CN109815541B - Method and device for dividing rail transit vehicle product parts and modules and electronic equipment - Google Patents
Method and device for dividing rail transit vehicle product parts and modules and electronic equipment Download PDFInfo
- Publication number
- CN109815541B CN109815541B CN201811569994.3A CN201811569994A CN109815541B CN 109815541 B CN109815541 B CN 109815541B CN 201811569994 A CN201811569994 A CN 201811569994A CN 109815541 B CN109815541 B CN 109815541B
- Authority
- CN
- China
- Prior art keywords
- correlation
- module
- rail transit
- parts
- transit vehicle
- 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 86
- 239000011159 matrix material Substances 0.000 claims abstract description 89
- 230000002068 genetic effect Effects 0.000 claims abstract description 57
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 51
- 238000007621 cluster analysis Methods 0.000 claims abstract description 49
- 230000008878 coupling Effects 0.000 claims abstract description 45
- 238000010168 coupling process Methods 0.000 claims abstract description 45
- 238000005859 coupling reaction Methods 0.000 claims abstract description 45
- 230000002776 aggregation Effects 0.000 claims abstract description 30
- 238000004220 aggregation Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 238000010219 correlation analysis Methods 0.000 claims abstract description 29
- 230000006870 function Effects 0.000 claims description 44
- 210000000349 chromosome Anatomy 0.000 claims description 36
- 238000004891 communication Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 12
- 230000035772 mutation Effects 0.000 claims description 10
- 238000006116 polymerization reaction Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013486 operation strategy Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 11
- 238000011161 development Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 238000000638 solvent extraction Methods 0.000 description 5
- 238000010353 genetic engineering Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012356 Product development Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000005070 ripening Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000012916 structural analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000035899 viability Effects 0.000 description 1
Classifications
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method and a device for dividing a rail transit vehicle product part module and electronic equipment, wherein the method comprises the following steps: performing correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix; based on the part correlation matrix, dividing all the parts into different module units through genetic algorithm cluster analysis based on module internal aggregation degree and module-to-module coupling degree calculation. According to the embodiment of the invention, the correlation analysis is carried out on the parts of the rail transit vehicle product example, and on the basis of the correlation analysis, the genetic algorithm cluster analysis based on the calculation of the intra-module aggregation degree and the inter-module coupling degree is carried out on all the parts, so that the module division of all the parts is realized, the operation period of the module division can be effectively shortened, the operation efficiency is improved, and the operation accuracy is further improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of rail transit product design, in particular to a method, a device and electronic equipment for dividing rail transit vehicle product parts and modules.
Background
The rail transit gradually becomes a hot spot for urban traffic construction due to the advantages of land saving, large running energy, stable running time, safety, environmental protection and the like. With the diversification development of rail transit, the rail transit is of more and more types, and is not only widely used for long-distance land transportation, but also widely applied to medium and short-distance urban public transportation.
Along with the increasing application demands, the development force of rail transit vehicle products is also increased by related enterprises of rail transit. In the development process of rail transit vehicle products, the development efficiency can be improved by constructing a modularized product base, and in the construction process of the modularized product base, modularized analysis is the core for effectively improving the development efficiency and shortening the development period.
The modular analysis refers to the fact that on the basis of the parts of the rail transit product, all the parts are clustered and divided by analyzing the characteristics of the parts, so that different module units can be called according to different customization demands, and the rail transit vehicle product related to the corresponding parts is configured. The advantages and disadvantages of module division directly determine the advantages and disadvantages of product quality and the research and development efficiency. At present, the module division of the parts still stays in the way of dividing the parts according to design experience and traditional habit, various consideration factors and division methods of the parts combined into the modules are not researched, and the association relation among the modules after the module division is ignored, so that the product development efficiency is low, the period is long, and the reliability of the product quality can be further influenced.
Disclosure of Invention
In order to overcome the above problems or at least partially solve the above problems, embodiments of the present invention provide a method, an apparatus, and an electronic device for dividing modules of components of a rail transit vehicle product, so as to effectively shorten a calculation period of module division, improve calculation efficiency, and further improve calculation accuracy.
In a first aspect, an embodiment of the present invention provides a method for dividing a rail transit vehicle product component module, including:
performing correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix;
based on the part correlation matrix, dividing all the parts into different module units through genetic algorithm cluster analysis based on module internal aggregation degree and module-to-module coupling degree calculation.
In a second aspect, an embodiment of the present invention provides a device for dividing a component module of a rail transit vehicle product, including:
the correlation analysis module is used for carrying out correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix;
and the clustering and dividing module is used for dividing all the parts into different module units based on the part correlation matrix through genetic algorithm cluster analysis based on the module internal aggregation degree and the module coupling degree calculation.
In a third aspect, an embodiment of the present invention provides an electronic device, including: at least one memory, at least one processor, a communication interface, and a bus; the memory, the processor and the communication interface complete mutual communication through the bus, and the communication interface is used for information transmission between the electronic equipment and the rail transit vehicle product instance information equipment; the memory stores a computer program which can be run on the processor, and when the processor executes the computer program, the method for dividing the track traffic vehicle product component modules is realized.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the rail transit vehicle product part module division method according to the first aspect above.
According to the method, the device and the electronic equipment for dividing the track traffic vehicle product component modules, provided by the embodiment of the invention, the components of the track traffic vehicle product example are subjected to correlation analysis, and on the basis, all the components are subjected to genetic algorithm cluster analysis based on the calculation of the internal polymerization degree of the modules and the coupling degree between the modules, so that the module division of all the components is realized, the operation period of the module division can be effectively shortened, the operation efficiency is improved, the operation accuracy is further improved, the module division in product development is guided, the workload of a designer is reduced, the product design quality is improved, and the enterprise competitiveness is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for dividing a component module of a rail transit vehicle product according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a chromosome coding matrix in a method for dividing a component module of a rail transit vehicle product according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a genetic crossover operation in a method for partitioning component modules of a rail transit vehicle product according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the operation of the genetic uniformity variation method in the method for dividing the modules of the components of the rail transit vehicle product according to the embodiment of the invention;
FIG. 5 is a schematic flow chart of a method for dividing a component module of a rail transit vehicle product according to another embodiment of the present invention;
FIG. 6 is a schematic diagram of an algorithm flow of component cluster analysis based on a genetic algorithm in a method for partitioning component modules of a rail transit vehicle product according to an embodiment of the present invention;
Fig. 7 is a schematic structural diagram of a device for dividing a component module of a rail transit vehicle product according to an embodiment of the present invention;
fig. 8 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the embodiments of the present invention.
