A hydrodynamic analysis method and apparatus for offshore photovoltaic platforms

Abstract

This application provides a hydrodynamic analysis method and apparatus for offshore photovoltaic platforms. The method acquires synchronous data streams from a multi-source sensor network deployed on the platform. These synchronous data streams contain multi-dimensional monitoring data reflecting the platform's operational status, including performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental conditions, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. A data fusion model is used to perform cross-domain correlation analysis on the multi-dimensional monitoring data, establishing dynamic correlations between performance data, environmental data, and hydrodynamic data. Based on these dynamic correlations, assessment information for evaluating the platform's overall operational status is generated. This method significantly improves the accuracy of hydrodynamic performance prediction for offshore photovoltaic platforms through nonlinear time-domain analysis involving multi-load coupling and dynamic wetted surface adaptation.

Description

Technical Field

[0001] This application relates to the field of offshore photovoltaic power generation technology, and more specifically, to a hydrodynamic analysis method and apparatus for offshore photovoltaic platforms. Background Technology

[0002] With the development of marine renewable energy, offshore photovoltaic (PV) power generation has become an important form. Offshore PV platforms typically consist of large-scale photovoltaic arrays fixed to floating foundations (such as pontoons or semi-submersible platforms) via flexible connectors (like hinges and ropes), forming a typical complex system involving rigid-flexible coupling and multi-body interference. Currently, when performing hydrodynamic analysis on this type of structure, one of the following two simplification methods is commonly used: The overall rigidity simplification method treats the entire photovoltaic array and its foundation as a single rigid body, ignoring the relative motion between array units and fluid interference effects, and only calculating the overall platform's motion response in waves. This method is computationally simple but deviates significantly from reality because the photovoltaic array is not rigidly connected; the motion of its parts is not synchronized, and there are significant wave shading and radiation interference effects between the array units.

[0003] Isolated Unit Superposition Method: This method calculates the hydrodynamics of individual photovoltaic panel units in waves, and then estimates the response of the entire array through simple linear superposition or static coupling. Although this method considers the existence of many bodies, it neglects the dynamic and nonlinear fluid interactions between units (such as eddy currents and wave diffraction superposition), as well as the energy transfer and motion hysteresis effects caused by flexible connections.

[0004] However, existing hydrodynamic analysis methods cannot accurately simulate the asymmetric and non-uniform dynamic load distribution induced by complex fluid interference effects and flexible connection coupling between large-scale photovoltaic array units and between them and the base platform in offshore photovoltaic platforms. This leads to significant deviations in the prediction of the platform's overall motion response, structural connection point loads, and fatigue life, directly affecting the platform's safety design and economic assessment. Summary of the Invention

[0005] The purpose of this application is to provide a hydrodynamic analysis method and apparatus for offshore photovoltaic platforms, which significantly improves the accuracy of hydrodynamic performance prediction of offshore photovoltaic platforms through nonlinear time-domain analysis of multi-load coupling and dynamic wet surface adaptation, and provides reliable technical support for platform optimization design and safety assessment.

[0006] Firstly, a hydrodynamic analysis method for offshore photovoltaic platforms is provided, which may include: Acquire synchronous data streams collected by a multi-source sensor network deployed on the platform. The synchronous data streams include multi-dimensional monitoring data reflecting the platform's operating status, including performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental status, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. Cross-domain correlation analysis is performed on the multidimensional monitoring data using a data fusion model to establish dynamic correlations between performance data, environmental data, and hydrodynamic data. Based on the dynamic correlation, evaluation information is generated to assess the overall operational status of the platform.

[0007] In one possible implementation, the multi-source sensor network adopts a hierarchical distributed topology, including: An energy capture and monitoring layer, deployed on the platform's energy harvesting device, is used to collect the performance data; The platform structure response layer is deployed on the load-bearing structure and motion-sensitive parts of the platform to collect the hydrodynamic data. An environmental field sensing layer, deployed above, around, and underwater on the platform, is used to collect the environmental data. The mooring boundary monitoring layer is deployed at the connection interface between the platform and the mooring system to collect hydrodynamic data reflecting the mechanical response of the mooring system. The sensors at each layer synchronize their data using a unified timing reference.

