CN114091304B - Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source - Google Patents
Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source Download PDFInfo
- Publication number
- CN114091304B CN114091304B CN202111367704.9A CN202111367704A CN114091304B CN 114091304 B CN114091304 B CN 114091304B CN 202111367704 A CN202111367704 A CN 202111367704A CN 114091304 B CN114091304 B CN 114091304B
- Authority
- CN
- China
- Prior art keywords
- processing
- heat source
- deformation
- plate
- wolf
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 152
- 238000000034 method Methods 0.000 title claims abstract description 41
- 241000282461 Canis lupus Species 0.000 claims abstract description 49
- 238000010438 heat treatment Methods 0.000 claims abstract description 24
- 238000004088 simulation Methods 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000005265 energy consumption Methods 0.000 claims abstract description 20
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 12
- 239000010959 steel Substances 0.000 claims abstract description 12
- 238000012706 support-vector machine Methods 0.000 claims abstract description 10
- 241000282421 Canidae Species 0.000 claims description 21
- 238000005457 optimization Methods 0.000 claims description 18
- 239000002245 particle Substances 0.000 claims description 16
- 230000004907 flux Effects 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 8
- 238000003912 environmental pollution Methods 0.000 claims description 8
- 230000006978 adaptation Effects 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000007493 shaping process Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000003754 machining Methods 0.000 description 5
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003856 thermoforming Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000010800 human waste Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Fluid Mechanics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent decision method for processing a ship hull plate by using an oxyhydrogen gas heat source, which comprises the steps of determining the relation between processing parameters and deformation of oxyhydrogen gas heating; establishing a heat source model of an oxyhydrogen heat source processing ship plate to obtain finite element simulation data; optimizing the deformation prediction of the support vector machine by improving the gray wolf algorithm to obtain a prediction result, interpolating and complementing the finite element simulation data to obtain a complete corresponding relation between the deformation and the processing parameters, and constructing a oxyhydrogen flame processing ship plate database; a drawing of a target board is subjected to a board unfolding method, a processing path and deformation of a corresponding path are obtained, and a processing parameter set is obtained through a corresponding relation with a database; an optimal green processing scheme is obtained. According to the method, high-precision prediction can be realized on the deformation of the steel plate, the ship plate processing scheme is determined by matching the plate unfolding mode with the database, and then the optimal processing scheme with time and energy consumption as optimal targets is obtained, so that the ship plate processing with low cost, high efficiency and high precision is realized.
Description
Technical Field
The invention relates to an intelligent decision method for processing a ship hull plate by using an oxyhydrogen gas heat source.
Background
The hull planking is as the important component part of hull, and the processingquality and the machining efficiency of hull planking can produce great influence to the production cycle and the quality of boats and ships. The numerical control technology is used in the processing of the hull plate, so that the processing efficiency and quality can be improved. In numerical control processing of the hull plate, an optimal scheme for processing the hull plate should be determined first, so how to determine the optimal scheme for processing the hull plate is a problem to be solved before processing the hull plate curved surface.
In the traditional hull plate processing, when the hull plate is subjected to curved surface processing, the processing mode is usually formulated by depending on experience of an operator, and in the mode, the processing precision is difficult to ensure, and the degree of automation is not high, so that the artificial waste is caused.
In addition, the ship body outer plate is thickened at the position with larger stress due to different stress of each position, so that the thickness of the ship body outer plate is different, and the same processing mode is used for steel plates with different thicknesses in the existing processing mode, so that energy waste is caused.
The above-mentioned problems are considered and solved in the process of processing the hull external plate by the oxyhydrogen gas heat source.
Disclosure of Invention
The invention aims to provide an intelligent decision method for processing a ship hull outer plate by using an oxyhydrogen gas heat source, which solves the problems of low processing precision and low automation degree resulting in human waste in the prior art.
