CN118133468B - Layout optimization method for steel structure support and related products - Google Patents
Layout optimization method for steel structure support and related products Download PDFInfo
- Publication number
- CN118133468B CN118133468B CN202410571370.4A CN202410571370A CN118133468B CN 118133468 B CN118133468 B CN 118133468B CN 202410571370 A CN202410571370 A CN 202410571370A CN 118133468 B CN118133468 B CN 118133468B
- Authority
- CN
- China
- Prior art keywords
- steel structure
- structure support
- design
- layout
- structural
- 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
- 238000000034 method Methods 0.000 title claims abstract description 82
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 72
- 239000010959 steel Substances 0.000 title claims abstract description 72
- 238000005457 optimization Methods 0.000 title claims abstract description 57
- 239000000463 material Substances 0.000 claims abstract description 145
- 238000013461 design Methods 0.000 claims abstract description 74
- 238000009826 distribution Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 230000002068 genetic effect Effects 0.000 claims abstract description 25
- 210000000349 chromosome Anatomy 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 73
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 15
- 238000006073 displacement reaction Methods 0.000 claims description 15
- 238000011478 gradient descent method Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 10
- 239000007787 solid Substances 0.000 claims description 8
- 210000004027 cell Anatomy 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims 1
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 230000007774 longterm Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000008439 repair process Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 11
- 230000035772 mutation Effects 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008303 genetic mechanism Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003938 response to stress Effects 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Abstract
The invention relates to the technical field of building engineering intellectualization, in particular to a layout optimization method of a steel structure support and related products, comprising the following steps: determining design space and size constraints of the steel structure support; determining mechanical properties, expected loads and boundary conditions; constructing a topological optimization objective function and obtaining final material density distribution; encoding into chromosomes according to the final material density; randomly generating a certain number of candidate designs, and constructing a fitness function to evaluate each design; optimizing through a genetic algorithm to obtain the final steel structure support layout; the invention combines the topology optimization and the genetic algorithm to the design of the steel structure support, effectively reduces the material cost on the premise of ensuring the structural safety by minimizing the material consumption, ensures the long-term use safety by optimizing the maximized structural strength, and reduces the maintenance and repair requirements.
Description
Technical Field
The invention relates to the technical field of building engineering intellectualization, in particular to a layout optimization method of a steel structure support and related products.
Background
In building construction, a steel structure is an important supporting device, so that the construction safety of the whole engineering is ensured, however, the traditional steel structure supporting design method often depends on experience and a simplified calculation model, which may lead to uneconomical material use or insufficient structural strength. The design of the steel structure not only needs to consider the mechanical property of the material and the durability of the structure, but also needs to consider the cost effectiveness and the construction convenience. Therefore, how to optimize the layout of the steel structural support to achieve higher structural efficiency and cost control is a technical challenge to be solved.
Disclosure of Invention
The invention aims to provide a layout optimization method of a steel structure support and related products, which are used for accurately simulating and optimizing the layout of the steel structure by accurately setting the design space and the size limit of the steel structure support and comprehensively considering the mechanical property and the expected load of materials.
The invention is realized by the following technical scheme:
a layout optimization method for a steel structure support, comprising:
Determining a design space of the steel structure support, and setting a size limit of the steel structure support;
Determining the mechanical properties of the material supported by the steel structure; determining an expected load acting on the steel structural support; determining boundary conditions of the steel structure support;
Constructing a topological optimization objective function with the aim of minimizing the material usage amount and maximizing the structural strength, and optimizing the topological objective function by a gradient descent method to obtain the final material density distribution;
Extracting key structural features according to the final material density distribution, converting the key structural features into adjustable parameters, and encoding the adjustable parameters into chromosomes;
randomly generating a number of candidate designs, each design represented by a string of encoded chromosomes, and constructing a fitness function to evaluate each design;
And optimizing the design scheme through a genetic algorithm to obtain the final steel structure support layout.