Aiming at the problems that in the prior art, when the module division of the parts is carried out, the operation efficiency is low, the period is long, and the operation accuracy is possibly further influenced, the method and the device for the module division of the rail transit vehicle product example are characterized in that the correlation analysis is carried out on the parts of the rail transit vehicle product example, and on the basis, the genetic algorithm cluster analysis based on the calculation of the internal aggregation degree of the modules and the coupling degree between the modules is carried out on all the parts, so that the module division of all the parts is realized, the operation period of the module division can be effectively shortened, the operation efficiency is improved, and the operation accuracy is further improved. Embodiments of the present invention will be described and illustrated below with reference to a number of embodiments.
Fig. 1 is a flow chart of a method for dividing a component module of a rail transit vehicle product according to an embodiment of the present invention, as shown in fig. 1, the method includes:
s101, carrying out correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix.
The embodiment of the invention aims to reasonably cluster the parts of the rail transit vehicle products, thereby providing convenience for developing the rail transit vehicle products. Therefore, the embodiment of the invention can identify all key parts according to the rail transit vehicle product example. Then, the correlation between these components is analyzed. For example, the independent feature correlations between the components may be analyzed from multiple aspects of the functions, structures, and physics of the components, and then the comprehensive analysis may be performed according to the independent feature correlations of the aspects to obtain a comprehensive correlation result, which may be represented as a component correlation matrix in a matrix form.
S102, dividing all parts into different module units based on the part correlation matrix through genetic algorithm cluster analysis based on the module internal aggregation degree and the module-to-module coupling degree calculation.
And on the basis of analyzing and obtaining the part correlation matrix corresponding to the rail transit vehicle product according to the steps, performing part cluster analysis based on a genetic algorithm on all parts based on the part correlation matrix. Specifically, initial cluster setting is performed according to the part correlation matrix to obtain initial modules of a plurality of clusters. And then, chromosome coding is carried out, and initialization setting of the population is carried out according to the number of parts and the number of initial modules. Meanwhile, the expressions of the objective criterion function and the fitness function in the genetic algorithm can be determined by determining the calculation form of the intra-module aggregation degree and the inter-module coupling degree. And finally, based on the setting, taking the part correlation matrix as input, performing clustering analysis based on a genetic algorithm, and outputting the maximum fitness value and the corresponding optimal individual, namely the final clustering result of all the parts. That is, all the components are divided into a plurality of different module units by cluster analysis based on a genetic algorithm.
According to the method for dividing the modules of the parts of the rail transit vehicle products, provided by the embodiment of the invention, the parts of the rail transit vehicle products are subjected to correlation analysis, and on the basis, all the parts are subjected to genetic algorithm cluster analysis based on the calculation of the intra-module aggregation degree and the inter-module coupling degree, so that the module division of all the parts is realized, the operation period of the module division can be effectively shortened, the operation efficiency is improved, and the operation accuracy is further improved.
It will be appreciated that prior to the step of cluster analysis by a genetic algorithm based on the computation of intra-module aggregation and inter-module coupling, the method of embodiments of the present invention may further comprise: based on the calculation of the intra-module aggregation degree and the inter-module coupling degree, an objective criterion function and an adaptability function of a genetic algorithm in cluster analysis are respectively constructed, and based on a part cluster analysis matrix, chromosome coding and chromosome population initialization of the genetic algorithm are respectively carried out, and a genetic operation strategy is determined.
The embodiment of the invention performs cluster analysis of the rail transit vehicle product parts based on the genetic algorithm, so that basic parameters of the genetic algorithm are set before specific application, and specifically, the method comprises target criterion function construction, chromosome coding and population initialization, fitness function construction and genetic operation strategy determination.
In the aspect of constructing the objective criterion function, the embodiment of the invention constructs the objective criterion function of the clustering analysis of the parts according to the internal aggregation degree of the modules and the coupling degree between the modules; in the aspect of constructing the fitness function, the fitness function is a standard for distinguishing the quality of individuals in the group, which is determined according to an objective function, and the larger and the better the value of the fitness function is hoped, so that the fitness function can be constructed according to the internal aggregation degree of the modules and the coupling degree among the modules; in the aspects of chromosome coding and population initialization, the part cluster analysis matrix A can be used as a chromosome coding matrix, and the part cluster analysis matrix A can be used as a chromosome for population initialization.
In practical application, when the fitness function of the target population meets the convergence rule, the algorithm is stopped, otherwise, the selection, crossing and mutation operations are needed to be further carried out, and a new chromosome is generated. It is therefore also necessary to set the genetic operating strategy of the genetic algorithm.
Optionally, according to the foregoing embodiments, the step of performing correlation analysis on a component of the rail transit vehicle product example to obtain a component correlation matrix specifically includes:
respectively establishing a functional correlation matrix based on the correlation of the functional characteristics among different parts, establishing a structural correlation matrix based on the correlation of the structural characteristics among different parts, and establishing a physical correlation matrix based on the correlation of the physical characteristics among different parts;
based on the product example, adopting an analytic hierarchy process to determine weights respectively corresponding to functional characteristics, structural characteristics and physical characteristics in the correlation among different parts;
the component correlation matrix is calculated based on the functional correlation matrix, the structural correlation matrix, the physical correlation matrix, and the weights.
