A method and system for planning a stentoplasty procedure

Abstract

The present application relates to the technical field of intelligent water conservancy of seawall engineering, and especially provides a kind of mouth door plugging process line planning method and system, including collecting original engineering data, constructing hydrodynamic model, evaluating the prediction accuracy of the trained prediction model on the validation set, and optimizing the prediction model parameters;Planning a plugging process line that meets the hydrodynamic constraint;The plugging process line planning is verified.The present application realizes the intelligent planning of the mouth door plugging process line, significantly improves the scientificity and efficiency of seawall engineering construction decision-making, at the same time, effectively integrates historical engineering data and simulation data, realizes the systematized accumulation and reuse of knowledge, and promotes the seawall engineering to the high-quality development direction of data-driven and intelligent decision-making.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of seawall engineering intelligent water conservancy, in particular to a kind of mouth gate plugging process line planning method and system. BACKGROUND

[0002] In coastal engineering, especially in the construction of sea embankment, the final closure of the gap is a key construction link to control water flow and complete closure. During the closure of the gap, as the cross-sectional area of the water flow through the gap narrows, the water flow velocity through the gap will significantly increase, forming a fast-moving tidal current. The rapid impact of the tidal current can pose a serious threat to the stability of the closure material already in place and the safety of the construction. Therefore, before the closure of the gap, detailed hydraulic calculations of the gap must be carried out, and the closure process line of the gap must be planned scientifically, i.e., the sequence of the remaining width and / or the cross-sectional area of the water flow through the gap changing over time must be determined, to ensure that the maximum tidal current velocity of the gap cross-section during the entire closure process does not exceed the critical starting flow velocity of the closure material used or the limit that the structure can withstand. Accurate planning of the closure process line requires comprehensive consideration of various factors such as complex tidal hydrodynamics, gap geometry, reservoir capacity characteristics, closure material characteristics, and construction capacity.

[0003] Prior Art 1, Chinese patent, application number: 2021105328402, discloses a rapid embankment breach closure construction method combining trestle and steel sheet pile, relating to the field of water conservancy. The method involves inserting and driving closure steel sheet piles into the river bottom to a certain depth, connecting the closure steel sheet piles with each other using a rebate structure, connecting the closure steel sheet piles using support beams, supporting one end of the support rod system on the support beam and the other end on the lower structure of the piling trestle, inserting the pile columns of the lower structure of the piling trestle into the soil to a certain depth under the stability of the piling positioning frame, and setting longitudinal and transverse reinforcement structures on the lower structure of the piling trestle to provide reliable support for the closure steel sheet piles and protection for the insertion of the pile columns of the lower structure of the piling trestle. The insertion and driving of the closure steel sheet piles and the pile columns of the lower structure of the piling trestle are alternately supported and protected to ensure the safe and reliable operation of the closure steel sheet piles and the smooth insertion of the pile columns of the lower structure of the piling trestle under high flow rates.

[0004] Prior Art 2, Chinese patent, application number: 2017114749245, discloses a suspended telescopic breach closure device and method, relating to the field of water conservancy. The method involves transporting flood control materials to the shores on both sides of the breach, erecting ropes on both sides of the breach, setting the breach closure baffle group on the erected ropes, and using methods such as steel reinforcement cage, gravel bag, sandbag, and stone to completely block the breach. The anti-flood device used has a simple structure and low failure rate, the breach closure method can be quickly and efficiently deployed, can be used in various weather conditions, is easy to operate, and can handle different breach conditions.

[0005] Prior art three, Chinese patent, application number 2017114783886 discloses a movable defense line type breach plugging device and method, relating to the field of water conservancy, transporting flood control materials to the shore on both sides of the breach, erecting a rope on both sides of the breach, setting the breach closure stop rod group on the erected rope, and setting the breach closure stop plate group on the erected rope, and adopting the methods of blocking the breach by throwing reinforcement cages, gravel bags, sandbags, stones and the like to completely block the breach. The breach plugging method can be quickly and efficiently deployed, can be used in various weather, is simple to operate, and can cope with different breach conditions.

[0006] The existing technologies one, two and three have defects. The existing technology one relies on mechanical insertion of steel sheet piles and trestle structures, has certain flow resistance, but does not consider the dynamic change law of the flow velocity of the breach under different tidal periods, lacks systematic prediction and evaluation of the hydrodynamic conditions, and is difficult to adapt to the selection of safe plugging time in complex hydrodynamic environments. The existing technologies two and three both use rope suspension type stop plate or stop rod combined with material throwing method, which belongs to emergency type and passive interception means, the construction process is extensive, the evolution trend of the water flow velocity in the plugging process cannot be quantified, and a physical or data driven model between the plugging progress and the water flow response is not established, resulting in low plugging efficiency, serious material waste, and easy structural instability under high flow velocity conditions. In addition, the three technologies do not involve the process line intelligent planning and verification mechanism based on the combination of hydrodynamic simulation and machine learning, and cannot generate an optimal plugging path that meets the material critical flow velocity constraint in advance. Therefore, the existing technologies generally remain in the traditional construction mode of "experience judgment + manual intervention", and lack a scientific and intelligent decision support system. Therefore, the present application proposes a breach closure process line planning method combining hydrodynamic numerical simulation, machine learning prediction and whole process verification, realizes the predictability, planability and verifiability of the plugging process by constructing a "geometry-flow velocity-material" multi-dimensional constraint model, and significantly improves the safety, economy and intelligent level of the plugging operation. SUMMARY

