CN112465013A - Method, device and equipment for predicting peak value of underwater slamming force of ocean flat-bottom structure - Google Patents
Method, device and equipment for predicting peak value of underwater slamming force of ocean flat-bottom structure Download PDFInfo
- Publication number
- CN112465013A CN112465013A CN202011344721.6A CN202011344721A CN112465013A CN 112465013 A CN112465013 A CN 112465013A CN 202011344721 A CN202011344721 A CN 202011344721A CN 112465013 A CN112465013 A CN 112465013A
- Authority
- CN
- China
- Prior art keywords
- flat
- geometric parameters
- function formula
- water
- slamming
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 108
- 238000012549 training Methods 0.000 claims abstract description 42
- 238000012360 testing method Methods 0.000 claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 230000002068 genetic effect Effects 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 180
- 238000004364 calculation method Methods 0.000 claims description 90
- 230000008569 process Effects 0.000 claims description 20
- 230000009189 diving Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 230000035772 mutation Effects 0.000 claims description 11
- 238000005094 computer simulation Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 210000004556 brain Anatomy 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 210000000349 chromosome Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000007876 drug discovery Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229940098006 multigen Drugs 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of artificial intelligence and discloses a peak value prediction method, a device and computer equipment for sea flat-bottom structure underwater crash force, wherein the method comprises the following steps: acquiring target geometric parameters of a target ocean flat-bottom structure; introducing the target geometric parameters into a preset optimal function formula, and predicting the peak value of the water-entering impact force of the target ocean flat-bottom structure by using the optimal function formula; the method for acquiring the preset optimal function formula comprises the following steps: acquiring geometric parameters of a plurality of groups of different ocean flat-bottom structures; determining the water inlet slamming force peak values of different ocean flat-bottom structures under corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of a plurality of groups of geometric parameters and the corresponding water inlet slamming force peak values, and excavating an optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set. Therefore, the water-entering slamming force is calculated by using an optimal function formula, and the prediction efficiency is effectively improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence prediction analysis, in particular to a peak value prediction method, a peak value prediction device and computer equipment for the diving impulsive force of an ocean flat-bottom structure.
Background
Marine flat bottom structures often slam when hoisted into the water. The penetration of marine flat-bottomed structures into water is a transient process, and since the duration of the slamming force of the marine flat-bottomed structure by the water body is short, the magnitude of the slamming force is often large, possibly causing deformation and destruction of the marine flat-bottomed structure. If the slamming force of the ocean flat-bottom structure is larger than the dead weight of the ocean flat-bottom structure, the rigging is easy to loose and is subjected to great sudden force. Therefore, in order to ensure that the safe load of the marine flat-bottomed structure and the rigging meets the operation requirement and avoid serious accidents, it is necessary to predict the peak value of the diving slamming force of the marine flat-bottomed structure in advance so as to guide the design of the marine flat-bottomed structure and the marine hoisting operation.
Since the problem of water inflow of the marine flat-bottom structure relates to coupling among solids, fluids and gases, the marine flat-bottom structure is a strong nonlinear complex transient physical process, and the peak value of the water inflow crashing force of the marine flat-bottom structure is difficult to be rapidly and accurately predicted by the existing prediction method.
Disclosure of Invention
The application mainly aims to provide a method, a device and computer equipment for predicting the peak value of the diving pop force of a marine flat-bottom structure, and aims to solve the technical problems of low efficiency and poor accuracy of the conventional method for predicting the peak value of the diving pop force of the marine flat-bottom structure.
In order to achieve the above object, the present application provides a method for predicting a peak value of an underwater crash force of a marine flat-bottomed structure, comprising:
acquiring target geometric parameters of a target ocean flat-bottom structure;
leading the target geometric parameters into a preset optimal function formula, and predicting the peak value of the water entrance slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the preset method for acquiring the optimal function formula comprises the following steps:
acquiring geometric parameters of a plurality of groups of different ocean flat-bottom structures;
determining the water inlet slamming force peak values of different ocean flat-bottom structures under corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of a plurality of groups of geometric parameters and corresponding water inlet slamming force peak values, and excavating an optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
Further, the step of determining numerically the peak values of the water intrusion thump force of the different marine flat-bottomed structures under the corresponding geometrical parameters comprises:
establishing a calculation model of the ocean flat-bottom structure by using three-dimensional modeling software, and configuring the geometric parameters in the calculation model; wherein the computational model is used to simulate an ocean flat bottom structure;
simulating an underwater slamming process of the marine flat-bottom structure under the geometric parameters by using the calculation model, carrying out stress analysis on the calculation model of the underwater slamming process, and determining a peak value of the underwater slamming force of the marine flat-bottom structure according to a stress analysis result;
and adjusting the values of the geometric parameters, reconfiguring the calculation model for the adjusted geometric parameters, and simulating the water-entering slamming process of the marine flat-bottom structure again to obtain the peak values of the water-entering slamming force under different values.