[0008] In one possible implementation, the energy capture monitoring layer includes a power generation monitoring unit and / or vibration sensors integrated into the photovoltaic array; The platform structure response layer includes an inertial measurement unit, a strain sensor, and a six-component force sensor arranged on the platform float or main structure. The environmental field sensing layer includes at least one of ultrasonic anemometer, wave radar, and acoustic Doppler current profiler. The mooring boundary monitoring layer includes tension sensors and tilt sensors installed at the connection ends of mooring cables or anchor chains.

[0009] In one possible implementation, the multi-source sensor network is also deployed with edge intelligent acquisition nodes; When at least one of the following parameters—the amplitude of the platform's motion acceleration, the rate of change of stress at key locations, or the dynamic fluctuation range of mooring tension—continuously exceeds its corresponding dynamic threshold, the edge intelligent acquisition node is triggered to perform at least one of the following operations: Increase the sampling frequency of sensors in the platform structure response layer and mooring boundary monitoring layer; The environmental field perception layer is triggered to start an enhanced scanning mode for wind and wave fields.

[0010] In one possible implementation, the synchronous data stream also carries a time-space tag; Cross-domain correlation analysis is performed on the multidimensional monitoring data using a data fusion model to establish dynamic correlations between performance data, environmental data, and hydrodynamic data, including: Based on the spatiotemporal tags carried by the synchronous data stream, time synchronization alignment and data fusion are performed on heterogeneous multidimensional monitoring data from multi-source sensor networks to obtain a fused dataset. The fused dataset is input into a multi-channel deep neural network model; the input channels of the model correspond to performance data, environmental data, hydrodynamic data of platform structure, and hydrodynamic data of mooring system mechanical response, respectively. Through the shared feature extraction layer in the multi-channel deep neural network, heterogeneous data is mapped to a unified implicit feature space; In the implicit feature space, dynamic correlations between monitoring data of different dimensions are calculated and established through an attention mechanism.

[0011] In one possible implementation, based on the dynamic correlation, evaluation information for assessing the overall operational status of the platform is generated, including: Based on the dynamic correlation, a digital twin simulation scenario of the platform under current and predicted environmental conditions is constructed; In the digital twin simulation scenario, preset extreme events or failure modes are injected to perform stress-life simulation and extrapolation. Based on the simulation results, an assessment is generated that includes predictions of the remaining service life of key components and recommendations for preventative maintenance windows.

[0012] In one possible implementation, the evaluation information is output in the form of a visual interactive interface.

[0013] Secondly, a hydrodynamic analysis device for offshore photovoltaic platforms is provided, the device comprising: The acquisition unit is used to acquire synchronous data streams collected by a multi-source sensor network deployed on the platform. The synchronous data streams include multi-dimensional monitoring data reflecting the platform's operating status, including performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental status, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. A data fusion model is used to perform cross-domain correlation analysis on the multidimensional monitoring data and establish dynamic correlation relationships between performance data, environmental data and hydrodynamic data. The generation unit is used to generate evaluation information for assessing the overall operating status of the platform based on the dynamic correlation relationship.

[0014] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0015] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0016] This application provides a hydrodynamic analysis method and apparatus for offshore photovoltaic platforms. The method acquires synchronous data streams from a multi-source sensor network deployed on the platform. These synchronous data streams contain multi-dimensional monitoring data reflecting the platform's operational status, including performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental conditions, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. A data fusion model is used to perform cross-domain correlation analysis on the multi-dimensional monitoring data, establishing dynamic correlations between performance data, environmental data, and hydrodynamic data. Based on these dynamic correlations, assessment information is generated to evaluate the platform's overall operational status. This method, through nonlinear time-domain analysis involving multi-load coupling and dynamic wetted surface adaptation, significantly improves the accuracy of hydrodynamic performance prediction for offshore photovoltaic platforms, providing reliable technical support for platform optimization design and safety assessment. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a hydrodynamic analysis method for offshore photovoltaic platforms provided in this application embodiment; Figure 2 A schematic diagram of a hydrodynamic analysis device for an offshore photovoltaic platform provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The words "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The words "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but do not exclude other elements or objects. The words "connected," "coupled," or "connected," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] The hydrodynamic analysis method for offshore photovoltaic platforms provided in this application relies on a multi-source sensor network deployed on the platform. This network employs a hierarchical distributed topology to achieve comprehensive, multi-dimensional state monitoring of the platform. The network comprises four functional layers, with sensors at each layer synchronizing data using a unified timing reference (e.g., a clock synchronization signal based on GPS or a high-precision crystal oscillator) to ensure strict time alignment of the acquired synchronized data streams.