It will be appreciated that the embodiments of the present invention first perform correlation analysis on components separately from functional, structural and physical aspects. Specifically:
The analysis of the functional relativity of the parts refers to that the parts realizing the same function are aggregated to form a module, so as to meet the principle of independent functions of the module as far as possible, wherein the definition of the functional relativity strength is shown in a table 1, and is an example table of the functional relativity definition of the parts according to an embodiment of the invention. Thereafter, a functional dependency matrix may be generated from the table.
TABLE 1 exemplary Table of definition of functional dependencies of Components according to one embodiment of the invention
The structural correlation analysis of the components refers to the physical connection strength between the components in space and structural relation, and the structural positioning precision such as verticality, parallelism and coaxiality, meets the principle that a module interface is easy to separate and connect, and the structural correlation strength is defined as shown in table 2, which is an example table of structural correlation definition of the components according to an embodiment of the invention. Thereafter, a structural correlation matrix may be generated from the table.
TABLE 2 exemplary Table of structural dependency definitions for parts in accordance with an embodiment of the invention
The analysis of the physical correlation of the components means that the energy flow, the information flow and the material flow are transmitted among the components, the definition of the physical correlation strength is shown in table 3, and an example table of the definition of the physical correlation of the components according to an embodiment of the invention is defined. A physical correlation matrix may then be generated from the table.
TABLE 3 physical dependency definition example Table of parts in accordance with one embodiment of the present invention
Then, because of the difference of the customization degree of different products, the correlation of three factors of functions, structures and physics is different, and the weights occupied in different types of products are also different. The rationality of weight distribution of each factor can influence the accuracy of the module dividing result, so the embodiment of the invention adopts a hierarchical analysis method to determine the weight of each correlation factor aiming at the characteristics of different types of products, and comprehensively analyzes the three correlations. The comprehensive analysis makes the determined modularized structure tree more accurate, wherein the definition of the related weight symbols is shown in table 4, and the related weight symbols are a functional, structural and physical related weight distribution example table according to an embodiment of the invention.
Table 4, example table of physical correlation weight assignment, structure, function according to one embodiment of the invention
The method comprises the steps of constructing a correlation matrix of each of three factors of functions, physics and structure among parts of a product, and obtaining a comprehensive correlation intensity matrix R after weighting, wherein the comprehensive correlation intensity matrix R is as follows:
wherein r is ij The direct correlation of any two parts in the product example can be seen through the matrix for the correlation value of any two parts i and j. Wherein r is ij The calculation formula of (2) is as follows:
r ij ＝ω 1 RF ij +ω 2 (ω 21 RC ij +ω 22 RL ij )+ω 3 (ω 31 RE ij +ω 32 RM ij +ω 33 RS ij )；
in RF ij For the functional correlation strength, RC ij And RL(s) ij Representing the coupling and shape phase intensities, RE, respectively, in the structural correlation ij ，RM ij And RS (reed-solomon) ij The energy flow, material flow and information flow correlation intensities in the physical correlation are represented respectively.
Wherein, when the objective criterion function is constructed, the example of the rail transit vehicle product is composed of n key parts, which can be expressed as P= { P 1 ，P 2 ，…，P n N parts are initially clustered into l initial modules m= { M 1 ，M 2 ，…，M l }. The number of parts in the module i is N i Since different components cannot occur in the same module, p=m 1 ∪M 2 ∪...∪M l ，The initial module after initial clustering by parts can be formally expressed as:
wherein A= [ a ] ij ] l×n Representing a component cluster analysis matrix, wherein a ij =1 or 0, a ij =1 represents part P j Belonging to the initial module M i ，a ij =0 denotes part P j Not belonging to the initial module M i 。
Wherein,
according to the embodiment of the invention, the objective criterion function of the clustering analysis of the parts is constructed according to the internal aggregation degree of the modules and the coupling degree between the modules, wherein the step of calculating the internal aggregation degree of the modules specifically comprises the following steps:
assume module M u The corresponding module cluster analysis vector is a u ＝[a u1 ,a u2 ,…,a ui ,…,a un ]Then it can be based on the initial module M u Corresponding module cluster analysis vector, calculating initial module M according to the following formula u Internal degree of polymerization of (2):
on this basis, the total degree of polymerization of a total of l initial modules can be calculated as follows:
wherein f u Representation module M u Internal degree of polymerization of a) ui Representing the value of the ith column of the ith row in the component cluster analysis matrix A, r ij Representing the correlation value of any two components i and j, F 1 The total polymerization degree of the l modules is represented.
For calculation of the coupling degree between the modules, the coupling degree between any two modules can be measured by the total association degree between all parts in one module and all parts in the other module. For example, assume module M p And M q The corresponding module dividing vectors are respectively a p ＝[a p1 ,a p2 ,…,a pi ,…,a pn ]And a q ＝[a q1 ,a q2 ,…,a qi ,…,a qn ]The step of calculating the degree of coupling between the modules may specifically include:
based on the initial module M p Corresponding module cluster analysis vector a p ＝[a p1 ,a p2 ,…,a p i,…,a pn ]And an initial module M q Corresponding module cluster analysis vector a q ＝[a q1 ,a q2 ,…,a q i,…,a qn ]The initial module M can be calculated as follows u And an initial module M q Degree of coupling between:
based on this, the total coupling between the total of l initial modules can be calculated as follows:
wherein f pq Representation module M p Sum module M q Degree of coupling between a pi Representation module M p The values of the ith row and ith column in row and column a, a qj Representation module M q The value of the jth column of the qth row in the cluster analysis matrix a, r ij Representing the correlation value of any two components i and j, F 2 Indicating the total coupling between the i modules.
Thus, according to the above embodiments, according to the basic principle of "internal high aggregation degree, external low coupling degree" of component clustering analysis, the step of constructing the objective criterion function based on the calculation of the internal aggregation degree of the module and the coupling degree between the modules may specifically include:
based on the total aggregation and total coupling of the total of l initial modules, the objective criterion function is constructed as follows:
in the aspect of chromosome coding and population initialization, according to the component cluster analysis matrix A= [ a ] ij ] l×n The matrix is made up of n elements, where a ij =1 or 0, which represents P j Whether or not it belongs to M i 。a ij =1 represents P j Belonging to M i ，a ij =0 denotes P j Not of M i And matrix a must satisfy:
wherein N is i Representing the number of components in module i.
According to the conditions, the component cluster analysis matrix A is taken as a chromosome coding matrix. Fig. 2 is a schematic diagram of a chromosome coding matrix in a method for dividing a component module of a rail transit vehicle product according to an embodiment of the present invention, where, as shown in fig. 2, each row in the matrix represents a clustering module, each column includes a component, and the component arrangement sequence is kept consistent with the element arrangement sequence in the dividing matrix, and in a genetic algorithm, a component cluster analysis matrix is equivalent to a chromosome.
Initializing a population by taking a part cluster analysis matrix A as a chromosome, and for any chromosome A i N columns are included, each column containing l elements, where i=1, 2, …, m, m represents the population number. According to the condition that the matrix A must meet, n columns in the matrix are sequentially and randomly assigned so that one element in each column is 1 and the rest elements are 0, and the chromosome A is obtained i . Too small a population may cause premature ripening, too large a population may reduce the computational efficiency, and the chromosome population is usually selected to be m=50-300.
In terms of the construction of fitness functions, it can be understood that fitness is a main index describing the performance of an individual in a genetic algorithm, and the individual is subjected to the superior and inferior elimination according to the size of the fitness. Fitness is the motive force driving genetic algorithms. From a biological perspective, fitness corresponds to the viability of "competing for survival, surviving the fittest" organism, and is of great importance in genetic processes.
In the genetic algorithm, the objective criterion function consisting of the internal aggregation degree of the modules and the coupling degree between the modules is the minimum value, and the objective of the fitness function is the maximum value. Thus, the fitness function of the target chromosome can be expressed as:
F(i)＝1/F 0 (i)；
Wherein F (i) is the fitness function value of the ith chromosome in the target population, F 0 (i) For the criterion function value of the ith chromosome in the target population, i=1, 2, …, m, m represents the population number.
The fitness function is a criterion for distinguishing between the quality of an individual in a population, which is determined from an objective function, and is always non-negative, in any case the larger its value is desired to be the better. When the fitness function of the target population meets the convergence rule, stopping the algorithm, and outputting an optimal modularized processing result; otherwise, further selecting, crossing, mutating and the like to generate a new chromosome.
Common genetic manipulations are selection, crossover and mutation in the determination of genetic manipulation strategies. Selecting preferred individuals from the population according to the fitness function value of the individuals in the population, eliminating inferior individuals, and increasing the probability of being selected as the fitness of the individuals is increased. Thus, according to the above embodiments, the step of determining the genetic manipulation strategy may specifically comprise: the probability of selection in the genetic algorithm is calculated as follows:
wherein, P (i) represents the selection probability of the ith target chromosome, F (k) represents the fitness value of the kth chromosome in the target population, and i, k=1, 2, …, m, m represent the population number;
In order to select mating individuals, selecting the selection probability of each individual in the population according to the formula P (i), carrying out multiple rounds of selection, generating a uniform random number between 0 and 1 for each round, selecting the next generation of individuals according to the size of the random number, carrying out crossover and mutation operation on the next generation of individuals, wherein common genetic operation comprises a single-point crossover method and a random uniform mutation method, and the specific method is as follows:
single point crossover method: fig. 3 is a schematic diagram of genetic crossover operation in the method for partitioning the components of the rail transit vehicle product according to the embodiment of the present invention, as shown in fig. 3, where one crossover point is taken between two parent chromosomes, and codes located on the right side of the crossover point position in the two parent chromosomes are swapped, so as to generate two child chromosomes.
Random uniform mutation method: FIG. 4 is a schematic diagram illustrating the operation of a genetic uniformity variation method in a method for dividing a component module of a rail transit vehicle product according to an embodiment of the present invention, wherein a parent chromosome is randomly selected according to a variation rate, then a variation point is randomly selected to produce a variation code, remaining row and column elements are kept unchanged, and a child chromosome is generated and replaced with the parent chromosome as shown in FIG. 4.
In order to further illustrate the technical solution of the embodiments of the present invention, the embodiments of the present invention provide the following processing flows according to the above embodiments, but do not limit the protection scope of the embodiments of the present invention.
Fig. 5 is a flow chart of a method for dividing a component module of a rail transit vehicle product according to another embodiment of the present invention, as shown in fig. 5, in the embodiment of the present invention, a design BOM of an a-type subway product is taken as input for several typical cities, and the component of the a-type subway bogie is divided in a modularized manner by component correlation analysis and component cluster analysis based on a genetic algorithm.
Specifically, 26 parts of the bogie were first identified according to the bogie design BOM, as shown in Table 5, which is a list of bogie parts identified according to an embodiment of the present invention.
TABLE 5 list of identified truck components according to an embodiment of the invention
And then, carrying out function, physical and structural analysis on the parts, and respectively constructing functional, physical and structural correlation matrixes of the bogie parts. Meanwhile, the weight value of each correlation is determined by an analytic hierarchy process, as shown in table 6, which is a table of weight values of functional, physical and structural correlations according to an embodiment of the present invention.
TABLE 6 weight value Table of functional, physical and structural dependencies according to one embodiment of the invention
| Correlation of | Weighting of | Weight value |
| Functional relevance | ω 1 | 0.537 |
| Physical correlation | ω 2 | 0.358 |
| Structural correlation | ω 3 | 0.105 |
The functional, physical and structural correlation matrices may then be weighted summed to obtain a composite correlation matrix.
