routes, different impeller diameters, different foundation types, etc.

[0055] like Figure 3 As shown, the monitoring method may include the following steps:

[0056] In step S310, monitoring data of monitoring objects in the offshore environment where the wind turbine is located may be obtained.

[0057] Here, the monitoring object may be an offshore object that can generate a load on the supporting structure of the wind turbine. As an example, the monitoring object may include, but is not limited to, sea ice, waves, scour, etc. Here, the monitoring object may be one or more. For example, according to actual monitoring needs, the monitoring data of sea ice, waves, and scour can be obtained at the same time, and the monitoring data of the three can be processed separately in subsequent steps to adopt corresponding control strategies. The monitoring of the monitoring object can be real-time observation and recording of relevant data of the monitoring object. For example, in sea ice monitoring, key parameters such as sea ice thickness, ice speed, ice direction, and sea ice coverage can be observed and recorded in real time.

[0058] Here, the monitoring object may refer to any object in the offshore environment that can generate loads on the unit support structure. The monitoring object may be a physical substance existing in the offshore environment, such as sea ice; or it may be a physical phenomenon occurring in the offshore environment, such as waves and scouring.

[0059] As an example, the monitoring object may exist for a period of time or for a long time. For example, in some sea areas, sea ice may only appear during the ice period, while in other sea areas, sea ice may always exist around the unit. In this regard, the timing of obtaining monitoring data can be set according to actual conditions. For example, in response to the time entering the ice period, the monitoring data of sea ice can be obtained at a predetermined time interval.

[0060] In addition, in step S310, the monitoring data may be acquired by any suitable method.

[0061] In one example, the monitoring data may include marine video data including the monitoring object acquired by a video capture device.

[0062] Specifically, the state of the monitored object can be photographed by a video capture device to obtain the marine video data of the monitored object, and the current state of the monitored object can be determined based on the marine video data. Here, the video capture device can be, for example, but not limited to, a high-definition camera.

[0063] In addition, as an example, the distance between the video capture device and the monitored object or the sea surface can also be measured by a distance measuring device to obtain distance measurement data, which can be used to assist in analyzing the marine video data, such as analyzing the actual size of the monitored object being photographed. Here, the distance measuring device can be, for example, but not limited to, a millimeter wave radar. However, the embodiments of the present disclosure are not limited thereto, and in some examples, the distance measuring device can also be omitted, for example, the distance between the video capture device and the sea surface can be measured in advance, or the video capture device is a device with a shooting distance mark.

[0064] As an example, offshore video data and / or ranging data can be transmitted to a wind turbine control system via a network cable. The wind turbine control system can be, for example, a local edge computing server of the wind turbine or a remote server on land.

[0065] In addition, the video capture device and / or the distance measuring device may be installed in the main monitoring direction of the wind turbine generator set, for example, and the installation method may be, for example but not limited to, fixed installation on the platform railing of the wind turbine generator set through a bracket.

[0066] Here, the main monitoring direction can be determined, for example, by the historical statistical distribution of the monitoring object in the area where the unit is located. Taking the monitoring object as sea ice as an example, the main monitoring direction can be the main sea ice direction with the highest probability of sea ice appearing. Based on the historical sea ice monitoring data, a sea ice direction rose diagram can be drawn, and the main sea ice direction can be determined from the diagram.

[0067] For example, Figure 4 As shown in the figure, the location of the unit can be used as the center of the circle to count the frequency and speed of sea ice in various directions in the historical sea ice monitoring data. Figure 4 It can be seen that the frequency of sea ice appearing due west of the unit is the highest. Therefore, the due west direction can be used as the main sea ice direction. The video capture device and the ranging device can be installed on the side of the unit facing the main sea ice direction to be able to monitor the sea ice data in this direction.

[0068] Here, although Figure 4 The directions shown include north (N), north-northeast (NNE), northeast (NE), east-northeast (ENE), east (E), east-southeast (ESE), southeast (SE), south-southeast (SSE), south (S), south-southwest (SSW), southwest (SW), west-southwest (WSW), west (W), west-northwest (WNW), northwest (NW), and north-northwest (NNW), but are not limited thereto, and monitoring data from more or fewer directions may also be counted and analyzed.

[0069] In another example, the monitoring data includes monitoring data obtained by monitoring a monitoring object through an environmental monitoring device.

[0070] Specifically, the monitoring object can be directly monitored by an environmental monitoring device to obtain monitoring data. Here, the environmental monitoring device can be, for example, but not limited to, a laser radar and a microwave radar.

[0071] For example, Figure 5 As shown, electromagnetic waves can be emitted to a target monitoring object through an environmental monitoring device such as a radar, and electromagnetic waves reflected from the target monitoring object can be received, so that information such as the time, position, angle of emitting the electromagnetic waves and the time, position, angle of receiving the electromagnetic waves can be used as monitoring data.

[0072] In addition, in an exemplary embodiment of the present disclosure, the wind turbines that need to obtain monitoring data may be wind turbines at the edge of the wind farm. For example, based on the wind farm micro-site selection map, the units at the edge of the wind farm can be determined to be monitored to meet the coverage requirements of wind farm monitoring. The units at the non-edge can adopt the same or similar control strategy as the units at the edge. In this way, the general status of the monitoring objects in the entire wind farm can be evaluated based on the monitoring data of these units, so as to achieve overall monitoring of the wind farm while minimizing the monitoring cost and workload. However, the embodiments of the present disclosure are not limited to this, and the monitoring method can also be applied to each wind turbine in the entire offshore wind farm.

[0073] In step S320, the current state of the monitored object may be determined based on the monitoring data.

[0074] The current state of the monitored object can reflect the degree of load that the monitored object can currently generate on the wind turbine. Thus, it is possible to determine whether the monitored object will generate vibration risk to the wind turbine by evaluating the current state.

[0075] As an example, the current state of the monitored object can be represented by an object state parameter, which can be a physical quantity used to describe the characteristics of the monitored object, which can quantitatively describe the state of the monitored object, and which physical quantity or quantities are specifically selected as the object state parameter can be determined according to the monitored object. In an embodiment of the present disclosure, a physical quantity of the monitored object related to the generation of the load can be used as the object state parameter.

[0076] For example, in the case where the monitoring object includes sea ice, the object state parameter may include at least one of sea ice thickness data, sea ice speed data, sea ice direction data, and sea ice coverage; and / or, in the case where the monitoring object may include waves, the object state parameter includes at least one of wave height, wave length, wave direction, and wave period; and / or, in the case where the monitoring object may include seabed scour, the object state parameter includes scour depth. As an example, in the case where the monitoring object includes sea ice, the object state parameter may include sea ice thickness data, sea ice speed data, sea ice direction data, and sea ice coverage; in the case where the monitoring object may include waves, the object state parameter includes wave height, wave length, wave direction, and wave period.

[0077] In step S320, the current state of the monitored object may be determined in different ways according to different monitoring data.

[0078] In one example, as described above, the monitoring data may include marine video data including the monitoring object acquired by a video capture device. In this example, the current state of the monitoring object may be determined by: inputting the marine video data into a pre-trained machine vision analysis model, and identifying the marine video data by the machine vision analysis model to obtain the current state of the monitoring object.

[0079] Here, the machine vision analysis model may be a model based on machine vision technology, and machine vision technology may refer to the use of image processing technology in the field of computer vision to capture key parameters of objects in an image. The machine vision analysis model may be, for example, a deep neural network model developed based on the PyTorch framework, however, the exemplary embodiments of the present disclosure are not limited thereto, and the machine vision analysis model may also be obtained by training based on other frameworks or algorithms.

[0080] The input of the machine vision analysis model can be the video frames of the collected marine video data, and its output can be the object state parameters of the monitored object. The machine vision analysis model can perform real-time dynamic recognition of images in the marine video data, extract features from dimensions such as grayscale, brightness, and edge gradient, and thus obtain information on object state parameters such as sea ice thickness, ice speed, ice direction, and coverage.

[0081] As an example, Figure 6 As shown, the machine vision analysis model may include a convolution layer, a pooling layer, a flattening layer, and a fully connected layer. The video frames in the marine video data may be input into the machine vision analysis model as raw data, and then the convolution layer and the pooling layer may be used to extract and aggregate features of each video frame to obtain a feature map. The feature map output by the last pooling layer may be flattened in the flattening layer to obtain a data structure suitable for a neural network, and then input into the fully connected layer, and data classification may be performed in the fully connected layer to output the current state of the monitored object.

[0082] In this example, monitoring data is acquired through a video capture device, and analyzed through a machine vision analysis model to obtain the current state of the monitored object. The required object state parameters can be obtained without using professional monitoring equipment, and the software's visual recognition technology can reduce hardware requirements and hardware costs.

[0083] In another example, as described above, the monitoring data may include monitoring data obtained by monitoring the monitoring object through the environment monitoring device. In this example, the current state of the monitoring object can be extracted from the monitoring data.

[0084] Specifically, the monitoring data obtained by the environmental monitoring device may include physical quantities related to the properties of the monitored object itself and its motion properties, so the required object state parameters can be extracted from it, such as the thickness, speed, direction and coverage of sea ice, etc. Here, extraction may refer to directly obtaining relevant data or calculating relevant data based on physical or geometric principles.

[0085] In this example, by obtaining monitoring data through the environmental monitoring device, the state of the monitored object can be extracted more directly and quickly, and the extraction result is more real and accurate.

[0086] In step S330, an early warning may be issued for the load of the monitored object according to the current state of the monitored object, and a current unit control strategy corresponding to the current state of the monitored object may be determined.

[0087] In this step, when the current state of the monitored object is determined, the load effect of the monitored object can be suppressed by adjusting the unit control strategy and controlling the unit operating state, thereby replacing the traditional passive load resistance mode with active control, and adjusting the unit control strategy in real time according to the on-site conditions of the monitored object, which can be more flexible than the passive load resistance scheme based on the physical structure. As an example, early warning of the load of the monitored object can refer to predicting the load change trend of the monitored object based on the parameter changes of the monitored object, so as to actively respond to the impact of the load of the monitored object.

[0088] Here, the unit control strategy can be used to control the operating state of the unit to suppress the load of the monitored object and the generated unit vibration. As an example, the unit control strategy can be used to increase the damping of the wind turbine. In this way, by increasing the unit damping, the load applied to the unit by the monitored object can be counteracted, the stability of the unit can be improved, and the vibration of the unit can be avoided or alleviated.

[0089] Here, the unit control strategy may, for example, include but is not limited to at least one of the following items: increasing the damping of the transmission chain of the wind turbine unit during the operation of the wind turbine unit, controlling the nacelle side of the wind turbine unit to face the wind when the wind turbine unit is shut down, and adjusting the retraction angle of the blades of the wind turbine unit when the wind turbine unit is shut down.

[0090] Specifically, during the operation of the unit, the transmission chain formed from the impeller to the generator can be increased in resistance, and the reverse torque of the transmission chain can be used to increase the damping of the unit. When the unit is stopped, the cabin side of the wind turbine can be made to face the wind, thereby increasing the contact area between the cabin and the air and increasing the damping of the unit. In addition, when the unit is stopped, the blade retraction angle can be reduced. For example, when the unit is stopped, the blades can be completely retracted, for example, to 90 degrees. When it is detected that the state of the monitored object may cause the unit to vibrate, the blade retraction angle can be adjusted from 90 degrees to 70 degrees, thereby increasing the aerodynamic damping of the unit.

[0091] Here, the specific control quantity of the unit control strategy can be determined according to the current state of the monitored object. For example, during the operation of the unit, different transmission chain resistance values ​​can be set; different wind angles can be set in the shutdown state; different blade retraction angles can be adjusted in the shutdown state. In this way, the different degrees of load on the monitored object can be dealt with by adjusting the control quantity.

[0092] As an example, in step S320, according to the parameter interval satisfied by the object state parameter, a unit control strategy corresponding to the parameter interval may be selected from a plurality of preset unit control strategies as the current unit control strategy.

[0093] For example, one or more parameter intervals may be preset for the object state parameter of the monitored object. In the case where a parameter interval is preset, when the object state parameter is in the parameter interval, it may indicate the need to actively respond to the load currently generated by the monitored object, and one or more strategies may be selected from the preset multiple unit control strategies for control. In the case where multiple parameter intervals are preset, different parameter intervals correspond to different degrees of load generated by the monitored object on the unit, and each parameter interval may be preset with one or more corresponding unit control strategies, so that the corresponding unit control strategy may be adopted according to the current interval.

[0094] Here, the parameter range can be set according to the type of actual unit and the sea environment in which it is located. As an example, based on the design safety of the offshore wind turbine unit and its supporting structure, the design safety boundary under different combinations of offshore environmental conditions can be given through simulation during the unit design phase, and the load design threshold corresponding to different load levels can be obtained. The parameter range can be determined by the load design threshold. For example, when the object state parameter is greater than the load design threshold, it can be considered that a unit control strategy needs to be adopted to actively respond to the load generated by the monitored object.

[0095] Taking the monitoring object as sea ice as an example, when the object state parameter is in the parameter interval of weak ice conditions, it can be considered that there is no need to actively respond to the monitored object, so that the current unit control strategy can be kept unchanged. When the object state parameter is in the parameter interval of strong ice conditions, it can be considered that it is necessary to actively respond to the monitored object, and one or more strategies can be selected from multiple preset unit control strategies for unit control. When the object state parameter is in the parameter interval of severe ice conditions, it is necessary to actively respond to the monitored object, and one or more strategies can be selected from multiple preset unit control strategies for unit control. After executing the strategy, unit vibration may still occur. In this way, the unit control strategy can be further updated to cope with the current vibration, such as using a combination of multiple control strategies for control, which will be described in detail later.

[0096] By setting parameter intervals for the object status parameters and presetting multiple unit control strategies, it is possible to distinguish different load levels and actively control the unit's operating status to deal with the load and related vibration risks generated by the monitored object. Compared with the passive response solution through physical structure, the potential vibration risks brought by the monitored object can be discovered in advance, timely warnings can be issued and corresponding control measures can be taken to avoid unit vibration problems as much as possible.

[0097] In step S340, vibration data of the wind turbine generator set after executing the current turbine generator set control strategy may be obtained.

[0098] In this step, after the current unit control strategy has been executed, vibration data of the unit can be obtained to determine whether the unit still has a vibration problem after the current unit control strategy has been executed.

[0099] As an example, the vibration data of the wind turbine generator may include vibration data at different heights on a tower of the wind turbine generator, wherein the vibration data includes at least one of vibration velocity, vibration acceleration, and vibration displacement.

[0100] Specifically, a structural vibration monitor can be used to monitor vibration data at different heights on the tower of the wind turbine. The structural vibration monitor can be equipped with multiple vibration sensors, such as accelerometers. As an example, the structural vibration monitor can include three vibration sensors, which can perform triaxial measurements in three directions. Here, the structural vibration monitor can be, for example, but not limited to, a structural vibration monitor.

