[go: up one dir, main page]

CN119129073B - A method and system for optimizing measurement points of venue lattice shell roof - Google Patents

A method and system for optimizing measurement points of venue lattice shell roof Download PDF

Info

Publication number
CN119129073B
CN119129073B CN202411308213.0A CN202411308213A CN119129073B CN 119129073 B CN119129073 B CN 119129073B CN 202411308213 A CN202411308213 A CN 202411308213A CN 119129073 B CN119129073 B CN 119129073B
Authority
CN
China
Prior art keywords
population
fitness
individuals
optimal
populations
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
Application number
CN202411308213.0A
Other languages
Chinese (zh)
Other versions
CN119129073A (en
Inventor
周春娟
柳明亮
陈思锦
苗鹏勇
邢国华
王军
张凌菲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changan University
Shaanxi Architecture Science Research Institute Co Ltd
Original Assignee
Changan University
Shaanxi Architecture Science Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changan University, Shaanxi Architecture Science Research Institute Co Ltd filed Critical Changan University
Priority to CN202411308213.0A priority Critical patent/CN119129073B/en
Publication of CN119129073A publication Critical patent/CN119129073A/en
Application granted granted Critical
Publication of CN119129073B publication Critical patent/CN119129073B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Computer Hardware Design (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Genetics & Genomics (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physiology (AREA)
  • Architecture (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明为一种场馆网壳屋盖测点优化方法及系统，涉及工程结构技术领域，包括将场馆网壳屋盖的所有节点作为初始化种群，并将此初始化种群划分为多个种群同时进行遗传迭代操作；基于非支配重组遗传算法构建场馆网壳屋盖测点布置优化模型，将种群的适应度作为优化目标；基于MAC矩阵对适应度函数进行设置，选择最小化MAC矩阵中的非对角元素作为优化函数的准则；根据所述优化函数准则对非支配重组遗传算法的迭代次数、交叉概率以及变异概率进行设置；迭代次数满足设定的条件时，得到最优解，即为场馆网壳屋盖的测点最优方案。提升传感器布置的效果和求解速度，尤其是处理复杂网壳结构的大规模待选测点问题。

The present invention is a method and system for optimizing measuring points of a stadium grid shell roof, which relates to the technical field of engineering structures, including taking all nodes of the stadium grid shell roof as an initialization population, and dividing the initialization population into multiple populations to simultaneously perform genetic iteration operations; constructing a stadium grid shell roof measuring point layout optimization model based on a non-dominated recombination genetic algorithm, and taking the fitness of the population as an optimization target; setting the fitness function based on a MAC matrix, and selecting the non-diagonal elements in the minimized MAC matrix as the criterion of the optimization function; setting the number of iterations, crossover probability, and mutation probability of the non-dominated recombination genetic algorithm according to the optimization function criterion; when the number of iterations meets the set conditions, the optimal solution is obtained, which is the optimal solution for measuring points of the stadium grid shell roof. The effect of sensor layout and the speed of solution are improved, especially for dealing with large-scale candidate measuring point problems of complex grid shell structures.