The technical scheme of the invention is as follows:
an intelligent decision making method for processing a ship hull plate by using an oxyhydrogen gas heat source comprises the following steps,
S1, determining a processing parameter and a deformation relation of oxyhydrogen gas heating by using oxyhydrogen mixed gas as a heat source for processing a ship body outer plate;
S2, a heat source model of an oxyhydrogen heat source processing ship plate is established according to the ship plate processing condition, the heat source model is a combined heat source model formed by coupling a Gaussian surface heat source and a cylindrical heat source, a corresponding temperature field and a deformation field are obtained through finite element simulation to verify and adjust, and finite element simulation data are obtained;
S3, optimizing the deformation prediction of the support vector machine by improving the gray wolf algorithm, obtaining a prediction result, interpolating and complementing the finite element simulation data, obtaining a complete corresponding relation between the deformation and the processing parameters, and constructing an oxyhydrogen flame processing ship plate database;
S4, a board unfolding method is adopted for the drawing of the target board, the processing path and the deformation of the corresponding path are obtained, the deformation is input into a database, and a processing parameter set is obtained through the corresponding relation with the database;
s5, optimizing and selecting a processing parameter set by considering the energy consumption and the environmental pollution problem to obtain an optimal green processing scheme;
S6, determining the plate thickness of the target plate, adopting different setting processing modes for the target plates with different thicknesses, and inputting the processing scheme and the processing mode into the mechanical arm to finish the processing of the target plate.
Further, in step S1, the processing parameters including gas flow, moving speed, heating radius are determined, the ship plate is processed through experiments, and the processed deformation amount including angular deformation and linear deformation is collected.
Further, in step S2, in the heat source model, the heat flux density distribution function formula of the Gaussian surface heat source model is as follows,
The heat flux density distribution function formula of the cylindrical heat source is as follows,
Wherein η 1,η2 is the heating efficiency of the Gaussian heat source and the cylindrical heat source respectively; mu 1,μ2 is the distribution coefficient of the heating source, and mu 1+μ2＝1;QH2 is the flow rate of oxyhydrogen gas; v is the flow rate and τ is the gas flow rate per unit time; b, R 2 is the effective action depth, the effective action half width and the effective action half length of the cylindrical heat source respectively; r is the heat source radius of the Gaussian surface heat source; q is the maximum heat flux density.
Further, in step S2, a corresponding temperature field and a deformation field are obtained through finite element simulation, specifically, the deformation field is constructed by analyzing the acquired deformation, and the temperature field is constructed by finite element simulation on the heat source, the thickness of the plate, the poisson coefficient, the thermal expansion coefficient, the flow of the oxyhydrogen gas heat source and the heating efficiency in the actual processing process by utilizing ANSYS.
Further, in step S3, the deformation prediction of the support vector machine is optimized by improving the wolf algorithm, so as to obtain a prediction result, specifically,
S31, taking the finite element simulation data obtained in the step S2 as a sample, dividing the finite element simulation data into a training set and a testing set, carrying out normalization processing, and constructing an SVM model as follows:
f(x)＝wT·gΦ(x)+c (3)
wherein f (x) is the deformation output by the SVM model, phi (x) is a nonlinear mapping function, and is used for mapping the input sample vector x into a high-dimensional feature space to perform linear approximation; b is bias, w is defined as weight vector; c is a penalty coefficient, i.e., the tolerance to errors; g is a parameter of the function;
s32, initializing wolves, and parameters a, A and C, setting the number N of the wolves and the maximum iteration number Tmax, wherein the mathematical formula of the gray wolf algorithm is as follows,
D＝||C1·Xp(t)-X(t)|| (4)
X(t+1)＝XP(t)-AD (5)
A＝2a·r1-a (6)
C＝2·r2 (7)
Wherein D represents a position distance vector between the wolf and the prey; t represents the current iteration time; A. c is a vector coefficient; x P is the position vector of the prey; x is the position vector of the gray wolves; a is a step factor, and the step factor is reduced from 2 to 0 along with the increase of the iteration times; r 1,r2 takes a uniform random value between [0,1 ];
S33, enabling the iteration times t=0, calculating the adaptation degree of the wolf group, and marking three wolves with the best adaptation degree as alpha wolves, beta wolves and delta wolves;
s34, according to the improved gray wolf position updating mode, the omega wolf position is updated according to the alpha wolf, beta wolf and delta wolf positions, the gray wolf position updating mode expression is as follows,
S35, updating parameters a, A and C, calculating the fitness of the wolf group, updating alpha wolf, beta wolf and delta wolf, and optimizing parameters C and g in the SVM model;
S36, when the iteration times t is smaller than the maximum iteration times Tmax, the iteration times t=t+1, and the step S34 is returned; otherwise, outputting optimal parameters c and g, and taking the optimal parameters c and g into an svm prediction model, wherein the processing parameters are taken as input, and the deformation is taken as output, so as to obtain a prediction result.