[0007] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0008] In one aspect of the present application, a breach closure process line planning method is provided, comprising the following steps:

[0009] Collecting original engineering data, and preliminarily processing and generalizing the original engineering data according to the input suitable for water conservancy modeling and machine learning, wherein the breach closure refers to the gap reserved in the engineering for water passage or construction convenience;

[0010] Constructing a hydrodynamic model, defining different narrowing states of a series of breaches, running hydrodynamic simulation for each narrowing state, extracting the tidal flow velocity and occurrence time, and constructing a hydrodynamic data set;

[0011] According to the geometric characteristics of different narrowing states of the estuary, the tidal current velocity is predicted, a prediction model is selected, the selected prediction model is trained, the prediction accuracy of the trained prediction model is evaluated on a verification set, and the prediction model parameters are optimized, and the geometric characteristics refer to the width of the estuary mouth and the bottom elevation;

[0012] The prediction model is used to train the critical flow velocity limit of the blocking material, and a blocking process line that meets the hydrodynamic constraints is planned;

[0013] The planning of the blocking process line is verified, and the estuary mouth blocking process line planning is completed.

[0014] In an optional implementation, the collection of original engineering data includes using 7-day or 15-day tidal level process time series outside the estuary mouth of the engineering sea area as external boundary conditions for hydrodynamic modeling, and the tidal level process time series refers to tidal level change data within 7 days or 15 days;

[0015] The preliminary processing includes using original bathymetric data of the estuary mouth area and surrounding inner and outer sea areas and original bathymetric data of the enclosed area in the estuary mouth for hydrodynamic model measurement, and the hydrodynamic model measurement refers to simultaneous measurement of water levels and tidal current velocities at different points in the enclosed area, and the planned blocking material type and the critical starting flow velocity or shear stress determined through experiments, and the critical starting tidal current velocity or shear stress refers to the maximum velocity limit that the material can withstand during the process of blocking the estuary mouth.

[0016] In an optional implementation, the generalization includes generalizing the topography of the enclosed area in the estuary mouth and generalizing the water depth profile of the estuary mouth area;

[0017] The generalization of the topography of the enclosed area in the estuary mouth includes simplifying the original topography of the enclosed area in the estuary mouth, calculating the water level-storage capacity curve of the original topography area according to the original topography data, generalizing the topography of the enclosed area in the estuary mouth to a region with an average water depth and an area, representing the parameters of the generalized topography, and using them as inputs to describe the characteristics of the engineering project, and building a hydrodynamic model;

[0018] The generalization of the water depth profile of the estuary mouth area includes simplifying the shape of the remaining flow section of the estuary mouth area with the blocking process to model different narrowing states in the hydrodynamic model;

[0019] In different remaining width of the gap, the actual terrain profile is generalized as the average bottom elevation or divided into N different bottom elevations, based on the actual or generalized gap section information, the total area parameter of the remaining flow section corresponding to different blocking states is calculated and extracted, the total area parameter will be used as a characteristic to describe the narrowing state of the gap, as the input of the water dynamic data set generation and machine learning model;

[0020] From the collected original engineering data and the preliminary processing and generalization, a project feature set for inputting the machine learning model is extracted, which refers to a set of parameters describing the macroscopic properties of an engineering project.

[0021] In an optional implementation, the construction of the water dynamic model includes constructing a two-dimensional or three-dimensional water dynamic numerical model of the engineering area according to the geographical information of the engineering sea area and the generalized internal and external terrain information, at this time, the water dynamic model refers to the completion of sufficient rating and verification according to the data of external boundary conditions, water level and maximum speed, the determination of parameters including roughness, and the construction of two-dimensional or three-dimensional water dynamic numerical model;

[0022] The definition of a series of different narrowing states of the gap includes changing the model gap area, so that the water dynamic model simulates different gap blocking states by modifying the geometric parameters or grid of the gap area, defines the gap blocking and narrowing states, covers the whole process from the initial opening of the gap to the complete closure, and each narrowing state is determined by the remaining gap width and the bottom elevation under the remaining gap width, at this time the input feature space of the water dynamic data set is formed;

[0023] The water dynamic simulation for each narrowing state includes setting the corresponding gap geometry in the water dynamic model for the defined gap narrowing state, running the water dynamic model, using the obtained 7-day or 15-day tidal level process time series as the external boundary condition for simulation, and capturing the maximum speed limit value under different tidal conditions;

[0024] The extraction of tidal current speed and occurrence time includes extracting the maximum speed limit value that occurs at the gap section position every day or every tidal cycle under each gap narrowing state from the simulation results, and recording the relative time point of the maximum speed limit value occurrence relative to the tidal cycle, i.e. several minutes before or after the highest or lowest tide;

[0025] The construction of the water dynamic data set includes combining the description of each gap narrowing state with the corresponding extracted maximum speed limit value sequence of each day or each tidal cycle to form a water dynamic data set, which reflects the physical relationship between the gap geometric narrowing and the maximum speed limit value under different tidal conditions, and divides the water dynamic data set into training set, validation set and test set according to the ratio of 8:1:1, which is used to train the maximum speed limit value prediction model.