Specifically, the method for optimizing the topological objective function comprises the following steps:
constructing a topology optimization objective function: Wherein, the method comprises the steps of, wherein, In order to use the amount of the material,For the structural strength of the steel sheet, the steel sheet is provided with a plurality of steel sheets,A weight factor for the amount of material used,Is a weight factor for the rigidity of the structure,For the density distribution of the material,，Representing a complete hollow of the hollow,Representing a complete solid;
discretizing the design space into finite element grids, and distributing corresponding material parameters for each grid unit according to the mechanical properties of the materials;
material distribution optimization is carried out by adopting a solid anisotropic microstructure evolution method, and the elastic modulus of the material is determined Wherein, the method comprises the steps of, wherein,In order to penalize the index,Is the original elastic modulus of the material;
obtaining stiffness matrix through material elastic modulus calculation And displacement vector under expected load；
Iterative computation is carried out by utilizing a gradient descent method, the material density of each grid cell is adjusted according to a topological optimization objective function,Wherein, the method comprises the steps of, wherein,In order for the rate of learning to be high,For the gradient of the objective function obtained by stiffness matrix and displacement vector calculation,For the material density of the finite element mesh unit in the current iteration step,A material density for the finite element mesh unit in the next iteration step;
Updating ，Wherein, the method comprises the steps of, wherein,Is the firstThe volume of the individual elements is such that,The material density of the iterative finite element grid unit;
and determining convergence conditions of the gradient descent method, and completing iteration after reaching any convergence conditions to obtain final material density distribution.
Optionally, the method for determining the weight factor of the material usage amount and the weight factor of the structural rigidity includes:
An initial weight factor is set up and the weight of the sample is calculated, ，; Setting a learning rate；
Calculate the firstNormalized performance of material usage after multiple iterationsWherein, the method comprises the steps of, wherein,For a set of material usage for each of all contemplated designs,For the minimum amount of material used in the collection,Maximum value of the material usage in the collection;
calculate the first Normalized performance of structural strength after multiple iterationsWherein, the method comprises the steps of, wherein,For the set of structural strengths of each of all the considered designs,As the minimum value of the structural strength in the set,Is the maximum value of the structural strength in the collection;
Update the first The weight factor after the number of iterations,，Wherein, the method comprises the steps of, wherein,Is the firstThe weight factor of the amount of material used after the number of iterations,Is the firstA weight factor of structural rigidity after the secondary iteration;
For the first The weight factors after the iterations are normalized,，。
Optionally, the method for calculating the gradient of the objective function is: Wherein, the method comprises the steps of, wherein, In the form of a matrix of stiffness,As a result of the displacement vector being a function of the displacement vector,Is a Lagrangian multiplier;
Stiffness matrix Wherein, the method comprises the steps of, wherein,In the form of a strain-displacement matrix,Is a constitutive matrix of material which is to be processed,Is the whole design space;
by solving linear equations ObtainingWherein, the method comprises the steps of, wherein,Is the expected load;
Constitutive matrix Wherein, the method comprises the steps of, wherein,Is poisson's ratio.
Optionally, the convergence condition of the gradient descent method includes:
the change of the objective function in the successive iterations is smaller than a preset threshold;
The variation of the material density is lower than a set value in successive iterations;
The set maximum number of iterations is reached.
Specifically, the method for optimizing the design scheme through the genetic algorithm comprises the following steps:
The fitness function is constructed so that, Wherein, the method comprises the steps of, wherein,As the evaluation function corresponding to the safety coefficient,As an evaluation function corresponding to the material cost,In order to evaluate the function corresponding to the construction simplicity,、AndIs a weight coefficient;
Setting a certain number of randomly generated candidate design schemes as a first generation population, and evaluating the first generation population through a fitness function;
Repeatedly executing genetic operations of selection, crossing and variation to generate a new population, and evaluating the new population through a fitness function;
and determining the convergence condition of the genetic algorithm, completing iteration after reaching any convergence condition, rotating the population with the highest fitness from the final population, and taking the corresponding design scheme as the final steel structure support layout.
Optionally, the convergence condition of the genetic algorithm includes:
The change of the fitness in the continuous several iterations is smaller than a preset threshold value;
the fitness is lower than a set value;
The set maximum number of iterations is reached.
Optionally, an evaluation function corresponding to the safety factorWherein, the method comprises the steps of, wherein,As a function of the allowable stress of the material,Maximum stress of the structure under expected load;
evaluation function corresponding to material cost Wherein, the method comprises the steps of, wherein,Is the firstThe material density of the individual elements is such that,Is the firstThe volume of the individual elements is such that,As a total number of finite element meshes,Is the firstCost per unit volume of material for the individual elements;
evaluation function corresponding to construction simplicity Wherein, the method comprises the steps of, wherein,In order to provide for the number of structural components,Is the firstThe design complexity of the individual structural components,Is the firstAnd the construction simplicity of the structural assembly.