Further, in step S5, the optimal green processing scheme is obtained by optimizing and selecting the processing parameters by considering the problems of energy consumption and environmental pollution, specifically, the environmental pollution and the energy consumption are considered, including noise accumulation and energy consumption in the processing process, so as to reduce the shaping production time of the hull outer plate curved surface and reduce the production energy consumption as optimization targets, the non-dominant sorting genetic algorithm NSGA-II with the elite strategy is optimized for the processing parameter set obtained in step S4 by adopting the particle swarm PSO, and an optimization target function is selected to obtain a Pareto optimal solution set as the optimal green processing scheme.
Further, in step S5, a non-dominant ranking genetic algorithm of particle swarm PSO optimization with elite strategy is adopted for the processing parameter set obtained in step S4, and an optimization objective function is selected to obtain a Pareto optimal solution set, specifically,
S51, initializing populations Pj and j=0, and setting a maximum iteration number J;
S52, optimizing a particle swarm, updating the particle speed and the position, and calculating the fitness;
S53, pj non-dominant sorting to generate a child population Qj;
S54, merging parent-child generations into Rj;
S55, quick non-dominant sorting and crowding degree calculation are carried out, N optimal individuals are selected, and a new parent population Pj+1 is generated; when j does not reach the maximum iteration number, j=j+1, returning to step S52; and when j reaches the maximum iteration number, ending, and obtaining a Pareto optimal solution set as an optimal green processing scheme.
Further, in step S6, different set processing methods are adopted for the target plates with different thicknesses, specifically, a linear heating method is adopted for the steel plates with the target plate thickness below 10mm, and a spiral heating method is adopted for the steel plates with the target plate thickness greater than 10 mm.
The beneficial effects of the invention are as follows:
1. the intelligent decision method for processing the ship hull plate by the oxyhydrogen gas heat source can realize high-precision prediction on the deformation of the steel plate, and decides a ship plate processing scheme by matching a plate unfolding mode with a database, so as to obtain an optimal processing scheme taking time and energy consumption as optimal targets, thereby realizing low-cost high-efficiency high-precision ship plate processing.
2. The intelligent decision method for processing the ship hull plate by the oxyhydrogen gas heat source optimizes the support vector machine to predict the deformation by improving the gray wolf algorithm, has the error obviously smaller than that of a single prediction model, has high prediction precision, and is suitable for predicting the deformation of the steel plate.
3. According to the intelligent decision-making method for processing the ship hull plate by the oxyhydrogen gas heat source, a ship plate processing scheme is decided by matching a plate unfolding mode with a database, and one group of deformation amount in the database corresponds to a plurality of groups of processing schemes; aiming at the problem, a green database with time and energy consumption as optimal targets is constructed, and a PSO (particle swarm optimization) NSGA-II algorithm is adopted to screen an optimal processing scheme, so that a final green intelligent decision is completed.
4. The intelligent decision method for processing the hull planking by using the oxyhydrogen gas heat source utilizes the ship plank curved surface thermoforming mechanism to construct a finite element model in the ship plank thermal processing process, and oxyhydrogen flame is selected as a combustion heat source.
Drawings
FIG. 1 is a flow chart of an intelligent decision making method for processing a ship hull plate by using an oxyhydrogen gas heat source according to an embodiment of the invention.
Fig. 2 is an explanatory diagram of three-dimensional point cloud data of a Tribon software derivation drawing in an embodiment.
FIG. 3 is an explanatory diagram of a combined heat source model in the embodiment.
FIG. 4 is a flow chart of improved gray wolf algorithm optimized support vector machine deformation prediction in an embodiment.