[0026] In an optional embodiment, the training of the selected prediction model refers to training of a machine learning model, including selection of a prediction model, training of the prediction model, and parameter tuning of the prediction model;

[0027] The selection of the prediction model includes selection of a machine learning regression model according to characteristics of the hydrodynamic data set;

[0028] The training of the prediction model includes training of the selected machine learning model using the constructed hydrodynamic data set;

[0029] The parameter tuning of the prediction model includes evaluation of prediction accuracy of the model on an independent validation set, and parameter tuning of the model as needed.

[0030] In an optional embodiment, the planning of a closure process line satisfying the hydrodynamic constraints includes the following steps:

[0031] Setting planning objectives and constraints;

[0032] Defining candidate closure process line representations;

[0033] Process line construction or search based on maximum velocity limit value prediction model;

[0034] Generating a recommended closure process line;

[0035] The setting of the planning objectives and constraints refers to setting of planning objectives and key constraints of the closure process line;

[0036] The defining of the candidate closure process line representations includes discretization of the entire closure process into a series of time steps, each time step corresponding to a remaining gate width or flow area;

[0037] The process line construction or search based on the maximum velocity limit value prediction model includes construction or search of a closure process line satisfying the constraint conditions using the trained maximum velocity limit value prediction model, combined with the acquired 7-day or 15-day tidal level process time series and the critical flow velocity limit of the closure material type, i.e., by the following method:

[0038] Based on a lookup table or curve, a lookup table or curve is constructed using the generated hydrodynamic data set, and the maximum flow velocity is queried according to the remaining gate state and tidal characteristics, including the current tidal level and the tidal level change rate, and the planning process selects a safe closure state sequence according to the lookup table;

[0039] The constraint conditions refer to that the predicted maximum flow velocity in any time period does not exceed the critical flow velocity limit, and an optimization algorithm is used to search in the closure process line space;

[0040] The generating the proposed closure process line comprises outputting a proposed closure process line satisfying the constraint condition constructed or searched, and the closure process line is represented in the form of a sequence of a time-varying residual gap width and a sequence of a gap bottom height.

[0041] In an alternative embodiment, the verifying the planning of the closure process line comprises the following steps:

[0042] converting the proposed process line into water dynamic model input;

[0043] running a water dynamic full-process verification simulation;

[0044] extracting and comparing the maximum flow velocity;

[0045] judging the feasibility of the scheme;

[0046] adjusting and refining the scheme;

[0047] The converting the proposed process line into water dynamic model input is converted into a water dynamic model according to the generated proposed closure process line;

[0048] The running the water dynamic full-process verification simulation comprises using the constructed water dynamic model, importing the converted time-varying geometry information of the gap, running the water dynamic model, using the obtained 15-day tidal level process time sequence as the external boundary condition, and simulating the water flow change in the entire closure process in a full tidal cycle;

[0049] The extracting and comparing the maximum flow velocity comprises extracting a sequence of maximum tidal flow velocities on the gap section appearing with the closure process during or after the simulation, and comparing the sequence of maximum tidal flow velocities with the critical starting flow velocity or shear stress limit of the closure material;

[0050] The judging the feasibility of the scheme comprises that when the maximum tidal flow velocity of the gap section obtained by simulation is always lower than or equal to the critical starting flow velocity or shear stress limit of the closure material in the entire closure process, it is considered that the proposed process line generated by machine learning is safe in terms of water dynamics;

[0051] The adjusting and refining the scheme comprises adjusting the scheme when the scheme is not feasible;

[0052] The adjustment mode comprises modifying the parameters input into the planning method, or manually correcting the generated proposed process line according to the water dynamic verification result by an engineer, and the corrected scheme needs to be re-executed to perform the steps of converting the proposed process line into water dynamic model input, running the water dynamic full-process verification simulation, and extracting and comparing the maximum flow velocity for water dynamic verification;

[0053] When the scheme is determined to be feasible, the feasible process line is processed in combination with the actual construction capacity of the project, the material supply plan, the ship scheduling, and the recorded relative time points at which the maximum flow rate occurs in each narrowing state to guide the on-site construction and complete the closure process line planning.

[0054] In another aspect of the present application, a mouth closure process line planning system is provided.

[0055] In an optional embodiment, an input information acquisition and processing module collects original project data, and performs preliminary processing and generalization on the original project data according to the input applicable to hydrodynamic modeling and machine learning.

[0056] A hydrodynamic data generation module constructs a hydrodynamic model, defines a series of different narrowing states of the gap, runs the hydrodynamic simulation for each narrowing state, extracts the tidal flow velocity and occurrence time, and constructs a hydrodynamic data set.

[0057] A flow rate prediction model training module predicts the flow rate according to the geometric characteristics of the different narrowing states of the gap, selects a prediction model, trains the selected prediction model, evaluates the prediction accuracy of the trained prediction model on the validation set, and optimizes the prediction model parameters.

[0058] A closure process line planning module plans a closure process line that satisfies the hydrodynamic constraints using the flow rate trained by the prediction model and the critical flow rate limit of the closure material.

[0059] A scheme verification and refinement module verifies the planning of the closure process line and completes the mouth closure process line planning.