Description

Method and system for optimizing venue latticed shell roof measuring points
Technical Field
The invention relates to the technical field of safety engineering, in particular to a venue latticed shell roof measuring point optimizing method and system.
Background
With the development of modern society and the improvement of living standard of people, the construction of various stadiums is more and more emphasized. These stadiums not only serve as the place of holding the sports event, but also carry many functions such as cultural performance, business activities, etc. Therefore, ensuring the safety and operation efficiency of such structures is particularly important. The latticed shell structure is widely used in the design of roofs of stadiums as a space structure form having high strength, light weight and beautiful appearance. However, the complexity of the reticulated shell structure and the number of large-scale points to be selected present a significant challenge to the optimal placement of the sensor.
When the existing sensor arrangement method is used for processing the measuring point scheme of the complex reticulated shell structure, the main problems of poor sensor arrangement optimizing effect, low solving speed, lack of research on external excitation identification and the like exist. In a stadium reticulated shell structure, the scale of the to-be-selected points is huge, and tens or even hundreds of sensors are usually required to be arranged. Because of the large number of degrees of freedom of the actual structural model, the conventional optimization algorithm often shows problems of low calculation efficiency and low solving speed when processing the large-scale to-be-selected points. To reduce computational complexity, existing studies often employ a simplified model to reduce the site locations to be selected. However, for the abnormal space reticulated shell structure, the simplification process is difficult and may affect the accuracy of the optimization results. Therefore, a high-performance optimization algorithm is needed to solve the problem of large-scale to-be-selected points, and improve the effect and efficiency of sensor arrangement.
Disclosure of Invention
In order to overcome the defects of weak self-adaptive capacity and insufficient prediction precision in the prior art, the main purpose of the invention is to provide a venue latticed shell roof measuring point optimizing method and system.
In order to achieve the above purpose, the invention adopts the following technical scheme that the sensor optimization arrangement method based on a multi-population non-dominant recombination genetic algorithm (MP-RGA) is realized, and comprises the following steps:
The population initialization is to divide the measuring point positions into a plurality of populations (population 1, population 2,..population N) in an initialization stage, and simultaneously perform genetic iterative operation to improve the optimizing capability of an algorithm, and the population initialization needs to be provided with a plurality of population numbers N. Theoretically, the more the number of the multiple groups is, the better, but under the condition that the total number of the groups is unchanged, the more the groups are divided, the less the number of the individuals in a single group is, and the optimal searching capability of an algorithm is seriously reduced.
The calculation fitness is embodied by a fitness value calculated by a fitness function f 1, and when the monitoring points of the complex net shell structure of the stadium are optimized, an MAC matrix is constructed based on a mode vector of the position estimation of the measuring points, and off-diagonal elements in the minimized MAC matrix are selected as the fitness function, namely:
Wherein, MAC ij represents the element of the ith row and jth column in the MAC matrix; and X represents the measurement point position arrangement scheme.
The reverse learning is realized by generating a reverse population corresponding to the original population, reserving individuals with adaptability superior to that of the original population, and eliminating poor individuals in the original population, so that the full search of a solution space is realized.
The population communication is implemented through a population communication ratio alpha and a population communication frequency f, and the population communication ratio and the population communication frequency influence the evolution directions and the similarity of individuals of different species in the process of multiple species communication. And the alternating current ratio and the alternating current frequency of the population are increased, the worst population in each generation in the multiple populations obtains excellent individual increase from the optimal population, and the updating speed of the worst population to the optimal population is increased.
The optimal population is an optimal population obtained by evaluating the population 1, the population 2 and the population N according to the fitness function f fit.
The worst population is the worst population obtained by evaluating population 1, population 2, and population N according to fitness function f fit.
The improved population refers to the introduction of elite individuals of the optimal population into the worst population, and the replacement of a corresponding number of worse individuals.
The self-adaptive population size means that the size of the population is dynamically adjusted according to a scaling ratio of 0.5-1.5, when the average fitness of the population parent individuals is better than that of the parent individuals of the previous generation, the parent of the previous generation is indicated to obtain a better searching effect, and the population size can be reduced. Otherwise, poor searching effect is obtained through iteration, and the population size is increased to improve the searching capability. Specifically, the method is determined according to the fitness value and the sigmoid function and comprises the following steps:
(a) Calculating the rate of change of fitness
(B) Calculating the scaling ratio β=sigmoid (5×α) +0.5
(C) Determining updated population size G N＝GN-1 x beta
Wherein f fit_(N-1) represents the fitness value of the generation N-1, f fit_(N) represents the fitness value of the generation N, alpha represents the fitness change rate, beta represents the scaling ratio, G N-1 represents the population size of the generation N-1, and G N represents the population size of the generation N.
The self-adaptive interdigital ensures the diversity of individuals through a non-dominant recombination method, and in the self-adaptive non-dominant recombination operation, each iteration carries out non-dominant recombination on a part of individuals in the population, so as to ensure the diversity of the population and simultaneously avoid the complete destruction of excellent gene segments of the population. The proportion of non-dominant recombination can be determined by measuring the similarity of the variance of the population fitness, and the larger the similarity is, the more population individuals are subjected to non-dominant recombination, and the calculation formula is as follows:
Nr＝-ln(D(fitness))·T·Nparent
Where N r represents the number of individuals undergoing non-dominant recombination, D (fitness) represents the variance of the fitness of the parent individuals, T represents a constant of 1/20, and N parent represents the number of parent individuals of the population.
The adaptive mutation means that smaller mutation probability is adopted in the early stage of optimizing and larger mutation probability is adopted in the later stage of optimizing. The mutation strategy can ensure that the algorithm can be quickly converged to the vicinity of the optimal solution in the early stage, and is beneficial to the local convergence of the jump-out in the later stage. The adaptive conversion function also adopts a sigmoid function, and the following formula is specifically calculated.
Where M is a constant of 0.1, and represents that the variation probability is generally not more than 0.1.
The optimal arrangement scheme refers to an optimal scheme obtained when the specified iteration times are completed and the set conditions are met.
Compared with the prior art, the method has the beneficial effects that by optimizing the positions of the measuring points, the arrangement scheme of the measuring points is ensured to reflect the dynamic characteristics of the structure more effectively, so that the accuracy and the reliability of structural health monitoring are improved. By minimizing off-diagonal elements in the MAC (ModalAssuranceCriterion) matrix, the degree of distinction between modal vectors is optimized, modal confusion is reduced, and accuracy of modal parameter identification is improved. The robustness and the efficiency of the algorithm are improved, and the searching efficiency and the global searching capability are improved by dividing a large population into a plurality of populations and simultaneously carrying out genetic iterative operation. By individual exchange among populations, richer genetic diversity is introduced, so that the method is helpful for jumping out of a local optimal solution and finding out a global optimal solution. The characteristic of the MAC matrix is considered in the design of the fitness function, so that the algorithm can effectively evaluate and guide specific structural optimization problems. The dynamic adjustment is performed according to the degree of adaptability convergence, so that the algorithm is ensured to find a satisfactory solution in enough time, and unnecessary calculation is avoided. Through self-adaptive adjustment, diversity of the population is maintained, meanwhile, the convergence of the algorithm is ensured to dynamically adjust the size of the population according to the change of the fitness value, and the method is beneficial to maintaining proper search range and search precision in different stages of the algorithm. By introducing elite individuals in the optimal population into the worst population, the convergence process of the algorithm is accelerated, while maintaining the excellent genetic characteristics of the population.
In conclusion, the optimization of the layout of the measuring points of the latticed shell roof of the venue is realized, the performance of the structural health monitoring system is improved, and meanwhile, the high efficiency of the algorithm and the reliability of the result are ensured. The realization of the technical effects is of great significance to the long-term health monitoring and safety evaluation of engineering structures.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application.