Further, the geometric parameter includes an entry velocity, and the step of configuring the geometric parameter in the calculation model further includes:
when the water entering speed of the ocean flat-bottom structure is determined not to be obtained, carrying out grid division on the surface of the calculation model according to the number of preset grids, and setting a calculation domain, grid density and an initial water entering point of the calculation model according to the divided grids; the calculation domain is a water inlet region of the calculation model;
and determining the water inlet speed of the ocean flat-bottom structure according to the calculation domain, the grid density and the initial water inlet point of the calculation model.
Further, the step of using a genetic algorithm to dig out an optimal function formula of the water-entering slamming force of the marine flat-bottomed structure according to the training set and the test set comprises:
randomly generating a plurality of first function formulas containing variables or constants, the plurality of first function formulas being used for predicting the peak value of the water-entering slamming force of the target marine flat-bottomed structure;
respectively importing the geometric parameters of the training set into the plurality of first function formulas to be calculated to obtain first calculation results, calculating the fitness of the plurality of first function formulas according to the first calculation results and the water-entering slamming force peak values corresponding to the geometric parameters in the training set, and taking the first function formula with the fitness larger than a preset value as a second function formula;
randomly selecting variables or constants in the second function formula for variation according to a preset variation probability and a preset variation mode to obtain a third function formula;
and respectively importing the geometric parameters of the test set into the third function formula for calculation to obtain a second calculation result, screening out the second calculation result closest to the water-entering slamming peak value corresponding to the geometric parameters of the test set, and taking the third function formula corresponding to the water-entering slamming peak value closest to the second calculation result as an optimal function formula.
Further, after the fitness calculation of the plurality of first function formulas according to the water-entering slamming force peak values corresponding to the geometric parameters in the first calculation result training set, the method further includes:
and eliminating the first function formula with the fitness smaller than a preset value.
Further, after the step of screening out a second function formula with the fitness greater than a preset value from the plurality of first function formulas, the method further includes:
and randomly exchanging variables or constants between every two second function formulas, and executing the step of randomly selecting the variables or constants in the second function formulas to be mutated according to a preset mutation probability and a preset mutation mode by using the exchanged second function formulas.
Further, after randomly generating a plurality of first function formulas containing variables or constants, the method further comprises the following steps;
and representing the first function formula by using a binary tree, wherein all leaf nodes in the binary tree are variables or constants of the first function formula, and all internal nodes in the binary tree are functions of the first function formula.
The present application further provides a peak value prediction device for the diving slamming force of a marine flat-bottomed structure, comprising:
the acquisition module is used for acquiring target geometric parameters of the target ocean flat-bottom structure;
the prediction module is used for leading the target geometric parameters into a preset optimal function formula and predicting the peak value of the water-entering slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the system also comprises an optimal function formula acquisition module which is used for acquiring the geometric parameters of a plurality of groups of different ocean flat-bottom structures, determining the water inlet slamming force peak values of the different ocean flat-bottom structures under the corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of the geometric parameters and the corresponding water inlet slamming force peak values, and excavating the optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
The present application further provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of any of the above methods when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the above.
According to the method, the device and the computer equipment for predicting the peak value of the underwater impulsive force of the marine flat-bottom structure, the target geometric parameters of the target marine flat-bottom structure are obtained and are led into the preset optimal function formula, the peak value of the underwater impulsive force of the target marine flat-bottom structure is predicted by directly utilizing the optimal function formula, a large amount of data operation is avoided, the efficiency of predicting the peak value of the underwater impulsive force of the marine flat-bottom structure in engineering is effectively improved, the calculated optimal function formula can also provide reference values for the design of the marine flat-bottom structure and the marine hoisting scheme, and the method and the device have wide engineering application prospects in marine engineering hoisting operation. In addition, when the preset optimal function formula is obtained, the geometric parameters of a plurality of groups of different ocean flat bottom structures are obtained, the water inlet impact force peak values of the different ocean flat bottom structures under the corresponding geometric parameters are determined by a numerical method, a training set and a testing set which are composed of the geometric parameters and the corresponding water inlet impact force peak values are generated, the optimal function formula of the water inlet impact force of the ocean flat bottom structures is excavated by a genetic algorithm according to the training set and the testing set, so that the genetic algorithm is further combined, the optimal function formula which is difficult to construct through the human brain is excavated, and the optimal function formula is used for calculating the water inlet impact force peak value of the ocean flat bottom structures so as to take prediction precision into consideration.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting the peak value of the diving pop force of a marine flat-bottomed structure according to an embodiment of the present application;
FIG. 2 is a block diagram of a schematic configuration of a peak value prediction device for the diving pop force of a marine flat-bottomed structure according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The application provides a genetic algorithm-based marine flat-bottom structure water-entering slamming force peak value prediction method, which is characterized in that symbolic regression is achieved through the genetic algorithm, a mathematical calculation formula of the marine flat-bottom structure water-entering slamming force peak value is found, and therefore a target variable (slamming peak value) is predicted through characteristic variables (main factors influencing the slamming peak value). According to the fact that the structure water-entering slamming pressure is mainly related to the water-entering speed and the structure shape, for the ocean flat-bottom structure, factors influencing the water-entering slamming force mainly comprise four parameters of the water-entering speed, the structure mass, the bottom surface length-width ratio and the bottom surface area. Therefore, the four parameters are set according to the actual offshore operation condition and the ocean flat-bottom structure, and the corresponding slamming force peak value is determined by using a numerical method.
