Offshore wind power foundation scour monitoring and early warning identification system, method and apparatus

Abstract

This application discloses a system, method, and apparatus for monitoring and early warning of scour on offshore wind power foundations. In a data processing and training module, a feature matching and a preset recurrent neural network algorithm are used to train a collected, preset scour early warning level dataset and a historical scour measurement dataset to obtain a target recurrent neural network model. When a scour disaster occurs, the target recurrent neural network model can be directly used in a monitoring and early warning identification module to monitor and identify the current scour situation and obtain a scour early warning level. Therefore, by implementing this application, the influence mechanism of horizontal cyclic loads on pile foundation scour is fully taken into consideration, the scour situation of offshore wind turbine foundations can be more timely, accurate, and reliable, and different scour levels can be quickly, accurately, and reliably identified. Based on the identification results, scour losses can be effectively prevented and technical support for the safe operation and maintenance of wind turbines can be provided.

Description

[Technical Field]

[0001] The present application relates to the field of offshore wind power generation intelligent monitoring technology, and in particular to a scour monitoring and early warning identification system, method and apparatus for offshore wind power generation foundation. [Background technology]

[0002] As the use of single pile foundations for offshore wind power generation units becomes more widespread, the problem of scouring of the soil body around the single pile foundation has received increasing attention and research attention. However, to date, research on single pile foundation scouring has not fully considered the effects of scouring on the soil body around the single pile foundation of offshore wind power generation units due to wave-current coupling action and pile-soil interaction under horizontal cyclic loads, making it impossible to perform real-time online monitoring of the scour situation and intelligent early warning of faults. Summary of the Invention [Problem to be solved by the invention]

[0003] In view of this, the embodiments of the present application provide a system, method and device for scour monitoring and early warning identification of offshore wind power generation foundations, to solve the technical problem of the prior art that real-time online monitoring and intelligent early warning of faults cannot be performed for the scour situation of offshore wind power generation foundations. [Means for solving the problem]

[0004] The technical solutions proposed in this application are as follows:

[0005] In a first aspect, an embodiment of the present application provides a scour monitoring and early warning identification system for an offshore wind power foundation, comprising: a data collection module for acquiring a predetermined scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation, and sending the predetermined scour early warning level dataset and the historical scour measurement dataset to a data processing and training module; the data processing and training module for establishing a target recurrent neural network model based on the predetermined scour early warning level dataset and the historical scour measurement dataset through feature matching and a predetermined recurrent neural network algorithm, and sending the target recurrent neural network model to a monitoring and early warning identification module; and the monitoring and early warning identification module for monitoring and identifying a scour situation corresponding to the offshore wind power foundation based on the target recurrent neural network model when a scour disaster occurs, and obtaining a scour early warning level.

[0006] In combination with the first aspect, in one possible embodiment of the first aspect, the step of establishing a target recurrent neural network model by feature matching and a preset recurrent neural network algorithm based on the preset scour early warning level dataset and the historical scour measurement dataset includes the steps of: obtaining at least one scour measurement average value by a preset calculation method based on the historical scour measurement data; obtaining a correspondence relationship between each of the scour measurement average values ​​and each scour early warning level in the preset scour early warning level dataset by feature matching based on each of the scour measurement average values ​​and the preset scour early warning level dataset; and establishing the target recurrent neural network model by a preset recurrent neural network algorithm based on the correspondence relationship and the historical scour measurement dataset.

[0007] In combination with the first aspect, in another possible embodiment of the first aspect, the data collection module is further used to acquire at least one scour measurement data transmitted by each scour sensor in a target monitoring area in the event of a scour disaster, and each scour sensor is pre-embedded in a heavily scoured soil layer around an offshore wind power generation foundation in the target monitoring area.

[0008] In combination with the first aspect, in yet another possible embodiment of the first aspect, when a scour disaster occurs, the step of acquiring scour measurement data transmitted by each scour sensor in a target monitoring area includes a step of, when a scour disaster occurs, each of the scour sensors in the target monitoring area using an end-to-end based wireless transmission sensor signal model to transmit each of the scour measurement data to the data collection module.