FIG. 5 is a schematic flow chart of the PSO optimized NSGA-II algorithm in an embodiment.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Examples
An intelligent decision method for processing a ship hull plate by using an oxyhydrogen gas heat source, as shown in figure 1, comprises the following steps,
S1, determining a processing parameter and a deformation relation of oxyhydrogen gas heating by using oxyhydrogen mixed gas as a heat source for processing a ship body outer plate; the processing parameters comprise gas flow, moving speed and heating radius, the ship plate is processed through experiments, and the processed deformation quantity comprising angular deformation and linear deformation is collected.
S2, a heat source model of the oxyhydrogen heat source processing ship plate is established according to the ship plate processing condition, the heat source model is a combined heat source model formed by coupling a Gaussian surface heat source and a cylindrical heat source, a corresponding temperature field and a deformation field are obtained through finite element simulation to verify and adjust, and finite element simulation data are obtained.
As shown in fig. 2, in the heat source model, the heat flux density distribution function formula of the gaussian surface heat source model is as follows,
The heat flux density distribution function formula of the cylindrical heat source is as follows,
Wherein η 1,η2 is the heating efficiency of the Gaussian heat source and the cylindrical heat source respectively; mu 1,μ2 is a distribution coefficient of the heating heat source, and mu 1+μ2 =1; Is the flow rate of oxyhydrogen gas; v is the flow rate and τ is the gas flow rate per unit time; b, R 2 is the effective action depth, the effective action half width and the effective action half length of the cylindrical heat source respectively; r is the heat source radius of the Gaussian surface heat source; q is the maximum heat flux density.
In step S2, a corresponding temperature field and a deformation field are obtained through finite element simulation, specifically, the deformation amount after collection is analyzed to construct the deformation field, and the temperature field is constructed through finite element simulation on the heat source, the thickness of the plate, the poisson coefficient, the thermal expansion coefficient, the flow of the oxyhydrogen gas heat source and the heating efficiency in the actual processing process by utilizing ANSYS.
S3, optimizing the deformation prediction of the support vector machine by improving the gray wolf algorithm, obtaining a prediction result, interpolating and complementing the finite element simulation data, obtaining a complete corresponding relation between the deformation and the processing parameters, and constructing an oxyhydrogen flame processing ship plate database; as shown in fig. 4, in particular,
S31, taking the finite element simulation data obtained in the step S2 as a sample, dividing the finite element simulation data into a training set and a testing set, carrying out normalization processing, and constructing an SVM model as follows:
f(x)＝wT·gΦ(x)+c (3)
wherein f (x) is the deformation output by the SVM model, phi (x) is a nonlinear mapping function, and is used for mapping the input sample vector x into a high-dimensional feature space to perform linear approximation; b is bias, w is defined as weight vector; c is a penalty coefficient, i.e., the tolerance to errors; g is a parameter of the function;
s32, initializing wolves, and parameters a, A and C, setting the number N of the wolves and the maximum iteration number Tmax, wherein the mathematical formula of the gray wolf algorithm is as follows,
D＝||C1·Xp(t)-X(t)|| (4)
X(t+1)＝XP(t)-AD (5)
A＝2a·r1-a (6)
C＝2·r2 (7)
Wherein D represents a position distance vector between the wolf and the prey; t represents the current iteration time; A. c is a vector coefficient; x P is the position vector of the prey; x is the position vector of the gray wolves; a is a step factor, and the step factor is reduced from 2 to 0 along with the increase of the iteration times; r 1,r2 takes a uniform random value between [0,1 ];
S33, enabling the iteration times t=0, calculating the adaptation degree of the wolf group, and marking three wolves with the best adaptation degree as alpha wolves, beta wolves and delta wolves;
s34, according to the improved gray wolf position updating mode, the omega wolf position is updated according to the alpha wolf, beta wolf and delta wolf positions, the gray wolf position updating mode expression is as follows,
S35, updating parameters a, A and C, calculating the fitness of the wolf group, updating alpha wolf, beta wolf and delta wolf, and optimizing parameters C and g in the SVM model;
S36, when the iteration times t is smaller than the maximum iteration times Tmax, the iteration times t=t+1, and the step S34 is returned; otherwise, outputting optimal parameters c and g, and taking the optimal parameters c and g into an svm prediction model, wherein the processing parameters are taken as input, and the deformation is taken as output, so as to obtain a prediction result.