A layout optimization terminal for a steel structure support, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing a layout optimization method for a steel structure support as described above when executing the computer program.
A computer program product comprising computer programs/instructions for execution by a processor to implement a layout optimization method for a steel structure support as described above.
Compared with the prior art, the invention has the following advantages and beneficial effects:
The invention combines the topology optimization and the genetic algorithm to the design of the steel structure support, can obviously improve the design efficiency and the economy of the steel structure support, effectively reduces the material cost on the premise of ensuring the structural safety by minimizing the material consumption, ensures the safety of long-term use by optimizing the maximum structural strength, and reduces the maintenance and repair requirements.
The topology optimization method can perform microscopic management of material distribution at the initial stage of design, and the density distribution of the material is optimized through algorithm iteration, so that the extreme optimization of material use is realized, the material consumption can be minimized, the distribution of the material can be ensured to optimally adapt to load conditions and mechanical requirements, and the structure can bear larger load under smaller material consumption;
the genetic algorithm optimizes the design by simulating natural selection and genetic mechanism, has the capacity of global search in complex design space, can effectively solve the multi-objective optimization problems, balances different design requirements through fitness function, and searches for the optimal solution.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the principles of the invention.
Fig. 1 is a schematic flow chart of a layout optimization method for a steel structure support according to the present invention.
Fig. 2 is a schematic flow chart of topology optimization according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and embodiments, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent. It is to be understood that the specific embodiments described herein are merely illustrative of the substances, and not restrictive of the invention.
It should be further noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
Embodiments of the present invention and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In a first embodiment, as shown in fig. 1, a layout optimization method for a steel structure support is provided, including:
Firstly, determining a design space of a steel structure support, and setting the size limit of the steel structure support; the design space of the steel structure support is determined according to the specific size and shape of the building unit to which the steel structure belongs, the design space refers to the usable area of the steel structure support and the shape thereof, and in addition, the size limit, namely the maximum size limit and the minimum size limit of the steel structure support, are set at the same time, so that the design of the steel structure support can be realized in the physical space and the construction feasibility.
Secondly, determining the mechanical properties of the material supported by the steel structure; determining an expected load acting on the steel structural support; determining boundary conditions of the steel structure support; the mechanical properties of the materials used, such as modulus of elasticity, yield strength, etc., are determined, which directly affect the performance and durability of the structure.
The expected load refers to the force required to be borne by the steel structure support under normal use conditions, and includes static load, dynamic load and the like.
Boundary conditions refer to the manner in which a steel structural support contacts other building parts, and these conditions affect the distribution and stability of structural stresses. Common boundary conditions include fixed, hinged or sliding, etc.
Thirdly, constructing a topological optimization objective function with the aim of minimizing the material usage amount and maximizing the structural strength, and optimizing the topological objective function by a gradient descent method to obtain the final material density distribution.
The topological optimization aims at realizing optimization of material use on the premise of meeting certain performance requirements. In this embodiment, the objective function of the construction is to minimize material usage and maximize structural strength. The material density distribution is continuously updated through an iterative process using a gradient descent method to approach the optimal solution step by step.
And fourthly, extracting key structural features according to the final material density distribution, converting the key structural features into adjustable parameters, and encoding the adjustable parameters into chromosomes.
And extracting key structural characteristics according to the optimized material density distribution, wherein the characteristics define the core mechanical properties and morphology of the steel structure support. These features are converted into adjustable parameters and encoded into chromosomes, which are the preconditions for the implementation of genetic algorithms.
Fifth, randomly generating a number of candidate designs, each design represented by a string of encoded chromosomes, and constructing a fitness function to evaluate each design; the fitness function is defined according to design performance such as safety, cost, and construction convenience.
And sixthly, optimizing the design scheme through a genetic algorithm to obtain the final steel structure support layout. And (3) performing selection, crossover and mutation operations in a genetic algorithm on the candidate schemes, continuously improving the designs, and selecting the design with the best performance according to the fitness function in each generation of population until convergence conditions are met or iteration times limit is reached.