Specifically, referring to fig. 1, the method for predicting the peak value of the diving pop force of the marine flat-bottomed structure provided in the embodiment of the present application relates to the technical field of artificial intelligence prediction analysis, and includes the steps of:
s1, acquiring target geometric parameters of the target ocean flat-bottom structure;
and S2, introducing the target geometric parameters into a preset optimal function formula, and predicting the peak value of the water-entering slamming force of the target ocean flat-bottom structure by using the optimal function formula.
As described in step S1, the ocean flat bottom structure includes a steel plate, an operation platform, a device, a ship, and other heavy objects that need to be hoisted. When calculating the slamming force generated by lifting the ocean flat-bottom structure into water, acquiring target geometric parameters of the target ocean flat-bottom structure, wherein the target geometric parameters comprise elements which influence the slamming force of the ocean flat-bottom structure into water, such as the water inlet speed, the bottom surface length-width ratio, the bottom area and the structure quality of the target ocean flat-bottom structure, and the more the elements are considered, the more accurate the calculated peak value prediction result of the slamming force of the ocean flat-bottom structure into water is. The water entering speed can be obtained by measuring the speed of the ocean flat-bottom structure entering water through a sensor, and the target ocean flat-bottom structure can be controlled manually to enter water at the designated water entering speed. The length-width ratio and the bottom area of the bottom surface can be obtained by measuring the length, the width and the height of the ocean flat bottom structure through calculation. The structure mass can be obtained by calculating the volume of the structure according to the length, the width and the height, and then calculating the structure mass according to the volume and the structure density of the structure.
The preset method for acquiring the optimal function formula comprises the following steps:
acquiring geometric parameters of a plurality of groups of different ocean flat-bottom structures;
determining the water inlet slamming force peak values of different ocean flat-bottom structures under corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of a plurality of groups of geometric parameters and corresponding water inlet slamming force peak values, and excavating an optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
In order to balance the peak value prediction efficiency and precision of the sea flat-bottom structure underwater crashing force, the four elements of the underwater speed, the structure quality, the bottom surface length-width ratio and the bottom area specified by the sea flat-bottom structure can be preferentially selected, so that the calculated amount is reduced, and the prediction precision is considered. Specifically, the method comprises the steps of determining the water inlet slamming force peak values of the marine flat-bottom structure under four geometric parameters of specified water inlet speed, structural mass, bottom surface length-width ratio and bottom surface area by using a numerical method, determining the water inlet slamming force peak values under the corresponding geometric parameters of different marine flat-bottom structures by using the numerical method, obtaining the water inlet slamming force peak values of a plurality of groups of different marine flat-bottom structures under the corresponding geometric parameters, generating a plurality of groups of training sets and test sets of 'geometric parameters-water inlet slamming force peak values', and excavating the optimal function formula of the water inlet slamming force of the marine flat-bottom structures by using a genetic algorithm according to the training sets and the test sets.
The genetic algorithm is a search algorithm for solving optimization in computational mathematics, and is one of evolutionary algorithms. Evolutionary algorithms were originally developed by using some phenomena in evolutionary biology, including inheritance, mutation, natural selection, and hybridization. Genetic algorithms are typically implemented as a computer simulation. For an optimization problem, a population of abstract representations (called chromosomes) of a certain number of candidate solutions (called individuals) evolves towards better solutions. Traditionally, solutions are represented in binary (i.e., strings of 0's and 1's), but other representations are possible. Evolution starts with a population of completely random individuals, followed by one generation. In each generation, fitness of the entire population is evaluated, a number of individuals are randomly selected from the current population (based on their fitness), a new life population is created through natural selection and mutation, which becomes the current population in the next iteration of the algorithm, resulting in an optimal solution.
As described in the above step S2, after the optimal function formula is extracted, the four target geometric parameters, i.e., the entry speed, the bottom aspect ratio, the bottom area, and the structural mass, may be introduced into the optimal function formula, and correspond to the variables in the optimal function formula, respectively, so as to predict the peak value of the entry slamming force of the target ocean flat-bottom structure under the current target geometric parameters.