[0021] The multi-source sensor network adopts a hierarchical distributed topology, including: The energy capture monitoring layer consists of sensors deployed on the platform's energy harvesting devices, primarily used to collect performance data reflecting the platform's energy capture performance. Specifically, this layer may include a power generation monitoring unit integrated into the photovoltaic array (for real-time monitoring of DC / AC side voltage, current, and power output) and / or vibration sensors (for monitoring micro-vibrations of the photovoltaic panels caused by wind-induced vibrations or wave-induced motion, which may affect photoelectric conversion efficiency or mechanical fatigue).

[0022] The platform structure response layer consists of sensors deployed on the platform's load-bearing structure (such as floats, support beams, and columns) and motion-sensitive parts (such as the platform's center of gravity and edges) to collect hydrodynamic data reflecting the platform's structure. This data directly characterizes the platform's dynamic response under the combined effects of wind, waves, and currents. Typical sensors in this layer include at least: (a) Inertial Measurement Unit (IMU): Used to measure the acceleration, angular velocity, and calculated displacement and attitude angle of the platform’s six degrees of freedom motion (sway, roll, heave, pitch, pitch and yaw).

[0023] (b) Strain sensor: attached or embedded on or inside the surface of critical load-bearing components to monitor local strain in the structure and thus estimate stress state.

[0024] (c) Six-component force sensor: installed at a specific connection point or support, used to directly measure the force and torque in three directions.

[0025] The environmental sensing layer consists of sensors deployed above, around, and underwater on the platform to collect environmental data reflecting the platform's environmental conditions. This layer is the source of understanding the external stimuli affecting the platform. Typical devices include at least one of the following: (a) Ultrasonic anemometer: installed on the mast at a high point of the platform to measure the wind speed and direction at the location of the platform.

[0026] (b) Wave radar: Installed at an appropriate location on the platform, it transmits electromagnetic waves to the sea surface and receives the echoes, and inverts wave parameters such as wave spectrum, significant wave height, and spectral peak period.

[0027] (c) Acoustic Doppler Current Profiler (ADCP): Installed on the underwater part of the platform or lowered via cable, it measures the velocity and direction profiles of ocean currents at different depths.

[0028] The mooring boundary monitoring layer consists of sensors deployed at the interface between the platform and the mooring system (such as cable guides and mooring points) to collect data reflecting the mechanical response of the mooring system. This data is crucial for assessing the safety of the mooring system and the platform's positioning capabilities. It mainly includes: Tension sensor: Installed at the connection end of the mooring cable or anchor chain, it directly measures the tension of the mooring cable.

[0029] Tilt sensor: Installed near the platform end of the mooring cable, it measures the cable exit angle and, combined with tension, can analyze the direction of force.

[0030] In addition, edge intelligent acquisition nodes can be deployed in multi-source sensor networks. These edge intelligent acquisition nodes are embedded devices with certain computing capabilities, responsible for coordinating and managing sensors within their assigned area, and capable of executing rapid responses based on local rules.

[0031] The sensors at each layer synchronize their data using a unified timing reference.

[0032] In some preferred embodiments, some or all of the sensor nodes in the multi-source sensor network are designed or upgraded to event-driven intelligent sensors. These sensors integrate microprocessors, local memory (such as cache), and embedded intelligent algorithms on top of traditional sensing units, enabling them to perform local computation, state judgment, and autonomous decision-making. That is, at least some or all of the sensors in the multi-source sensor network can be event-driven intelligent sensors; event-driven intelligent sensors have a built-in normal data model for real-time determination of whether the collected data (multi-dimensional monitoring data) deviates from the normal state.

[0033] Among them, the following sensors are preferably event-driven: Strain sensors: crucial for monitoring fatigue hotspots in critical load-bearing components (such as main beam welds and connections between columns and the float). Stress abrupt changes in these areas may indicate crack initiation or localized buckling. Inertial measurement units (IMUs): especially those deployed in motion-sensitive areas of the platform (such as the four corners). Abnormal abrupt changes in platform motion (such as large-amplitude instantaneous accelerations) are direct signals of extreme wave impacts or resonance.

[0034] Six-component force sensor: installed on the main load path, its data can directly reflect the anomalies of the overall or local load.

[0035] Tension sensor: Sudden and large fluctuations in mooring tension or a sustained approach to the safe limit are the most direct signs that the mooring system is facing the risk of failure.

[0036] Tilt sensor: A rapid change in the cable outgoing angle may indicate that the anchor chain is dragging, the anchor is running, or it is snagging on an underwater obstacle.

[0037] Wave Radar: It can be configured to output statistical wave parameters at a lower frequency under normal conditions, but the built-in algorithm can analyze the raw echo spectrum in real time and trigger an event when abnormal wave (such as distorted wave or extreme wave group) spectral characteristics are detected.

[0038] Vibration sensor (integrated into photovoltaic panel): An abnormal increase in local vibration of the photovoltaic panel may indicate loose fasteners or structural damage.

[0039] The internal working mechanism of event-driven smart sensors is as follows: when a deviation from the normal state is detected, the sensor autonomously triggers the event reporting mode, including increasing the local sampling rate, caching high-resolution data before and after the event, and reporting through a high-priority communication link; based on the first event report received, according to the preset association map, it triggers other sensors that are physically or logically associated with the event to enter the collaborative event monitoring state.

[0040] Each event-driven smart sensor internally runs a routine data model. This model is a lightweight model designed for embedded environments, for example: Statistical Model: During the initial learning phase (such as the first quiet period after platform installation), the sensor autonomously learns the statistical characteristics of its measurement data under normal operating conditions, including but not limited to the mean, standard deviation, amplitude distribution (such as Rayleigh distribution, Weibull distribution parameters), and short-term time series characteristics (such as zero-crossing rate). These characteristics together constitute a normal envelope.

[0041] Lightweight machine learning models, such as one-class support vector machines (SVMs) or autoencoders, can effectively distinguish between normal data and anomalous data that deviates from the norm after being trained on normal data. Autoencoders determine anomalies by comparing the error between the input data and the reconstructed data, and are particularly suitable for processing waveform data such as vibration and strain.

[0042] Real-time judgment process: While sampling at a fundamental frequency (e.g., 1Hz), the sensor inputs real-time data into a built-in normal data model for calculation. The criteria for judging "deviation from normal" can be composite, such as: the current sampled value exceeds the range of "mean ± K times standard deviation" based on historical statistics N times consecutively; the real-time calculated data characteristics (e.g., the root mean square value, peak factor, and energy proportion of the spectrum in a certain dangerous frequency band of the signal in the last 10 seconds) exceed the learned normal threshold; the reconstruction error of the autoencoder is continuously higher than the preset threshold.

[0043] For the specific operation of the event reporting mode: Once a deviation from the normal state is detected, the sensor immediately and seamlessly switches from the "periodic sleep / listening" mode to the event reporting mode, which includes the following sequential operations: Increase the local sampling rate: for example, instantly increase it from a base of 1Hz to 100Hz or higher to capture transient details and the complete waveform of anomalous events.

[0044] High-resolution data caching: The circular buffer inside the sensor (typically designed to store tens of seconds of data before and after the event trigger) stops overwriting, completely locking in the high-resolution raw data for a full duration before and after the event trigger point. This ensures that complete information including the event's cause, development process, and peak values ​​is preserved.

[0045] Reporting via high-priority communication link: The sensor immediately sends a compact "event alarm message" to the central processing unit via its reserved high-priority communication channel (e.g., in a wireless network using TDMA or priority scheduling, the event message has the highest interrupt privileges). This message includes at least: the sensor's unique ID, the event trigger timestamp, a preliminary determination of the event type (e.g., "sudden increase in tension," "abnormal vibration"), the event severity level, and a summary of the characteristics of the cached high-resolution data segment (e.g., peak value, duration).

[0046] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0047] Figure 1 This is a flowchart illustrating a hydrodynamic analysis method for offshore photovoltaic platforms, provided as an embodiment of this application. Figure 1 As shown, the method may include: Step S110: Obtain the synchronous data stream collected by the multi-source sensor network deployed on the platform. This synchronous data stream contains multi-dimensional monitoring data reflecting the platform's operating status.

[0048] The multidimensional monitoring data may include performance data reflecting the platform's energy capture performance, environmental data reflecting the environmental conditions in which the platform is located, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system.

[0049] Each layer of sensors continuously collects raw data according to a preset sampling frequency (e.g., 1Hz to 100Hz, set according to monitoring requirements). All sensors are connected to a synchronous clock network, assigning a high-precision spatiotemporal tag (including an absolute timestamp and sensor location / number) to each frame of data. The data is transmitted to the central processing unit (or cloud server) via wired (e.g., Ethernet) or wireless (e.g., LoRa, 5G) methods, forming a unified synchronous data stream. This data stream integrates multi-dimensional monitoring data reflecting the platform's operational status, specifically including: Performance data: from the energy capture monitoring layer, such as the instantaneous power of the photovoltaic array, cumulative power generation, vibration spectrum, etc.

[0050] Environmental data: from the environmental field sensing layer, such as wind speed U10, wind direction, significant wave height Hs, spectral peak period Tp, surface flow velocity Vc, etc.

[0051] Hydrodynamic data includes: hydrodynamic data of the platform structure: from the platform structure response layer, such as the time histories of motion acceleration / displacement of the six degrees of freedom of the platform, the time histories of strain / stress of key parts, and the time histories of the six force components at specific measuring points. Hydrodynamic data of the mechanical response of the mooring system: from the mooring boundary monitoring layer, such as the time histories of tension and cable departure angles of each mooring cable.

[0052] This step, through a hierarchical, distributed, and synchronous sensor network, enables the systematic and synchronized collection of data across the entire chain of "power generation performance - environmental excitation - structural response - mooring constraints" of offshore photovoltaic platforms, providing a high-quality and highly consistent data foundation for subsequent cross-domain correlation analysis.

[0053] Step S120: Perform cross-domain correlation analysis on multidimensional monitoring data through a data fusion model to establish dynamic correlation relationships between performance data, environmental data, and hydrodynamic data.

[0054] The specific implementation includes the following sub-steps: Step 1: Based on the spatiotemporal labels carried by the synchronous data stream, perform time synchronization and alignment on heterogeneous multidimensional monitoring data from different sensors (heterogeneous data sources) in the multi-source sensor network. Alignment algorithms can employ interpolation methods (such as linear interpolation or spline interpolation) to unify data from different sampling times onto the same time series. Subsequently, necessary data cleaning (such as outlier removal and smoothing filtering) and normalization are performed. The aligned and cleaned data are organized into a structured fusion dataset according to the time series. Each row in this dataset corresponds to a synchronization time point, and each column corresponds to the observation values ​​from different sensor channels.

[0055] Step 2: Divide the preprocessed fused dataset into four logical channels according to the physical meaning of the data, and use them as input to the multi-channel deep neural network model. These four input channels correspond to: performance data channel, environmental data channel, platform structure hydrodynamic data channel, and mooring system mechanical response hydrodynamic data channel. Each channel may contain multiple time series variables.

[0056] Step 3: Map heterogeneous data to a unified implicit feature space through a shared feature extraction layer in a multi-channel deep neural network. Specifically, the first part of the multi-channel deep neural network is a shared feature extraction layer (typically composed of a Convolutional Neural Network (CNN) or a Long Short-Term Memory (LSTM) network). This layer is designed to allow data from the four channels to interact in the early stages. Specifically, the data from each channel first undergoes shallow feature extraction through an independent sub-network, and then these features are concatenated or interact through a specific fusion layer (such as a fully connected layer), ultimately mapping to a unified implicit feature space. In this feature space, the original low-level observation data is transformed into high-dimensional abstract features that can simultaneously characterize the intrinsic relationships between environmental stimuli, structural responses, mooring states, and performance outputs.

[0057] Step 4: In the implicit feature space, calculate and establish dynamic correlations between monitoring data of different dimensions through an attention mechanism. Specifically: In the obtained implicit feature space, an attention mechanism (such as the self-attention or cross-attention module in Transformer) is introduced. This mechanism can calculate the correlation weights between feature vectors of different time steps and different data channels. For example, it can calculate the correlation strength between the platform's pitch motion (structural response feature) and the power fluctuation of a certain photovoltaic array (performance feature) under a specific wave condition (environmental feature), or the causal time-series relationship between mooring tension mutation (boundary response feature) and platform sway motion (structural response feature). These correlations calculated and established by attention weights are dynamic, meaning they will adaptively adjust as the input data (i.e., the real-time state of the platform) changes, thereby accurately capturing the dominant coupling mechanism of the system under different operating conditions.

[0058] This step leverages the powerful nonlinear fitting and feature learning capabilities of deep learning models, overcoming the limitations of simplified assumptions in traditional physical models. It can automatically and accurately extract the complex and dynamic mapping relationships between environment, structure, mooring, and performance from massive amounts of measured data, laying the foundation for accurate state assessment and prediction.

[0059] Step S130: Based on dynamic correlation, generate evaluation information for assessing the overall operational status of the platform.

[0060] The specific implementation includes the following steps: Step 1: Based on dynamic relationships, construct a digital twin simulation scenario of the platform under current and predicted environmental conditions. Specifically: Based on the obtained dynamic relationships (essentially a data-driven system proxy model), and combining current monitoring data to initialize the model state, construct a digital twin of the platform under current environmental conditions in the digital space.

[0061] Furthermore, short-term wind and wave forecast data can be integrated, and the predicted environmental conditions (such as the forecast wind speed and wave height for the next hour) can be input into the model to construct a digital twin simulation scenario under the predicted environmental conditions.

[0062] Step 2: In the digital twin simulation scenario, inject preset extreme events or failure modes to perform stress-life simulation. Specifically: In the constructed digital twin simulation scenario, preset extreme events or failure modes can be injected for simulation. For example: Injecting extreme events: Input a 50-year return period extreme wave sequence into the simulation to simulate the platform's dynamic response and mooring load under these conditions.

[0063] Injection Failure Mode: Simulate the sudden breakage of a mooring cable, and deduce the platform's motion trajectory after the failure of a single cable, the load redistribution of the remaining mooring cables, and the possible structural collision risks.

[0064] The core of these simulations is stress-life simulation. That is, based on the time-varying stress history of key structural parts (such as welds and support points) obtained from the simulation, combined with the material's SN curve (stress-life curve) and fatigue cumulative damage theory (such as Miner's linear cumulative damage rule), the fatigue damage increment of the part under the simulated working conditions is calculated, and its cumulative damage value is updated accordingly.

[0065] Step 3: Based on the simulation results, generate assessment information including predictions of the remaining service life of key components and recommendations for preventative maintenance windows. Specifically: Based on the simulation results and fatigue damage calculations, generate structured assessment information with direct guiding significance. This information not only includes a description of the current state (e.g., the platform is currently moving smoothly and the mooring tension is within a safe range), but more importantly, it includes predictive content, such as: predictions of the remaining service life of key components: based on the predictions of current cumulative damage and future typical environmental load spectra, estimate the remaining fatigue life of key welded joints, mooring cables, and other components (e.g., "Under current sea conditions, the remaining fatigue life of the connector at mooring point 3 is expected to be 8.2 years").

[0066] Recommended preventive maintenance window: Taking into account factors such as the platform's power generation plan, weather window, and operation and maintenance resources, and based on the predicted remaining life and damage development rate, the optimal time window for maintenance or replacement is recommended (e.g., "It is recommended to conduct fatigue crack inspection on photovoltaic support No. 5 during the calm period in April next year").

[0067] Furthermore, the generated assessment information is preferably output to platform operations and maintenance personnel or a remote monitoring center in the form of a visual interactive interface. This interface is a comprehensive dashboard that integrates at least the following functional modules: Real-time 3D motion posture display of the platform: Based on IMU data, the six degrees of freedom motion of the platform is rendered in real time in the form of 3D animation, intuitively displaying the platform's swaying state.

[0068] Key data time series curve comparison: The time series curves of environmental data (wind, waves), structural response data (motion, stress), mooring data (tension), and performance data (power) are displayed side by side on the same time axis, and the strongly correlated periods identified by the attention mechanism in S2 can be highlighted, which is convenient for manual analysis and verification.

[0069] Assessment Conclusion Summary Panel: Clearly presents the assessment conclusions generated by S3.3 in the form of structured text, charts, dashboards, etc., including safety status rating, remaining life prediction, maintenance recommendations, early warning information, etc.

[0070] In some embodiments, when at least one of the evaluation information, including the amplitude of the platform's motion acceleration, the rate of change of stress at key locations, or the dynamic fluctuation range of mooring tension, continuously exceeds its corresponding dynamic threshold, the edge intelligent acquisition node may be triggered to perform at least one of the following operations: increase the sampling frequency of the sensors in the platform structure response layer and the mooring boundary monitoring layer; trigger the environmental field perception layer to start an enhanced scanning mode for wind and wave fields.

[0071] Specifically: The edge intelligent acquisition node continuously receives evaluation information (some key indicators) from the central processing unit or calculated locally. This node has preset dynamic thresholds (which can be set based on historical statistics or simulation calculations and can be updated adaptively). When the node detects that at least one of the key indicators included in the evaluation information, such as the platform's motion acceleration amplitude, the rate of change of stress in key parts, or the dynamic fluctuation range of mooring tension, continuously exceeds its corresponding dynamic threshold, it determines that the platform may be in an abnormal or high-risk operating condition. At this time, the edge node will automatically trigger the execution of at least one of the following localized rapid response operations without waiting for cloud instructions: Increase the sampling frequency of the sensors in the platform structure response layer and mooring boundary monitoring layer (e.g., from 10Hz to 100Hz) to obtain more detailed data with higher time resolution for fine analysis of transient impacts or resonance phenomena.

[0072] Trigger the environmental field sensing layer to activate an enhanced scanning mode for wind and wave fields (such as switching the wave radar from periodic scanning mode to continuous wave mode, or increasing the vertical layer density of ADCP) to more accurately capture the details of environmental conditions that induce anomalous responses.

[0073] This approach introduces intelligent judgment and execution capabilities at the network edge, enabling rapid, low-latency response to sudden high-risk operating conditions and enhancing the system's adaptive monitoring capabilities and ability to capture extreme events.

[0074] Corresponding to the above method, this application also provides a hydrodynamic analysis device for offshore photovoltaic platforms, such as... Figure 2 As shown, the device includes: Acquisition unit 210 is used to acquire synchronous data streams collected by a multi-source sensor network deployed on the platform. The synchronous data streams include multi-dimensional monitoring data reflecting the platform's operating status. The multi-dimensional monitoring data includes performance data reflecting the platform's energy capture performance, environmental data reflecting the environmental status of the platform, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. Establishment unit 220 is used to perform cross-domain correlation analysis on the multidimensional monitoring data through a data fusion model, and establish dynamic correlation relationships between performance data, environmental data and hydrodynamic data. The generation unit 230 is used to generate evaluation information for assessing the overall operating status of the platform based on the dynamic correlation relationship.

[0075] The functions of each functional unit of the hydrodynamic analysis device for offshore photovoltaic platforms provided in the above embodiments of this application can be realized through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the hydrodynamic analysis device for offshore photovoltaic platforms provided in the embodiments of this application will not be repeated here.

[0076] This application also provides an electronic device, such as... Figure 3 As shown, it includes a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340.

[0077] Memory 330 is used to store computer programs; When the processor 310 executes the program stored in the memory 330, it performs the following steps: Acquire synchronous data streams collected by a multi-source sensor network deployed on the platform. The synchronous data streams include multi-dimensional monitoring data reflecting the platform's operating status. The multi-dimensional monitoring data includes performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental status, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. Cross-domain correlation analysis is performed on the multidimensional monitoring data using a data fusion model to establish dynamic correlations between performance data, environmental data, and hydrodynamic data. Based on the dynamic correlation, evaluation information is generated to assess the overall operational status of the platform.

[0078] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0079] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0080] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0081] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0082] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0083] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform any of the hydrodynamic analysis methods for offshore photovoltaic platforms described in the above embodiments.

[0084] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the hydrodynamic analysis methods for offshore photovoltaic platforms described in the above embodiments.

[0085] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0087] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0089] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.

[0090] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims in this application and their equivalents, then this application also intends to include these modifications and variations.

Claims

1. A hydrodynamic analysis method for offshore photovoltaic platforms, characterized in that, The method includes: Acquire synchronous data streams collected by a multi-source sensor network deployed on the platform. The synchronous data streams include multi-dimensional monitoring data reflecting the platform's operating status, including performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental status, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. Cross-domain correlation analysis is performed on the multidimensional monitoring data using a data fusion model to establish dynamic correlations between performance data, environmental data, and hydrodynamic data. Based on the dynamic correlation, evaluation information is generated to assess the overall operational status of the platform.

2. The method as described in claim 1, characterized in that, The multi-source sensor network adopts a hierarchical distributed topology, including: An energy capture and monitoring layer, deployed on the platform's energy harvesting device, is used to collect the performance data; The platform structure response layer is deployed on the load-bearing structure and motion-sensitive parts of the platform to collect the hydrodynamic data. An environmental field sensing layer, deployed above, around, and underwater on the platform, is used to collect the environmental data. The mooring boundary monitoring layer is deployed at the connection interface between the platform and the mooring system to collect hydrodynamic data reflecting the mechanical response of the mooring system. The sensors at each layer synchronize their data using a unified timing reference.

3. The method as described in claim 2, characterized in that, The energy capture monitoring layer includes a power generation monitoring unit and / or vibration sensor integrated into the photovoltaic array; The platform structure response layer includes an inertial measurement unit, a strain sensor, and a six-component force sensor arranged on the platform float or main structure. The environmental field sensing layer includes at least one of ultrasonic anemometer, wave radar, and acoustic Doppler current profiler. The mooring boundary monitoring layer includes tension sensors and tilt sensors installed at the connection ends of mooring cables or anchor chains.

4. The method as described in claim 2 or 3, characterized in that, The multi-source sensor network also deploys edge intelligent acquisition nodes; When at least one of the following parameters—the amplitude of the platform's motion acceleration, the rate of change of stress at key locations, or the dynamic fluctuation range of mooring tension—continuously exceeds its corresponding dynamic threshold, the edge intelligent acquisition node is triggered to perform at least one of the following operations: Increase the sampling frequency of sensors in the platform structure response layer and mooring boundary monitoring layer; The environmental field perception layer is triggered to start an enhanced scanning mode for wind and wave fields.

5. The method as described in claim 1, characterized in that, The synchronous data stream also carries a time-space tag; Cross-domain correlation analysis is performed on the multidimensional monitoring data using a data fusion model to establish dynamic correlations between performance data, environmental data, and hydrodynamic data, including: Based on the spatiotemporal tags carried by the synchronous data stream, time synchronization alignment and data fusion are performed on heterogeneous multidimensional monitoring data from multi-source sensor networks to obtain a fused dataset. The fused dataset is input into a multi-channel deep neural network model; the input channels of the model correspond to performance data, environmental data, hydrodynamic data of platform structure, and hydrodynamic data of mooring system mechanical response, respectively. Through the shared feature extraction layer in the multi-channel deep neural network, heterogeneous data is mapped to a unified implicit feature space; In the implicit feature space, dynamic correlations between monitoring data of different dimensions are calculated and established through an attention mechanism.

6. The method as described in claim 1, characterized in that, Based on the aforementioned dynamic correlation, evaluation information is generated for assessing the overall operational status of the platform, including: Based on the dynamic correlation, a digital twin simulation scenario of the platform under current and predicted environmental conditions is constructed; In the digital twin simulation scenario, preset extreme events or failure modes are injected to perform stress-life simulation and extrapolation. Based on the simulation results, an assessment is generated that includes predictions of the remaining service life of key components and recommendations for preventative maintenance windows.

7. The method as described in claim 1, characterized in that, The evaluation information is output in the form of a visual interactive interface.

8. A hydrodynamic analysis device for offshore photovoltaic platforms, characterized in that, The device includes: The acquisition unit is used to acquire synchronous data streams collected by a multi-source sensor network deployed on the platform. The synchronous data streams include multi-dimensional monitoring data reflecting the platform's operating status, including performance data reflecting the platform's energy capture performance, environmental data reflecting the platform's environmental status, and hydrodynamic data reflecting the platform's structure and the mechanical response of the mooring system. A data fusion model is used to perform cross-domain correlation analysis on the multidimensional monitoring data and establish dynamic correlation relationships between performance data, environmental data and hydrodynamic data. The generation unit is used to generate evaluation information for assessing the overall operating status of the platform based on the dynamic correlation relationship.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images