S4, a board unfolding method is adopted for the drawing of the target board, the processing path and the deformation of the corresponding path are obtained, the deformation is input into a database, and a processing parameter set is obtained through the corresponding relation with the database;
And S5, optimizing and selecting the processing parameter set by considering the problems of energy consumption and environmental pollution, so as to obtain an optimal green processing scheme. In step S5, the optimal green processing scheme is obtained by optimizing and selecting the processing parameters by considering the problems of energy consumption and environmental pollution, specifically, the environmental pollution and the energy consumption are considered, including noise accumulation and energy consumption in the processing process, so as to reduce the shaping production time of the hull outer plate curved surface and reduce the production energy consumption as optimization targets, the non-dominant ranking genetic algorithm NSGA-II with the elite strategy is optimized for the processing parameter set obtained in step S4 by adopting the particle swarm PSO, and an optimization target function is selected to obtain the Pareto optimal solution set as the optimal green processing scheme.
As shown in fig. 5, a non-dominant ranking genetic algorithm of particle swarm PSO optimization with elite policy is adopted for the processing parameter set obtained in step S4, and an optimization objective function is selected to obtain a Pareto optimal solution set, specifically,
S51, initializing populations Pj and j=0, and setting a maximum iteration number J;
S52, optimizing a particle swarm, updating the particle speed and the position, and calculating the fitness;
S53, pj non-dominant sorting to generate a child population Qj;
S54, merging parent-child generations into Rj;
S55, quick non-dominant sorting and crowding degree calculation are carried out, N optimal individuals are selected, and a new parent population Pj+1 is generated; when j does not reach the maximum iteration number, j=j+1, returning to step S52; and when j reaches the maximum iteration number, ending, and obtaining a Pareto optimal solution set as an optimal green processing scheme.
S6, determining the plate thickness of the target plate, adopting different setting processing modes for the target plates with different thicknesses, and inputting the processing scheme and the processing mode into the mechanical arm to finish the processing of the target plate.
In step S6, different set processing modes are adopted for target plates with different thicknesses, specifically, a linear heating mode is adopted for steel plates with the target plate thickness below 10mm, and a spiral heating mode is adopted for steel plates with the target plate thickness greater than 10 mm.
Embodiment a specific example of an intelligent decision method for processing a ship hull plate by using an oxyhydrogen gas heat source is as follows:
1) And (3) carrying out experiments on oxyhydrogen flame processing ship plates, and collecting processing parameters and deformation data.
2) And building a heat source model of the oxyhydrogen heat source processing ship plate according to the processing condition of the ship plate, wherein the heat source model is a combined heat source model formed by coupling a Gaussian surface heat source and a cylindrical heat source, constructing a finite element model of the oxyhydrogen flame processing ship plate by ANSYS finite element analysis software, accumulating a batch of data of ship hull outer plate processing parameters and residual deformation, and obtaining finite element simulation data.
3) The data are input into an improved gray wolf algorithm optimization support vector machine prediction model to obtain the deformation of the hull plate under different processing parameters, so that a large amount of data for accurately representing the key processing parameters and residual deformation of the hull plate are accumulated to construct a database.
4) As shown in fig. 3, importing a target board drawing into a Tribon software to export three-dimensional point cloud data of the drawing, and using an unfolding surface finally obtained by a board unfolding method as a reference for processing a raw board; the developed cracks are the actual processing path, and the size of the cracks is the contraction amount of the ship plate. And comparing the actual processing path with data representing the key processing parameters and residual deformation of the hull plate in the database of the shrinkage, and obtaining a processing parameter set of the target plate.
5) And the obtained processing parameter sets take the reduction of the shaping production time of the hull plate curved surface and the reduction of the production energy consumption as optimization targets, and a non-dominant ordering genetic algorithm NSGA-II with elite strategy is optimized by adopting particle swarm PSO, so that a final green processing scheme is determined according to the requirements of users.
6) And obtaining plate thickness information according to the target plate drawing, selecting a proper machining mode, and finally inputting the machining scheme and the machining mode into the mechanical arm to finish machining tasks.
