3773 results about "Offshore wind power" patented technology

The invention relates to the technical field of wind turbine generator data analysis, and discloses an offshore wind turbine generator operation data analysis and prediction system. The system comprises a marine environment data integration module for collecting data to generate a multi-source time-space synchronization data set; the multi-modal feature fusion module is used for extracting cross-modal correlation features to generate a high-dimensional fusion feature tensor; the dynamic fault prediction module is used for constructing a two-way gating circulation network model to predict the degradation probability and the residual life of key components of the equipment; and the self-adaptive optimization control module is used for constructing a multi-target dynamic programming model to optimize a fan operation strategy. In addition, the system is further provided with a feedback correction module for correcting prediction model parameters, and a virtual sensor module based on a physical information neural network is used for monitoring tower stress and diagnosing sensor faults. According to the system, comprehensive monitoring, accurate fault prediction and optimal control of the offshore wind turbine generator are realized, the operation efficiency, reliability and safety of the wind turbine generator are effectively improved, and the operation and maintenance cost is reduced.

The invention relates to an offshore energy platform coordinated scheduling method based on multi-energy complementation and hierarchical optimization, which combines multi-energy complementation characteristic modeling, multi-target opportunity constraint optimization and rolling optimization, and realizes offshore multi-energy coordinated scheduling by constructing a hierarchical decoupling optimization and control system. Based on prediction and historical data of multiple types of energy such as offshore wind power, photovoltaic energy and tidal energy, complementarity and flexibility of the energy are quantified, high-quality data support is provided for scheduling optimization, a day-ahead layered optimization model containing renewable energy priority consumption and flexible standby configuration is constructed, and a medium-and-long-term output strategy is formulated. Output of various energy sources is dynamically adjusted through a rolling optimization mechanism, and flexible response to renewable energy fluctuation is achieved. And finally, second-level frequency and voltage support is realized by using a virtual synchronous machine and droop control, and the self-adaptive capability of the system is enhanced. According to the invention, the cooperative regulation capability and operation stability of the offshore platform multi-energy system can be effectively improved, and the dependence on a traditional standby power supply is reduced.

The invention relates to the technical field of power system stability control, in particular to a broadband oscillation suppression method and system for an offshore wind power flexible direct current grid-connected system and a medium, and the method comprises the steps: sequentially injecting positive and negative sequence perturbation sine harmonic signals at a grid-connected point of a wind turbine generator, constructing a multi-input multi-output impedance matrix, reducing the order of the multi-input and multi-output impedance matrix into single-input and single-output equivalent positive sequence impedance; the stability margin of the offshore wind power flexible direct current grid-connected system is obtained based on equivalent positive sequence impedance quantification; when the stability margin is lower than a preset margin threshold value, reconstructing the fan grid-side converter into a matrix control structure by cascading a weighting coefficient matrix between the inner and outer ring control loops of the fan grid-side converter; and iteratively optimizing the matrix type control structure based on impedance sensitivity, and synchronously connecting a low-pass filter in series in a voltage and current feedback channel to carry out impedance remodeling so as to finish broadband oscillation risk suppression. According to the invention, broadband oscillation suppression of the offshore wind power flexible direct current grid-connected system is realized through impedance modeling and a matrix type control strategy.

An offshore wind power plant composite ring current collection system topology planning method based on an N-1 safety criterion comprises the following steps that S1, wind power plant basic data including wind turbine and transformer substation node coordinates, wind turbine rated power, cable electrical parameters and the like are obtained; s2, generating a candidate cable set and a cable cross avoidance constraint pair set based on the basic data; s3, a scene set containing a normal scene and all single cable fault scenes is constructed, an optimization model with the minimum total cost of the whole life cycle as the target is established, and cable construction / operation variables and direct current power flow power balance, node degrees and cable cross avoidance constraints are integrated; s4, solving the model to obtain an initial topology scheme; and S5, carrying out full fault set N-1 security verification on the initial scheme, and bringing a violation scene into a fault set to resolve until the scheme meets an N-1 criterion. According to the method, through non-predefined topological optimization and planning, reliability and economical efficiency are taken into consideration, calculation complexity is reduced, and the method can be expanded to a cross-substation scene.