The embodiment is based on structural mechanics, material science and algorithm optimization theory. By combining topology optimization and genetic algorithm, the system can optimize the use of materials on the basis of ensuring structural safety and functionality, thereby achieving the maximization of cost effectiveness.
The core principle of topology optimization is to adjust the material distribution of the structure to meet performance requirements while minimizing material usage. This is accomplished by mathematical models that calculate mechanical properties, such as stiffness and strength, for different material distributions and adjust the material distribution based on these calculations.
Genetic algorithms mimic the natural selection and genetic mechanisms in the process of biological evolution. The design scheme (solution) evolves gradually through "chromosome" coding, and the algorithm finds the optimal solution by selecting (evaluating the merits of the scheme based on fitness function), crossing (generating new scheme by combining the features of both schemes) and mutation (randomly changing some parameters of the scheme) operations.
In the second embodiment, optimization of the topological objective function is a core link in the optimization method of the steel structure support layout. This process involves a balance of material usage and structural strength, with optimization of the design achieved by mathematical and computational methods.
As shown in fig. 2, the method for optimizing the topological objective function includes:
constructing a topology optimization objective function: Wherein, the method comprises the steps of, wherein, In order to use the amount of the material,For the structural strength of the steel sheet, the steel sheet is provided with a plurality of steel sheets,A weight factor for the amount of material used,Is a weight factor for the rigidity of the structure,For the density distribution of the material,，Representing a complete hollow of the hollow,Representing a complete solid;
In order to convert the continuous design problem into a discrete numerical problem, discretizing the design space into a finite element grid, and distributing corresponding material parameters for each grid unit according to the mechanical property of the material;
material distribution optimization is carried out by adopting a solid anisotropic microstructure evolution method, and the elastic modulus of the material is determined Wherein, the method comprises the steps of, wherein,The penalty index is used to control the effect of material density on elastic modulus, and can take on a value of 3,Is the original elastic modulus of the material;
obtaining stiffness matrix through material elastic modulus calculation And displacement vector under expected load；
Iterative computation is carried out by utilizing a gradient descent method, the material density of each grid cell is adjusted according to a topological optimization objective function,Wherein, the method comprises the steps of, wherein,The size of the update step is determined for the learning rate,For the gradient of the objective function obtained by stiffness matrix and displacement vector calculation,For the material density of the finite element mesh unit in the current iteration step,A material density for the finite element mesh unit in the next iteration step;
Calculating the total material usage amount of the whole structure and updating ，Wherein, the method comprises the steps of, wherein,Is the firstThe volume of the individual elements is such that,The material density of the iterative finite element grid unit; it is ensured that the calculation of the amount of material used is directly related to the material density, so that the optimization process can precisely control the use of material to reduce waste. And evaluate the performance of the structure by quantifying the response of the structure, which is the key to evaluate whether the structural design can meet the safety standard.
And determining convergence conditions of the gradient descent method, and completing iteration after reaching any convergence conditions to obtain final material density distribution. I.e. by iteratively updating the decision variables to find the minimum of the function, the convergence conditions for a specific gradient descent method include:
the change of the objective function in the successive iterations is smaller than a preset threshold; if the value of the objective function varies by less than a preset threshold in several consecutive iterations, this indicates that the optimization process has been stabilized and that further iterations may not lead to significant improvement.
The variation of the material density is lower than a set value in successive iterations; in the optimization process, if the amount of change in material density is below a set point in successive iterations, this also indicates that the current material distribution has approached the optimal solution.
The set maximum number of iterations is reached, and a maximum number of iterations is typically set in order to control the computational resources and time. Once this number of times is reached, the optimization process will end even if other convergence conditions are not fully met.
In the gradient descent method, the method for calculating the gradient of the objective function is as follows: Wherein, the method comprises the steps of, wherein, In the form of a matrix of stiffness,As a result of the displacement vector being a function of the displacement vector,Is a Lagrangian multiplier; The partial derivative of the material usage amount relative to the material density directly reflects the influence of the material density change on the total material usage amount.
Is the partial derivative of the stiffness matrix with respect to the material density, reflecting the effect of the material density variation on the structural stiffness.