The intelligent decision method for processing the ship hull plate by the oxyhydrogen gas heat source can realize high-precision prediction on the deformation of the steel plate, and decides a ship plate processing scheme by matching a plate unfolding mode with a database, so as to obtain an optimal processing scheme taking time and energy consumption as optimal targets, thereby realizing low-cost high-efficiency high-precision ship plate processing.
According to the intelligent decision-making method for processing the ship hull plate by using the oxyhydrogen gas heat source, the ship hull plate is processed by using the mechanical arm, wherein the thick plate adopts a spiral heating process, so that the problem that the thick plate is difficult to form by using a linear heating process is solved;
the intelligent decision method for processing the ship hull plate by the oxyhydrogen gas heat source optimizes the support vector machine to predict the deformation by improving the gray wolf algorithm, has the error obviously smaller than that of a single prediction model, has high prediction precision, and is suitable for predicting the deformation of the steel plate.
According to the intelligent decision-making method for processing the ship hull plate by the oxyhydrogen gas heat source, a ship plate processing scheme is decided by matching a plate unfolding mode with a database, and one group of deformation amount in the database corresponds to a plurality of groups of processing schemes; aiming at the problem, a green database with time and energy consumption as optimal targets is constructed, and a PSO (particle swarm optimization) NSGA-II algorithm is adopted to screen an optimal processing scheme, so that a final green intelligent decision is completed.
The intelligent decision method for processing the hull planking by using the oxyhydrogen gas heat source utilizes the ship plank curved surface thermoforming mechanism to construct a finite element model in the ship plank thermal processing process, and oxyhydrogen flame is selected as a combustion heat source.
The present invention is not limited to the preferred embodiments, but is intended to be limited to the following description, and any simple modification, equivalent changes and adaptations of the embodiments according to the technical principles of the present invention are within the scope of the present invention, as long as the modifications and equivalents can be made by those skilled in the art without departing from the scope of the present invention.
Claims (6)
1. An intelligent decision making method for processing a ship hull plate by using an oxyhydrogen gas heat source is characterized by comprising the following steps of: comprises the steps of,
S1, determining a processing parameter and a deformation relation of oxyhydrogen gas heating by using oxyhydrogen mixed gas as a heat source for processing a ship body outer plate;
S2, a heat source model of an oxyhydrogen heat source processing ship plate is established according to the ship plate processing condition, the heat source model is a combined heat source model formed by coupling a Gaussian surface heat source and a cylindrical heat source, a corresponding temperature field and a deformation field are obtained through finite element simulation to verify and adjust, and finite element simulation data are obtained;
S3, optimizing the deformation prediction of the support vector machine by improving the gray wolf algorithm, obtaining a prediction result, interpolating and complementing the finite element simulation data, obtaining a complete corresponding relation between the deformation and the processing parameters, and constructing an oxyhydrogen flame processing ship plate database;
In step S3, the deformation prediction of the support vector machine is optimized by improving the gray wolf algorithm to obtain a prediction result, specifically,
S31, taking the finite element simulation data obtained in the step S2 as a sample, dividing the finite element simulation data into a training set and a testing set, carrying out normalization processing, and constructing an SVM model as follows:
f(x)＝wT·gΦ(x)+c (3)
Wherein f (x) is the deformation output by the SVM model, phi (x) is a nonlinear mapping function, and is used for mapping the input sample vector x into a high-dimensional feature space to perform linear approximation; w is defined as a weight vector; c is a penalty coefficient, i.e., the tolerance to errors; g is a parameter of the function;
s32, initializing wolves, and parameters a, A and C, setting the number N of the wolves and the maximum iteration number Tmax, wherein the mathematical formula of the gray wolf algorithm is as follows,
D＝||C1·Xp(t)-X(t)|| (4)
X(t+1)＝XP(t)-AD (5)
A＝2a·r1-a (6)
C＝2·r2 (7)
Wherein D represents a position distance vector between the wolf and the prey; t represents the current iteration time; A. c is a vector coefficient; x P is the position vector of the prey; x is the position vector of the gray wolves; a is a step factor, and the step factor is reduced from 2 to 0 along with the increase of the iteration times; r 1,r2 takes a uniform random value between [0,1 ];
S33, enabling the iteration times t=0, calculating the adaptation degree of the wolf group, and marking three wolves with the best adaptation degree as alpha wolves, beta wolves and delta wolves;
s34, according to the improved gray wolf position updating mode, the omega wolf position is updated according to the alpha wolf, beta wolf and delta wolf positions, the gray wolf position updating mode expression is as follows,
S35, updating parameters a, A and C, calculating the fitness of the wolf group, updating alpha wolf, beta wolf and delta wolf, and optimizing parameters C and g in the SVM model;
s36, when the iteration times t is smaller than the maximum iteration times Tmax, the iteration times t=t+1, and the step S34 is returned; otherwise, outputting optimal parameters c and g, and taking the optimal parameters c and g into an svm prediction model, wherein the processing parameters are taken as input, and the deformation is taken as output, so as to obtain a prediction result;
S4, a board unfolding method is adopted for the drawing of the target board, the processing path and the deformation of the corresponding path are obtained, the deformation is input into a database, and a processing parameter set is obtained through the corresponding relation with the database;
S5, optimizing and selecting a processing parameter set by considering the energy consumption and the environmental pollution problem to obtain an optimal green processing scheme; specifically, considering the problems of environmental pollution and energy consumption, including noise accumulation and energy consumption in the processing process, taking reduction of the shaping production time of a hull outer plate curved surface and reduction of the production energy consumption as optimization targets, adopting a particle swarm PSO (particle swarm optimization) optimization algorithm NSGA-II with elite strategy for the processing parameter set obtained in the step S4, and selecting an optimization objective function to obtain a Pareto optimal solution set as an optimal green processing scheme;
S6, determining the plate thickness of the target plate, adopting different setting processing modes for the target plates with different thicknesses, and inputting the processing scheme and the processing mode into the mechanical arm to finish the processing of the target plate.
2. The intelligent decision making method for processing a ship hull external plate by using an oxyhydrogen gas heat source according to claim 1, wherein: in step S1, processing parameters including gas flow, moving speed, heating radius are determined, the ship plate is processed through experiments, and the processed deformation amount including angular deformation and linear deformation is collected.
3. The intelligent decision making method for processing a ship hull external plate by using an oxyhydrogen gas heat source according to claim 1, wherein: in step S2, in the heat source model, the heat flux density distribution function formula of the Gaussian surface heat source model is as follows,
The heat flux density distribution function formula of the cylindrical heat source is as follows,
Wherein η 1,η2 is the heating efficiency of the Gaussian heat source and the cylindrical heat source respectively; mu 1,μ2 is a distribution coefficient of the heating heat source, and mu 1+μ2 =1; Is the flow rate of oxyhydrogen gas; v is the flow rate and τ is the gas flow rate per unit time; b, R 2 is the effective action depth and the effective action half-width of the cylindrical heat source respectively; r 1 is the heat source radius of the Gaussian surface heat source; q is the maximum heat flux density.
4. The intelligent decision making method for processing a ship hull external plate by using an oxyhydrogen gas heat source according to claim 1, wherein: in step S2, a corresponding temperature field and a deformation field are obtained through finite element simulation, specifically, the deformation amount after collection is analyzed to construct the deformation field, and the temperature field is constructed through finite element simulation on the heat source, the thickness of the plate, the poisson coefficient, the thermal expansion coefficient, the flow of the oxyhydrogen gas heat source and the heating efficiency in the actual processing process by utilizing ANSYS.
5. The intelligent decision making method for processing a ship hull external plate by using an oxyhydrogen gas heat source according to claim 1, wherein: in step S5, a non-dominant ranking genetic algorithm of particle swarm PSO optimization with elite policy is adopted for the processing parameter set obtained in step S4, and an optimization objective function is selected to obtain a Pareto optimal solution set, specifically,
S51, initializing populations Pj and j=0, and setting a maximum iteration number J;
S52, optimizing a particle swarm, updating the particle speed and the position, and calculating the fitness;
S53, pj non-dominant sorting to generate a child population Qj;
S54, merging parent-child generations into Rj;
S55, quick non-dominant sorting and crowding degree calculation are carried out, N optimal individuals are selected, and a new parent population Pj+1 is generated; when j does not reach the maximum iteration number, j=j+1, returning to step S52; and when j reaches the maximum iteration number, ending, and obtaining a Pareto optimal solution set as an optimal green processing scheme.
6. An intelligent decision making method for processing a ship hull plate by using an oxyhydrogen gas heat source according to any one of claims 1 to 4, wherein: in step S6, different set processing modes are adopted for target plates with different thicknesses, specifically, a linear heating mode is adopted for steel plates with the target plate thickness below 10mm, and a spiral heating mode is adopted for steel plates with the target plate thickness greater than 10 mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111367704.9A CN114091304B (en) | 2021-11-19 | 2021-11-19 | Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111367704.9A CN114091304B (en) | 2021-11-19 | 2021-11-19 | Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114091304A CN114091304A (en) | 2022-02-25 |
| CN114091304B true CN114091304B (en) | 2024-06-21 |
Family
ID=80301561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111367704.9A Active CN114091304B (en) | 2021-11-19 | 2021-11-19 | Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114091304B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115347300B (en) * | 2022-08-04 | 2023-09-08 | 东软睿驰汽车技术（沈阳）有限公司 | Box body structure design method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682139A (en) * | 2011-03-17 | 2012-09-19 | 齐亮 | Method for forming shell plate curve of ship body |
| KR20210011811A (en) * | 2019-07-23 | 2021-02-02 | 대우조선해양 주식회사 | Apparatus and method for forming of curved surface by using machine learning and computer readable medium storing the same |
| CN112906136B (en) * | 2021-03-16 | 2022-07-22 | 上海交通大学 | Method and system for predicting laser thermoforming deformation of hull plate |
-
2021
- 2021-11-19 CN CN202111367704.9A patent/CN114091304B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于SVM的船体外板冷弯回弹预测模型研究;苏绍娟;胡勇;王呈方;;舰船科学技术;20150515(05);全文 * |
| 水火弯板专家系统研究;陈尤力;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》;20160315;C036-126 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114091304A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112488315B (en) | Batch scheduling optimization method based on deep reinforcement learning and genetic algorithm | |
| CN109214449A (en) | A kind of electric grid investment needing forecasting method | |
| CN104881707B (en) | A kind of sintering energy consumption Forecasting Methodology based on integrated model | |
| CN114091304B (en) | Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source | |
| CN111832839B (en) | Energy consumption prediction method based on sufficient incremental learning | |
| CN116757057A (en) | Air quality prediction method based on PSO-GA-LSTM model | |
| CN115600492A (en) | Laser cutting process design method and system | |
| CN117289652A (en) | Numerical control machine tool spindle thermal error modeling method based on multi-universe optimization | |
| CN115656439A (en) | Online monitoring method for nitrogen oxide emission concentration of coal-fired unit based on transfer learning | |
| Tian et al. | Knowledge-based lot-splitting optimization method for flexible job shops considering energy consumption | |
| CN118261011A (en) | Intelligent optimization method for load cell structure based on parameter optimization | |
| CN110245398A (en) | The hard measurement deep learning method of air preheater rotor heat distortion amount | |
| CN112100819B (en) | Casting riser design method based on integrated calculation and data driving | |
| CN117493987A (en) | Carbon emission prediction method and system for power industry | |
| Gao et al. | A 6-sigma robust optimization method for stamping forming of automobile covering parts based on residual error and radial basis interpolation | |
| CN116502566A (en) | Multi-objective optimization method for performance of combustion chamber of gas turbine based on Bayesian optimization | |
| CN113935556B (en) | Temperature sensor optimal arrangement method based on DNA genetic algorithm | |
| CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| CN113435083B (en) | Additive manufacturing residual stress and deformation prediction method and system based on machine learning | |
| CN110096742B (en) | Pre-forging forming die design method based on prediction model and particle swarm optimization | |
| Li et al. | Modeling and applying of RBF neural network based on fuzzy clustering and pseudo-inverse method | |
| CN116345495B (en) | Power plant unit frequency modulation optimization method based on data analysis and modeling | |
| CN115183921B (en) | Full-automatic material residual stress measuring method based on real-time peak position error feedback | |
| Wang et al. | Machine learning-enabled early prediction of dimensional accuracy for complex products of investment casting | |
| CN113902193B (en) | Method for predicting provincial moon electricity consumption based on POFP-SVM algorithm |
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 |