[0060] The present application has the advantages of intelligent planning of the mouth closure process line, significantly improving the scientificity and efficiency of the seawall construction decision-making. Compared with the traditional method relying on experience and trial and error, the present application uses a machine learning model to quickly predict the flow rate response under different closure states, greatly shortens the planning period, and reduces the dependence on expert experience; by constructing a multi-dimensional constraint model of "geometry-tide-flow rate-material", the present application supports efficient exploration and optimization of various closure strategies, improves the economic efficiency of the scheme under the premise of ensuring construction safety; in combination with the terrain and cross-section generalization technology, the present application improves the calculation efficiency while ensuring the simulation accuracy of the key hydrodynamic characteristics, and ensures the physical feasibility and construction safety of the scheme through a full-process hydrodynamic verification mechanism; at the same time, the present application effectively integrates historical engineering data and simulation data, realizes systematic accumulation and reuse of knowledge, and promotes the high-quality development of seawall engineering towards a data-driven and intelligent decision-making direction. BRIEF DESCRIPTION OF DRAWINGS

[0061] The accompanying drawings are included to provide a further understanding of the application, and are incorporated in and constitute a part of this specification, illustrate embodiments of the application, and together with the description serve to explain the application, and do not limit the application. In the drawings:

[0062] Figure 1 A method flow chart of a mouth gate plugging process line planning method and system provided for an embodiment of the application;

[0063] Figure 2 A system schematic diagram of a mouth gate plugging process line planning method and system provided for an embodiment of the application;

[0064] Figure 3 A block diagram of an electronic device of a system of a mouth gate plugging process line planning method and system provided for an embodiment of the application;

[0065] Figure 4 A computer readable storage medium block diagram of a system of a mouth gate plugging process line planning method and system provided for an embodiment of the application. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the application will be described below with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments of the application.

[0067] Hereinafter, the terms "first", "second", and the like are used only to describe convenience, and should not be construed as indicating or implying relative importance or a number of the indicated technical features. Therefore, the features defined with "first", "second", and the like can explicitly or implicitly include one or more of the features. In the description of the application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0068] In the present application, unless otherwise explicitly specified and limited, the term "connection" should be understood broadly, for example, the "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or the "connection" can be direct connection, or indirect connection through an intermediate medium. In addition, unless otherwise explicitly specified and limited, the term "coupling" should be understood broadly, for example, the "coupling" can be direct electrical connection, for example, physical contact and electrical conduction between two components, or can be understood as electrical connection between different components through solid lines such as copper foil or wire on a printed circuit board (PCB) in a circuit configuration, to transmit electrical signals; or the "coupling" can be indirect electrical connection between two components through an intermediate medium; or the "coupling" can be electrical connection between two components through a non-contact / air gap, for example, electrical connection between two components through capacitive coupling to transmit electrical signals.

[0069] In the embodiments of the present application, the orientation terms such as "upper", "lower", "left", "right" and the like can include but are not limited to the orientation defined by the relative placement of the components in the drawings. It should be understood that these directional terms can be relative concepts, which are used for relative description and clarification, and can change accordingly according to the change of the placement of the components in the drawings.

[0070] Embodiment 1:

[0071] As shown in the drawings, the present application provides a method comprising the following steps: Figure 1

[0072] Step S100: Collecting original engineering data, and performing preliminary processing and generalization on the original engineering data according to the input suitable for hydrodynamic modeling and machine learning.

[0073] Step S200: Constructing a hydrodynamic model, defining different narrowing states of a series of narrows, running hydrodynamic simulation for each narrowing state, extracting tidal current velocity and corresponding time, and constructing a hydrodynamic data set.

[0074] Step S300: Predicting the tidal current velocity according to the geometric characteristics of the different narrowing states of the narrows, selecting a prediction model, training the selected prediction model, evaluating the prediction accuracy of the trained prediction model on a validation set, and optimizing the prediction model parameters. The geometric characteristics refer to the width and bottom elevation of the mouth.

[0075] Step S400: Using the prediction model to train the critical velocity limit of the tidal current velocity and the sealing material, and planning a sealing process line that satisfies the hydrodynamic constraint. ​

[0076] Step S500: verifying the planning of the closure process line, completing the planning of the entrance closure process line.

[0077] Embodiment 2

[0078] On the basis of embodiment 1, the step S100 provided by the present embodiment comprises

[0079] Step S101: collecting original engineering data, including 7-day or 15-day tidal level process time series outside the entrance of the engineering sea area as external boundary conditions for water dynamics modeling, the tidal level process time series refers to the tidal level change data within 7 days or 15 days;

[0080] The preliminary processing includes the original bathymetric data of the strait area and the surrounding inner and outer sea areas and the original bathymetric data of the enclosed area in the strait, which are used for water dynamics modeling, the water level and tidal current velocity measurement data of different points in the enclosed area at the same period are used for water dynamics modeling, the planned type of closure material and the critical starting flow velocity or shear stress determined by experiment, the critical starting tidal current velocity or shear stress refers to the maximum velocity limit that the material can withstand during the process of closing the entrance.

[0081] Step S102: constructing a water dynamics model, including constructing a two-dimensional or three-dimensional water dynamics numerical model of the engineering area according to the geographical information of the engineering sea area and the generalized inner and outer topographic information, at this time, the water dynamics model refers to the completion of sufficient rating and verification according to the external boundary conditions, water level and maximum velocity data, the determination of parameters including roughness, and the construction of a two-dimensional or three-dimensional water dynamics numerical model;

[0082] Defining a series of different narrowing states of the strait includes changing the model strait area, so that the water dynamics model simulates different strait closure states by modifying the geometric parameters or grid of the strait area, defining the narrowing states of the strait closure, covering the entire process from the initial opening of the strait to the complete closure, each narrowing state is determined by the remaining strait width and the bottom elevation under the remaining strait width, at this time, the input feature space of the water dynamics data set is formed;

[0083] Running water dynamics simulation for each narrowing state includes setting the corresponding strait geometry in the water dynamics model for the defined strait narrowing state, running the water dynamics model, using the obtained 7-day or 15-day tidal level process time series as external boundary conditions for simulation, and capturing the maximum velocity limit value under different tidal conditions;

[0084] Extracting tidal current velocity and occurrence time includes extracting the maximum velocity limit value that occurs at the strait section position every day or every tidal cycle under each entrance narrowing state from the simulation results, and recording the relative time point of the maximum velocity limit value occurrence relative to the tidal cycle, i.e. several minutes before or after the highest or lowest tide.

[0085] The water dynamic data set is constructed by combining the description defining each gap narrowing state with the corresponding extracted maximum velocity limit value sequence of each day or each tide, forming a water dynamic data set reflecting the physical relationship between the gap geometric narrowing and the maximum velocity limit value under different tidal conditions. The water dynamic data set is divided into a training set, a verification set and a test set according to a ratio of 8:1:1, which is used to train the maximum velocity limit value prediction model

[0086] Step S103: training the selected prediction model means training the machine learning model, including selecting the prediction model, training the prediction model and prediction model parameter optimization;

[0087] Selecting the prediction model includes selecting a machine learning regression model according to the characteristics of the dynamic data set;

[0088] Training the prediction model includes training the selected machine learning model using the constructed water dynamic data set;

[0089] Prediction model parameter optimization includes evaluating the prediction accuracy of the model on an independent verification set, and performing model parameter optimization as needed.

[0090] Step S104: planning a closure process line that satisfies the water dynamic constraint includes the following steps:

[0091] Setting planning objectives and constraints;

[0092] Defining candidate closure process line representations;

[0093] Building or searching a process line based on the maximum velocity limit value prediction model;

[0094] Generating a recommended closure process line;

[0095] Setting planning objectives and constraints means setting the planning objectives and key constraints of the closure process line;

[0096] Defining candidate closure process line representations includes discretizing the entire closure process into a series of time steps, each time step corresponding to a remaining gap width or flow area;

[0097] Building or searching a process line based on the maximum velocity limit value prediction model includes using the trained maximum velocity limit value prediction model, combining the obtained 7-day or 15-day tidal level process time sequence and the critical flow velocity limit of the closure material type, to build or search a closure process line that satisfies the constraint conditions, that is, by the following method:

[0098] Based on the lookup table or curve, a lookup table or curve is constructed using the generated hydrodynamic data set to query the maximum flow rate according to the residual gate status and tidal characteristics, including the current tidal level and tidal level change rate. The planning process selects a safe closure status sequence according to the lookup table;

[0099] The constraint condition refers to that the predicted maximum flow rate of any time period does not exceed the critical flow rate limit. An optimization algorithm is used to search in the closure process line space;

[0100] Generating a recommended closure process line includes outputting a recommended closure process line that satisfies the constraint condition and is constructed or searched. The closure process line is represented in the form of a sequence of residual gate width and gate bottom height varying with time.

[0101] Step S105: verifying the planning of the closure process line includes the following steps;

[0102] Converting the recommended process line into hydrodynamic model input;

[0103] Running a hydrodynamic full-process verification simulation;

[0104] Extracting and comparing the maximum flow rate;

[0105] Judging the feasibility of the scheme;

[0106] Adjusting and refining the scheme;

[0107] Converting the recommended process line into hydrodynamic model input according to the generated recommended closure process line;

[0108] Running a hydrodynamic full-process verification simulation includes using the constructed hydrodynamic model, importing the converted dynamic geometric information of the gate opening varying with time, running the hydrodynamic model, using the obtained 15-day tidal level process time series as external boundary conditions, and simulating the flow changes during the entire closure process in a full tidal cycle;

[0109] Extracting and comparing the maximum flow rate includes extracting the maximum tidal flow velocity sequence that appears on the gate opening section during the closure process, and comparing the maximum tidal flow velocity sequence with the critical starting flow rate or shear stress limit of the closure material;

[0110] Judging the feasibility of the scheme includes that when the maximum tidal flow velocity of the gate opening section obtained by simulation is always lower than or equal to the critical starting flow rate or shear stress limit of the closure material during the entire closure process, it is considered that the recommended process line generated by machine learning is safe in terms of hydrodynamics;

[0111] Adjusting and refining the scheme includes adjusting the scheme when the scheme is not feasible;

[0112] The adjustment mode includes modifying parameters input to the planning method, or manually correcting the generated recommended process line according to the hydrodynamic verification result by an engineer, and the corrected scheme needs to be re-executed to convert the recommended process line into hydrodynamic model input, run the hydrodynamic full-process verification simulation, extract and compare the maximum flow rate steps to perform hydrodynamic verification;

[0113] When it is judged that the scheme is feasible, the feasible process line is processed in combination with the actual construction capacity of the project, the material supply plan, the ship scheduling, and the recorded relative time point at which the maximum flow rate occurs in each narrowing state, to guide the on-site construction and complete the plugging process line planning.

[0114] Embodiment 3:

[0115] On the basis of embodiment 2, in the steps provided by the embodiment of the application, the generalization includes simplifying the original terrain of the enclosed area in the gap, calculating a water level-storage capacity curve of the original terrain area according to original terrain data, generalizing the terrain of the enclosed area in the gap into an area with an average water depth and an area, representing the parameters of the generalized terrain, and taking the parameters as input for describing the characteristics of the project, and constructing a hydrodynamic model.

[0116] The water level-storage capacity curve of the original terrain area is calculated according to original terrain data, which is an important basis for constructing a hydrodynamic model and subsequent machine learning input. The curve reflects the water storage volume corresponding to the enclosed area at different water levels The water level-storage capacity curve of the original terrain area is calculated according to original terrain data, which is an important basis for constructing a hydrodynamic model and subsequent machine learning input. The curve reflects the water storage volume corresponding to the enclosed area at different water levels

[0117]

[0118] Among them, represents the total water storage volume when the water level is , represents the water level, represents the lowest terrain elevation of the enclosed area, represents the integral variable, represents the geomorphic subarea, represents the area growth reference coefficient of the th geomorphic subarea, represents the area growth nonlinear index of the th geomorphic subarea, represents the terrain slope influence weight coefficient of the th geomorphic subarea, represents the local terrain slope square.

[0119] ​​The actual terrain profile is approximated as an average bottom elevation or divided into N different bottom elevations under different remaining width of the gap, based on the actual or approximated gap section information, the total area parameter of the remaining flow section corresponding to different closure states is calculated and extracted, and the total area parameter will be used as a feature to describe the narrowing state of the gap, as the input of the water dynamic data set generation and machine learning model.

[0120] The calculation formula of the total area parameter of the remaining flow section is:

[0121]

[0122] wherein, the total area parameter, the lateral width of the subsection, the water surface elevation at the current time, the average bottom elevation of the subsection, the standard deviation of the bottom elevation of the subsection, the main flow direction angle of the subsection, the terrain submergibility correction function, the structure shielding function.

[0123] Example 4:

[0124] As shown in Figure 2 , on the basis of example 1, including a preferred embodiment, a gap closure process line planning system, the system includes an input information acquisition and processing module, which collects original engineering data, and preliminarily processes and generalizes the original engineering data according to the input suitable for water dynamic modeling and machine learning, and the gap closure refers to the gap reserved for water passage or construction convenience in the project;

[0125] a water dynamic data generation module, which constructs a water dynamic model, defines different narrowing states of a series of gaps, runs water dynamic simulation for each narrowing state, extracts tidal current velocity and occurrence time, and constructs a water dynamic data set;

[0126] a flow velocity prediction model training module, which predicts flow velocity according to the geometric characteristics of different narrowing states of the gap, selects a prediction model, trains the selected prediction model, evaluates the prediction accuracy of the trained prediction model on the validation set, and optimizes the prediction model parameters;

[0127] a closure process line planning module, which uses the flow velocity trained by the prediction model and the critical flow velocity limit of the closure material to plan a closure process line that satisfies the water dynamic constraints;

[0128] A scheme verification and refinement module verifies the planning of the occlusion process line, and completes the planning of the orifice occlusion process line.

[0129] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to the above-mentioned modules by the processor.

[0130] In an embodiment, a computer device is provided. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, a carrier network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0131] Figure 3 A block diagram of an exemplary electronic device suitable for implementing an embodiment of the present application is shown.

[0132] The electronic device can include a central processor / microprocessor / master control chip, etc. 4; a storage medium 5 coupled to the central processor / microprocessor / master control chip, etc. 4 and storing computer executable instructions therein for performing the steps of the various methods of the embodiments of the present application when executed by the processor.

[0133] The central processor / microprocessor / master control chip, etc. 4 can include, but is not limited to, for example, one or more processors or microprocessors, etc.

[0134] The storage medium 5 can include, but is not limited to, for example, a random access memory (RAM), a read-only memory (ROM), a flash memory, an EPROM memory, an EEPROM memory, a register, a computer storage medium (such as a hard disk, a floppy disk, a solid state disk, a removable disk, a CD-ROM, a DVD-ROM, a Blu-ray disc, etc.).

[0135] In addition, the electronic device can further include (but is not limited to) a data bus 6, an input / output bus / external bus / device bus, etc. 7, a display 8, and an input / output device 9 (such as a keyboard, a mouse, a speaker, etc.).

[0136] The central processor / microprocessor / master chip or the like 4 can communicate with external devices (8, 9, etc.) via a wired or wireless network (not shown) through the I / O bus 7.

[0137] The storage medium 5 can also store at least one computer-executable instruction for performing the steps of the various functions and / or methods in the embodiments described in the present technology when executed by the central processor / microprocessor / master chip or the like 4.

[0138] In one embodiment, the at least one computer-executable instruction can also be compiled or constitute a software product in which one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described in the present technology.

[0139] Figure 4 A schematic diagram of a computer-readable storage medium according to an embodiment of the present application is shown.

[0140] As Figure 4 shown, a non-transitory computer-readable storage medium 11 stores instructions, for example, computer-readable instructions 10. When the computer-readable instructions 10 are executed by a processor, the various methods described above can be performed. The non-transitory computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory can include, for example, a random access memory (RAM) and / or a cache memory, etc. The non-transitory non-volatile memory can include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then when the computing device executes the computer-readable instructions 10 stored on the non-transitory computer-readable storage medium 11, the various methods described above can be performed.

[0141] In several embodiments provided by the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the described apparatus embodiments are merely schematic. The division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0142] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0143] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0144] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for executing all or part of the steps of the method of each embodiment of the application by a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), a random access memory (English full name: Random Access Memory, English abbreviation: RAM), a magnetic disk or an optical disk, and various program code storage media.

[0145] The above embodiments are only used to illustrate the technical solutions of the application, but not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. A method for planning the process line of gate sealing, characterized in that, Includes the following steps: Collect raw engineering data, perform preliminary processing and generalization on the raw engineering data according to the input of hydrodynamic modeling and machine learning, and the gate refers to the gap reserved in the project for water passage or construction convenience; A hydrodynamic model was constructed, defining different narrowing states of a series of sluice gates. Hydrodynamic simulations were run for each narrowing state to extract tidal current velocity and occurrence time, and a hydrodynamic dataset was constructed. The tidal current velocity is predicted based on the geometric characteristics of the different narrowing states of the sluice gate. A prediction model is selected, and the selected prediction model is trained. The prediction accuracy of the trained prediction model is evaluated on the validation set, and the prediction model parameters are tuned. The geometric characteristics refer to the width and bottom elevation of the sluice gate. By using a predictive model to train the tidal current velocity and the critical velocity limit of the plugging material, a plugging process line that satisfies hydrodynamic constraints is planned. Verify the planning of the closure process line and complete the planning of the closure process line of the entrance. The construction of the hydrodynamic model includes constructing a two-dimensional or three-dimensional hydrodynamic numerical model of the engineering area based on the geographical information of the engineering sea area and the generalized internal and external topographic information. At this time, the hydrodynamic model refers to the complete calibration and verification based on the data of external boundary conditions, water level and maximum velocity, determining parameters including roughness, and completing the construction of the two-dimensional or three-dimensional hydrodynamic numerical model. The definition of different narrowing states of the dragon mouth includes changing the dragon mouth region of the model, so that the hydrodynamic model can simulate different dragon mouth blocking states by modifying the geometric parameters or mesh of the dragon mouth region. The definition of the dragon mouth blocking and narrowing states covers the entire process from the initial opening of the dragon mouth to complete closure. Each narrowing state is determined by the remaining dragon mouth width and the bottom elevation below the remaining dragon mouth width, which constitutes the input feature space of the hydrodynamic dataset. The hydrodynamic simulation for each narrowing state includes setting the corresponding geometries of the narrowing mouth in the hydrodynamic model for the defined narrowing mouth state, running the hydrodynamic model, using the obtained 7-day or 15-day tidal process time series as external boundary conditions for simulation, and capturing the maximum speed limit value under different tidal conditions. The extraction of tidal velocity and occurrence time includes extracting the maximum velocity limit value at the tidal cross-section position in each day or each tidal cycle under the narrowing state of each tidal gate from the simulation results, and recording the relative time point of the occurrence of the maximum velocity limit value with respect to the tidal cycle, that is, a few minutes before or after the highest or lowest tide. The construction of the hydrodynamic dataset includes combining the description of the narrowing state of each sluice gate with the corresponding extracted daily or tidal maximum speed limit value sequence to form a hydrodynamic dataset. The hydrodynamic dataset refers to the physical relationship between the geometric narrowing of the sluice gate and the maximum speed limit value under different tidal conditions. The hydrodynamic dataset is divided into a training set, a validation set and a test set in an 8:1:1 ratio for training the maximum speed limit value prediction model.

2. The port sealing process line planning method as described in claim 1, characterized in that, The collection of raw engineering data includes using the 7-day or 15-day tidal process time series outside the engineering sea area entrance as the external boundary condition for hydrodynamic modeling. The tidal process time series refers to the tidal change data within 7 days or 15 days. The preliminary processing includes using the original water depth and topographic data of the Longkou area and surrounding sea areas, as well as the original water depth and topographic data of the enclosed area within Longkou, for actual measurements of the hydrodynamic model. The actual measurements used for the hydrodynamic model refer to the measured data of water level and tidal current velocity at different points in the enclosed area during the same period. The planned type of sealing material and the critical starting tidal current velocity or shear stress determined through experiments are also considered. The critical starting tidal current velocity or shear stress refers to the maximum velocity limit that the material can withstand during the sealing process of the opening.

3. The gate sealing process line planning method as described in claim 1, characterized in that, The generalization includes generalizing the topography of the enclosed area within the mouth and generalizing the water depth profile of the mouth area; The generalization includes generalizing the terrain of the enclosed area within the Longkou, which involves simplifying the original terrain of the enclosed area within the Longkou, calculating the water level-storage capacity curve of this original terrain area based on the original terrain data, generalizing the terrain of the enclosed area within the Longkou into an area with average water depth and area, and using the parameters corresponding to the generalized terrain representation as input to describe the characteristics of the engineering project to construct a hydrodynamic model. The generalized water depth profile of the sluice gate area includes a simplified representation of the shape of the remaining flow cross section in the sluice gate area as the closure process progresses, so as to model different narrowing states in the hydrodynamic model. Under different remaining widths of the sluice gate, the actual topographic profile is generalized to the average bottom elevation or divided into N parts with different bottom elevations. Based on the actual or generalized sluice gate cross-section information, the total area parameter of the remaining flow cross section corresponding to different blocking states is calculated and extracted. The total area parameter will be used as a feature describing the narrowing state of the sluice gate and as input for hydrodynamic dataset generation and machine learning model. From the collected raw engineering data and the process of preliminary processing and generalization, a project feature set is extracted for input into the machine learning model. The project feature set refers to a set of parameters that describe the macroscopic attributes of an engineering project.

4. The gate sealing process line planning method as described in claim 1, characterized in that, The training of the selected prediction model refers to training the machine learning model, including selecting the prediction model, training the prediction model, and tuning the prediction model parameters. The selection of the prediction model includes selecting a machine learning regression model based on the characteristics of the dynamic dataset; The training prediction model includes training a selected machine learning model using a constructed hydrodynamic dataset; The prediction model parameter tuning includes evaluating the model's prediction accuracy on an independent validation set and tuning the model parameters as needed.

5. The port sealing process line planning method as described in claim 1, characterized in that, The planning of a closure process line that satisfies hydrodynamic constraints includes the following steps: Set planning goals and constraints; Define the candidate blocking process line representation; Process line construction or search based on the maximum speed limit prediction model; Generate a suggested closure process line; The setting of planning objectives and constraints refers to setting the planning objectives and key constraints for the closure process line; The definition of the candidate plugging process line includes discretizing the entire plugging process into a series of time steps, with each time step corresponding to a remaining gate width or flow cross-sectional area. The process line construction or search based on the maximum velocity limit prediction model involves using the trained maximum velocity limit prediction model, combined with the obtained 7-day or 15-day tidal process time series and the critical velocity limit of the plugging material type, to construct or search for a plugging process line that meets the constraints. This is achieved through the following methods: Based on a lookup table or curve, a lookup table or curve is constructed using the generated hydrodynamic dataset. The maximum flow velocity is queried according to the remaining gate status and tidal characteristics, including the current tide level and the rate of change of tide level. The planning process selects a safe closure state sequence based on the lookup table. The constraint condition is that the predicted maximum flow velocity in any time period does not exceed the critical flow velocity limit, and an optimization algorithm is used to search in the blocking process line space; The generated proposed blocking process line includes outputting the proposed blocking process line that meets the constraints obtained by construction or search. The blocking process line is represented in the form of a sequence of remaining gate widths and gate bottom heights that change over time.

6. The port sealing process line planning method as described in claim 1, characterized in that, The verification of the planning of the closure process line includes the following steps; Transform the suggested process line into hydrodynamic model input; Full-process hydrodynamic verification simulation; Extract and compare maximum flow rates; Assess the feasibility of the proposed solution; Plan adjustments and refinements; The process of converting the proposed process line into a hydrodynamic model input is based on the generated proposed closure process line; The full-process hydrodynamic verification simulation includes using the constructed hydrodynamic model, importing the transformed dynamic geometric information of the sluice gate over time, running the hydrodynamic model, using the obtained 15-day tidal level process time series as external boundary conditions, and simulating the water flow changes during the entire closure process of the full tidal cycle. The extraction and comparison of the maximum flow velocity includes extracting the maximum tidal flow velocity sequence that appears on the Longkou section during or after the simulation process, and comparing the maximum tidal flow velocity sequence with the critical starting flow velocity or shear stress limit of the obtained sealing material. The feasibility assessment of the scheme includes the following: if the maximum tidal current velocity of the simulated sluice gate section is always lower than or equal to the critical starting velocity or shear stress limit of the sealing material during the entire sealing process, then the suggested process line generated by machine learning is considered to be safe in terms of hydrodynamics. The adjustment and refinement of the plan includes adjusting the plan when it is determined to be infeasible; The adjustment methods include modifying the parameters input to the planning method, or having engineers manually correct the generated suggested process line based on the hydrodynamic verification results. The corrected scheme needs to be re-executed to convert the suggested process line into hydrodynamic model input, run the full hydrodynamic verification simulation, and extract and compare the maximum flow velocity steps for hydrodynamic verification. When a feasible plan is determined, the feasible process line is processed by combining the actual construction capacity of the project, material supply plan, ship scheduling, and the relative time points of the maximum flow velocity in each narrowing state, to guide on-site construction and complete the planning of the closure process line.

7. A gate sealing process line planning system, based on the gate sealing process line planning method according to any one of claims 1 to 6, characterized in that: include: The input information acquisition and processing module collects raw engineering data and performs preliminary processing and generalization on the raw engineering data in accordance with the input of hydrodynamic modeling and machine learning. The gate sealing refers to the gap reserved in the project for water passage or construction convenience. The hydrodynamic data generation module constructs a hydrodynamic model, defines different narrowing states of a series of gorges, runs hydrodynamic simulations for each narrowing state, extracts tidal current velocity and occurrence time, and constructs a hydrodynamic dataset. The flow velocity prediction model training module predicts flow velocity based on the geometric features of different narrowing states of the sluice gate, selects a prediction model, trains the selected prediction model, evaluates the prediction accuracy of the trained prediction model on the validation set, and fine-tunes the prediction model parameters. The plugging process planning module uses the flow velocity trained by the prediction model and the critical flow velocity limit of the plugging material to plan a plugging process line that meets hydrodynamic constraints. The scheme verification and refinement module verifies the planning of the closure process line and completes the planning of the closure process line of the port.

8. An electronic device, comprising: At least one memory stores computer-executable instructions non-transiently; At least one processor, configured to run the computer-executable instructions, The computer-executable instructions are executed by the processor to implement the gate blocking process line planning method according to any one of claims 1 to 6.

9. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer-executable instructions, which, when executed by at least one processor, implement the gate sealing process line planning method according to any one of claims 1 to 6.

Images