The invention relates to the technical field of offshore wind power, and discloses a bearing performance degradation evaluation method for an offshore wind power foundation structure, which effectively solves the problem of neglecting corrosion heterogeneity in the prior art by acquiring initial three-dimensional geometric point cloud data and historical service data and constructing a first finite element model. The model better fits the actual structure state; the local damage evolution and cumulative effect are simulated by means of a second finite element model, meanwhile, material degradation evaluation is combined, the interaction of three key factors including corrosion thinning, local damage and material mechanical property degradation is comprehensively considered, and the defect that the multi-factor coupling influence is not fully solved in the prior art is overcome; the extreme environment load condition is introduced to construct the third finite element model, the performance degradation law of the structure in the extreme environment can be analyzed, and then the reliability and applicability of evaluation are improved by establishing a mathematical relation model and predicting the full life cycle bearing performance.

An offshore wind power plant current collection system optimization method considering cable type selection comprises the following steps: S1, acquiring wind power plant basic data including fan and transformer substation coordinates, fan rated power, multi-specification cable electrical and cost parameters and the like; s2, on the basis of the basic data, generating a candidate cable set by using clustering partitions and a distance threshold value, completing candidate set reduction, and synchronously generating a cable crossing avoidance constraint pair set; s3, an optimization model with the minimum total cost of the whole life cycle is established, the double-side ring path does not need scene variables, and the composite ring path needs to integrate scene driving variables; s4, carrying out path accelerated solution, carrying out hot start on a double-sided ring, carrying out cross constraint simplification, and carrying out additional fault set dimension reduction on a composite ring to obtain an initial scheme; and S5, performing full fault set N-1 verification on the initial scheme, bringing a violation scene into a fault set for resolution until the scheme meets an N-1 criterion, and outputting a final result. According to the method, topology and cable type selection integrated optimization is realized, and the solving quality and efficiency are considered.

The invention discloses a multi-modal offshore wind power ultra-short-term prediction method in the field of offshore wind power plant cluster power prediction, and aims to solve the technical problems of spatial-temporal feature splitting and insufficient dynamic dependency relationship modeling. The method comprises the steps of performing anomaly detection and restoration on fan data, and generating a corrected wind power cluster data set; extracting a mean value, a standard deviation and a latest value of core operation data of each fan through a dynamic time window, and constructing a multi-dimensional node feature; a static geographic similarity matrix is generated based on geographic coordinates, a basic wake effect matrix is generated in combination with real-time wind direction data, correction is carried out through the maximum mutual information quantization time-delay effect, and then a dynamic adjacency matrix is obtained through self-adaptive fusion; and integrating the multi-dimensional node features and the dynamic adjacency matrix into a space-time diagram sequence data architecture, inputting the space-time diagram sequence data architecture into a multi-scale wake flow perception diagram space-time prediction model, and outputting a multi-fan power prediction value. According to the invention, high-precision multi-fan power prediction can be realized.

The invention relates to a high-performance solid-waste-based offshore wind power grouting material and a preparation method thereof, and a solid-waste-based cementing material is a hydraulic cementing material prepared by processing and grinding one or more solid wastes such as water-quenched blast furnace slag, steel slag, desulfurized gypsum, fly ash, red mud, tailings, carbide slag and phosphogypsum as raw materials according to a certain proportion. The solid waste-based cementing material is adopted to replace 525 Portland cement, the prepared grouting material product is excellent in performance, the carbon emission of the grouting material product is remarkably reduced, the cost is also reduced, resource utilization of industrial solid waste is facilitated, meanwhile, the performance of the grouting material is obviously improved, and the grouting material is suitable for popularization and application. The advantages of ultrahigh strength, elasticity modulus, high flowability, low shrinkage and high durability are realized.