Stiffness matrixWherein, the method comprises the steps of, wherein,For a strain-displacement matrix (responsible for converting displacement vectors into strain vectors),Is a constitutive matrix of a material (describing the mechanical properties of the material such as modulus of elasticity and poisson's ratio),For the entire design space (the integral expression represents the result accumulated in the entire design space);
by solving linear equations ObtainingWherein, the method comprises the steps of, wherein,Is the expected load;
Constitutive matrix Wherein, the method comprises the steps of, wherein,Is poisson's ratio.
In topology optimization, the importance of different optimization targets can be balanced by dynamically adjusting the weight factors, and the optimization direction is adjusted according to actual conditions in the iteration process.
The method for determining the weight factors of the material usage amount and the weight factors of the structural rigidity comprises the following steps:
An initial weight factor is set up and the weight of the sample is calculated, ，Meaning that at the beginning of the optimization, the amount of material used and the structural rigidity are given equal importance; setting a learning rateThe speed and amplitude of the weight update can be controlled, and the value range is generally 0.001 to 0.1.
Calculate the firstNormalized performance of material usage after multiple iterationsWherein, the method comprises the steps of, wherein,For a set of material usage for each of all contemplated designs,For the minimum amount of material used in the collection,Maximum value of the material usage in the collection; and comparing the material usage after a certain iteration with the minimum and maximum material usage in all design schemes through normalization processing, thereby obtaining a performance index between 0 and 1.
Calculate the firstNormalized performance of structural strength after multiple iterationsWherein, the method comprises the steps of, wherein,For the set of structural strengths of each of all the considered designs,As the minimum value of the structural strength in the set,Is the maximum value of the structural strength in the collection; a normalization index is set for the structural strength, reflecting the relative behavior of the structural strength in all designs.
Update the firstThe weight factor after the number of iterations,，Wherein, the method comprises the steps of, wherein,Is the firstThe weight factor of the amount of material used after the number of iterations,Is the firstA weight factor of structural rigidity after the secondary iteration; the update rule is based on comparing two normalized performances, automatically adjusting weights to favor the currently less optimal target.
For the firstThe weight factors after the iterations are normalized,，. The updated weight factors are normalized to ensure that their sum is 1, so that the relative proportions of the weights can be maintained.
By adjusting the weighting factors in real time, it can be ensured that neither key objective is deviated too far during the optimization process, thus making the final design both economical and reliable.
The adjustment of the weighting factors is typically done after each topology optimization iteration, since each iteration may change the material distribution of the structure, affecting the calculation of the material usage M (x) and the structural stiffness S (x). After each iteration, the weighting factors are updated according to the new material distribution and the corresponding performance indicators (material usage and structural stiffness) to ensure that the two indicators can be reasonably weighted in the next iteration.
In the third embodiment, the layout of the steel structure support is optimized by applying a genetic algorithm, and an approximate global optimal solution can be found in a complex design space by using the genetic algorithm, meanwhile, various design schemes are reserved, and the possibility of finding an innovative solution is increased. The method for optimizing the design scheme through the genetic algorithm comprises the following steps:
The fitness function is constructed so that, Wherein, the method comprises the steps of, wherein,For the evaluation function (measure the safety of design scheme) corresponding to the safety coefficient,For the corresponding evaluation function of the material cost (measuring the economic investment required for the design),To evaluate the function (reflect the degree of convenience of the design) corresponding to the convenience of the construction,、AndIs a weight coefficient;
a number of randomly generated candidate designs are set as a primary population, and the primary population is evaluated by a fitness function.
Repeatedly executing genetic operations of selection, crossing and variation to generate a new population, and evaluating the new population through a fitness function;
selection (Selection): the preferred individuals are selected according to the fitness function to provide "genetic material" for the next generation. Roulette selection, tournament selection, etc. are commonly used.
Crossover (Crossover): the selected individuals are crossed and paired according to a certain probability, and part of genes of the selected individuals are exchanged to generate new individuals. This mimics the sexual propagation process in biological genetics.
Mutation (Mutation): partial genes of some individuals are randomly changed with small probability, so that the diversity of the population is increased, and the algorithm is prevented from being converged to a local optimal solution prematurely.
And determining the convergence condition of the genetic algorithm, completing iteration after reaching any convergence condition, rotating the population with the highest fitness from the final population, and taking the corresponding design scheme as the final steel structure support layout.