According to the method for predicting the peak value of the diving impact force of the marine flat-bottom structure, the target geometric parameters of the target marine flat-bottom structure are obtained and are led into the preset optimal function formula, the peak value of the diving impact force of the target marine flat-bottom structure is predicted by directly utilizing the optimal function formula, a large amount of data operation is avoided, the efficiency of predicting the peak value of the diving impact force of the marine flat-bottom structure in engineering is effectively improved, the calculated optimal function formula can also provide reference value for the design of the marine flat-bottom structure and the marine hoisting scheme, and the method has wide engineering application prospect in marine engineering hoisting operation. In addition, when the preset optimal function formula is obtained, the geometric parameters of a plurality of groups of different ocean flat bottom structures are obtained, the water inlet impact force peak values of the different ocean flat bottom structures under the corresponding geometric parameters are determined by a numerical method, a training set and a testing set which are composed of the geometric parameters and the corresponding water inlet impact force peak values are generated, the optimal function formula of the water inlet impact force of the ocean flat bottom structures is excavated by a genetic algorithm according to the training set and the testing set, so that the genetic algorithm is further combined, the optimal function formula which is difficult to construct through the human brain is excavated, and the optimal function formula is used for calculating the water inlet impact force peak value of the ocean flat bottom structures so as to take prediction precision into consideration.
In one embodiment, the step of numerically determining the peak values of the water intrusion thump force of the different marine flat-bottomed structures under the corresponding geometric parameters may comprise:
establishing a calculation model of the ocean flat-bottom structure by using three-dimensional modeling software, and configuring the geometric parameters in the calculation model; wherein the computational model is used to simulate an ocean flat bottom structure;
simulating an underwater slamming process of the marine flat-bottom structure under the geometric parameters by using the calculation model, carrying out stress analysis on the calculation model of the underwater slamming process, and determining a peak value of the underwater slamming force of the marine flat-bottom structure according to a stress analysis result;
and adjusting the values of the geometric parameters, reconfiguring the calculation model for the adjusted geometric parameters, and simulating the water-entering slamming process of the marine flat-bottom structure again to obtain the peak values of the water-entering slamming force under different values.
As described in the above steps, the present embodiment uses three-dimensional modeling software to build a calculation model of the marine flat-bottom structure, so as to simulate the water entry condition of the marine flat-bottom structure, and perform stress analysis on the calculation model of the water entry slamming process. The three-dimensional modeling software can adopt software such as 3DMAX, MAYA, Multigen Creator, Sketch up, Deep expression and the like, and sets geometric parameters, namely length, width, height and model density, of the calculation model according to the ocean flat-bottom structure to obtain the aspect ratio, the bottom area and the mass of the bottom surface of the calculation model, and simultaneously sets the water inlet speed of the calculation model, so that the configured calculation model simulates the water inlet condition of the ocean flat-bottom structure according to the water inlet speed, the water inlet slamming force of each water inlet state of the calculation model is obtained, and the peak value of the water inlet slamming force is determined. In addition, the geometric parameters of the marine flat-bottom structure are continuously adjusted, such as one factor of the water inlet speed, the length-width ratio, the bottom area or the quality of the marine flat-bottom structure is randomly changed, the geometric parameters after the numerical values are adjusted are reconfigured into the calculation model to simulate the water inlet condition of the marine flat-bottom structure again, the calculation model in the water inlet slamming process is subjected to stress analysis again to obtain the peak value of the water inlet slamming force of the marine flat-bottom structure under the geometric parameters with different numerical values, so that multiple groups of geometric parameters, namely the peak value of the water inlet slamming force, are conveniently obtained in a simulation mode, one-by-one experiments on a hoisting site are not needed, the operation is simple, the accuracy is high, and the potential risk of the site experiments is avoided.
In addition, when the peak value of the water-entering impact force of the marine flat-bottom structure under the geometric parameters is simulated by using the calculation model, different virtual wave environments can be set according to the real sea conditions, such as setting parameters of the height, the impact force and the like of waves, so that the water-entering condition of the marine flat-bottom structure is simulated really, the calculation model of the water-entering impact process is subjected to stress analysis, the water-entering impact force with the largest stress is obtained, the water-entering impact force is used as the peak value of the water-entering impact force of the marine flat-bottom structure, and the accuracy of the calculated water-entering impact force is higher.
In one embodiment, the geometric parameter includes an entry velocity, and the step of configuring the geometric parameter in the computational model further includes:
when the water entering speed of the ocean flat-bottom structure is determined not to be obtained, carrying out grid division on the surface of the calculation model according to the number of preset grids, and setting a calculation domain, grid density and an initial water entering point of the calculation model according to the divided grids; the calculation domain is a water inlet region of the calculation model;
and determining the water inlet speed of the ocean flat-bottom structure according to the calculation domain, the grid density and the initial water inlet point of the calculation model.
In this embodiment, the water entry speed of the ocean flat bottom structure is related to parameters such as structure quality, initial water entry point, and sea surface contact area, so the present application can also obtain the water entry speed by using a computational model simulation according to the parameters. Specifically, the bottom surface of the calculation model can be divided into a plurality of grids, a calculation domain, grid density and an initial water entry point of the calculation model are set according to the divided grids, the water entry speed of the ocean flat-bottom structure is determined according to the calculation domain, grid density and initial water entry point of the calculation model, a proper solver is used for solving geometric parameters containing the water entry speed to obtain a peak value of the water entry slamming force of the ocean flat-bottom structure, and finally the peak value of the water entry slamming force under different geometric parameters is solved to serve as a training set and a testing set. The computational domain is a water inlet area of the computational model, the initial water inlet point is the position where the computational model is firstly contacted with the sea surface, and the grid density is determined according to the bottom area of the computational model and the grid number.