FIG. 1 is a schematic flow diagram of a non-dominant recombinant genetic algorithm of the present invention;
FIG. 2 is a comparative schematic diagram of the effective effects of various algorithms in an embodiment of the invention.
Detailed Description
The invention will be further described with reference to the drawings and embodiments.
The optimization of the monitoring points of the complex latticed shell structure of the stadium is realized by a sensor optimization arrangement method based on a multi-population non-dominant recombination genetic algorithm (MP-RGA), which is shown in figure 1.
The population initialization is to divide the measuring point positions into a plurality of populations (population 1, population 2..population N) in the initialization stage, and simultaneously perform genetic iterative operation to improve the optimizing capability of an algorithm, and the population initialization needs to be provided with a plurality of populations N. Theoretically, the more the number of the multiple groups is, the better, but under the condition that the total number of the groups is unchanged, the more the groups are divided, the less the number of the individuals in a single group is, and the optimal searching capability of an algorithm is seriously reduced.
The fitness is lower than the calculated fitness, the fitness value calculated by the fitness function f 1 is embodied, when the monitoring point of the complex net shell structure of the stadium is optimized in the technical scheme, the MAC matrix is constructed based on the mode vector of the position estimation of the measuring point, and the non-diagonal elements in the minimized MAC matrix are selected as the fitness, namely:
Wherein, MAC ij represents the element of the ith row and jth column in the MAC matrix; Represents the maximum value in the off-diagonal cells in the MAC matrix and X represents the sensor placement scheme. The measuring point position is the sensor position. The design objective of this fitness function is to minimize the sum of the attribute differences between the stations, thereby optimizing the station placement scheme.
Based on the measuring point positions, constructing a MAC matrix, which comprises the following steps:
Acquiring structure dynamic response data at the measuring point position, and estimating modal parameters including modal frequency, damping ratio and modal vector through signal processing;
constructing an M×M MAC matrix, wherein M is the number of identified modalities;
For each off-diagonal element (i, j) in the MAC matrix, calculating the dot product of the ith and jth modal vectors Dividing the dot product result by the product of the norms of the ith and jth modal vectors to obtain a normalized MAC value;
and filling the calculated MAC value into a corresponding position (i, j) of the MAC matrix to obtain the MAC matrix.
Reverse learning is performed by generating a reverse population corresponding to the original population, retaining individuals with fitness superior to that of the original population, and eliminating poor individuals in the original population, so that sufficient search of a solution space is realized.
The population communication is implemented through a population communication ratio alpha and a population communication frequency f, and the population communication ratio and the population communication frequency influence the evolution directions and the similarity of individuals of different species in the process of multiple species communication. And the alternating current ratio and the alternating current frequency of the population are increased, the worst population in each generation in the population obtains excellent individuals from the optimal population, and the updating speed of the worst population to the optimal population is increased.
The optimal population is the optimal population obtained by evaluating the population 1, the population 2 and the population N according to the fitness function f fit.
The worst population refers to the worst population obtained by evaluating population 1, population 2, population N according to fitness function f fit.
Improving a population refers to introducing elite individuals of an optimal population into a worst population, replacing a corresponding number of worse individuals.
The self-adaptive population size means that the size of the population is dynamically adjusted according to a scaling ratio of 0.5-1.5, when the average fitness of parent individuals of the population is better than that of parent individuals of the previous generation, the parent of the previous generation is indicated to obtain a better searching effect, and the population size can be reduced. Otherwise, poor searching effect is obtained through iteration, and the population size is increased to improve the searching capability. Specifically, the method is determined according to the fitness value and the sigmoid function and comprises the following steps:
(a) Calculating the rate of change of fitness
(B) Calculate the scaling ratio β= aigmoid (5×α) +0.5