[0009] In combination with the first aspect, in yet another possible embodiment of the first aspect, the monitoring and early warning identification module includes a first monitoring and early warning identification sub-module including a data processing sub-module for receiving each of the scour measurement data transmitted by the data collection module, processing each of the scour measurement data based on a preset processing method to obtain at least one target scour measurement data, and transmitting each of the target scour measurement data to a second monitoring and early warning identification sub-module; and the second monitoring and early warning identification sub-module for identifying a target using a recurrent neural network model based on each of the target scour measurement data to obtain the scour early warning level.

[0010] In combination with the first aspect, in yet another possible embodiment of the first aspect, the data collection module is further used to acquire a wave parameter set and a water current velocity data information set transmitted by the scour sensor in the target monitoring area when a scour disaster occurs, and to determine an evolutionary relationship between the water current velocity and wave characteristics in the target monitoring area based on the wave parameter set and the water current velocity data information set.

[0011] In a second aspect, an embodiment of the present application provides a scour monitoring and early warning identification method for an offshore wind power generation foundation, which is used in the scour monitoring and early warning identification system for an offshore wind power generation foundation described in the first aspect of the embodiment of the present application. The scour monitoring and early warning identification method for offshore wind power foundations includes the steps of: when a scour disaster occurs, obtaining at least one scour measurement data from each scour sensor within a target monitoring area through an end-to-end based wireless transmission sensor signal model, where each scour sensor is pre-embedded in a heavily scoured soil layer around the offshore wind power foundation within the target monitoring area; obtaining at least one target scour measurement data based on each of the scour measurement data through a pre-defined processing method; and identifying and obtaining a scour early warning level based on each of the target scour measurement data using a target recurrent neural network model, where the target recurrent neural network model is obtained by training a pre-defined scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation through feature matching and a pre-defined recurrent neural network algorithm.

[0012] In a third aspect, an embodiment of the present application provides an offshore wind power generation foundation scour monitoring and early warning identification device for use in the offshore wind power generation foundation scour monitoring and early warning identification system described in the first aspect of the embodiment of the present application. The scour monitoring and early warning identification device for offshore wind power foundations includes: an acquisition module for, when a scour disaster occurs, using each scour sensor within a target monitoring area to obtain at least one scour measurement data through an end-to-end based wireless transmission sensor signal model, where each scour sensor is pre-embedded in a heavily scoured soil layer around the offshore wind power foundation within the target monitoring area; a processing module for obtaining at least one target scour measurement data based on each of the scour measurement data through a pre-set processing method; and an early warning identification module for identifying and obtaining a scour early warning level based on each of the target scour measurement data through a target recurrent neural network model, where the target recurrent neural network model is obtained by training a pre-set scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation through feature matching and a pre-set recurrent neural network algorithm.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer instructions stored therein, the computer instructions being used to cause the computer to execute the method for monitoring and early warning identification of scour for offshore wind power generation foundations described in the second aspect of the embodiment of the present application.

[0014] In a fifth aspect, an embodiment of the present application provides an electronic device comprising a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions stored in the memory, and the processor executing the computer instructions to perform the method for monitoring and identifying scouring of an offshore wind power generation foundation and early warning described in the second aspect of the embodiment of the present application.

[0015] The technical solution provided in this application has the following effects: In an embodiment of the present application, the scour monitoring and early warning identification system for offshore wind power foundations includes a data collection module that acquires a preset scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation, a data processing and training module that uses feature matching and a preset recurrent neural network algorithm to train the preset scour early warning level dataset and the historical scour measurement dataset to obtain a target recurrent neural network model, and when a scour disaster occurs, the monitoring and early warning identification module directly uses the target recurrent neural network model to monitor and identify the current scour situation and obtain a scour early warning level. Therefore, by implementing the present application, the influence mechanism of the horizontal cyclic load of the pile body on pile foundation scour can be fully taken into consideration, the scour situation of the offshore wind turbine foundation can be more timely, accurate, and reliable, and different scour levels can be quickly, accurately, and reliably identified. Based on the identification results, scour losses can be effectively prevented and technical support for the safe operation and maintenance of the wind turbine can be provided.