The convergence conditions of the genetic algorithm include:
the change of the fitness in the continuous several iterations is smaller than a preset threshold value; if the change in fitness in several consecutive iterations is less than a preset threshold, indicating that the solution has tended to stabilize, the iteration may be stopped.
The fitness is lower than a set value; if the fitness reaches or falls below a certain set point, it may be indicated that a sufficiently good solution is found.
The set maximum number of iterations is reached.
In the fitness function, an evaluation function corresponding to the safety coefficientWherein, the method comprises the steps of, wherein,Is the limit of allowable stress of a material, i.e., the maximum stress that the material can withstand without permanent deformation or failure; The maximum stress of the structure under expected load, i.e. the stress response of the design under the most adverse load. The larger this evaluation function value, the larger the safety margin of the design. The safety factor should be greater than 1, and ideally should be much greater than 1 to ensure the safety of the structure.
Evaluation function corresponding to material costWherein, the method comprises the steps of, wherein,Is the firstThe material density of the individual elements is such that,Is the firstThe volume of the individual elements is such that,As a total number of finite element meshes,Is the firstCost per unit volume of material for the individual elements; the lower the value of this function, the lower the material cost, and the better the design performs in terms of economy.
Evaluation function corresponding to construction simplicityWherein, the method comprises the steps of, wherein,In order to provide for the number of structural components,Is the firstThe design complexity of the individual structural components,Is the firstAnd the construction simplicity of the structural assembly. The lower the value of this function, the easier the entire structure is to construct, and the time and cost in the construction process may be relatively low.
In a fourth embodiment, a layout optimization terminal for a steel structure support includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the layout optimization method for the steel structure support as described above when executing the computer program.
The memory may be used to store software programs and modules, and the processor executes various functional applications of the terminal and data processing by running the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an execution program required for at least one function, and the like.
The storage data area may store data created according to the use of the terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
A computer readable storage medium storing a computer program which when executed by a processor implements a layout optimization method for a steel structure support as above.
Computer readable media may include computer storage media and communication media without loss of generality. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instruction data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will recognize that computer storage media are not limited to the ones described above. The above-described system memory and mass storage devices may be collectively referred to as memory.
A computer program product comprising computer programs/instructions for execution by a processor to implement a layout optimization method for a steel structure support as above.
The computer program product comprises a computer program or set of instructions for performing specific tasks or implementing specific functions. These programs or instructions are designed to be executed by a processor to implement a series of predefined steps or operations. The program product may be stored on various forms of computer storage media, such as memory, hard disk, solid state drive, optical disk, or other forms of digital storage devices. Either in the form of compiled binary code or in the form of scripts or bytecodes that can be executed by an interpreter. The program product enables the processor to process data in a specific order and manner through well-designed algorithms and logic instructions to perform various functions such as data analysis, user interaction, device control, etc.
In the description of the present specification, reference to the terms "one embodiment/manner," "some embodiments/manner," "example," "a particular example," "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/manner or example is included in at least one embodiment/manner or example of the application. In this specification, the schematic representations of the above terms are not necessarily for the same embodiment/manner or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/modes or examples described in this specification and the features of the various embodiments/modes or examples can be combined and combined by persons skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
It will be appreciated by persons skilled in the art that the above embodiments are provided for clarity of illustration only and are not intended to limit the scope of the invention. Other variations or modifications of the above-described invention will be apparent to those of skill in the art, and are still within the scope of the invention.
Claims (9)
1. A layout optimization method for a steel structure support, comprising:
Determining a design space of the steel structure support, and setting a size limit of the steel structure support;
Determining the mechanical properties of the material supported by the steel structure; determining an expected load acting on the steel structural support; determining boundary conditions of the steel structure support;
Constructing a topological optimization objective function with the aim of minimizing the material usage amount and maximizing the structural strength, and optimizing the topological objective function by a gradient descent method to obtain the final material density distribution;
Extracting key structural features according to the final material density distribution, converting the key structural features into adjustable parameters, and encoding the adjustable parameters into chromosomes;
randomly generating a number of candidate designs, each design represented by a string of encoded chromosomes, and constructing a fitness function to evaluate each design;
Optimizing a design scheme through a genetic algorithm to obtain a final steel structure support layout;
the method for optimizing the topological objective function comprises the following steps:
Constructing a topology optimization objective function: f (x) =w 1·M(x)-w2 ·s (x), where M (x) is the material usage, S (x) is the structural strength, w 1 is the weight factor of the material usage, w 2 is the weight factor of the structural rigidity, x is the density distribution of the material, 0.ltoreq.x.ltoreq.1, x=0 represents a complete void, and x=1 represents a complete solid;
discretizing the design space into finite element grids, and distributing corresponding material parameters for each grid unit according to the mechanical properties of the materials;
Carrying out material distribution optimization by adopting a solid anisotropic microstructure evolution method, and determining the elastic modulus E (x) =x η·E0 of the material, wherein eta is a punishment index, and E 0 is the original elastic modulus of the material;
obtaining a rigidity matrix K and a displacement vector U under the action of expected load through material elastic modulus calculation;
Iterative computation is carried out by utilizing a gradient descent method, the material density of each grid cell is adjusted according to a topological optimization objective function, Wherein alpha is the learning rate,For the gradient of the objective function obtained by the stiffness matrix and displacement vector calculation, x old is the material density of the finite element mesh unit in the current iteration step, and x new is the material density of the finite element mesh unit in the next iteration step;
Updating M (x) = Σ ixi·vi,S(x)＝UT KU, wherein v i is the volume of the ith element, and x i is the material density of the iterative finite element grid unit;
and determining convergence conditions of the gradient descent method, and completing iteration after reaching any convergence conditions to obtain final material density distribution.
2. The method for optimizing the layout of a steel structure support according to claim 1, wherein the method for determining the weight factor of the material usage amount and the weight factor of the structural rigidity comprises:
An initial weight factor is set up and the weight of the sample is calculated, Setting a learning rate gamma;
Calculating normalized performance of material usage after the t-th iteration Wherein M (X) is a set of material usage of each of all considered design schemes, minM (X) is a minimum value of material usage in the set, and maxM (X) is a maximum value of material usage in the set;
calculating normalized performance of structural strength after t-th iteration Wherein S (X) is the set of structural strength of each of all considered design schemes, minS (X) is the minimum value of the structural strength in the set, and maxS (X) is the maximum value of the structural strength in the set;
updating the weight factor after the t+1st iteration, Wherein,A weight factor for the amount of material used after the t-th iteration,A weight factor for structural rigidity after the t-th iteration;
normalizing the weight factor after the t+1st iteration,
3. The layout optimization method of a steel structure support according to claim 1, wherein the method for calculating the gradient of the objective function is as follows: wherein K is a rigidity matrix, U is a displacement vector, and lambda is a Lagrangian multiplier;
A rigidity matrix K= ΩBT DBdΩ, wherein B is a strain-displacement matrix, D is a constitutive matrix of the material, and Ω is the whole design space;
Obtaining U by solving the linear equation ku=f, where F is the expected load;
Constitutive matrix Where v is poisson's ratio.
4. The layout optimization method of a steel structure support according to claim 1, wherein the convergence condition of the gradient descent method comprises:
the change of the objective function in the successive iterations is smaller than a preset threshold;
The variation of the material density is lower than a set value in successive iterations;
The set maximum number of iterations is reached.
5. The method for optimizing the layout of a steel structure support according to claim 1, wherein the method for optimizing the design scheme by a genetic algorithm comprises:
The fitness function is constructed so that, Wherein Safe is an evaluation function corresponding to a safety coefficient, cost is an evaluation function corresponding to material Cost, const is an evaluation function corresponding to construction simplicity, and v 1、v2 and v 3 are weight coefficients;
Setting a certain number of randomly generated candidate design schemes as a first generation population, and evaluating the first generation population through a fitness function;
Repeatedly executing genetic operations of selection, crossing and variation to generate a new population, and evaluating the new population through a fitness function;
and determining the convergence condition of the genetic algorithm, completing iteration after reaching any convergence condition, rotating the population with the highest fitness from the final population, and taking the corresponding design scheme as the final steel structure support layout.
6. The method for optimizing the layout of a steel structure support according to claim 5, wherein the convergence condition of the genetic algorithm comprises:
The change of the fitness in the continuous several iterations is smaller than a preset threshold value;
the fitness is lower than a set value;
The set maximum number of iterations is reached.
7. The layout optimization method of steel structure support according to claim 5, wherein the evaluation function corresponding to the safety factorWhere σ allow is the allowable stress of the material and σ max is the maximum stress of the structure under expected load;
evaluation function corresponding to material cost Wherein x i is the material density of the ith element, v i is the volume of the ith element, n is the total number of finite element grids, and c i is the material cost per unit volume of the ith element;
evaluation function corresponding to construction simplicity Where m is the number of structural components, d j is the design complexity of the jth structural component, and s j is the ease of construction of the jth structural component.
8. A layout optimizing terminal for a steel structure support, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the computer program.
9. A computer program product comprising computer program/instructions for execution by a processor to perform a layout optimization method for implementing a steel structure support according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410571370.4A CN118133468B (en) | 2024-05-10 | Layout optimization method for steel structure support and related products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410571370.4A CN118133468B (en) | 2024-05-10 | Layout optimization method for steel structure support and related products |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118133468A CN118133468A (en) | 2024-06-04 |
| CN118133468B true CN118133468B (en) | 2024-07-16 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255142A (en) * | 2018-05-16 | 2019-01-22 | 浙江大学 | Tensegrity torus Topology Optimization Method based on niche genetic algorithm |
| CN113779842A (en) * | 2021-09-15 | 2021-12-10 | 哈尔滨理工大学 | Reinforcing rib structure layout optimization design method based on genetic algorithm |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255142A (en) * | 2018-05-16 | 2019-01-22 | 浙江大学 | Tensegrity torus Topology Optimization Method based on niche genetic algorithm |
| CN113779842A (en) * | 2021-09-15 | 2021-12-10 | 哈尔滨理工大学 | Reinforcing rib structure layout optimization design method based on genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108964042B (en) | Regional power grid operating point scheduling optimization method based on deep Q network | |
| Wang et al. | A compact constraint incremental method for random weight networks and its application | |
| CN110046434B (en) | Mechanical part reliability design method based on Gauss process regression and genetic algorithm | |
| CN103105246A (en) | Greenhouse environment forecasting feedback method of back propagation (BP) neural network based on improvement of genetic algorithm | |
| CN113240307B (en) | Power system economic dispatching method based on improved differential evolution algorithm | |
| CN113361761A (en) | Short-term wind power integration prediction method and system based on error correction | |
| CN108647820A (en) | Based on the distributed generation resource addressing constant volume optimization method and system for improving particle cluster algorithm | |
| CN114362175B (en) | Wind power prediction method and system based on depth certainty strategy gradient algorithm | |
| CN116562331B (en) | Method for optimizing SVM by improving reptile search algorithm and application thereof | |
| CN111950180A (en) | Reliability analysis method and system for cable bearing bridge structure system | |
| CN111461443B (en) | Optimal design method and system for wind power plant, electronic device and storage medium | |
| CN112036651A (en) | Electricity price prediction method based on quantum immune optimization BP neural network algorithm | |
| CN115860170A (en) | Power quality optimization method of power distribution system considering power electronic load | |
| Bekdaş et al. | Estimation of optimum design of structural systems via machine learning | |
| Xu et al. | Multi-cluster based equilibrium optimizer algorithm with compact approach for power system network | |
| CN117353359B (en) | Battery combined energy storage and power supply method and system | |
| CN118133468B (en) | Layout optimization method for steel structure support and related products | |
| CN111339616A (en) | Topology optimization method for maximizing fundamental frequency of mechanical structure | |
| CN111311001A (en) | Bi-LSTM network short-term load prediction method based on DBSCAN algorithm and feature selection | |
| CN118133468A (en) | Layout optimization method for steel structure support and related products | |
| CN117252085A (en) | Cable-stayed bridge cable force tolerance optimization method and system based on neural network and particle swarm | |
| Zhao et al. | Initial prestress design and optimization of cable-stiffened latticed shells | |
| CN113947332A (en) | Method and system for evaluating comprehensive guarantee capability of underground engineering | |
| CN110910164A (en) | Product sales forecasting method, system, computer device and storage medium | |
| CN114970239B (en) | Multi-type monitoring data measuring point arrangement method, equipment and medium based on Bayesian system identification and heuristic deep reinforcement learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |