236 results about "Tidal current" patented technology

The invention discloses a power flow generating capacity prediction method based on STL decomposition and multi-model fusion, which adopts an STL decomposition method to perform trend term, season term and residual term decomposition on historical generating capacity data, optimizes the decomposition process through a Bisquare weighting function and an internal loop iteration mechanism, and enhances the processing capacity for abnormal values and high-frequency fluctuations. The method comprises the following steps: extracting multi-scale frequency domain features by using a TimeNet model in combination with fast Fourier transform (FFT), predicting a trend term and a seasonal term, and performing accurate modeling on a residual term by using an Itransform model in combination with a self-attention mechanism and gating residual connection. Meteorological factors related to the tidal current generating capacity are screened, prediction is carried out in combination with historical operation data, and high-precision prediction of the tidal current generating capacity is achieved. The method has high adaptability and robustness, can effectively deal with multi-source influence and high-frequency fluctuation in tidal current power generation data, and provides an accurate and stable prediction result.

The invention relates to the technical field of coast engineering, in particular to a beach change evolution inversion method combining numerical simulation and actually measured data, which comprises the following steps: S1, acquiring an actually measured shoreline data set of a current period; s2, establishing a wave-tidal current-sediment coupling numerical model; s3, outputting a simulated shoreline data set; s4, performing spatial matching on the actually measured shoreline data set and the simulated shoreline data set to generate a spatial discrete residual field; s5, taking the spatial discrete residual field as a constraint condition, and reversely solving an optimal hydrodynamic parameter combination; and S6, inputting the optimal hydrodynamic parameter combination into the wave-tide-sediment coupling numerical model, and outputting the beach evolution form in the future period. According to the method, dynamic coupling of the hydrodynamic parameters and the beach evolution process is realized by constructing an inversion optimization mechanism based on actual measurement data driving, and the accuracy of shoreline change simulation and the reliability of prediction are greatly improved.

The invention relates to the technical field of marine disaster early warning, and discloses a digital bay hydrological condition early warning method and system, and the method comprises the steps: collecting historical meteorological data and real-time meteorological data of a to-be-predicted bay region; according to the historical meteorological data, establishing a wind and wave relation model by using a deep reinforcement learning and genetic algorithm, and generating wave prediction data based on the relation model and the real-time wind data of the to-be-predicted bay area; based on the theoretical model wind field and the background wind field, synthesizing a synthesized wind field of the to-be-predicted bay area; performing storm surge simulation by using a hydrodynamic mathematical model and a tidal current mathematical model according to the synthesized wind field and the real-time meteorological data; and on the basis of the wave prediction data and the storm surge simulation result, hydrological condition early warning information is generated in combination with an early warning index threshold value, the prediction precision and early warning timeliness of waves and storm surge in the bay area are improved, and accurate grading response of complex meteorological disasters is realized.

The invention discloses a virtual power plant dispatching system and method, and particularly relates to the technical field of power dispatching. By monitoring the output characteristics of the distributed energy, whether nonlinear interference is generated or not is judged. And further analyzing the disturbance of the distributed energy on the power flow inversion path, judging the abnormal change of the coupling correlation degree between potential hidden resources, and evaluating the influence on the scheduling precision. And in combination with a node differentiation response mode of a distributed energy storage aggregation region and a flexible load community, analyzing the influence of a local grouping cooperation effect on the overall output boundary identification precision of the virtual power plant. Potential erosion of scheduling errors caused by demand side multi-dimensional elastic cooperation to scheduling precision is evaluated by analyzing spectral domain characteristics of demand side elastic gradients and transient disturbance under different spatial and temporal scales. Through comprehensive analysis, the internal regulation and control scheme of the virtual power plant is adjusted, and the overall scheduling efficiency and stability of the virtual power plant are improved.

The invention discloses a disperse relaxation factor tidal current model based minimum electricity generating cost incremental quantity obtaining method. When a minimum electricity generating cost incremental quantity model only containing one balance node tidal current model is solved, the total demand unit change of a system is fixed on a balance node, and an obtained lambda, namely electricity generating cost minimum incremental quantity cannot reflect actual operation of the system in most cases during total demand unit change of a system. The disperse relaxation factor tidal current model based minimum electricity generating cost incremental quantity obtaining method adopts solves the provided model by means of an original antithesis interior point method, and the lambda of the system is controllable according to selected disperse relaxing factors.

The invention discloses an integrated energy system low-carbon scheduling method considering energy-carbon coupling, and the method is based on a carbon emission flow theory, is combined with the strong fitting capability of a neural network, proposes a carbon flow constraint learning method, converts a complex mapping relation between power flow and carbon flow into mixed integer linear constraint, and achieves the low-carbon scheduling of an integrated energy system. And effective embedding of the carbon flow constraint in the optimization model is realized. Meanwhile, in order to reduce the structural complexity of the neural network, a sparse training strategy is introduced, the model parameter scale is effectively compressed, a ReLU activation function is linearized through an improved large-M method, and a cut plane constraint is introduced to gradually tighten a feasible region, so that the solving efficiency of an optimization model is remarkably improved. And finally, embedding the carbon flow constraint model into the optimal scheduling problem of the integrated energy system, exciting the carbon emission reduction consciousness of the load side, and promoting the load side to perform low-carbon energy consumption adjustment by guiding the demand response behavior of the load side based on the carbon signal of the load side, thereby realizing low-carbon scheduling under energy-carbon coordination and reducing the overall carbon emission level of the system.

The invention relates to the technical field of coast engineering, in particular to an estuary sandy coast erosion and deposition simulation system based on the coupling effect of flood peak runoff, waves and tide, which comprises a training data generation module, an intelligent agent model construction module, a dynamic prediction engine module and a scene evaluation module. The training data generation module is used for outputting a hydrodynamic state field, a wave characteristic field, a bed surface shear stress field and a bed surface elevation variable quantity by utilizing a traditional numerical model to construct a training data set; the intelligent agent model building module is based on a deep learning network and introduces physical constraint loss function training to obtain an intelligent agent model; the dynamic prediction engine module loads the trained deep learning network to realize bed surface elevation variation prediction and update terrain boundary conditions; and the scene evaluation module executes erosion and deposition evolution simulation according to different hydrological boundary condition combinations and extracts terrain evolution data to quantitatively evaluate the coast stability and the channel deposition risk. The invention relates to the field of estuary dynamic landform simulation and coast engineering.

The invention relates to the technical field of port engineering construction, in particular to a tide wave joint test method and system based on multi-source data in port engineering construction. At present, the problems of insufficient data utilization, low test precision and the like exist in tide and wave joint test in port engineering construction. The method comprises the following steps: constructing a nested unstructured grid and dynamically configuring discrete parameters of a wave direction spectrum; a variation assimilation algorithm is adopted to optimize hydrodynamic parameters; solving a wave flow coupling equation to generate a combined field data set; the pile foundation stress is calculated in combination with an improved Morison equation, and a safety evaluation report is output through basin resonance characteristic analysis; the system sets corresponding modules to realize various functions based on the method. The device is mainly used for precise combined testing of tidal waves in port engineering construction so as to guarantee the safety of an engineering structure.

The invention relates to the technical field of data processing, and discloses a wind turbine generator optimization design method based on tidal current-wave-sediment coupling simulation. The method comprises the following steps: carrying out adaptive time step adjustment on marine environment data through a physical process intensity discrimination algorithm to obtain tidal current field, wave field and sediment transportation data; carrying out fluid-solid coupling calculation on the structural parameters of the wind turbine generator to obtain structural vibration response and ocean load distribution data, and predicting pile foundation scouring depth distribution; carrying out time-varying coefficient correction on the pile foundation bearing capacity parameters to obtain dynamic bearing capacity evaluation data; inputting a multi-objective optimization algorithm to obtain a Pareto optimal solution set; and obtaining a wind turbine generator optimization design scheme through engineering feasibility verification and screening. The technical problems that in existing offshore wind turbine generator design, tidal current-wave-sediment coupling simulation space-time scales are not matched, the pile foundation scouring prediction precision is insufficient, bearing capacity evaluation lacks time-varying characteristic consideration, and the multi-target optimization design capacity is insufficient are solved.

The invention relates to the technical field of port machinery loading and unloading, and provides a ship-shore linkage loading and unloading method and system suitable for a mast crane. The method comprises the steps that position data, course data and attitude data of a ship are obtained in real time through ship navigation equipment, and tide height data and tide flow velocity data of the sea surface are obtained in real time through tide monitoring equipment; inputting the obtained ship position data, course data, attitude data, tidal height data and tidal flow velocity data into a control system of the mast crane; the control system generates a corresponding control instruction according to the calculated dynamic compensation parameter, and sends the control instruction to a variable amplitude control system of the mast crane; the hoisting path and the hoisting posture of the mast crane are adjusted in real time through the variable amplitude control system according to the control instruction, so that the hoisting point is kept vertical and the stress is balanced in the equipment lowering process; in the whole hoisting operation process, the operation process is monitored in real time through monitoring equipment arranged on the mast crane and the ship.

The invention discloses a multi-parameter cooperative control underwater propeller turnover hoisting control method, particularly relates to the field of underwater propeller hoisting, and aims to solve the problem of unstable turnover control of a propeller under tidal current disturbance. The iteration interval of a high-risk section is compressed in time by means of self-adaptive step length mapping, then angle increment and target tension are synchronously corrected before the winding action by means of prediction correction circulation, and three-line linkage of angle adjustment, tension adjustment and environmental safety is achieved. The safety margin diagram is continuously refreshed under the driving of vibration and flow velocity dual information sources, and step length rollback is triggered once a node approaches a warning domain, so that potential oscillation is blocked in a germination stage. The synchronization reliability coefficient runs through the whole process, the winch synchronization quality is evaluated, real-time weighting is performed on step length mapping, and then a convergence path is kept close to a real balance channel. Therefore, the turning-over time is shortened, and the tension fluctuation amplitude is stabilized.

The invention relates to a local washout test method for a single-column composite barrel type foundation under an actual wave current condition. The method comprises the following steps: acquiring basic data of a target wind power plant area; determining a scale, and constructing a reduced scale physical model water tank according to similar conditions; parameters of the first two-way pump, the second two-way pump and the wave maker are determined through adjustment and measurement; excavating a test scour area, installing a reduced-scale single-column composite cylindrical foundation, and laying model sand; and carrying out a scouring test until scouring is balanced, recording the scouring depth and the scouring range, and converting the scouring depth and the scouring range into prototype quantities. According to the method, the superposition effect of actual rotating tidal current and waves in a sea area can be well simulated, the scouring form conforming to the sea area site is simulated, and therefore the local scouring condition of the single-column composite barrel type foundation under the actual wave current condition can be accurately judged.

The invention discloses an ROV ocean current and wake flow interference analysis method and system for an offshore wind plant, and the method comprises the steps: calculating tidal current velocity vectors of different depths of an ocean current shallow layer, and calculating a wake flow velocity vector; obtaining projection velocity components of tidal current velocity vectors of different depths of the ocean current shallow layer; the operation of the ROV is divided into a wake flow-free influence area, a wake flow and ocean current direction consistent influence area and a wake flow and ocean current direction opposite influence area; obtaining a projection velocity component of the wake flow velocity vector; according to the projection velocity component, constructing a final velocity calculation relational expression of the superposed ocean current and wake flow influence; calculating the final speed of the superposed ocean current and wake flow influence; and calculating the relative velocity component of the superposed ocean current and wake flow influence, and updating the relative velocity component in the damping matrix of the dynamical model of the ROV into the relative velocity component of the superposed ocean current and wake flow influence. According to the method, the problems of insufficient ocean current modeling dimension, no consideration of wake flow disturbance, weak path interference analysis capability and the like in offshore wind plant inspection ROV path interference analysis are effectively solved.

The invention discloses a near-shore wave energy focusing-wave-to-current combined power generation wave absorbing device. The wave power generation device belongs to the technical field of ocean engineering wave power generation and is composed of wave power generation floaters, a conical net guide frame, a wave gathering-wave absorbing cylinder, a wave gathering platform, paddles, a gear accelerator, a turbine worm and the like. The wave gathering platform is controlled to ascend and descend according to different water depths, so that the position of the wave power generation floater is controlled to make full contact with the water surface; the wave focusing device improves the oscillation of the wave power generation floater so as to improve the efficiency; the wave power generation floater adopts a dual power generation mode of swing power generation and vertical oscillation power generation to improve the power generation efficiency; the wave focusing-absorbing device not only utilizes reflected waves to focus waves, but also weakens wave propagation; part of waves penetrate through the wave gathering-absorbing cylinder to generate tidal current to drive the tidal current generator to rotate to form a secondary power generation effect; the blades connected to the wave gathering-absorbing device not only form a secondary power generation effect, but also scatter the waves propagated through gaps of the column body so as to reduce the influence of coast erosion and the like.

Submersible box-winged vehicle systems generate hydroelectric energy using naturally occurring tidal flows and / or water currents in a body of water. The vehicle systems include a submersible hull, an upright dorsal fin extending from an aft portion of the submersible hull, port and starboard wing assemblies each having respective proximal ends joined to a forward region of the hull an and an upper region of the dorsal fin so as to establish a box wing configuration, and electrical power generation units attached to the port and starboard wings, wherein each of the electrical power generation units include a generator and a marine propeller operatively connected to the generator so as to cause the generator to generate electrical energy in response to the marine propeller turning. The vehicle system when submerged in a body of water thereby allows tidal flows and / or currents associated with the body of water to responsively turn the marine propeller of each of the electrical power units thereby generating electricity by the generator operably associated therewith

The invention discloses a marine environment spring layer characteristic diagnosis data processing method, and aims at complex dynamic characteristics of a land frame edge sea spring layer to realize accurate diagnosis through multi-source data cooperation and an intelligent algorithm. The method comprises the following steps: acquiring and preprocessing field observation, remote sensing, sonar, terrain and tidal ocean current data; extracting spatio-temporal characteristics based on a CNN-LSTM hybrid network, and generating a dynamic spring layer threshold; fusing multi-source data by adopting an improved D-S evidence theory, and constructing a three-dimensional spring layer characteristic field; predicting an internal wave in combination with an attention mechanism model, and optimizing a preorder model by using sonar data. The method breaks through the limitation of a fixed threshold value, realizes spring layer dynamic identification, three-dimensional reconstruction and internal wave prediction, improves the diagnosis precision of a complex sea area, and provides key technical support for underwater detection, engineering safety and environmental research.

The invention relates to the technical field of power systems, and discloses a wind and light output scene-oriented power system power flow data reconstruction method, system and device and a medium, and the method comprises the steps of constructing structured boundary input data; generating a voltage amplitude and a phase angle estimation vector of each node through a deep neural network model, and taking the voltage amplitude and the phase angle estimation vector as a power flow initial solution; performing physical constraint check on the initial solution, identifying out-of-limit nodes and determining an adjustable point set with reactive power regulation capability; and in the range of the adjustable point set, constructing an optimization function, solving to obtain a local adjustment quantity, correcting the initial solution, and generating a final power flow solution meeting the operation constraint of the power system. According to the method, data-driven modeling and physical constraint checking are fused, overall mapping is performed on a high-dimensional scene formed by wind and light output and load by using the deep neural network, the problem that the convergence performance is sharply reduced when the dimension is increased and the number of scenes is increased in a traditional iteration method is avoided, and rapid, stable and engineering-available power flow data generation is realized.

The invention relates to a power grid side energy storage two-stage locating and sizing method in a sea wind access scene considering the influence of temperature on a tide safety domain. The method comprises the following steps: adopting a temperature trend prediction model combining LSTM and TCN; a Gaussian mixture model is adopted to calculate a temperature variable capacitance expectation coefficient, and a power flow safety domain is reconstructed; establishing a random optimization scene set of source-load space-time coupling by adopting a typical source-load daily trajectory clustering method; establishing a power distribution network energy storage locating and sizing planning layer model taking the maximum comprehensive utility as a target; a power distribution network energy storage locating and sizing operation layer model with the minimum voltage fluctuation quadratic sum as the target is established; constructing a DistFlow multi-period optimal power flow model under the sea wind access scene; and solving the planning layer by adopting second-order cone relaxation, and carrying out secondary optimization on a charge-discharge and capacity configuration strategy on the operation layer by adopting a target cascade algorithm on the basis of anchoring a locating and sizing decision variable of the planning layer. According to the method, planning and operation targets can be more effectively coordinated, and comprehensive optimal configuration of power grid side energy storage is realized.

The invention discloses a power flow section out-of-limit elimination method based on section sensitivity hierarchical optimization adjustment, and relates to the field of electric power system operation control, and the method comprises the steps: collecting static operation boundary parameters of a non-market unit, constructing an initial non-market flexibility resource parameter library, and completing basic data standardization mapping; performing reading initialization on the initial data of the flexibility resources; taking the minimum adjustment amount as an optimization target, and respectively constructing optimization models based on section node sensitivity by utilizing four flexible resources, namely non-market unit output, new energy output prediction, bus load prediction and power flow section limit capacity; and performing priority ranking on the optimization models, outputting an optimization result and updating the corresponding non-market flexibility resource adjustment amount and the changed section power flow after optimization adjustment of the models with high priorities every time until the power flow section out-of-limit is completely eliminated. The method solves the problem that the traditional method is difficult to balance the fast limit elimination and the global economy target.

The present invention relates to the field of marine technology and engineering, and in particular to a floating wind power platform attitude control system. The present invention effectively controls the attitude of the floating wind power platform through the mutual cooperation between a measurement system, a control system, and a platform attitude control system, thereby providing good protection for the safe and stable operation of the floating wind turbine. At the same time, the platform attitude control system is provided with a second tidal energy power generation system to provide electrical energy for the electrical connection between the various systems, without additionally consuming the energy of the floating wind turbine, thereby improving resource utilization.

The invention discloses an oscillating hydrofoil type optimization long-time self-sustaining energy collection device and an energy collection method. The energy collecting device comprises a plurality of oscillating hydrofoil units which are arranged at intervals, and the oscillating hydrofoil units are distributed in an array mode. Each oscillating hydrofoil unit comprises a hydrofoil shell and a friction nano-generator, a plurality of friction nano-generators which are arranged in parallel along the chord length of the hydrofoil chord and cling to each other are arranged in the hydrofoil shell, and the size of each friction nano-generator changes along with the thickness of the hydrofoil shell; and the upper and lower cambered surfaces of each friction nano-generator are tangent to the inner wall of the hydrofoil shell. When the oscillating hydrofoil unit performs pitching or surging under the action of tidal current, the friction nano-generator in the oscillating hydrofoil unit captures mechanical energy in real time and generates power, a traditional oscillating hydrofoil energy conversion device is replaced, the structure is simpler, production is simpler and more convenient, cost is lower, and energy capturing efficiency and self-sustaining performance are improved.

The invention relates to the technical field of offshore wind power engineering, in particular to an offshore wind power anti-scouring device which comprises a sea wind pile foundation, an anti-scouring cover, an energy storage assembly and a water spraying assembly. The energy storage assembly is arranged on the anti-scouring cover and used for converting water flow energy into electric energy, the water spraying assembly is connected with the energy storage assembly, and the water spraying assembly sprays water in the water flow direction; mechanical energy of tidal currents and waves around the sea wind pile foundation is converted into electric energy, then the electric energy is converted into water flow opposite to the tidal currents and the waves for energy dissipation, the design is ingenious, and the engineering feasibility is high.

The invention relates to the technical field of crossing of water conservancy and nuclear power engineering, in particular to a nuclear power water taking open channel flow field analysis method based on a physical model test, and solves the problems that flow field analysis in the prior art mainly depends on theoretical calculation or numerical simulation, flow field characteristics under the combined action of tidal current, waves, water taking operation and other factors are difficult to truly restore, and the flow field analysis accuracy is low. And the analysis result is greatly deviated from the actual analysis result. The method comprises the following steps: constructing a physical model for accurately simulating key facilities such as a water intake, a drain grating net and a pump room, setting multiple typical working conditions, carrying out a flow field simulation test, and recording data such as a flow velocity, a flow direction and a water level. Through a physical model test means, actual water flow characteristics under a complex marine environment and various working conditions can be reflected more truly, the accuracy and reliability of flow field analysis are remarkably improved, and a scientific basis and technical support are provided for design, operation and risk assessment of a water intake system of a nuclear power plant.

The utility model provides an offshore floating barge type photovoltaic energy storage power station. A barge is composed of a photovoltaic system arranged on a two-layer deck, an energy storage system and a wireless charging and discharging system arranged on a first-layer deck, and a control protection and energy management system arranged on a bottom-layer cabin. The photovoltaic system can generate power to charge the energy storage system when the barge sails on the sea and is berthed in the daytime; the energy storage system can run to a land power grid with sufficient electric quantity to absorb electric energy to charge an energy storage container, and can also run to power-lacking power grids such as islands or offshore working platforms to discharge electric energy to supply power to the power grids; and the control protection and energy management system is used for control of system switches of the whole station, relay protection and energy flow direction control. According to the utility model, the construction cost of the submarine cable can be reduced, the technical limitation range of the laying length of the alternating-current submarine cable is broken through, the power supply of a deep and far sea working platform is guaranteed, and the working range of an offshore working platform is expanded.

The invention discloses a harbor pollutant concentration distribution analysis method and system based on a tracer method, and relates to the technical field of pollutant concentration analysis, and the method comprises the steps: calculating the tidal capacity of a harbor based on tidal flow characteristics; constructing a water exchange model based on a tracer technology, calculating the water exchange capacity of the harbor by using the water exchange model, and analyzing the influence of river discharge in different seasons on the pollutant concentration distribution of the harbor in combination with the water exchange capacity and the tide absorption capacity of the harbor; calculating the environment capacity of the harbor by combining the pollutant concentration distribution influence with a seawater exchange rate formula; and according to the environment capacity of the harbor and the predefined pollutant substance transportation residence time, adjusting a pollutant control threshold value by using the sea-entering pollutant distribution optimization model so as to realize optimal distribution of the sea-entering pollutants. According to the method, the pollutant control threshold value is optimized based on the harbor environment capacity and the pollutant transportation residence time, scientific distribution of the pollutants entering the sea is achieved, and therefore the accuracy of pollutant management is improved.

The invention provides a hydrodynamic environment forecasting method and system for green navigation of coastal ships, and relates to the technical field of navigation. Aiming at the problem of relatively low accuracy of a forecast result in the prior art, the method comprises the steps of obtaining a calculation boundary condition; monitoring mark stations are arranged at the key positions, and actually-measured hydrodynamic environment data and actually-measured storm data are obtained; establishing a tide wave coupling numerical model according to calculation boundary conditions, and performing model calibration according to measured data; the calibrated tidal current wave coupling numerical model outputs initial environment forecast data according to calculation boundary conditions; comparing the actually measured real-time data with the initial environment forecast data to obtain forecast deviation; and dynamically correcting the calibrated tide wave coupling numerical model in a periodic manner according to the forecast deviation, and correcting the tide wave coupling numerical model to output final environment forecast data according to calculation boundary conditions. The periodic dynamic correction mode accurately adapts to the change characteristics of tidal current and waves, small deviation of each period is eliminated in time, and the accuracy of a forecast result is improved.

The invention discloses a multi-scale power system post-earthquake toughness evaluation method, which comprises the following steps: collecting network topology structure information of a power system and a transformer substation, and collecting damage probability information of key equipment in the transformer substation and a power transmission tower on a power transmission line; establishing an urban power grid linear power flow model, and establishing post-earthquake function and toughness evaluation indexes of a power system and post-earthquake function evaluation indexes of a transformer substation; obtaining the equipment damage and line damage conditions of the transformer substation in each earthquake scene through simulation; evaluating post-earthquake function evaluation indexes and power transmission line functions of the transformer substation based on the damage condition; establishing a system load flow calculation model of the post-earthquake power system, and calculating the post-earthquake function of the power system; and outputting post-earthquake function distribution and toughness evaluation results of the power system. The method can consider the influence of the damage of the earthquake to the infrastructure in the power system such as the transformer substation and the transmission tower on the system function of the power system, and helps a manager comprehensively evaluate the anti-seismic toughness of the power system.

The invention relates to a coastal vegetation revetment efficiency evaluation method, which comprises the following steps: S1, on the basis of field measurement or remote sensing data, collecting meteorological and hydrological elements and topographic and geomorphic data of a target coast; s2, quantifying key characteristic parameters of vegetation, wherein the key characteristic parameters comprise a planting scheme, a vegetation diameter, a height and a form; s3, constructing a tidal water power-vegetation coupling model, analyzing an interaction mechanism of a tidal current field and vegetation, and quantitatively evaluating the vegetation bank protection efficiency from the aspect of tidal current flow velocity weakening amplitude; s4, establishing a wave-vegetation coupling model, simulating a vegetation wave dissipation and energy consumption process, and quantitatively evaluating the vegetation bank protection efficiency from the aspect of wave reduction amplitude; and S5, integrally constructing a hydrodynamic force-wave-sediment-vegetation coupling numerical model, and quantitatively evaluating the vegetation bank protection efficiency from the aspect of bank slope form change.

The invention discloses a quantitative prediction method for the scouring rate of an offshore wind power pile foundation based on machine learning, and the method comprises the steps: collecting historical multi-source topographic observation data, and generating a topographic spatio-temporal evolution graph; collecting tidal current sediment dynamic field data to obtain calibrated tidal current sediment dynamic field data; constructing a learnable terrain disturbance mapper, and outputting a seabed digital elevation field at a target prediction moment; constructing a physically-driven attention guidance dual-channel diffusion network; respectively obtaining a local scouring rate prediction field and an overall state evolution rate prediction field; outputting the scouring rate prediction result data and the scouring depth prediction result data of the surrounding area of the pile foundation; generating updated scouring rate prediction result data and updated scouring depth prediction result data; and a pile foundation collaborative protection scheme is automatically generated. According to the method, collaborative protection optimization design of local scouring and overall scouring of the offshore wind power pile foundation is achieved, and the protection effect and economic benefits are remarkably improved.

The invention discloses a motorized underwater robot for tidal and tidal current observation, relates to the technical field of robots, and mainly aims to solve the problem that an existing motorized underwater robot for tidal and tidal current observation is difficult to meet long-term stable tidal and tidal current observation requirements. Comprising a main cabin body (1), a plurality of auxiliary cabin bodies (2), a plurality of connecting mechanisms (3) and a plurality of supporting feet (4), wherein the main cabin body (1) is used for carrying different detection devices to execute detection tasks, and is provided with a buoyancy adjusting cabin section (11) for adjusting the buoyancy of the underwater robot; each auxiliary cabin body (2) is connected with the main cabin body (1) through a connecting mechanism (3), and each auxiliary cabin body (2) and the main cabin body (1) are arranged on the same plane and used for providing power for the underwater robot; the supporting feet (4) are arranged below the auxiliary cabin body (2) and used for supporting the underwater robot so that the underwater robot can complete the bottom-sitting detection task.