[0016] The scour monitoring and early warning identification method for offshore wind power generation foundations according to the embodiments of the present application uses the scour monitoring and early warning identification system for offshore wind power generation foundations described in the embodiments of the present application to perform identification, thereby enabling the scour situation of offshore wind turbine foundations to be grasped more timely, accurately and reliably. Furthermore, by scientifically optimizing the existing scour and protection design method for single pile foundations of offshore wind turbines, the development and maintenance costs of offshore wind power generation foundations can be effectively reduced and the safety of offshore wind power generation foundations can be improved. [Brief explanation of the drawings]

[0017] In order to more clearly describe the specific embodiments of the present application or the technical solutions of the prior art, the following will briefly describe the drawings that need to be used to describe the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings based on these drawings without any creative efforts. [Figure 1] 1 is a structural block diagram of a scour monitoring and early warning identification system for an offshore wind power generation foundation according to an embodiment of the present application; [Figure 2] FIG. 1 is a schematic diagram of single pile foundation scour under horizontal cyclic loading according to an embodiment of the present application. [Figure 3] FIG. 1 is a schematic diagram of a wind power foundation scour sensor according to an embodiment of the present application. [Figure 4] 1 is a structural schematic diagram of an intelligent monitoring and early warning management platform for scour of offshore wind power foundations according to an embodiment of the present application; FIG. [Figure 5] 1 is an operational flowchart of an intelligent monitoring and early warning system for a scouring process according to an embodiment of the present application; [Figure 6] 1 is an exemplary schematic diagram of the principle of an intelligent monitoring system for wind turbine foundation scour according to an embodiment of the present application; FIG. [Figure 7] 1 is a flowchart of a scour monitoring and early warning identification method for an offshore wind power generation foundation according to an embodiment of the present application. [Figure 8] 1 is an overall flowchart of an offshore wind power foundation scour monitoring and intelligent early warning identification algorithm according to an embodiment of the present application; [Figure 9] 1 is a structural block diagram of a scour monitoring and early warning identification device for an offshore wind power generation foundation according to an embodiment of the present application; [Figure 10] 1 is a structural schematic diagram of a computer-readable storage medium according to an embodiment of the present application; [Figure 11] 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0018] In order to clarify the objectives, technical solutions and advantages of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments of the present application, other embodiments that a person skilled in the art can obtain without any creative efforts all belong to the protection scope of the present application.

[0019] It should be noted that terms such as "first," "second," etc. in the specification and claims of this application and in the drawings are intended to distinguish between similar objects and not necessarily to describe a particular order or chronological order. Such terms, as used herein, should be understood to be interchangeable where appropriate, such that the embodiments of this application described herein may be performed in orders other than those illustrated or described herein. Furthermore, the terms "comprise," "have," and any variations thereof are intended to cover non-exclusive inclusions; for example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units expressly recited, but may include other steps or units not expressly recited or inherent in the process, method, product, or apparatus.

[0020] An embodiment of the present application provides a scour monitoring and early warning identification system for offshore wind power generation foundations. As shown in Figure 1, the scour monitoring and early warning identification system for offshore wind power generation foundations 1 includes a data collection module 11, a data processing and training module 12, and a monitoring and early warning identification module 13.

[0021] Here, the data processing and training module 12 is connected to the data collection module 11 and the monitoring and early warning identification module 13 respectively.

[0022] It should be understood that the system may further comprise other devices and equipment.

[0023] Here, the monitoring and early warning identification module 13 includes a first monitoring and early warning identification sub-module 131 and a second monitoring and early warning identification sub-module 132 , and the first monitoring and early warning identification sub-module 131 includes a data processing sub-module 1311 .

[0024] Here, the first monitoring and early warning identification sub-module 131 is a real-time monitoring module, and the second monitoring and early warning identification sub-module 132 is a wireless remote monitoring module.

[0025] Furthermore, the functions of each device in the above system will be explained.

[0026] Specifically, the data collection module 11 acquires a pre-set scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation, and transmits the pre-set scour early warning level dataset and the historical scour measurement dataset to the data processing and training module 12.

[0027] After receiving the preset scour early warning level dataset and the historical scour measurement dataset, the data processing and training module 12 first calculates at least one scour measurement average value based on the historical scour measurement dataset, then determines a corresponding scour early warning level in the preset scour early warning level dataset based on each scour measurement average value, thereby obtaining a correspondence between each scour measurement average value and each scour early warning level, and finally trains a preset recurrent neural network algorithm (RNN neural network algorithm) based on the correspondence and the historical scour measurement dataset, thereby obtaining the target recurrent neural network model, and sends the target recurrent neural network model to the monitoring and early warning identification module 13.

[0028] Specifically, the algorithm model, i.e., the target recurrent neural network model, is determined by continuously training the algorithm model at different sensor signal modeling stages and finding the optimal parameters.

[0029] When a scour disaster occurs, the monitoring and early warning identification module 13 can directly use the received target recurrent neural network model to monitor and identify the scour situation corresponding to the offshore wind power generation foundation, and obtain the scour early warning level.

[0030] First, when a scour disaster occurs, the data collection module 11 acquires at least one scour measurement data transmitted from each scour sensor within the target monitoring area, processes each scour measurement data using the data processing sub-module 1311 to obtain at least one target scour measurement data, and transmits each target scour measurement data to the second monitoring and early warning identification sub-module 131.

[0031] Here, as shown in Figure 2, scour sensors are pre-embedded in heavily scoured soil layers around the offshore wind power foundation within the target monitoring area, and scour sensors at different depths of the soil layers correspond to different scour early warning levels.

[0032] As shown in Figure 3, when a scour disaster occurs, the scour sensors in the soil layers at different depths will be washed away by the water flow and transmit measurement data related to the scour process to the data collection module 11.

[0033] Here, the scour sensor transmits data using an end-to-end based wireless transmission sensor signal model, which can achieve the goal of increasing the inter-class distance and decreasing the intra-class distance of features, allowing for the rapid preparation of a reliable discrimination model, and, because it has few parameters, is more suitable for deployment in embedded hardware.

[0034] Next, the second monitoring and early warning identification submodule 132 receives the target scour measurement data, and then inputs the target scour measurement data into a target recurrent neural network model (RNN model) to perform early warning identification, thereby obtaining a corresponding scour early warning level.

[0035] Optionally, the data collection module 11 can further acquire a wave parameter set and a water current velocity data information set transmitted by the scour sensor in the target monitoring area when a scour disaster occurs, and can be used to determine the evolutionary relationship between the water current velocity and wave characteristics in the target monitoring area based on the wave parameter set and the water current velocity data information set; optionally, a corresponding evolutionary process diagram can be formed based on the evolutionary relationship; and synchronous observation of the scour process and water current characteristics is realized based on the evolutionary process diagram.

[0036] In an embodiment of the present application, the scour monitoring and early warning identification system for offshore wind power foundations includes a data collection module that acquires a preset scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation, a data processing and training module that uses feature matching and a preset recurrent neural network algorithm to train the preset scour early warning level dataset and the historical scour measurement dataset to obtain a target recurrent neural network model, and when a scour disaster occurs, the monitoring and early warning identification module directly uses the target recurrent neural network model to monitor and identify the current scour situation and obtain a scour early warning level. Therefore, by implementing the present application, the influence mechanism of the horizontal cyclic load of the pile body on pile foundation scour can be fully taken into consideration, the scour situation of the offshore wind turbine foundation can be more timely, accurate, and reliable, different scour levels can be quickly, accurately, and reliably identified, and based on the identification results, scour losses can be effectively prevented and technical support for the safe operation and maintenance of the wind turbine.

[0037] In one example, a scour remote intelligent monitoring and fault early warning system suitable for offshore wind turbine foundations is provided, which includes a scour sensor module for measuring scour depth, wave current, and water current velocity data information, a base station real-time monitoring module for receiving, screening, and processing feedback data from the scour sensor, a wireless remote monitoring module for monitoring the hydroscour process and issuing early warnings, and an early warning intelligent identification model. A schematic diagram of the specific implementation principle is shown in Figures 4 and 5.

[0038] Specifically, scour sensors are embedded in the heavily scoured soil layer around the pile foundation. When a scour disaster occurs, the scour sensors at different depths of the soil layer are washed away by the water flow and transmit measurement data related to the scour process. The base station real-time monitoring module screens and processes the relevant data and transmits it to the remote monitoring center. As shown in Figure 6, an intelligent early warning identification algorithm can identify the collected signals transmitted by different sensors, and then obtain different scour early warning levels.

[0039] Another example is an offshore wind turbine foundation scour monitoring and intelligent early warning identification system. Its hardware includes a Beidou GPS ATGM336H, a wireless serial port E32-TTL-100, a single-chip computer STC15F2K, and the signal receiver SS-DTU68G required for the base station real-time monitoring module. The software is compiled in Python, and data information such as sensor number, latitude and longitude, date, and water current speed can be displayed through a code compiler program, allowing the client to view the required data concisely, clearly, and accurately, achieving the goal of real-time monitoring.

[0040] An embodiment of the present application provides a method for monitoring and early warning identification of scour for offshore wind power generation foundations, which is used in the scour monitoring and early warning identification system 1 for offshore wind power generation foundations described in the embodiment of the present application. As shown in FIG. 7 , the method includes the following steps:

[0041] In step 201, when a scour disaster occurs, each scour sensor in the target monitoring area obtains at least one scour measurement data through an end-to-end based wireless transmission sensor signal model.

[0042] Here, each of the scour sensors is pre-embedded in a heavily scoured soil layer around an offshore wind power plant foundation within the target monitoring area.

[0043] For the specific implementation process, please refer to the function description and limitations of the data collection module 11 of the offshore wind power foundation scour monitoring and early warning identification system 1 in the above embodiment, and repeated description will be omitted here.

[0044] In step 202, based on each of the scour measurement data, at least one target scour measurement data is obtained through a preset processing method.

[0045] For the specific implementation process, please refer to the description of the connection relationship between the data collection module 11 and the monitoring and early warning identification module 13 of the offshore wind power foundation scour monitoring and early warning identification system 1 in the above embodiment, and the description of the function of the first monitoring and early warning identification sub-module 131 of the monitoring and early warning identification module 13, and repeated explanations will be omitted here.

[0046] In step 203, based on each of the target scour measurement data, a target recurrent neural network model is used to identify and obtain a scour early warning level.

[0047] Here, the target recurrent neural network model is obtained by training the pre-set scour early warning level dataset and the historical scour measurement dataset corresponding to the offshore wind power foundation through feature matching and a pre-set recurrent neural network algorithm. For the specific training process, please refer to the description of the function of the data processing and training module 12 of the offshore wind power foundation scour monitoring and early warning identification system 1 in the above embodiment, and the description will not be repeated here.

[0048] For the specific early warning identification process, please refer to the description of the connection relationship and function between the first monitoring and early warning identification sub-module 131 and the second monitoring and early warning identification sub-module 132 of the offshore wind power foundation scour monitoring and early warning identification system 1 in the above embodiment, and repeated explanations will be omitted here.

[0049] The scour monitoring and early warning identification method for offshore wind power generation foundations according to the embodiments of the present application uses the scour monitoring and early warning identification system for offshore wind power generation foundations described in the embodiments of the present application to perform identification, thereby enabling the scour situation of offshore wind turbine foundations to be grasped more timely, accurately and reliably. Furthermore, by scientifically optimizing the existing scour and protection design method for single pile foundations of offshore wind turbines, the development and maintenance costs of offshore wind power generation foundations can be effectively reduced and the safety of offshore wind power generation foundations can be improved.

[0050] In one example, as shown in Figure 8, an overall flowchart of the scour monitoring and intelligent early warning identification algorithm for offshore wind power foundations is provided.

[0051] In another example, a method for scour monitoring and early warning rapid identification of an offshore wind power foundation is provided, the method comprising the steps of:

[0052] S1. Set a plurality of scour sensor collection points, and the sensor collection points are used to collect scour situation information of sensors under the action of wave current loads, and the sensor information includes the magnitude of sensor transmission signals.

[0053] S2, the average value of the information transmitted by multiple sensors is x, and the early warning level corresponding to x is y.

[0054] S3: Perform sample statistics, i.e., take N samples, among which, one scour early warning level y n is the average value of the information sent by one sensor x n where n represents a non-zero natural number.

[0055] S4, use an information collection processing module to collect sensor information, and remove noise from N sample sensor information to obtain N groups of qualified sensor information.

[0056] S5, N groups of qualified sensor information are sent to the RNN neural network model for training.

[0057] S6: Obtain the correspondence between the average value x of the information transmitted by the M sensors and the scour warning level y.

[0058] S7: Determine a scour warning level based on the correspondence.

[0059] An embodiment of the present application further provides an offshore wind power generation foundation scour monitoring and early warning identification device used in the offshore wind power generation foundation scour monitoring and early warning identification system 1 described in the embodiment of the present application, and as shown in FIG. 9 , the device includes the following modules:

[0060] The acquisition module 301 is used to obtain at least one scour measurement data through an end-to-end based wireless transmission sensor signal model by each scour sensor in a target monitoring area when a scour disaster occurs, and each of the scour sensors is pre-embedded in a heavily scoured soil layer around an offshore wind power generation foundation in the target monitoring area.