Still further, a bogie component cluster analysis may be performed based on a genetic algorithm. Fig. 6 is a schematic flowchart of an algorithm of component cluster analysis based on a genetic algorithm in a method for partitioning a component module of a rail transit vehicle product according to an embodiment of the present invention, including the steps of:
(1) Genetic algorithm initial condition determination
The dividing number range of the bogie modules can be determined to be 4-8 more reasonable according to the bogie related data and the analysis of the practical application situation.
The number of population individuals is 200, the crossover probability is 0.99, the variation probability is 0.05, and the iteration number is 2000 (result convergence) according to the related data of the genetic algorithm.
(2) Establishing an initial population
And establishing a matrix of m x n by the number of modules and the number of parts, wherein m is the number of modules, and n is the number of parts. Individuals were randomly assigned to the requirement that the sum of each column was equal to 1, and a random matrix of 200 population individuals was randomly generated in total, taking m=7, n=26 as an example. Taking cell array A1 as an initial population, A1 contains 200 random matrices.
(3) Calculating fitness
And solving an objective function of 200 individuals in the initial population A1, and then bringing the corresponding objective function value into an fitness calculation formula to obtain fitness values of 200 individuals, and storing the fitness values by using a cell array F0.
(4) Selection of excellent individuals
And selecting individuals with larger fitness from the population A1 by using a roulette algorithm to form a new population A2.
(5) Individuals cross each other
Individuals are grouped in pairs, i.e., individuals 1 and 2 are grouped in pairs, individuals 3 and 4 are grouped in pairs … …, 199 and 200. And randomly generating 1 numerical value (0-1), and comparing the numerical value with the crossover probability to judge whether crossover behavior occurs. The crossover occurs, the crossover points are randomly selected for two individuals in the same group, and the matrix after the crossover points is exchanged to generate 2 new individuals. All new individuals constitute population A3.
(6) Individual variation
And randomly generating 1 numerical value (0-1), and comparing the numerical value with the mutation probability to judge whether mutation behaviors occur. The variation occurs by randomly selecting a certain column, and randomly changing the position of the row for the row where the column number 1 is located. The newly generated individuals and individuals who have not undergone mutation form a new population A4.
(7) Judgment of iteration times
And judging the magnitude relation between the iterated times and the iterative times. And (5) continuing iteration if the number of times is less than 2000, and repeating the steps (3) to (6).
(8) Outputting the maximum fitness value and the optimal individual
The number of modules is 4-8, the genetic algorithm is carried in, the operation result is shown in table 7, and the maximum adaptability value corresponding table when the number of modules is 4-8 according to one embodiment of the invention.
TABLE 7 maximum fitness value correspondence table for a number of modules of 4-8 according to one embodiment of the invention
| Sequence number | Number of modules | Maximum fitness value |
| 1 | 4 | 2.4762*10 3 |
| 2 | 5 | 3.8529*10 3 |
| 3 | 6 | 4.2576*10 3 |
| 4 | 7 | 4.6481*10 3 |
| 5 | 8 | 4.3648*10 3 |
The comparison is made that the individual fitness value is maximum when the number of modules m=7. The optimal individual at m=7 is taken as the optimal result of the genetic algorithm, as shown in table 8, which is the result of the cluster analysis at 7 modules according to one embodiment of the present invention.
TABLE 8 clustering analysis results at a module count of 7 in accordance with one embodiment of the invention
| Module | The modules comprising part numbers |
| 1 | 4,5,6 |
| 2 | 22,23 |
| 3 | 24,25,26 |
| 4 | 11,12,13,14,15 |
| 5 | 16,17,18,19,20,21 |
| 6 | 7,8,9,10 |
| 7 | 1,2,3 |
Table 8 shows the results of clustering analysis of the A-type subway product bogie components by the method of the embodiment of the invention, wherein all 26 components are divided into 7 modules, and the whole processing process has short operation period and high efficiency.
As another aspect of the embodiments of the present invention, the embodiments of the present invention provide a rail transit vehicle product component module dividing apparatus according to the above embodiments, which is used to achieve the module division of the rail transit vehicle product component in the above embodiments. Therefore, the descriptions and definitions in the method for dividing the component modules of the rail transit vehicle product in the above embodiments may be used for understanding each execution module in the embodiment of the present invention, and specific reference may be made to the above embodiments, which are not repeated herein.
According to an embodiment of the present invention, a structure of a rail transit vehicle product component module dividing device is shown in fig. 7, which is a schematic structural diagram of the rail transit vehicle product component module dividing device provided by the embodiment of the present invention, where the device may be used to implement the module division of the rail transit vehicle product component in the above method embodiments, and the device includes: a relevance analysis module 701 and a cluster partitioning module 702. Wherein:
the correlation analysis module 701 is configured to perform correlation analysis on components of the rail transit vehicle product instance, and obtain a component correlation matrix; the cluster division module 702 is configured to divide all parts into different module units based on the part correlation matrix through genetic algorithm cluster analysis based on the intra-module aggregation degree and inter-module coupling degree calculation.
Specifically, the correlation analysis module 701 may first identify all critical components based on rail transit vehicle product instances. The correlation analysis module 701 then analyzes the correlation between the components. For example, the independent feature correlations between the components may be analyzed from multiple aspects of the functions, structures, and physics of the components, and then the comprehensive analysis may be performed according to the independent feature correlations of the aspects to obtain a comprehensive correlation result, which may be represented as a component correlation matrix in a matrix form.
Thereafter, the cluster classification module 702 may perform component cluster analysis based on a genetic algorithm on all components based on the component correlation matrix. Specifically, first, the cluster classification module 702 performs initial cluster setting according to the part correlation matrix, and obtains an initial module of a plurality of clusters. Then, the cluster division module 702 performs chromosome coding, and performs initialization setting of the population according to the number of parts and the number of initial modules. Meanwhile, the expressions of the objective criterion function and the fitness function in the genetic algorithm can be determined by determining the calculation form of the intra-module aggregation degree and the inter-module coupling degree. Finally, based on the setting, the clustering module 702 takes the part correlation matrix as input, performs clustering analysis based on a genetic algorithm, and outputs the maximum fitness value and the corresponding optimal individual, namely the final clustering result of all parts. That is, all the components are divided into a plurality of different module units by cluster analysis based on a genetic algorithm.
According to the device for dividing the modules of the components of the rail transit vehicle products, provided by the embodiment of the invention, the corresponding execution modules are arranged to perform correlation analysis on the components of the rail transit vehicle product examples, and on the basis, genetic algorithm cluster analysis based on the calculation of the intra-module aggregation degree and the inter-module coupling degree is performed on all the components, so that the module division of all the components is realized, the operation period of the module division can be effectively shortened, the operation efficiency is improved, and the operation accuracy is further improved.
It will be appreciated that in embodiments of the present invention, each of the relevant program modules in the apparatus of each of the above embodiments may be implemented by a hardware processor (hardware processor). In addition, the device for dividing the track traffic vehicle product component module according to the embodiment of the present invention can implement the process of dividing the track traffic vehicle product component module according to the above method embodiments by using the above program modules, and when the device is used for implementing the division of the track traffic vehicle product component module according to the above method embodiments, the beneficial effects generated by the device according to the embodiment of the present invention are the same as those generated by the corresponding method embodiments, and reference may be made to the method embodiments, which are not repeated herein.
As still another aspect of the embodiments of the present invention, this embodiment provides an electronic device according to the foregoing embodiments, referring to fig. 8, which is a schematic entity structure diagram of the electronic device provided by the embodiment of the present invention, including: at least one memory 801, at least one processor 802, a communication interface 803, and a bus 804.
The memory 801, the processor 802 and the communication interface 803 complete communication with each other through the bus 804, and the communication interface 803 is used for information transmission between the electronic device and the rail transit vehicle product example information device; the memory 801 stores a computer program executable on the processor 802, and when the processor 802 executes the computer program, the method for dividing the components of the rail transit vehicle product according to the above embodiments is implemented.
It should be understood that the electronic device at least includes a memory 801, a processor 802, a communication interface 803 and a bus 804, where the memory 801, the processor 802 and the communication interface 803 form a communication connection with each other through the bus 804, and can perform communication with each other, for example, the processor 802 reads program instructions of the component module dividing method of the rail transit vehicle product from the memory 801. In addition, the communication interface 803 can also realize communication connection between the electronic device and the rail transit vehicle product instance information device, and can complete information transmission between the electronic device and the rail transit vehicle product instance information device, such as module division of rail transit vehicle product components and the like through the communication interface 803.
When the electronic device is running, the processor 802 invokes program instructions in the memory 801 to perform the methods provided in the above method embodiments, for example, including: performing correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix; based on the part correlation matrix, all parts are divided into different module units and the like through genetic algorithm cluster analysis based on the module internal aggregation degree and the module coupling degree calculation.
The program instructions in the memory 801 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Alternatively, all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program when executed performs steps including the above method embodiments; and the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Embodiments of the present invention also provide a non-transitory computer readable storage medium according to the above embodiments, where the non-transitory computer readable storage medium stores computer instructions that cause a computer to execute the method for dividing a rail transit vehicle product component module according to the above embodiments, for example, including: performing correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix; based on the part correlation matrix, all parts are divided into different module units and the like through genetic algorithm cluster analysis based on the module internal aggregation degree and the module coupling degree calculation.
The electronic equipment and the non-transitory computer readable storage medium provided by the embodiment of the invention perform correlation analysis on the parts of the rail transit vehicle product instance by executing the method for dividing the parts of the rail transit vehicle product module, and perform genetic algorithm cluster analysis based on the calculation of the intra-module aggregation degree and the inter-module coupling degree on all the parts on the basis, so that the module division of all the parts is realized, the operation period of the module division can be effectively shortened, the operation efficiency is improved, and the operation accuracy is further improved.
It will be appreciated that the embodiments of the apparatus, electronic device and storage medium described above are merely illustrative, wherein the elements illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over different network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a usb disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc., and includes several instructions for causing a computer device (such as a personal computer, a server, or a network device, etc.) to execute the method described in the foregoing method embodiments or some parts of the method embodiments.
In addition, it will be understood by those skilled in the art that 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. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the description of the embodiments of the invention, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description. Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects.
However, the disclosed method should not be construed as reflecting the intention that: i.e., an embodiment of the invention that is claimed, requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the embodiments of the present invention, and are not limited thereto; although embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for dividing a rail transit vehicle product component module, comprising:
Performing correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix; the method for carrying out correlation analysis on the components of the rail transit vehicle product example further comprises the following steps: identifying components included in the rail transit vehicle product instance;
dividing all the parts into different module units through genetic algorithm cluster analysis based on module internal aggregation degree and module-to-module coupling degree calculation based on the part correlation matrix;
the step of performing correlation analysis on the components of the rail transit vehicle product example to obtain the component correlation matrix specifically comprises the following steps:
respectively establishing a functional correlation matrix based on the correlation of the functional characteristics among different parts, establishing a structural correlation matrix based on the correlation of the structural characteristics among different parts, and establishing a physical correlation matrix based on the correlation of the physical characteristics among different parts;
based on the product example, determining weights respectively corresponding to the functional characteristic, the structural characteristic and the physical characteristic in the correlation among different parts by adopting an analytic hierarchy process;
calculating the part correlation matrix based on the functional correlation matrix, the structural correlation matrix, the physical correlation matrix and the weights;
The component correlation matrix is expressed as:
wherein r is ij Is the correlation value of any two parts i and j, wherein r is as follows ij The calculation formula of (2) is as follows:
r ij ＝ω 1 RF ij +ω 2 (ω 21 RC ij +ω 22 RL ij )+ω 3 (ω 31 RE ij +ω 32 RM ij +ω 33 RS ij )
in RF ij For the functional correlation strength, RC ij And RL(s) ij Representing the coupling and shape phase intensities, RE, respectively, in the structural correlation ij ，RM ij And RS (reed-solomon) ij Respectively representing the energy flow, the material flow and the information flow correlation intensity in the physical correlation; omega 1 For weights corresponding to functional characteristics, ω 2 For weights corresponding to structural characteristics, ω 3 Weights corresponding to physical characteristics，ω 21 Is the weight, omega corresponding to the connection relation in the structural correlation 22 Is the weight, omega corresponding to the shape and position relation in the structural correlation 31 Is the weight, omega, corresponding to the energy flow in the physical correlation 32 Is the weight, omega, corresponding to the material flow in the physical correlation 33 Is the weight corresponding to the information flow in the physical correlation.
2. The method according to claim 1, further comprising, prior to the step of clustering analysis by a genetic algorithm calculated based on intra-module aggregation and inter-module coupling:
based on the calculation of the intra-module aggregation degree and the inter-module coupling degree, an objective criterion function and an adaptability function of a genetic algorithm in cluster analysis are respectively constructed, and based on a part cluster analysis matrix, chromosome coding and chromosome population initialization of the genetic algorithm are respectively carried out, and a genetic operation strategy is determined.
3. The method according to claim 2, characterized in that it is assumed that the rail transit vehicle production instance consists of n critical components, denoted as p= { P 1 ，P 2 ，…，P n N parts are initially clustered into l initial modules m= { M 1 ，M 2 ，…，M l The initial module after initial clustering of the parts is expressed as:
wherein A= [ a ] ij ] l×n Representing the component cluster analysis matrix, wherein a ij =1 or 0, a ij =1 represents part P j Belonging to the initial module M i ，a ij =0 denotes part P j Not belonging to the initial module M i ；
The step of calculating the polymerization degree inside the module specifically includes:
based on the initial module M u Corresponding module cluster analysis vector a u ＝[a u1 ,a u2 ,…,a ui ,…,a un ]The initial module M is calculated according to the following method u Internal degree of polymerization of (2):
and calculating the total polymerization degree of the initial modules according to the following formula:
wherein f u Representation module M u Internal degree of polymerization of a) ui Representing the value of the ith column of the ith row in the component cluster analysis matrix A, r ij Representing the correlation value of any two components i and j, F 1 The total polymerization degree of the l modules is represented.
4. A method according to claim 3, wherein the step of calculating the degree of coupling between the modules comprises:
based on the initial module M p Corresponding module cluster analysis vector a p ＝[a p1 ,a p2 ,…,a pi ,…,a pn ]And an initial module M q Corresponding module cluster analysis vector a q ＝[a q1 ,a q2 ,…,a qi ,…,a qn ]The initial module M is calculated according to the following method p And an initial module M q Degree of coupling between:
and calculating the total coupling degree among the l initial modules according to the following formula:
wherein f pq Representation module M p Sum module M q Degree of coupling between a pi Representation module M p The values of the ith row and ith column in row and column a, a qj Representation module M q The value of the jth column of the qth row in the cluster analysis matrix a, r ij Representing the correlation value of any two components i and j, F 2 Indicating the total coupling between the i modules.
5. The method of claim 4, wherein the step of constructing the objective criterion function based on the calculation of the intra-module aggregation level and the inter-module coupling level comprises:
based on the total degree of aggregation and the total degree of coupling, constructing the objective criterion function as follows:
6. the method according to claim 2, wherein the step of determining a genetic operating strategy comprises in particular:
the probability of selection in the genetic algorithm is calculated as follows:
wherein, P (i) represents the selection probability of the ith target chromosome, F (k) represents the fitness value of the kth chromosome in the target population, and i, k=1, 2, …, m, m represent the population number;
and determining to adopt a single-point crossover method to carry out chromosome crossover operation and adopting a random uniform mutation method to carry out chromosome mutation operation.
7. A rail transit vehicle product component module dividing apparatus, comprising:
the correlation analysis module is used for carrying out correlation analysis on the parts of the rail transit vehicle product example to obtain a part correlation matrix; the method for carrying out correlation analysis on the components of the rail transit vehicle product example further comprises the following steps: identifying components included in the rail transit vehicle product instance;
the clustering division module is used for dividing all the parts into different module units based on the part correlation matrix through genetic algorithm cluster analysis based on the module internal aggregation degree and the module coupling degree calculation;
the correlation analysis module is specifically configured to:
respectively establishing a functional correlation matrix based on the correlation of the functional characteristics among different parts, establishing a structural correlation matrix based on the correlation of the structural characteristics among different parts, and establishing a physical correlation matrix based on the correlation of the physical characteristics among different parts;
based on the product example, determining weights respectively corresponding to the functional characteristic, the structural characteristic and the physical characteristic in the correlation among different parts by adopting an analytic hierarchy process;
Calculating the part correlation matrix based on the functional correlation matrix, the structural correlation matrix, the physical correlation matrix and the weights;
the component correlation matrix is expressed as:
wherein r is ij Is the correlation value of any two parts i and j, wherein r is as follows ij The calculation formula of (2) is as follows:
r ij ＝ω 1 RF ij +ω 2 (ω 21 RC ij +ω 22 RL ij )+ω 3 (ω 31 RE ij +ω 32 RM ij +ω 33 RS ij )
in RF ij For the functional correlation strength, RC ij And RL(s) ij Representing the coupling and shape phase intensities, RE, respectively, in the structural correlation ij ，RM ij And RS (reed-solomon) ij Respectively representing the energy flow, the material flow and the information flow correlation intensity in the physical correlation; omega 1 For weights corresponding to functional characteristics, ω 2 For weights corresponding to structural characteristics, ω 3 Weight, ω, corresponding to physical characteristics 21 Is the weight, omega corresponding to the connection relation in the structural correlation 22 Is the weight, omega corresponding to the shape and position relation in the structural correlation 31 Is the weight, omega, corresponding to the energy flow in the physical correlation 32 Is the weight, omega, corresponding to the material flow in the physical correlation 33 Is the weight corresponding to the information flow in the physical correlation.
8. An electronic device, comprising: at least one memory, at least one processor, a communication interface, and a bus;
the memory, the processor and the communication interface complete the communication among each other through the bus, and the communication interface is also used for information transmission between the electronic equipment and the rail transit vehicle product instance information equipment;
Stored in the memory is a computer program executable on the processor, which when executed, implements the method according to any one of claims 1 to 6.
9. A non-transitory computer readable storage medium storing computer instructions that cause the computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811569994.3A CN109815541B (en) | 2018-12-21 | 2018-12-21 | Method and device for dividing rail transit vehicle product parts and modules and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811569994.3A CN109815541B (en) | 2018-12-21 | 2018-12-21 | Method and device for dividing rail transit vehicle product parts and modules and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109815541A CN109815541A (en) | 2019-05-28 |
| CN109815541B true CN109815541B (en) | 2023-11-28 |
Family
ID=66602191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811569994.3A Active CN109815541B (en) | 2018-12-21 | 2018-12-21 | Method and device for dividing rail transit vehicle product parts and modules and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109815541B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209941B (en) * | 2019-12-30 | 2024-04-26 | 中车工业研究院有限公司 | Product module type identification method and device |
| CN112633994B (en) * | 2020-11-20 | 2023-04-18 | 西南交通大学 | Rail transit vehicle product platform planning method |
| CN112612926B (en) * | 2020-11-20 | 2022-07-12 | 西南交通大学 | Method for constructing modular structure tree of rail transit vehicle product |
| CN113450194B (en) * | 2020-11-20 | 2023-04-18 | 西南交通大学 | Rail transit vehicle product platform construction method |
| CN113191457A (en) * | 2021-05-26 | 2021-07-30 | 重庆高新技术产业研究院有限责任公司 | Production data and BOM automatic classification gathering method applied to manufacturing enterprises |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779078A (en) * | 2016-12-21 | 2017-05-31 | 武汉科技大学 | A kind of intelligent modularized method of product structure |
| CN107992717A (en) * | 2018-01-16 | 2018-05-04 | 华东交通大学 | A kind of suspension hook group module partition method for considering any intermodule incidence relation two-by-two |
-
2018
- 2018-12-21 CN CN201811569994.3A patent/CN109815541B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779078A (en) * | 2016-12-21 | 2017-05-31 | 武汉科技大学 | A kind of intelligent modularized method of product structure |
| CN107992717A (en) * | 2018-01-16 | 2018-05-04 | 华东交通大学 | A kind of suspension hook group module partition method for considering any intermodule incidence relation two-by-two |
Non-Patent Citations (4)
| Title |
|---|
| Research on a Genetic Algorithm for Solving Module Partition Problem;Junyou Shi et al.;《2010 Sixth International Conference on Natural Computation》;20101231;全文 * |
| 刘电霆.绿色设计中产品模块划分的不确定优化及GA求解.《桂林理工大学学报》.2013,第33卷(第4期),第1-4节. * |
| 基于解析结构模型的产品模块构建及其优化;丁力平 等;《计算机集成制造系统》;20080630;第14卷(第6期);第1-3节 * |
| 绿色设计中产品模块划分的不确定优化及GA求解;刘电霆;《桂林理工大学学报》;20131130;第33卷(第4期);第1-4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109815541A (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815541B (en) | Method and device for dividing rail transit vehicle product parts and modules and electronic equipment | |
| AU2024200810A1 (en) | Training tree-based machine-learning modeling algorithms for predicting outputs and generating explanatory data | |
| Scrucca | GA: A package for genetic algorithms in R | |
| Taboada et al. | Practical solutions for multi-objective optimization: An application to system reliability design problems | |
| CN102063339B (en) | Resource load balancing method and equipment based on cloud computing system | |
| CN111612252B (en) | Automatic site selection method and device for large-scale emergency facilities and readable storage medium | |
| CN102902772B (en) | Web community discovery method based on multi-objective optimization | |
| CN104035816A (en) | Cloud computing task scheduling method based on improved NSGA-II | |
| CN109816474B (en) | Modular configuration method and device of rail transit product and electronic equipment | |
| CN112785005B (en) | Multi-objective task assistant decision-making method and device, computer equipment and medium | |
| CN105512755A (en) | Decomposition-based multi-objective distribution estimation optimization method | |
| CN117077981B (en) | Method and device for distributing stand by fusing neighborhood search variation and differential evolution | |
| CN110390014A (en) | A kind of Topics Crawling method, apparatus and storage medium | |
| CN108846480B (en) | Multi-specification one-dimensional nesting method and device based on genetic algorithm | |
| Han et al. | An efficient genetic algorithm for optimization problems with time-consuming fitness evaluation | |
| CN102708298B (en) | A kind of Vehicular communication system electromagnetic compatibility index distribution method | |
| Shirmohammady et al. | PPI‐GA: A Novel Clustering Algorithm to Identify Protein Complexes within Protein‐Protein Interaction Networks Using Genetic Algorithm | |
| CN110972060B (en) | Deployment method of edge control center accessed to terminal on power communication network | |
| CN110189230B (en) | Construction method of analytic model of dynamic partition | |
| CN104809098A (en) | Method and device for determining statistical model parameter based on expectation-maximization algorithm | |
| Fedorchenko et al. | Modified genetic algorithm to determine the location of the distribution power supply networks in the city | |
| Saeheaw et al. | A comparative study among different parallel hybrid artificial intelligent approaches to solve the capacitated vehicle routing problem | |
| CN116011071A (en) | Method and system for analyzing structural reliability of air building machine based on active learning | |
| Tlusty | Casting polymer nets to optimize noisy molecular codes | |
| CN110162704B (en) | Multi-scale key user extraction method based on multi-factor genetic 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 |