The embodiment calculates the water entering speed of the ocean flat-bottom structure through the calculation model, and the water entering speed of the ocean flat-bottom structure does not need to be measured on site through a sensor, so that manpower and material resources are saved, and the operation efficiency is improved.
In one embodiment, the step of mining an optimal function formula of the underwater impulsive force of the marine flat-bottomed structure by using a genetic algorithm according to the training set and the test set may specifically include:
randomly generating a plurality of first function formulas containing variables or constants, the plurality of first function formulas being used for predicting the peak value of the water-entering slamming force of the target marine flat-bottomed structure;
respectively importing the geometric parameters of the training set into the plurality of first function formulas to be calculated to obtain first calculation results, calculating the fitness of the plurality of first function formulas according to the first calculation results and the water-entering slamming force peak values corresponding to the geometric parameters in the training set, and taking the first function formula with the fitness larger than a preset value as a second function formula;
randomly selecting variables or constants in the second function formula for variation according to a preset variation probability and a preset variation mode to obtain a third function formula; wherein the variation mode comprises subtree variation, host variation and point variation;
and respectively importing the geometric parameters of the test set into the third function formula for calculation to obtain a second calculation result, screening out the second calculation result closest to the water-entering slamming peak value corresponding to the geometric parameters of the test set, and taking the third function formula corresponding to the water-entering slamming peak value closest to the second calculation result as an optimal function formula.
As described above, in the initial stage, a certain number of first function formulas are randomly generated, that is, first generation individuals are used for predicting the peak value of the underwater impulsive force of the target marine flat-bottomed structure, each first function formula includes at least four variables and constants, the geometric parameters of the training set obtained in advance are respectively introduced into a plurality of first function formulas for calculation to obtain a first calculation result, the first calculation result is a first peak value of the underwater impulsive force, the first peak value is compared with the peak value of the underwater impulsive force corresponding to the geometric parameters in the training set, and fitness calculation is performed on the plurality of first function formulas to evaluate all the first function formulas, and the obtained fitness value is an expression for measuring the degree of superiority and inferiority of the current first function formula. And if the first peak value is closer to the water-entering slamming force peak value corresponding to the geometric parameter in the training set, the higher the fitness is, and the corresponding first function formula is closer to the optimal function formula. Wherein, the fitness can select mean absolute error, mean squared error or root mean squared error.
Further, according to the fitness obtained by calculation, a first function formula with the fitness greater than a preset value is screened out, and the first function formula with the fitness greater than the preset value is used as a second function formula; and randomly selecting the variable or constant in the second function formula according to a preset variation probability and a preset variation mode to perform multiple variations, and finally obtaining a third function formula. The variation mode is that one or more variables and constants in the second function formula can be randomly selected for conversion, for example, the parameter of the water inlet speed in the second function formula is converted to obtain a third function formula; or converting constants in the second function formula to obtain a third function formula. In addition, each time of variation, if the water inlet speed in the second function formula is changed in the last variation, and the second function formula is changed this time, other parameters except the water inlet speed are changed to obtain a third function formula, namely, the variation probability of the untransformed variables or constants in the second function formula is higher, so as to obtain the function formula which cannot be constructed by the human brain.
And finally, respectively introducing the geometric parameters of the test set obtained in advance into a third function formula after multiple times of variation to calculate to obtain a second calculation result, wherein the second settlement result is a second peak value of the water-entering thumping force, comparing the second peak value with the water-entering thumping force peak value corresponding to the geometric parameters in the test set, calculating the fitness of the third function formulas to evaluate the superiority and inferiority of the varied third function formula, screening out a second calculation result which is closest to the water-entering thumping force peak value corresponding to the geometric parameters in the test set, and taking the third function formula which is closest to the water-entering thumping force peak value of the second calculation result as an optimal function formula. Therefore, with the increase of the iteration times, the first function formula is continuously reproduced, selected, mutated and evolved so as to continuously approach the rule of data distribution, a hidden optimal function formula is excavated, a function formula which is difficult to construct through the human brain is excavated, a universal mathematical calculation formula is provided, a large amount of numerical calculation is avoided, and the precision of the engineering prediction of the water inlet slamming pressure peak value of the marine structure is effectively improved.
In one embodiment, after the performing the fitness calculation on the plurality of first function formulas according to the first calculation result and the peak value of the water-entering slamming force corresponding to the geometric parameter in the training set, the method may further include:
and eliminating the first function formula with the fitness smaller than a preset value.
In this embodiment, when the second function formula is selected according to the fitness, the probability that the first function formula with high fitness is selected as the second function formula is high, and the first function formula with low fitness is eliminated.
In an embodiment, after the screening out the second function formula with the fitness greater than the preset value from the plurality of first function formulas, the method may further include:
and randomly exchanging variables or constants for every two second function formulas, and executing the step of randomly selecting the variables or constants in the second function formulas to be mutated according to a preset mutation probability and a preset mutation mode by using the exchanged second function formulas.