[0061] The processing module 302 is used to obtain at least one target scour measurement data through a preset processing method based on each of the scour measurement data, for details, please refer to the relevant description of step 202 in the above method embodiment, and the repeated description will be omitted here.

[0062] The early warning identification module 303 is used to identify and obtain a scour early warning level by a target recurrent neural network model based on each of the target scour measurement data, and the target recurrent neural network model is obtained by training a pre-set scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation through feature matching and a pre-set recurrent neural network algorithm. For details, please refer to the relevant description of step 203 in the above method embodiment, and the description will not be repeated here.

[0063] The scour monitoring and early warning identification device for offshore wind power generation foundations according to the embodiments of the present application uses the scour monitoring and early warning identification system for offshore wind power generation foundations described in the embodiments of the present application to perform identification, thereby enabling the scour situation of offshore wind turbine foundations to be grasped more timely, accurately and reliably. Furthermore, by scientifically optimizing the scour and protection design method for the conventional single pile foundations of offshore wind turbines, the development and maintenance costs of offshore wind power generation foundations can be effectively reduced and the safety of offshore wind power generation foundations can be improved.

[0064] For details of the function of the scour monitoring and early warning identification device for offshore wind power generation foundations according to the embodiments of the present application, please refer to the description of the scour monitoring and early warning identification method for offshore wind power generation foundations in the above embodiments.

[0065] An embodiment of the present application further provides a storage medium, which stores a computer program 401 as shown in Figure 10, and when the instructions are executed by a processor, the steps of the method for monitoring scouring and identifying early warnings for offshore wind power foundations in the embodiment are realized. Here, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), a solid-state drive (SSD), etc., and the storage medium may also include a combination of the above types of memory.

[0066] As can be understood by those skilled in the art, all or part of the processes of the methods according to the above embodiments can be realized by instructing relevant hardware using a computer program, and the program may be stored in a computer-readable storage medium, which, when executed, can include the processes of each of the above method embodiments. Here, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), a solid-state drive (SSD), etc., and the storage medium may also include a combination of the above types of memory.

[0067] An embodiment of the present application further provides an electronic device, which may include a processor 51 and a memory 52, as shown in FIG. 11, where the processor 51 and the memory 52 may be connected via a bus or other method, and FIG. 11 takes connection via a bus as an example.

[0068] Processor 51 may be a central processing unit (CPU), or may be a chip such as another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or a combination of various chips described above.

[0069] The memory 52 may be used as a non-transitory computer-readable storage medium to store non-transitory software programs, non-transitory computer-executable programs and modules, such as corresponding program instructions / modules in the embodiments of the present application. The processor 51 executes the non-transitory software programs, instructions and modules stored in the memory 52 to perform various functional applications and data processing of the processor, i.e., to realize the scour monitoring and early warning identification method for offshore wind power generation foundations in the above-mentioned method embodiment.

[0070] The memory 52 may include a program storage area and a data storage area, where the program storage area may store an application program required for an operating device or at least one function, and the data storage area may store data created by the processor 51. The memory 52 may also include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the Internet, a corporate intranet, a local area network, a mobile communication network, and combinations thereof.

[0071] The one or more modules are stored in the memory 52, and when executed by the processor 51, execute the method for monitoring and identifying scour of an offshore wind power generation foundation and early warning in the embodiment shown in Figs.

[0072] Specific details of the electronic device may be understood by referring to the corresponding related descriptions and effects in the embodiments shown in FIGS. 7 and 8, and repeated descriptions will be omitted here.

[0073] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and all such modifications and variations are included within the scope defined by the appended claims.

Claims

1. An offshore wind power generation foundation scour monitoring and early warning identification system, a data collection module for acquiring a pre-defined scour early warning level dataset and a historical scour measurement dataset corresponding to an offshore wind power foundation, and sending the pre-defined scour early warning level dataset and the historical scour measurement dataset to a data processing and training module; the data processing and training module for establishing a target recurrent neural network model through feature matching and a pre-defined recurrent neural network algorithm based on the pre-defined scour early warning level dataset and the historical scour measurement dataset, and sending the target recurrent neural network model to a monitoring and early warning identification module; and a monitoring and early warning identification module for, when a scour disaster occurs, monitoring and identifying the scour situation corresponding to the offshore wind power generation foundation based on the target recurrent neural network model, and obtaining a scour early warning level.

2. Establishing a target recurrent neural network model through feature matching and a pre-defined recurrent neural network algorithm based on the pre-defined scour early warning level dataset and the historical scour measurement dataset, obtaining at least one scour measurement average value based on historical scour measurement data using a predetermined calculation method; According to each of the scour measurement average values ​​and the preset scour early warning level dataset, obtaining a correspondence relationship between each of the scour measurement average values ​​and each of the scour early warning levels in the preset scour early warning level dataset by feature matching; and establishing the target recurrent neural network model based on the correspondence and the historical scour measurement data set using a pre-configured recurrent neural network algorithm.

3. 2. The system of claim 1, wherein the data collection module is further used to acquire at least one scour measurement data transmitted by each scour sensor within a target monitoring area in the event of a scour disaster, and each scour sensor is pre-embedded in a heavily scoured soil layer around an offshore wind power generation foundation within the target monitoring area.

4. When a scour disaster occurs, the step of acquiring scour measurement data transmitted by each scour sensor in the target monitoring area includes:

4. The system of claim 3, further comprising a step in which, when a scour disaster occurs, each of the scour sensors in a target monitoring area transmits each of the scour measurement data to the data collection module using an end-to-end based wireless transmission sensor signal model.

5. The monitoring and early warning identification module includes: a first monitoring and early warning identification sub-module, including a data processing sub-module for receiving each of the scour measurement data sent by the data collection module, processing each of the scour measurement data based on a preset processing method, obtaining at least one target scour measurement data, and sending each of the target scour measurement data to a second monitoring and early warning identification sub-module; and the second monitoring and early warning identification sub-module for identifying the target by the recurrent neural network model based on each of the target scour measurement data and obtaining the scour early warning level.

6. The system of claim 1, wherein the data collection module is further used to acquire a wave parameter set and a water current velocity data information set transmitted by a scour sensor in a target monitoring area when a scour disaster occurs, and to determine an evolutionary relationship between the water current velocity and wave characteristics in the target monitoring area based on the wave parameter set and the water current velocity data information set.

7. A method for monitoring and early warning identification of scour of an offshore wind power generation foundation used in the system for monitoring and early warning identification of a scour of an offshore wind power generation foundation according to any one of claims 1 to 6, When a scour disaster occurs, obtaining at least one scour measurement data by each scour sensor in a target monitoring area through an end-to-end based wireless transmission sensor signal model, wherein each scour sensor is pre-embedded in a heavily scoured soil layer around an offshore wind power generation foundation in the target monitoring area; obtaining at least one target scour measurement data based on each of the scour measurement data through a preset processing method; and a step of identifying a target recurrent neural network model based on each of the target scour measurement data to obtain a scour early warning level, wherein the target recurrent neural network model is obtained by training a pre-set scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation through feature matching and a pre-set recurrent neural network algorithm.

8. An offshore wind power generation foundation scour monitoring and early warning identification device used in the offshore wind power generation foundation scour monitoring and early warning identification system according to any one of claims 1 to 6, an acquisition module that is used by each scour sensor in a target monitoring area to obtain at least one scour measurement data through an end-to-end based wireless transmission sensor signal model when a scour disaster occurs, and each scour sensor is pre-embedded in a heavily scoured soil layer around an offshore wind power generation foundation in the target monitoring area; a processing module for obtaining at least one target scour measurement data by a preset processing method based on each of the scour measurement data; and an early warning identification module, which is used to identify and obtain a scour early warning level by a target recurrent neural network model based on each of the target scour measurement data, wherein the target recurrent neural network model is obtained by training a pre-set scour early warning level dataset and a historical scour measurement dataset corresponding to the offshore wind power foundation through feature matching and a pre-set recurrent neural network algorithm.

9. A computer-readable storage medium storing computer instructions for causing a computer to execute the method for monitoring and identifying early warnings for scour of an offshore wind power generation foundation according to claim 7.

10. An electronic device, 10. An electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other; computer instructions being stored in the memory; and the processor executing the computer instructions to perform the method for monitoring and identifying scouring and early warning for an offshore wind power generation foundation according to claim 7.

Images