This invention introduces a kinetic energy recovery wind-wave integrated system for offshore wind power generation. The system consists of a semi-submersible platform equipped with a fan and an internal wave energy device. The device includes a shell housing a Power Take-Off (PTO) system, featuring a permanent magnet synchronous linear motor and an active controller. The motor's stator is fixed inside the shell, while its mover is connected to a counterweight block outside the stator, linked to the shell's top via a spring. Limiters are installed at both ends of the shell to restrict the counterweight block's movement. This system utilizes the wave energy device to absorb kinetic energy, which otherwise affects wind turbine stability, and converts it into usable electrical energy via the PTO system. This enhances the stability and safety of offshore wind turbine power generation.

The invention provides a marine ecological environment influence tracking and monitoring method based on an offshore wind power project, and relates to the technical field of marine ecological environment, and the method comprises the steps: carrying out the ecological risk index calculation based on an obtained multi-modal feature vector, and obtaining ecological risk data, and configuring a space-time sequence based on the preprocessed comprehensive data source and the ecological risk data, and predicting a pollution diffusion path and migration blocking based on the preprocessed comprehensive data source. By introducing a dynamic evaluation model of an ecological risk index and combining time sequence modeling and spatial distribution modeling, dynamic analysis and future trend prediction of the ecological risk are realized, and by generating a risk thermodynamic diagram in real time, identifying a high-risk area and simulating a pollutant diffusion path and a biological migration blocking condition, the risk of the ecological risk can be predicted. According to the invention, the monitoring strategy can be dynamically adjusted according to the real-time monitoring data, a scientific basis is provided for construction optimization and ecological restoration, and the accuracy and timeliness of monitoring and evaluation are improved.

The invention discloses an offshore wind power low-frequency networking system based on hybrid topology and a control method, in N onshore receiving end nodes of the offshore wind power low-frequency networking system, one node adopts an M3C current converter, N-1 nodes adopt DRU and MMC current converters, an offshore low-frequency power grid voltage is established through the M3C current converter, and the M3C current converter is connected with the M3C current converter; the power flow control of other power control nodes is realized through the DRU and the MMC, and by adopting the technical scheme of the invention, the engineering construction cost can be obviously reduced under the condition of ensuring the reliable operation of the system, and the method has a good application prospect.

The invention relates to an offshore wind speed prediction method based on a TVFEMD-FE-TCN-Transform model, and the method comprises the steps: obtaining historical offshore wind speed data, carrying out the preprocessing of the data, decomposing the original wind speed data through TVFEMD to obtain a plurality of IMF components, improving the data stability, and carrying out the prediction of the offshore wind speed. According to the method, four types of signals including a high-frequency signal, an intermediate-frequency signal, a low-frequency signal and a trend signal are generated through reconstruction according to IMF component complexity through fuzzy entropy FE, calculation complexity is reduced, a time domain convolutional network TCN is adopted to extract reconstructed signal features, fusion is performed, the reconstructed signal features are input into Transform for wind speed prediction, meanwhile, Transform model parameters are optimized through MWOA, and the wind speed prediction accuracy is improved. Predicting the offshore wind speed by using the optimal parameter combination Transform model to obtain a final offshore wind speed prediction value; according to the method provided by the invention, the problems of insufficient signal decomposition, weak feature extraction capability and low prediction precision of a single prediction model are effectively solved, and powerful support is provided for operation and maintenance management and power grid dispatching of the offshore wind power plant under the condition that the offshore wind speed has intermittent and fluctuation characteristics.

The invention provides an offshore wind turbine generator fault diagnosis method and system based on multi-source sensor data fusion. The method comprises the steps that a vibration signal from at least one component of a wind turbine generator is acquired through a vibration sensor; performing time-frequency conversion on the vibration signal by applying synchronous compression wavelet transform to obtain time-frequency representation of the vibration signal; when the reconstruction error exceeds a preset threshold value, it is judged that an abnormal event exists in the vibration signal; obtaining the position of a part corresponding to the abnormal event; starting an image sensor and an acoustic sensor according to the position of the component, and acquiring an image signal and a sound signal of the component according to the image sensor and the acoustic sensor; according to the DS evidence theory, the vibration signal, the image signal and the sound signal, obtaining the confidence of the fault type; the fault type of the component is judged according to the maximum confidence allocation principle, high-resolution time-frequency analysis can be achieved through synchronous compression wavelet transform (SST), and the fault feature identification degree is improved in combination with the self-encoding neural network and the D-S evidence theory.

The invention discloses an offshore wind power plant micro-siting optimization method considering regular layout. The method comprises the following steps: firstly, obtaining wind data, wind power plant parameters, fan parameters and wake flow parameters; performing multi-angle rotation on the wind power plant based on an equivalent rotation coordinate method, constructing a gridding mixed integer quadratic programming model, and performing rotation rule layout optimization (RRLO-1) to obtain an initial fan layout; on the basis of the initial layout, a hybrid algorithm (GA-ISSA) of a genetic algorithm and a sparrow search algorithm is adopted, the position of a draught fan and the rotation angle of the wind power plant are finely adjusted, and fine rule layout optimization (RRLO-2) is completed; and finally, the wake flow influence is calculated through a Cosine wake flow model and a quadratic sum superposition model, a fan power curve is processed in a piecewise linearization mode, and the final layout is output by taking the maximization of the total generating capacity as the target. According to the method, a fan position configuration scheme meeting the engineering rule layout requirement is provided for early-stage planning of the offshore wind plant, the wake effect is reduced, the power generation efficiency is improved, and development of the offshore wind power industry and low-carbon target implementation are facilitated.

A method for configuring reactive power capacity of a power grid to which offshore wind power is connected on a large scale includes the following steps. Static voltage stability index of substations in a regional power grid to which the offshore wind power is connected on the large scale and at multiple points and relative dynamic voltage drop area index for an N-2 fault are calculated. Thus, weak nodes in voltage stability are located, thereby implementing a prediction of a risk to the voltage stability of the regional power grid. These nodes are used as candidate reactive power compensation configuration nodes. An objective function is established as the minimum total cost of reactive power compensation devices at the candidate reactive power compensation configuration nodes. A multi-type reactive power optimization configuration model including static voltage stability constraints, voltage stability constraints under faulty state, and other constraints is solved.

The invention relates to an offshore wind power prediction method, and aims to improve the accuracy and reliability of prediction. The method comprises the following steps: (1) a data preprocessing stage: detecting an abnormal value in data by using a DBSCAN clustering algorithm, reconstructing the abnormal value by using a KNN interpolation method, detecting time sequence abnormity through an LSTM automatic encoder, and performing regression reconstruction by using LSTM to ensure the retention of time sequence features; (2) a feature engineering stage: screening out key features through correlation analysis, generating a label column through K-means clustering and wind direction classification, and extracting features such as wind direction change rate, time periodicity and wind speed interaction; and (3) a model construction stage: constructing a composite model in combination with multi-scale convolution (Inception), a bidirectional long short-term memory neural network (BiLSTM) and a multi-head self-attention mechanism, extracting local features through a convolution layer, capturing a time dependency relationship through a bidirectional LSTM layer, enhancing the attention of key features by using the multi-head self-attention mechanism, and finally realizing high-precision wind power prediction.

The invention relates to the technical field of monitoring, in particular to a method and system for detecting and evaluating the corrosion risk of an offshore wind power steel structure. The method comprises the following steps: acquiring corrosion environment parameters and corrosion response parameters of a corrosion area in the offshore wind power steel structure; according to the corrosion environment parameters and the corrosion response parameters, the real-time corrosion rate of the corrosion area is determined; determining a local stress concentration factor of the corrosion area according to the three-dimensional scanning characteristics of corrosion deposits in the corrosion area; the dynamic pressure parameters of the marine environment serve as dynamic boundary conditions, the real-time corrosion rate and the local stress concentration factor serve as the basis, and the structural rigidity degradation amount of the steel structure in the corrosion area is determined through finite element iteration; according to the structural rigidity degradation amount, the structural safety coefficient of the steel structure in the corrosion area is determined; and determining the corrosion risk of the steel structure in the corrosion area according to the dynamic pressure fluctuation range of the marine environment and the structure safety coefficient of the steel structure in the corrosion area.

The invention discloses an offshore wind power fault monitoring method based on a knowledge graph and digital twinning, and aims to solve the problems that multi-source data acquisition is dispersed, the transmission delay is high, and real-time convergence and integration are difficult to realize in the operation state monitoring of offshore wind power equipment. According to the invention, the following modules are provided: a multi-source data acquisition layer is used for solving the problems of dispersed data acquisition and transmission lag and ensuring the real-time performance; the knowledge graph construction module is used for solving the problems of extraction, fusion and storage of equipment entity relationships; the digital twin modeling module realizes visual presentation and accurate simulation of the state of physical equipment; the fault monitoring reasoning module solves the problems of anomaly detection and root cause positioning; the intelligent early warning decision module determines an early warning level and efficiently matches a solution; the visual interaction module solves the problems of scattered information display and poor linkage, supports third-party docking, realizes accurate early warning and root cause positioning, improves the decision-making efficiency, adapts to severe environments, supports large-scale wind power plant monitoring, and reduces the operation and maintenance cost.

The invention discloses a fault ride-through test method for an offshore wind power flexible direct output system, and the method comprises the steps: building a fault equivalent circuit of the offshore wind power flexible direct output system, analyzing the operation characteristics of an AC power grid side under a low-voltage fault, and determining the incidence relation between the DC side excess energy and the power grid voltage drop; establishing a model representing each component in the fault equivalent circuit, wherein the components at least comprise a machine-side converter, a grid-side converter, a direct-current capacitor and an unloading resistor; when a low-voltage fault of an alternating-current power grid side is detected, executing the following cooperative control based on the model: synchronously starting unloading resistance control and reactive power support control, wherein an unloading resistor dissipates excess energy of a direct-current side through a direct-current chopper; the grid-side converter injects a capacitive reactive current which is deeply matched with the voltage drop of the power grid so as to improve the voltage of a grid-connected point; and if the direct-current voltage continuously exceeds the preset threshold value, starting power prompt drop control, and reducing the output power of the unit according to a gradient until the system recovers to be stable.

The invention discloses a double-layer multi-target planning method and system for a bilateral looped network current collection system of an offshore wind plant, and the method comprises the steps: inputting the data of the offshore wind plant into a double-layer planning model of the bilateral looped network current collection system, and enabling an outer-layer model to be used for constructing a plurality of two-dimensional populations composed of weights and the number of clusters, and inputting the two-dimensional populations into an inner-layer model; the inner-layer model is used for grouping the wind turbine generators under different two-dimensional populations by adopting a clustering algorithm, taking minimum cable investment cost and minimum network loss as objective functions and adding constraint conditions to construct a path optimization model so as to carry out path planning on the wind turbine generator groups, solving total cost and outputting the total cost to the outer-layer model; and ending iteration of the outer layer model when the total cost is converged, if not, continuing to output an optimal solution result, and otherwise, continuing to update the two-dimensional population. The invention aims to spontaneously cluster wind turbine generators through a heuristic algorithm and find the optimal path of the bilateral looped network of the wind turbine generators so as to realize accurate planning of the bilateral looped network current collection system of the offshore wind power plant.

The invention relates to an offshore wind power operation environment scene construction method considering typhoon forecast errors. The method comprises the steps of selecting similar historical typhoon forecast data according to current typhoon forecast information; based on wind speeds of similar historical typhoon forecast and current typhoon forecast, combining marine environment element information to construct a marine environment scene information space; a kernel density estimation model of historical typhoon wind speed forecast errors is constructed, corresponding kernel density bandwidths are calculated and updated according to different typhoon forecast timeliness, and historical forecast wind speed error distribution is obtained; and inputting the marine environment scene information space and the historical forecast wind speed error distribution into the improved generative adversarial network, and generating a marine environment scene of which the wind speed interval meets the historical typhoon wind speed forecast error distribution through the wind speed interval constraint loss. Compared with the prior art, the marine environment scene is updated according to the wind speed error distribution under different forecast time periods of the typhoon, and the scene generation quality is improved.

The invention provides a physical-numerical hybrid scale model test method for a floating fan, and belongs to the technical field of offshore wind power generation. The test method comprises the steps that the floating fan is modeled into a physical model and a numerical model, and besides the physical model and the numerical model, a test platform further comprises a measuring system and a loading system; real-time interaction is carried out on actual measurement signals of the measurement system and calculation results of the numerical model through the computer, loading of the signals is achieved through the loading system, and building and closed-loop control of the hybrid test platform are achieved. And finally, required information is extracted through visual interface monitoring. According to the method, the dynamic response performance of the key structure can be accurately captured, and a series of problems of scale effect, scale criterion incompatibility caused by the scale effect, difficulty in indoor test simulation of the offshore floating fan and the like can be solved.

An offshore wind turbine integral coupling fatigue calculation method based on artificial intelligence belongs to the technical field of offshore wind power engineering, is used for solving the problem of efficient and high-precision evaluation of the fatigue life of an offshore wind turbine, and is characterized in that key environment parameter vectors influencing structural response and a data set of corresponding fatigue damage labels are acquired; training a deep neural network model by using the data set; the deep neural network model outputs corresponding fatigue damage per unit time in response to a central point parameter of an environment working condition block in an input long-term joint probability distribution diagram of the wind power site; according to the method, the defects that a traditional time domain simulation method is high in calculation cost and long in period are overcome, the calculation efficiency is improved by a plurality of orders of magnitude while the precision is guaranteed, and a powerful tool is provided for rapid design and optimization of the offshore wind turbine.

The invention relates to the technical field of power systems, and discloses a broadband oscillation risk assessment method and system for offshore wind power through a flexible direct current sending-out system, and the method comprises the steps: dividing a broadband oscillation risk assessment frequency band into a medium-high frequency band and a sub-super-synchronous frequency band; aiming at different broadband oscillation risk assessment frequency bands, respectively establishing an offshore wind power plant side impedance model and a flexible direct current converter side impedance model in a corresponding offshore wind power flexible direct current sending-out system, and determining an equivalent impedance frequency characteristic curve of the offshore wind power plant side and the flexible direct current converter side. The broadband oscillation risk of the offshore wind power through the flexible direct current sending-out system is comprehensively evaluated by using the equivalent impedance frequency characteristic curve, the topological structure and the operation condition are fully considered, and the accuracy and adaptability of evaluation are improved. And when the broadband oscillation risk occurs, the system is adjusted in a targeted manner according to different evaluation frequency bands, so that the broadband oscillation risk is effectively eliminated, and the operation stability of the offshore wind power output system through the flexible direct current is enhanced.

The invention relates to a large-scale offshore engineering geologic model modeling system and method, and relates to the technical field of offshore engineering geologic investigation and modeling. According to the method, through the steps of multi-source data acquisition, preprocessing, fusion, three-dimensional geological modeling, model optimization, dynamic updating, visual analysis and the like, large-scale geological survey data can be efficiently processed, a high-precision three-dimensional geological model is generated, and dynamic updating and visual analysis are supported. The method has the advantages of high efficiency, high precision, real-time performance, engineering applicability and the like, and is suitable for geological modeling and geological condition analysis of engineering such as offshore wind power, submarine pipelines, ocean platforms and the like.

The invention relates to an offshore wind power plant wake flow optimization control method based on deep reinforcement learning, and the method comprises the following steps: constructing a directed graph, and for each node in the directed graph, updating the input feature of the current node through the input features of a graph neural volume accumulation and surrounding neighbor nodes, the digraph takes each offshore wind turbine in an offshore wind plant as a node and the upstream and downstream relationship between the wind turbines as an edge; and taking the input characteristics of each node as the input of the trained Actor-Critic network, obtaining an input characteristic action value, and realizing wake flow optimization control of the offshore wind plant. Compared with the prior art, the method has the advantages of enhanced generalization ability, strong timeliness and dynamic adaptability, efficient wake flow control and the like.

The invention provides a single-point mooring floating type fan platform capable of actively yawing, and belongs to the technical field of offshore wind power. The problem that the aerodynamic efficiency of an impeller is reduced due to the fact that a fan platform needs to bear multiple coupling effects of ocean currents and waves and the fan platform deviates from the best windward direction due to the hydrodynamic force coupling effect when an included angle is formed between the ocean current direction and the wind direction under the action of the complex ocean environment is solved. The system comprises a wind turbine generator, a mast type tower, a platform foundation, a single-point mooring device and a flow guide device, the edge of the platform foundation is connected with the single-point mooring device and can rotate by 360 degrees around the single-point mooring device. The flow guiding device is installed at the edge position of the platform foundation and arranged opposite to the single-point mooring device, the horizontal section of the flow guiding device is in a symmetrical streamline shape, and the flow guiding device is provided with a driving device which drives the flow guiding device to rotate in the horizontal direction and adjusts the acting force of ocean current on the fan platform. The power generation device is mainly used for improving the power generation efficiency of the mast type tower offshore wind turbine platform.

The invention discloses a short-term wind speed prediction method for multiple offshore wind power plants, relates to the technical field of power system intellectualization, and constructs a dynamic graph structure fusing the correlation between geographic distance and wind speed according to the correlation between the geographic position of a target area and the wind speed, namely a multi-wind-plant connected graph, and represents the spatial topological relation of a wind power plant group. A wind power plant group is mapped into a node network by constructing a dynamic graph structure fusing geographic distance and wind speed correlation, spatial dependence intensity between nodes is quantized by using a weighted adjacent matrix, spectral domain convolution operation is carried out by a graph convolution network based on a normalized Laplacian matrix, and the spatial dependence intensity between nodes is quantized by using a normalized Laplacian matrix. Efficient neighborhood feature aggregation is achieved through Chebyshev polynomial approximation, complex spatial association caused by geographic position difference and meteorological condition interaction can be accurately captured, the defect of non-Euclidean spatial relationship modeling in a traditional method is overcome, and the representation capacity of the spatial dependency relationship in the multi-wind-power-plant environment is remarkably improved.

The anti-scour device comprises a protective cover and a spoiler, the protective cover is used for being arranged on a pile body of the wind power single pile in a sleeving mode and enabling the protective cover to be arranged on a gravel layer around the pile body in a covering mode, a flow guide face is arranged on the outer side of the protective cover, and the flow guide face gradually rises from the periphery of the protective cover to the middle of the protective cover. The spoilers are arranged on the outer side of the protective cover at intervals in the circumferential direction of the protective cover, one ends of the spoilers in the length direction face the middle of the protective cover, and the other ends of the spoilers in the length direction face the periphery of the protective cover. And under the action of the protective cover and the spoiler, the anti-scouring performance of the whole anti-scouring device applied to the offshore wind power single pile is improved, and the mounting stability of the wind power single pile is guaranteed.

The invention discloses a foundation scouring depth monitoring method and a foundation scouring depth monitoring system for an offshore wind turbine generator, and relates to the technical field of monitoring. Analyzing the relationship between the scouring depth safety value threshold value and the scouring rate of the offshore wind turbine generator set in different environments and states and each parameter of seawater, monitoring each information of the current offshore wind turbine generator set, judging the stability of the current offshore wind turbine generator set, if the stability is poor, performing early warning, and if the stability is good, performing early warning. If yes, whether maintenance early warning needs to be carried out or not is analyzed, if yes, parameters of current seawater are obtained, early warning levels of maintenance and the like of the offshore wind turbine generator are judged according to the parameters of the current seawater and the relation between the scouring rate and the parameters of the seawater, early warning is carried out, and the effectiveness of stability judgment of the offshore wind turbine generator is guaranteed; and the timeliness of maintenance of the offshore wind turbine generator is also ensured.