[0101] As an example, according to the tower simulation results, a vibration sensor can be installed at the maximum displacement of the tower to test the relevant modal parameters, for example, the maximum displacement at the first-order modal frequency, the second-order modal frequency and the third-order modal frequency of the tower can be tested. For example, multiple vibration sensors for measuring vibrations in different directions can be arranged at the top, the middle and the bottom of the tower to monitor the tower body in all directions. Here, the vibration sensor can measure vibration-related quantities such as vibration velocity, vibration acceleration and vibration displacement, for example, the effective value, maximum value, peak value or peak-to-peak value of these vibration-related quantities can be measured. The vibration data monitored by the structural vibration monitor can be fed back to the unit control system of the wind turbine to determine whether to update the unit control strategy of the wind turbine.

[0102] In step S350, the unit control strategy of the wind turbine generator set may be updated according to the vibration data, so as to control the wind turbine generator set based on the updated unit control strategy.

[0103] In this step, the vibration data can be compared with the vibration design threshold to determine whether the current vibration level of the unit exceeds the design safety boundary. If the vibration exceeds the limit, the main control device further activates the anti-icing protection strategy to protect the safe operation of the unit.

[0104] As an example, in this step, in response to the vibration data satisfying a preset vibration condition, a combination of the current unit control strategy and at least one other unit control strategy may be used as an updated unit control strategy.

[0105] Here, the preset vibration condition may indicate that the vibration data exceeds the design safety boundary of the wind turbine. For example, the preset vibration condition may be that the vibration data is greater than a preset vibration design threshold value, which may be set according to the type of the actual unit and the strength of the supporting structure. As an example, during the unit design phase, based on the design safety of the offshore wind turbine and its supporting structure, a safety boundary of the structural vibration value may be given by simulation to obtain a vibration design threshold value (also referred to as a design simulation vibration value). When the vibration data is greater than the design threshold value, it may be considered that the current vibration level of the unit exceeds the safety boundary given in the design phase, and the vibration needs to be suppressed to ensure the safety of the unit.

[0106] In the above steps, when the vibration data meets the preset vibration conditions, the current unit control strategy can be combined with at least one other unit control strategy to control the unit together. Here, the other unit control strategy can be, for example, any strategy in the preset unit control strategy.

[0107] As described above, the unit control strategy may include at least one of the following items: increasing the damping of the transmission chain of the wind turbine during operation of the wind turbine, controlling the nacelle of the wind turbine to face the wind when the wind turbine is stopped, and adjusting the retracting angle of the blades of the wind turbine when the wind turbine is stopped. Multiple strategies in the above control strategies may be combined as an updated unit control strategy.

[0108] In this way, after executing the unit control strategy for load warning, the vibration condition of the unit can be further monitored. When the vibration of the unit exceeds the limit, vibration suppression can be achieved by combining different control strategies, thereby providing double protection for the safety of the unit.

[0109] In addition, in response to the vibration data not satisfying the preset vibration condition, it can be considered that the current vibration condition of the unit is within the design safety range and no vibration suppression is required. In this case, the current unit control strategy can be kept unchanged.

[0110] It is described above that when the current state of the monitored object is determined, the current unit control strategy corresponding to the current state of the monitored object can be determined and the unit can be controlled. However, the embodiments of the present disclosure are not limited to this. As an example, before determining the current unit control strategy, the current state of the monitored object can also be evaluated to determine whether the current load can be coped with by the unit control strategy.

[0111] Specifically, the monitoring method according to the exemplary embodiment of the present disclosure may also include: in response to the current state of the monitored object satisfying the preset state condition, executing the step of determining the current unit control strategy corresponding to the current state of the monitored object; in response to the current state of the monitored object not satisfying the preset state condition, notifying external measures outside the wind turbine to destroy the current state of the monitored object.

[0112] Here, the preset state condition may indicate that the current state of the monitored object is within the designed safety boundary of the wind turbine generator set.

[0113] In one example, the preset state condition may include that an object state parameter of the monitored object is less than or equal to a preset control threshold, and the control threshold may be greater than the load design threshold mentioned above.

[0114] When the object state parameter is less than or equal to the control threshold, that is, the current state of the monitored object meets the preset state condition, it can be considered that the load generated by the monitored object can be dealt with through the unit control strategy. When the object state parameter is greater than the control threshold, that is, the current state of the monitored object does not meet the preset state condition, it can be considered that external measures are needed to deal with the load generated by the monitored object.

[0115] Taking sea ice as an example, when at least one of the thickness, speed, direction and coverage of sea ice exceeds the preset control threshold, external icebreaking measures can be taken in time to break the ice. External icebreaking measures can be implemented, for example, through an external icebreaking system, which can refer to the use of equipment such as external icebreakers to break ice in an offshore wind farm area. In addition, in addition to the external icebreaking system, external icebreaking measures can also be implemented by installing temporary on-site icebreaking facilities to break ice on the side of the machine position.

[0116] In another example, in addition to or alternatively including a comparison relationship between the object state parameters of the monitored object and the control threshold, the preset state condition may also include that the environmental forecast of the monitored object exceeds the design safety boundary. For example, taking the monitored object as sea ice, the preset state condition may include that the sea ice forecast exceeds the preset sea ice design safety boundary. When a comprehensive judgment based on the sea ice forecast and the object state parameters is made that the current state of the sea ice has exceeded the ice conditions considered in the active anti-ice design of the unit, external ice-breaking measures may be taken in time to break the current state of the sea ice to ensure the safety of the unit.

[0117] Here, by evaluating the status of the monitored object before taking active response measures using the unit control strategy, we can choose to take active response or take external measures based on the status of the monitored object, thereby optimizing the load response plan and achieving more targeted and accurate load response.

[0118] In addition, it should be noted that although it is described above that the load design threshold, vibration design threshold and control threshold can be determined through simulation during the unit design stage, the embodiments of the present disclosure are not limited to this, and these thresholds can also be determined by real-time calculation. For example, after obtaining the object state parameters or vibration data, these data can be sent to the simulation and measurement integration system. The simulation and measurement integration system can be a system that performs real-time simulation during the operation of the unit. The system can obtain the above-mentioned thresholds through real-time simulation calculation. In this way, the monitoring of the unit can be deeply integrated with structural health monitoring, and further developed using the simulation and measurement integration technology to realize the digital twin function, thereby enhancing the developability of the system.

[0119] The above describes a monitoring method for a wind turbine according to an exemplary embodiment of the present disclosure. Figure 7 An example architecture for implementing a wind turbine monitoring method is described.

[0120] like Figure 7 As shown, an example architecture for implementing a monitoring method for a wind turbine generator system may include a video data acquisition module 710 , a machine vision analysis module 720 , a load control warning module 730 , a unit control strategy selection module 740 , a vibration data evaluation module 750 , and a vibration protection control module 760 .

[0121] The video data acquisition module 710 may acquire monitoring data for real-time monitoring of a monitoring object from a video capture device such as a camera, and may send the monitoring data to the machine vision analysis module 720 .

[0122] The machine vision analysis module 720 can capture object state parameters of the monitored object from the monitoring data, such as ice thickness, ice speed, ice direction and coverage of sea ice, and send the captured object state parameters to the load control warning module 730.

[0123] The load control warning module 730 can be set in the unit control system, for example, which can compare, analyze and judge the object state parameters with the preset control thresholds, and according to the judgment results, control the unit to enter the active load response mode or take external measures to destroy the current state of the monitored object.

[0124] When the object state parameter is less than or equal to the control threshold, it can be considered that the current state of the monitored object is within the range of the unit's active load response. The unit control strategy selection module 740 can select any one of the preset multiple unit control strategies as the current unit control strategy according to the current state of the monitored object to control the unit.

[0125] When the object state parameter is greater than the control threshold, it can be considered that the current state of the monitored object exceeds the range of the unit's active load response, and the current state of the monitored object may produce extremely severe load effects. External ice-breaking measures can be taken in time to destroy the current state of the monitored object and ensure the safety of the unit and its supporting structure.

[0126] After the current unit control strategy is determined by the unit control strategy selection module 740 and the strategy is executed, the vibration data evaluation module 750 can obtain the vibration data of the unit from the structural vibration monitor in real time and determine whether the vibration data is greater than a preset vibration design threshold.

[0127] When the vibration data is greater than the vibration design threshold, the vibration protection control module 760 may adopt further unit control strategies, such as combining multiple strategies for unit control to provide secondary protection for the unit and the supporting structure.

[0128] It should be noted that the various modules described above are divided according to functions. In an actual monitoring system, different modules can be implemented in the same software program or hardware device. For example, the video data acquisition module 710 and the machine vision analysis module 720 can be implemented in the object monitoring system in the monitoring system, the load control warning module 730, the unit control strategy selection module 740 and the vibration protection control module 760 can be implemented in the unit control system in the monitoring system, and the vibration protection control module 760 can be implemented in the vibration monitoring system in the monitoring system.

[0129] According to the monitoring method of the wind turbine set of the exemplary embodiment of the present disclosure, a new design concept and scheme based on the monitoring of offshore environmental objects can be proposed to address the shortcomings of the existing offshore wind power support structure design scheme. The load of the monitored object can be warned in advance, and an active resistance mode to the load can be achieved through the unit control strategy or external measures. It can be applied to load conditions of different degrees and has the characteristics of a wide range of applications and excellent load coping performance.

[0130] Taking sea ice as an example, compared with the flexible foundation of upright columns, this method can effectively suppress ice-induced vibrations, effectively reduce sea ice loads without strengthening the supporting structure, and achieve engineering optimization; compared with the anti-ice cone structure, this scheme relies on the unit control strategy for load suppression, does not require an anti-ice cone structure, and does not have excessive wave loads or construction problems; compared with other anti-ice devices, this scheme has no special anti-ice structure, and does not have problems with processing, manufacturing, corrosion protection, and sea ice abrasion of these special structures.

[0131] In addition, in the monitoring method of the wind turbine set according to the exemplary embodiment of the present disclosure, it is possible to effectively reduce the object load, optimize the engineering volume of the offshore unit support structure, optimize the cost of the ice-resistant structure, and improve the overall economy of the offshore unit support structure in the sea ice area without strengthening the structure of the unit itself. This avoids the on-site construction process of the physical structure and improves the construction convenience.

[0132] In addition, in the monitoring method of a wind turbine according to the exemplary embodiment of the present disclosure, an early warning can be issued on the status of the monitored object, and the unit can be controlled to implement an active response strategy to reduce the impact of the load, which can effectively suppress the structural vibration and load caused by the load of the offshore environment object.

[0133] In addition, in the monitoring method of the wind turbine set according to the exemplary embodiment of the present disclosure, multiple protection mechanisms can be set up. In addition to the active response of the unit itself, an external ice-breaking mode can also be set to deeply ensure the operating stability of the offshore unit and the safety of the supporting structure, and improve the adaptability of the offshore unit in sea ice areas.

[0134] In addition, in the monitoring method of the wind turbine according to the exemplary embodiment of the present disclosure, by applying multiple load coping measures, the design conditions of the support structure can be optimized and the design life can be reduced. For example, for the 50-year extreme design conditions required by the specification, a technical solution of simultaneously applying the active load coping strategy of the unit and external measures is adopted; while for the technical solution of only adopting the active load coping strategy of the unit, the extreme design condition life can be optimized, thereby optimizing the extreme sea ice environment conditions, and then optimizing the engineering volume of the offshore unit support structure, improving its economy and competitiveness.

[0135] According to a second aspect of the present disclosure, a monitoring system for a wind turbine is provided. Figure 8 As shown, the monitoring system may include an object monitoring system 100 , a group control system 200 , and a vibration monitoring system 300 .

[0136] The object monitoring system 100 is used to obtain monitoring data of a monitoring object in an offshore environment where a wind turbine is located, and determine a current state of the monitoring object based on the monitoring data.

[0137] The unit control system 200 is used to issue an early warning to the load of the monitored object according to the current state of the monitored object, and determine the current unit control strategy corresponding to the current state of the monitored object.

[0138] The vibration monitoring system 300 is used to obtain vibration data of the wind turbine after executing the current turbine control strategy.

[0139] Here, the unit control system 200 is also used to update the unit control strategy for the wind turbine generator set according to the vibration data, so as to control the wind turbine generator set based on the updated unit control strategy.

[0140] As an example, the object monitoring system 100 includes a video capture device and a pre-trained machine vision analysis model, wherein the video capture device is used to obtain marine video data containing a monitoring object, and the machine vision analysis model receives the marine video data, identifies the marine video data, and outputs the current state of the monitoring object.

[0141] As an example, the object monitoring system 100 includes an environment monitoring device, which is used to monitor the monitoring object and obtain monitoring data.

[0142] As an example, the current state of the monitored object is represented by the object state parameters, wherein the unit control system 200 is also used to: select a unit control strategy corresponding to the parameter interval from a plurality of preset unit control strategies as the current unit control strategy according to the parameter interval satisfied by the object state parameters.

[0143] As an example, in the case where the monitored object includes sea ice, the object state parameters include at least one of sea ice thickness data, sea ice speed data, sea ice direction data and sea ice coverage; and / or, in the case where the monitored object includes waves, the object state parameters include at least one of wave height, wave length, wave direction and wave period; and / or, in the case where the monitored object includes seabed scour, the object state parameters include scour depth.

[0144] As an example, the unit control system 200 is further configured to: in response to the vibration data satisfying a preset vibration condition, combine the current unit control strategy with at least one other unit control strategy as an updated unit control strategy.

[0145] As an example, the unit control system 200 is also used to: in response to the current state of the monitored object satisfying a preset state condition, execute the step of determining a current unit control strategy corresponding to the current state of the monitored object; in response to the current state of the monitored object not satisfying the preset state condition, notify external measures outside the wind turbine to destroy the current state of the monitored object, wherein the preset state condition indicates that the current state of the monitored object is within the design safety boundary of the wind turbine.

[0146] As an example, the vibration data of the wind turbine include vibration data at different heights on the tower of the wind turbine, wherein the vibration data include at least one of vibration velocity, vibration acceleration and vibration displacement, wherein the wind turbine is a wind turbine at the edge of a wind farm, wherein the unit control strategy is used to increase the damping of the wind turbine, and the unit control strategy includes at least one of the following items: increasing the damping of the transmission chain of the wind turbine during the operation of the wind turbine, controlling the side of the nacelle of the wind turbine to face the wind when the wind turbine is shut down, and adjusting the retraction angle of the blades of the wind turbine when the wind turbine is shut down.

[0147] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0148] According to a third aspect of the present disclosure, a wind turbine group is provided. The wind turbine group includes a monitoring system for the wind turbine group according to an exemplary embodiment of the present disclosure.

[0149] For example, the monitoring system of a wind turbine generator set can obtain monitoring data of a monitoring object in the offshore environment where the wind turbine generator set is located, wherein the monitoring object is an offshore object that can generate a load on the supporting structure of the wind turbine generator set. The monitoring system of the wind turbine generator set can also determine the current state of the monitoring object based on the monitoring data, and issue an early warning for the load of the monitoring object according to the current state of the monitoring object, and determine the current unit control strategy corresponding to the current state of the monitoring object. The monitoring system of the wind turbine generator set can also obtain the vibration data of the wind turbine generator set after executing the current unit control strategy, and update the unit control strategy of the wind turbine generator set according to the vibration data, so as to control the wind turbine generator set based on the updated unit control strategy.

[0150] The monitoring method for a wind turbine generator set according to an embodiment of the present disclosure may be executed by an electronic device, which may include: a processor; a memory, the memory storing computer executable instructions, wherein the computer executable instructions, when executed by the processor, prompt the processor to execute the monitoring method for a wind turbine generator set according to the exemplary embodiment of the present disclosure.

[0151] As an example, the electronic device can be a PC computer, a tablet device, a personal digital assistant, a smart phone or other devices capable of executing the above-mentioned instruction set. Here, the electronic device is not necessarily a single electronic device, but can also be any device or circuit that can execute the above-mentioned instruction (or instruction set) individually or jointly. The electronic device can also be a part of an integrated control system or a system manager, or can be configured to be a portable electronic device interconnected with an interface locally or remotely (for example, via wireless transmission). In addition, the electronic device can also include a video display (such as, a liquid crystal display) and a user interaction interface (such as, a keyboard, a mouse, a touch input device, etc.). All components of the electronic device can be connected to each other via a bus and / or a network.

[0152] The processor may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. As an example and not limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0153] The processor can execute instructions or codes stored in the memory, wherein the memory can also store data. Instructions and data can also be sent and received through the network via the network interface device, wherein the network interface device can adopt any known transmission protocol.

[0154] The memory may be integrated with the processor, for example, RAM or flash memory is arranged within an integrated circuit microprocessor or the like. In addition, the memory may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The memory and the processor may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor can read files stored in the memory.

[0155] In addition, the monitoring method of the wind turbine according to the embodiment of the present disclosure or some operations in the monitoring method can be written as a computer program and stored on a computer-readable storage medium. Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disk storage, hard disk drive (HDD), solid state drive (SSD), card storage (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device, any other device is configured to store computer program and any associated data, data files and data structures in a non-transitory manner and provide the computer program and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer program. In one example, the computer program and any associated data, data files and data structures are distributed on a networked computer system so that the computer program and any associated data, data files and data structures are stored, accessed and executed in a distributed manner by one or more processors or computers.

[0156] The specific implementation methods of the present disclosure have been described in detail above. Although some embodiments have been shown and described, those skilled in the art should understand that these embodiments may be modified and varied without departing from the principles and spirit of the present disclosure, the scope of which is defined by the claims and their equivalents. These modifications and variations should also be within the scope of protection of the claims of the present disclosure.

Claims

1. A monitoring method for a wind turbine generator set, characterized in that: The monitoring method comprises: Acquiring monitoring data of a monitoring object in an offshore environment where a wind turbine is located, wherein the monitoring object is an offshore object that can generate a load on a supporting structure of the wind turbine; Based on the monitoring data, determining a current state of the monitored object; According to the current state of the monitored object, early warning is given to the load of the monitored object, and a current unit control strategy corresponding to the current state of the monitored object is determined; Acquiring vibration data of the wind turbine after executing the current turbine control strategy; The unit control strategy of the wind turbine generator set is updated according to the vibration data, so as to control the wind turbine generator set based on the updated unit control strategy.

2. The monitoring method according to claim 1, characterized in that: The monitoring data includes marine video data including the monitoring object acquired by a video capture device, The current state of the monitored object is determined by: The marine video data is input into a pre-trained machine vision analysis model, and the marine video data is identified by the machine vision analysis model to obtain the current state of the monitored object.

3. The monitoring method according to claim 1, characterized in that: The monitoring data includes monitoring data obtained by monitoring the monitoring object through an environmental monitoring device, The current state of the monitored object is determined by: The current state of the monitored object is extracted from the monitoring data.

4. The monitoring method according to claim 1, characterized in that: The current state of the monitored object is represented by an object state parameter, Wherein, the step of determining the current unit control strategy corresponding to the current state of the monitored object according to the current state of the monitored object comprises: According to the parameter interval satisfied by the object state parameter, a unit control strategy corresponding to the parameter interval is selected from a plurality of preset unit control strategies as the current unit control strategy.

5. The monitoring method according to claim 4, characterized in that: In the case where the monitoring object includes sea ice, the object state parameter includes at least one of sea ice thickness data, sea ice speed data, sea ice direction data and sea ice coverage; and / or, In the case where the monitored object includes waves, the object state parameter includes at least one of wave height, wave length, wave direction and wave period; and / or, In the case where the monitoring object includes seabed scour, the object state parameter includes scour depth.

6. The monitoring method according to any one of claims 1 to 5, characterized in that: The step of updating the wind turbine control strategy according to the vibration data comprises: In response to the vibration data satisfying a preset vibration condition, combining the current unit control strategy with at least one other unit control strategy as an updated unit control strategy, The preset vibration condition indicates that the vibration data exceeds the design safety boundary of the wind turbine generator set.

7. The monitoring method according to claim 1, characterized in that: The monitoring method further comprises: In response to the current state of the monitored object satisfying a preset state condition, executing the step of determining a current unit control strategy corresponding to the current state of the monitored object; In response to the current state of the monitored object not satisfying the preset state condition, notifying external measures outside the wind turbine generator set to destroy the current state of the monitored object, The preset state condition indicates that the current state of the monitored object is within the designed safety boundary of the wind turbine generator set.

8. The monitoring method according to claim 1, characterized in that: The vibration data of the wind turbine generator set includes vibration data at different heights on a tower of the wind turbine generator set, wherein the vibration data includes at least one of vibration velocity, vibration acceleration and vibration displacement, Wherein, the wind turbine generator set is a wind turbine generator set located at the edge of a wind farm. Among them, the unit control strategy is used to increase the damping of the wind turbine unit, and the unit control strategy includes at least one of the following items: increasing the damping of the transmission chain of the wind turbine unit during the operation of the wind turbine unit, controlling the nacelle side of the wind turbine unit to face the wind when the wind turbine unit is stopped, and adjusting the retraction angle of the blades of the wind turbine unit when the wind turbine unit is stopped.

9. A monitoring system for a wind turbine generator set, characterized in that: The monitoring system comprises: An object monitoring system, used to obtain monitoring data of a monitoring object in an offshore environment where a wind turbine is located, and determine a current state of the monitoring object based on the monitoring data; A unit control system, used to give an early warning of the load of the monitored object according to the current state of the monitored object, and determine a current unit control strategy corresponding to the current state of the monitored object; A vibration monitoring system is used to obtain vibration data of the wind turbine after executing the current unit control strategy, The unit control system is further used to update the unit control strategy for the wind turbine unit according to the vibration data, so as to control the wind turbine unit based on the updated unit control strategy.

10. The monitoring system according to claim 9, characterized in that: The object monitoring system includes a video capture device and a pre-trained machine vision analysis model, The video capture device is used to obtain marine video data containing the monitored object. The machine vision analysis model receives the marine video data, identifies the marine video data, and outputs the current state of the monitored object.

11. The monitoring system according to claim 9, characterized in that: The object monitoring system includes an environment monitoring device, and the environment monitoring device is used to monitor the monitoring object to obtain the monitoring data.

12. The monitoring system according to claim 9, characterized in that: The current state of the monitored object is represented by an object state parameter, The unit control system is further used to: select a unit control strategy corresponding to the parameter interval from a plurality of preset unit control strategies according to the parameter interval satisfied by the object state parameter, as the current unit control strategy.

13. The monitoring system according to claim 12, characterized in that: In the case where the monitoring object includes sea ice, the object state parameter includes at least one of sea ice thickness data, sea ice speed data, sea ice direction data and sea ice coverage; and / or, In the case where the monitored object includes waves, the object state parameter includes at least one of wave height, wave length, wave direction and wave period; and / or, In the case where the monitoring object includes seabed scour, the object state parameter includes scour depth.

14. The monitoring system according to any one of claims 9 to 13, characterized in that: The unit control system is further configured to: in response to the vibration data satisfying a preset vibration condition, combine a current unit control strategy with at least one other unit control strategy as an updated unit control strategy.

15. The monitoring system according to claim 9, characterized in that: The unit control system is also used for: In response to the current state of the monitored object satisfying a preset state condition, executing the step of determining a current unit control strategy corresponding to the current state of the monitored object; In response to the current state of the monitored object not satisfying the preset state condition, notifying external measures outside the wind turbine generator set to destroy the current state of the monitored object, The preset state condition indicates that the current state of the monitored object is within the designed safety boundary of the wind turbine generator set.

16. The monitoring system according to claim 9, characterized in that: The vibration data of the wind turbine generator set includes vibration data at different heights on a tower of the wind turbine generator set, wherein the vibration data includes at least one of vibration velocity, vibration acceleration and vibration displacement, Wherein, the wind turbine generator set is a wind turbine generator set located at the edge of a wind farm. Among them, the unit control strategy is used to increase the damping of the wind turbine unit, and the unit control strategy includes at least one of the following items: increasing the damping of the transmission chain of the wind turbine unit during the operation of the wind turbine unit, controlling the nacelle side of the wind turbine unit to face the wind when the wind turbine unit is shut down, and adjusting the retraction angle of the blades of the wind turbine unit when the wind turbine unit is shut down.

17. A wind turbine generator set, characterized in that: The wind turbine group comprises a monitoring system for the wind turbine group according to any one of claims 9 to 16.

Images