(C) Determining updated population size G N＝GN-1 x beta
Wherein f fit_(N-1) represents the fitness value of the generation N-1, f fit_(N) represents the fitness value of the generation N, alpha represents the fitness change rate, beta represents the scaling ratio, G N-1 represents the population size of the generation N-1, and G N represents the population size of the generation N.
The self-adaptive interdigital ensures the diversity of individuals through a non-dominant recombination method, and in the self-adaptive non-dominant recombination operation, each iteration carries out non-dominant recombination on a part of individuals in the population, so as to ensure the diversity of the population and simultaneously avoid the complete destruction of excellent gene segments of the population. The proportion of non-dominant recombination can be determined by measuring the similarity of the variance of the population fitness, and the larger the similarity is, the more population individuals are subjected to non-dominant recombination, and the calculation formula is as follows:
Nr＝-ln(D(fitness))·T·Nparent
Where N r represents the number of individuals undergoing non-dominant recombination, D (fitness) represents the variance of the fitness of the parent individuals, T represents a constant of 1/20, and N parent represents the number of parent individuals of the population.
The adaptive mutation means that smaller mutation probability is adopted in the early stage of optimizing and larger mutation probability is adopted in the later stage of optimizing. The mutation strategy can ensure that the algorithm can be quickly converged to the vicinity of the optimal solution in the early stage, and is beneficial to the local convergence of the jump-out in the later stage. The adaptive conversion function also adopts a sigmoid function, and the following formula is specifically calculated.
Wherein M is a constant of 0.1, which means that the variation probability is generally not more than 0.1.
The optimal arrangement scheme is that when the preset iteration times meet the set condition fitness value and are converged, an individual with the highest fitness is selected as an optimal solution, and the optimal scheme is obtained according to the parameters of the optimal solution.
Examples
The stadium net shell roof measuring point optimizing method is applied to a space net frame roof structure of the western security international football center. The method is characterized in that 30, 50 and 100 sensors are arranged on the roof structure, and a plurality of group non-dominant recombination genetic algorithm (MP-RGA), quantum Genetic Algorithm (QGA) and particle swarm optimization algorithm (PSO) are adopted to perform measurement point optimization to obtain measurement point optimization schemes. In the comparison process, the initial population size of a plurality of non-dominant recombination genetic algorithms (MP-RGAs) is taken as 100, the total population is 3, the population alternating ratio is set to be 0.2, the population alternating frequency is set to be once in every 10 generations of alternating, and the Quantum Genetic Algorithm (QGA) and the particle swarm optimization algorithm (PSO) are taken as single populations, so the population size is taken as 300. Other parameters are set as follows, the QGA method realizes the evolution of the population by using double quantum bit codes and quantum rotation gate functions, the coding length of each gene is 10, the PSO method considers the optimal solution of each generation of the population and the optimal solution of individual history to update the population, the learning factors C1 and C2 in the updating are both 2, and the speed is limited to 10, so that the situation that the optimal solution is skipped due to overlarge movement step length is avoided. For individuals who do not meet the constraints, the QGA method and the PSO method replace with regeneration. To eliminate errors in the test procedure, the above three algorithms were run independently 3 times, and the comparison results are shown in fig. 2. The results show that if 30, 50, 100 sensors are deployed on the roof structure, the MP-RGA converges at the fastest rate, already at 200 iterations. The QGA converges at a rate of about 400 iterations. PSO converges at the slowest rate and only at 1000 times. Regarding the fitness value (f 1), the fitness value of the MP-RGA is between 0.95 and 1.0, the QGA is converged between 0.9 and 0.96, the PSO is converged between 0.7 and 0.85, and after the same number of iterations, the proposed multi-group non-dominant recombination genetic algorithm (MP-RGA) obtains a larger fitness value (f 1) than the Quantum Genetic Algorithm (QGA) and the particle swarm optimization algorithm (PSO), which indicates that the algorithm is more suitable for the measuring point arrangement of a stadium roof structure than the previous method, and the optimal measuring point optimization scheme is obtained.
It is noted that in the present invention, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The above embodiments are merely illustrative of the present invention and are not to be construed as limiting the scope of the present invention, and all designs which are the same or similar to the present invention are within the scope of the present invention.

Claims (9)

1. The venue latticed shell roof measuring point optimizing method is characterized by comprising the following steps of:
Acquiring all measuring point positions of a venue net shell roof as an initialized large population, dividing the large population into a plurality of populations, and simultaneously carrying out genetic iterative operation;
Constructing an MAC matrix based on the modal vector of the measuring point position estimation, selecting off-diagonal elements in the minimized MAC matrix as fitness functions, and taking the fitness functions as optimization targets;
presetting iteration times, cross probability and variation probability, when the iteration times meet a set value and the fitness function converges, selecting an individual with the highest fitness as an optimal solution, and determining a measuring point optimal scheme of the stadium net shell roof according to parameters of the optimal solution;
Performing genetic iterative operations on a plurality of populations using a non-dominant recombinant genetic algorithm comprising the steps of:
By generating a reverse population corresponding to the original population, retaining individuals with adaptability superior to that of the original population to obtain a new population,
Determining population ac ratio based on fitnessFrequency of group alternating currentExchanging individuals among the new populations to obtain the exchanged populations;
Identifying an optimal population and a worst population in each population in the population after communication, introducing elite individuals in the optimal population into the worst population, and replacing worse individuals in the optimal population to obtain an improved population;
updating the sizes of a plurality of populations of the optimal population, the worst population and the improved population by utilizing a self-adaptive population updating mechanism, intersecting individuals of the populations according to the similarity of variance measurement, and carrying out self-adaptive mutation treatment on the updated populations by using a sigmoid function;
and repeating the iteration process, and judging whether the iteration times reach the set conditions.
2. The venue-meshed roof measurement optimization method of claim 1, wherein the fitness function is expressed as:
;
Wherein, Elements representing the ith row and jth column of the MAC matrix; And X represents the measurement point position arrangement scheme.
3. The venue-meshed roof measurement point optimization method of claim 1, wherein the constructing a MAC matrix based on measurement point positions comprises the steps of:
Acquiring structure dynamic response data at the measuring point position, and estimating modal parameters including modal frequency, damping ratio and modal vector through signal processing;
constructing an M×M MAC matrix, wherein M is the number of identified modalities;
for each off-diagonal element (i, j) in the MAC matrix, calculating the dot product of the ith and jth modal vectors Dividing the dot product result by the product of the norms of the ith and jth modal vectors to obtain a normalized MAC value;
And filling the calculated MAC value into a corresponding position (i, j) of the MAC matrix to obtain the MAC matrix.
4. The venue latticed shell roof measurement point optimization method according to claim 1, wherein the iteration number of the non-dominant recombination genetic algorithm is initially set to be an integer greater than 1000, and expansion adjustment is performed according to the fitness convergence degree until the fitness converges;
The cross probability of the population in the non-dominant recombination genetic algorithm is determined according to the similarity of the variance measurement of the population fitness;
And the mutation probability of the population in the non-dominant recombination genetic algorithm is adaptively adjusted through a sigmoid function adaptive conversion function.
5. The venue pod roof measurement optimization method of claim 1, wherein the population size in the non-dominant reorganization algorithm is determined by a fitness value and a sigmoid function, comprising the steps of:
The adaptation degree change rate is obtained, and the calculation formula is as follows:
;
The scaling ratio is obtained, and the calculation formula is as follows:
;
the updated population size is determined, and the calculation formula is as follows:
;
Wherein, Represents the fitness value of the generation N-1,Represents the fitness value of the generation N,The rate of change of the fitness is indicated,The scale ratio is indicated as such,Represents the population size of the generation N-1,Representing the population size of the N generations.
6. The venue casing roof measurement point optimization method of claim 1, wherein the cross probability of the population in the non-dominant recombination genetic algorithm is determined according to the similarity of the variance measures of the population fitness, and the calculation formula is:
;
Where Nr represents the number of individuals undergoing non-dominant recombination, D (fitness) represents the variance of the fitness of the parent individuals, T represents a constant of 1/20, and N parent represents the number of parent individuals of the population.
7. The venue net shell roof measurement point optimization method of claim 1, wherein the mutation probability of the population in the non-dominant recombination genetic algorithm is adaptively adjusted through a sigmoid function adaptive transfer function, and the calculation formula is as follows:
;
wherein M is a constant of 0.1, and the variation probability is not more than 0.1.
8. The method of optimizing stadium net housing roof measurement points of claim 1, wherein identifying the optimal and worst population in each of the post-ac populations comprises:
Passing fitness function on population after communication And (5) evaluating the numbers to obtain an optimal population and a worst population.
9. A venue net shell roof site optimization system, comprising:
The measuring point data acquisition module is used for acquiring the positions of all measuring points of the venue net shell roof as an initialized large population, dividing the large population into a plurality of populations and simultaneously carrying out genetic iterative operation;
The system comprises a measuring point optimization analysis module, a MAC matrix constructing module, a monitoring point optimization analysis module and a monitoring point optimization analysis module, wherein the measuring point optimization analysis module constructs a venue net shell roof measuring point arrangement optimization model based on a non-dominant recombination genetic algorithm, takes the fitness of a population as an optimization target, constructs a MAC matrix based on a modal vector of measuring point position estimation, and selects off-diagonal elements in the minimized MAC matrix as fitness functions, wherein the off-diagonal elements are expressed as:
;
Wherein, Elements representing the ith row and jth column of the MAC matrix; the method comprises the steps of representing the maximum value in a non-diagonal unit in an MAC matrix, wherein X represents a measuring point position arrangement scheme, and setting the iteration times, the crossover probability and the variation probability of a non-dominant recombination genetic algorithm;
The optimization scheme acquisition module is used for selecting an individual with the highest fitness as an optimal solution when the iteration times meet a set value and the fitness value is converged, and further obtaining a measuring point optimal scheme of the stadium net shell roof;
Performing genetic iterative operations on a plurality of populations using a non-dominant recombinant genetic algorithm comprising the steps of:
By generating a reverse population corresponding to the original population, retaining individuals with adaptability superior to that of the original population to obtain a new population,
Determining population ac ratio based on fitnessFrequency of group alternating currentExchanging individuals among the new populations to obtain the exchanged populations;
Identifying an optimal population and a worst population in each population in the population after communication, introducing elite individuals in the optimal population into the worst population, and replacing worse individuals in the optimal population to obtain an improved population;
updating the sizes of a plurality of populations of the optimal population, the worst population and the improved population by utilizing a self-adaptive population updating mechanism, intersecting individuals of the populations according to the similarity of variance measurement, and carrying out self-adaptive mutation treatment on the updated populations by using a sigmoid function;
and repeating the iteration process, and judging whether the iteration times reach the set conditions.
CN202411308213.0A 2024-09-19 2024-09-19 A method and system for optimizing measurement points of venue lattice shell roof Active CN119129073B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411308213.0A CN119129073B (en) 2024-09-19 2024-09-19 A method and system for optimizing measurement points of venue lattice shell roof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411308213.0A CN119129073B (en) 2024-09-19 2024-09-19 A method and system for optimizing measurement points of venue lattice shell roof

Publications (2)

Publication Number Publication Date
CN119129073A CN119129073A (en) 2024-12-13
CN119129073B true CN119129073B (en) 2025-05-06

Family

ID=93761782

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411308213.0A Active CN119129073B (en) 2024-09-19 2024-09-19 A method and system for optimizing measurement points of venue lattice shell roof

Country Status (1)

Country Link
CN (1) CN119129073B (en)

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1166027A (en) * 1997-08-22 1999-03-09 Hisashi Shimodaira Allocation/combination method for optimum resource and its device
EP1557788B1 (en) * 2004-01-26 2008-04-16 Honda Research Institute Europe GmbH Reduction of fitness evaluations using clustering technique and neural network ensembles
US8073790B2 (en) * 2007-03-10 2011-12-06 Hendra Soetjahja Adaptive multivariate model construction
CN115409387B (en) * 2022-08-30 2023-04-18 华中科技大学 Reservoir optimal scheduling method and system based on improved differential evolution
CN115841230A (en) * 2022-12-13 2023-03-24 安徽工业大学 Emergency resource overall planning and allocating method based on improved NSGA-II algorithm
CN116579420A (en) * 2023-02-22 2023-08-11 中国人民解放军国防科技大学 Project cluster optimization method, device and system
CN117724512A (en) * 2023-12-21 2024-03-19 重庆邮电大学 A UAV path planning method based on improved sparrow search algorithm
CN118643891A (en) * 2024-07-29 2024-09-13 建投国电准格尔旗能源有限公司 A big data optimization control method and system based on genetic algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于改进遗传算法的大型体育场馆传感器优化布置研究;邢国华, 陈思锦, 苗鹏勇等;建筑科学与工程学报;20241231;第41卷(第6期);19-30 *

Also Published As

Publication number Publication date
CN119129073A (en) 2024-12-13

Similar Documents

Publication Publication Date Title
CN111199016A (en) DTW-based improved K-means daily load curve clustering method
CN106295899B (en) Wind power probability density Forecasting Methodology based on genetic algorithm Yu supporting vector quantile estimate
CN106527381B (en) A kind of fast evaluation method towards parallel batch processing machine dynamic dispatching
CN108509335A (en) Software Test Data Generation Method based on genetic algorithm optimization
CN115186803B (en) Data center calculation force load demand combination prediction method and system considering PUE
WO2023217290A1 (en) Genophenotypic prediction based on graph neural network
CN112015719A (en) Regularization and adaptive genetic algorithm-based hydrological prediction model construction method
CN114580762A (en) An error correction method for hydrological forecast based on XGBoost
CN112307672A (en) Short-term wind power prediction method based on BP neural network optimization based on cuckoo algorithm
CN117458480A (en) Photovoltaic power generation power short-term prediction method and system based on improved LOF
CN102761881A (en) Method for solving optimal coverage control set of static node in wireless sensor network
CN114707422A (en) Intelligent power check method based on load prediction
CN102760209A (en) Transmembrane helix predicting method for nonparametric membrane protein
CN119129073B (en) A method and system for optimizing measurement points of venue lattice shell roof
CN113011589B (en) Co-evolution-based hyperspectral image band selection method and system
CN115062759A (en) Fault diagnosis method based on improved long and short memory neural network
CN114997261A (en) A kind of residential power data clustering method and system
CN117829822B (en) Power transformer fault early warning method and system
CN117708690B (en) Building fire hazard prediction system and method based on artificial intelligence
CN117768273B (en) A Sparse Signal Reconstruction Method Based on Fuzzy Adaptive Genetic Algorithm
CN118039023A (en) Dynamic heterogram-based drug-target relation prediction method and system
CN112132433A (en) Multi-target brainstorm community detection method based on novelty search
CN115796237A (en) Fault prediction method for armored vehicle chassis engine based on ICSA-VS-bpNet
CN115293430A (en) Unmanned node cooperation method and system based on cooperative coevolution algorithm
CN114329702A (en) High-stability method and device for calibrating and designing reaction spectrum based on improved differential evolution 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
GR01 Patent grant