In this embodiment, chromosome crossing in genetics is simulated, and a variable or constant of a second function formula with high fitness is selected to replace a variable or constant of a second function formula with lower fitness, where the selected second function formula with high fitness is usually the highest fitness among the remaining second function formulas. In addition, two second function formulas can be selected at will, random exchange of variables or constants is carried out between every two second function formulas, the exchanged second function formulas are used for randomly selecting the variables or constants in the second function formulas to carry out mutation according to preset mutation probability and a preset mutation mode, so that new function formulas are continuously generated on the basis of the first function formulas, fitness calculation is carried out on the newly generated function formulas, and the hidden optimal function formulas are mined out.
In one embodiment, after randomly generating a plurality of first function formulas containing variables or constants, the method further comprises;
and representing the first function formula by using a binary tree, wherein all leaf nodes in the binary tree are variables or constants of the first function formula, and all internal nodes in the binary tree are functions of the first function formula.
In computer science, a binary tree is a tree structure with at most two subtrees per node. The subtrees are typically referred to as a "left subtree" and a "right subtree," which are also binary trees. Subtrees of the binary tree have left and right scores and the order cannot be arbitrarily reversed for sorting and improving the efficiency of retrieval. In this embodiment, the first function formula is represented by a binary tree, leaf nodes of all binary trees are variables or constants of the first function formula, and all internal nodes in the binary tree are functions of the first function formula, so as to simplify the first function formula, facilitate continuous reproduction, selection, variation and evolution of the first function formula, and improve processing efficiency.
Referring to fig. 2, the present application further provides a peak value prediction apparatus for an underwater crash force of a marine flat-bottomed structure, including:
the acquisition module 1 is used for acquiring target geometric parameters of a target ocean flat-bottom structure;
the prediction module 2 is used for leading the target geometric parameters into a preset optimal function formula and predicting the peak value of the water-entering slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the system also comprises an optimal function formula acquisition module 3, which is used for acquiring the geometric parameters of a plurality of groups of different ocean flat-bottom structures, determining the water inlet slamming force peak values of the different ocean flat-bottom structures under the corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are formed by the plurality of groups of geometric parameters and the corresponding water inlet slamming force peak values, and excavating the optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
As described above, it can be understood that the components of the device for predicting the peak value of the water-entering impact force of a marine flat-bottomed structure proposed in the present application may implement the functions of any one of the methods for predicting the peak value of the water-entering impact force of a marine flat-bottomed structure described above, and the detailed structure is not described again.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for data such as a relational extraction model, a drug discovery model and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method for peak prediction of the diving pop force of a marine flat bottom structure.
The processor executing the method for predicting the peak value of the diving pop force of the marine flat-bottomed structure comprises the following steps:
acquiring target geometric parameters of a target ocean flat-bottom structure;
leading the target geometric parameters into a preset optimal function formula, and predicting the peak value of the water entrance slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the preset method for acquiring the optimal function formula comprises the following steps:
acquiring geometric parameters of a plurality of groups of different ocean flat-bottom structures;
determining the water inlet slamming force peak values of different ocean flat-bottom structures under corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of a plurality of groups of geometric parameters and corresponding water inlet slamming force peak values, and excavating an optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
An embodiment of the present application further provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for peak prediction of the diving pop force of a marine flat bottom structure, comprising the steps of:
acquiring target geometric parameters of a target ocean flat-bottom structure;
leading the target geometric parameters into a preset optimal function formula, and predicting the peak value of the water entrance slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the preset method for acquiring the optimal function formula comprises the following steps:
acquiring geometric parameters of a plurality of groups of different ocean flat-bottom structures;
determining the water inlet slamming force peak values of different ocean flat-bottom structures under corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of a plurality of groups of geometric parameters and corresponding water inlet slamming force peak values, and excavating an optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
To sum up, the most beneficial effect of this application lies in:
according to the method, the device and the computer equipment for predicting the peak value of the underwater impulsive force of the marine flat-bottom structure, the target geometric parameters of the target marine flat-bottom structure are obtained and are led into the preset optimal function formula, the peak value of the underwater impulsive force of the target marine flat-bottom structure is predicted by directly utilizing the optimal function formula, a large amount of data operation is avoided, the efficiency of predicting the peak value of the underwater impulsive force of the marine flat-bottom structure in engineering is effectively improved, the calculated optimal function formula can also provide reference values for the design of the marine flat-bottom structure and the marine hoisting scheme, and the method, the device and the computer equipment have wide engineering application prospects in marine engineering hoisting operation. In addition, when the preset optimal function formula is obtained, the geometric parameters of a plurality of groups of different ocean flat bottom structures are obtained, the water inlet impact force peak values of the different ocean flat bottom structures under the corresponding geometric parameters are determined by a numerical method, a training set and a testing set which are composed of the geometric parameters and the corresponding water inlet impact force peak values are generated, the optimal function formula of the water inlet impact force of the ocean flat bottom structures is excavated by a genetic algorithm according to the training set and the testing set, so that the genetic algorithm is further combined, the optimal function formula which is difficult to construct through the human brain is excavated, and the optimal function formula is used for calculating the water inlet impact force peak value of the ocean flat bottom structures so as to take prediction precision into consideration.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A method for predicting the peak value of the diving pop of a marine flat-bottomed structure, comprising:
acquiring target geometric parameters of a target ocean flat-bottom structure;
leading the target geometric parameters into a preset optimal function formula, and predicting the peak value of the water entrance slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the preset method for acquiring the optimal function formula comprises the following steps:
acquiring geometric parameters of a plurality of groups of different ocean flat-bottom structures;
determining the water-entering slamming force peak values of different ocean flat-bottom structures under corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of a plurality of groups of geometric parameters and the corresponding water-entering slamming force peak values, and excavating an optimal function formula of the water-entering slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
2. The method of claim 1, wherein the step of numerically determining the water intrusion pop peaks for different marine flat bottom structures at corresponding geometric parameters comprises:
establishing a calculation model of the ocean flat-bottom structure by using three-dimensional modeling software, and configuring the geometric parameters in the calculation model; wherein the computational model is used to simulate an ocean flat bottom structure;
simulating an underwater slamming process of the marine flat-bottom structure under the geometric parameters by using the calculation model, carrying out stress analysis on the calculation model of the underwater slamming process, and determining a peak value of the underwater slamming force of the marine flat-bottom structure according to a stress analysis result;
and adjusting the values of the geometric parameters, reconfiguring the calculation model for the adjusted geometric parameters, and simulating the water-entering slamming process of the marine flat-bottom structure again to obtain the peak values of the water-entering slamming force under different values.
3. The method of claim 2, wherein the geometric parameter comprises an entry velocity, and wherein the step of configuring the geometric parameter in the computational model further comprises, prior to:
when the water entering speed of the ocean flat-bottom structure is determined not to be obtained, carrying out grid division on the surface of the calculation model according to the number of preset grids, and setting a calculation domain, grid density and an initial water entering point of the calculation model according to the divided grids; the calculation domain is a water inlet region of the calculation model;
and determining the water inlet speed of the ocean flat-bottom structure according to the calculation domain, the grid density and the initial water inlet point of the calculation model.
4. The method of claim 1, wherein said step of using a genetic algorithm to develop an optimal functional formula for the water-ingress slamming force of marine flat-bottomed structures based on said training and test sets comprises:
randomly generating a plurality of first function formulas containing variables or constants, the plurality of first function formulas being used for predicting the peak value of the water-entering slamming force of the target marine flat-bottomed structure;
respectively importing the geometric parameters of the training set into the plurality of first function formulas to be calculated to obtain first calculation results, calculating the fitness of the plurality of first function formulas according to the first calculation results and the water-entering slamming force peak values corresponding to the geometric parameters in the training set, and taking the first function formula with the fitness larger than a preset value as a second function formula;
randomly selecting variables or constants in the second function formula for variation according to a preset variation probability and a preset variation mode to obtain a third function formula;
and respectively importing the geometric parameters of the test set into the third function formula for calculation to obtain a second calculation result, screening out the second calculation result closest to the water-entering slamming peak value corresponding to the geometric parameters of the test set, and taking the third function formula corresponding to the water-entering slamming peak value closest to the second calculation result as an optimal function formula.
5. The method of claim 4, wherein after the fitness calculating the plurality of first functional formulas based on the first calculation and the corresponding water-entry pop peak values for the geometric parameters in the training set, further comprising:
and eliminating the first function formula with the fitness smaller than a preset value.
6. The method of claim 4, wherein after the step of screening out a second function formula with a fitness greater than a predetermined value from the plurality of first function formulas, further comprising:
and randomly exchanging variables or constants between every two second function formulas, and executing the step of randomly selecting the variables or constants in the second function formulas to be mutated according to a preset mutation probability and a preset mutation mode by using the exchanged second function formulas.
7. The method of claim 4, wherein after randomly generating a plurality of first functional formulas containing variables or constants, further comprising;
and representing the first function formula by using a binary tree, wherein all leaf nodes in the binary tree are variables or constants of the first function formula, and all internal nodes in the binary tree are functions of the first function formula.
8. An apparatus for predicting the peak value of the diving pop of a marine flat-bottomed structure, comprising:
the acquisition module is used for acquiring target geometric parameters of the target ocean flat-bottom structure;
the prediction module is used for leading the target geometric parameters into a preset optimal function formula and predicting the peak value of the water-entering slamming force of the target ocean flat-bottom structure by using the optimal function formula;
the system also comprises an optimal function formula acquisition module which is used for acquiring the geometric parameters of a plurality of groups of different ocean flat-bottom structures, determining the water inlet slamming force peak values of the different ocean flat-bottom structures under the corresponding geometric parameters by using a numerical method, generating a training set and a testing set which are composed of the geometric parameters and the corresponding water inlet slamming force peak values, and excavating the optimal function formula of the water inlet slamming force of the ocean flat-bottom structures by using a genetic algorithm according to the training set and the testing set.
9. A computer device comprising a memory and a processor, said memory storing a computer program, wherein said processor when executing said computer program performs the steps of a method for peak prediction of the diving pop force of a marine flat-bottomed structure according to any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method for peak prediction of the water break-in force of a marine flat-bottomed structure according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011344721.6A CN112465013B (en) | 2020-11-25 | 2020-11-25 | Peak value prediction method, device and equipment for water slamming force of ocean flat-bottom structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011344721.6A CN112465013B (en) | 2020-11-25 | 2020-11-25 | Peak value prediction method, device and equipment for water slamming force of ocean flat-bottom structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112465013A true CN112465013A (en) | 2021-03-09 |
| CN112465013B CN112465013B (en) | 2024-02-02 |
Family
ID=74808431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011344721.6A Active CN112465013B (en) | 2020-11-25 | 2020-11-25 | Peak value prediction method, device and equipment for water slamming force of ocean flat-bottom structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465013B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077544A1 (en) * | 2006-09-27 | 2008-03-27 | Infosys Technologies Ltd. | Automated predictive data mining model selection |
| CN107392399A (en) * | 2017-08-30 | 2017-11-24 | 桂林电子科技大学 | A kind of SVM Sensory Quality of Cigarette Forecasting Methodologies based on improved adaptive GA-IAGA |
| CN111753467A (en) * | 2020-06-23 | 2020-10-09 | 中山大学 | Mineral product result prediction method and device, computer equipment and storage medium |
| CN111767518A (en) * | 2020-06-05 | 2020-10-13 | 国家核安保技术中心 | Method, device and equipment for determining parameter value of AWCC (active-vector configuration center) and computer storage medium |
-
2020
- 2020-11-25 CN CN202011344721.6A patent/CN112465013B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077544A1 (en) * | 2006-09-27 | 2008-03-27 | Infosys Technologies Ltd. | Automated predictive data mining model selection |
| CN107392399A (en) * | 2017-08-30 | 2017-11-24 | 桂林电子科技大学 | A kind of SVM Sensory Quality of Cigarette Forecasting Methodologies based on improved adaptive GA-IAGA |
| CN111767518A (en) * | 2020-06-05 | 2020-10-13 | 国家核安保技术中心 | Method, device and equipment for determining parameter value of AWCC (active-vector configuration center) and computer storage medium |
| CN111753467A (en) * | 2020-06-23 | 2020-10-09 | 中山大学 | Mineral product result prediction method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112465013B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Muduli et al. | CPT-based seismic liquefaction potential evaluation using multi-gene genetic programming approach | |
| Rezania et al. | An evolutionary‐based data mining technique for assessment of civil engineering systems | |
| CN113052371A (en) | Residual oil distribution prediction method and device based on deep convolutional neural network | |
| Zhou et al. | Parameters inversion of high central core rockfill dams based on a novel genetic algorithm | |
| Behnia et al. | Predicting crest settlement in concrete face rockfill dams using adaptive neuro-fuzzy inference system and gene expression programming intelligent methods | |
| CN111523713A (en) | Method and device for predicting residual oil saturation distribution in oil field | |
| CN111859733B (en) | Method for optimizing reliability of automobile exhaust system based on ant colony algorithm | |
| CN115659749B (en) | Foundation pit deformation prediction method and system, electronic equipment and storage medium | |
| Sadrossadat et al. | A new design equation for prediction of ultimate bearing capacity of shallow foundation on granular soils | |
| Gandomi et al. | Hybridizing genetic programming with orthogonal least squares for modeling of soil liquefaction | |
| Alavi et al. | High-precision modeling of uplift capacity of suction caissons using a hybrid computational method | |
| CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
| CN116641688A (en) | Method, system, equipment and storage medium for improving gas reservoir recovery ratio by CO2 and sealing storage thereof | |
| CN115982141A (en) | Characteristic optimization method for time series data prediction | |
| Provenzano et al. | Interpretation of a model footing response through an adaptive neural fuzzy inference system | |
| CN112465013A (en) | Method, device and equipment for predicting peak value of underwater slamming force of ocean flat-bottom structure | |
| CN107480724A (en) | A kind of determination method of cluster centre, determine system and a kind of clustering method | |
| CN116629111A (en) | Shale heat injection in-situ exploitation hydrocarbon discharge potential prediction method based on neural network | |
| CN111582634A (en) | Multi-factor safety grading method and system for underground large-space construction | |
| Yin et al. | Deep learning-based design model for suction caissons on clay | |
| KR102408827B1 (en) | Preparation method of forest water map using computer program and the system | |
| Pourzangbar | Determination of the most effective parameters on scour depth at seawalls using genetic programming (GP) | |
| CN111428420B (en) | Method and device for predicting sea surface flow velocity, computer equipment and storage medium | |
| CN114764546A (en) | Method for predicting residual oil of fault block oil reservoir based on generation of antagonistic neural network | |
| Song et al. | Parameter Determination Method of Soil Constitutive Model Based on Machine Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |