CN111950204B - Hinge structure optimization method and device, computer equipment and storage medium - Google Patents
Hinge structure optimization method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111950204B CN111950204B CN202010814004.9A CN202010814004A CN111950204B CN 111950204 B CN111950204 B CN 111950204B CN 202010814004 A CN202010814004 A CN 202010814004A CN 111950204 B CN111950204 B CN 111950204B
- Authority
- CN
- China
- Prior art keywords
- opening
- target
- individual
- current
- population
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Genetics & Genomics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Physiology (AREA)
- Computational Mathematics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Feedback Control In General (AREA)
Abstract
The embodiment of the invention discloses a method and a device for optimizing a hinge structure, computer equipment and a storage medium, wherein the method comprises the following steps: establishing a multi-body dynamic model of the hinge and the opening and closing piece; acquiring a corresponding relation between an independent variable of an elastic component in the hinge and a dependent variable of an opening and closing piece; establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model; determining a target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to an ergonomic principle; constructing a multi-objective optimization genetic algorithm model according to independent variables of elastic components in the hinge and an optimization target of the opening and closing piece; and determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model. According to the technical scheme of the embodiment of the invention, the application operating force of the hinge structure can be optimized on the premise of ensuring the universality of the hinge structure, so that the operation comfort of the hinge structure is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a hinge structure optimization method and device, computer equipment and a storage medium.
Background
The hinge is also called a hinge, is used for connecting two solids and allowing a mechanical device to rotate relatively between the two solids, and can be widely applied to moving parts such as automobile parts, furniture and the like.
In order to improve the universality of the hinge structure and enable the hinge to be suitable for more accessories or houses, the hinge structure needs to be designed in a universal way. For example, the main body part of the hinge is subjected to platform processing, and the connecting part is subjected to universality processing to form a universal connecting part, so that the hinge can be combined according to styles of different application parts, for example, different hinges can be combined according to different vehicle types, and the effects of low combination cost and flexible design can be achieved. Or the different opening angles of the hinge are realized by adding the limiting blocks with different diameters on the hinge, so that the hinge is universal for different application parts.
In the process of implementing the invention, the inventor finds that the prior art has the following defects: the influence of the universal design of the hinge on the operation comfort is not considered in the conventional universal design scheme of the hinge. In fact, for different application components, the dead weight of the hinged moving part, the distance between the action point of the operation force and the hinge fixing point, namely the arm of the operation force is different, so that the operation force of a new component is difficult to meet the requirements of human engineering, the comfort level is reduced, and the product quality is reduced.
Disclosure of Invention
The embodiment of the invention provides a hinge structure optimization method and device, computer equipment and a storage medium, which can optimize the application operating force of the hinge structure on the premise of ensuring the universality of the hinge structure, thereby improving the operation comfort of the hinge structure.
In a first aspect, an embodiment of the present invention provides a method for optimizing a hinge structure, including:
establishing a multi-body dynamic model of the hinge and the opening and closing piece;
acquiring a corresponding relation between an independent variable of an elastic component in the hinge and a dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force;
establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model;
determining the target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to an ergonomic principle;
constructing a multi-objective optimization genetic algorithm model according to independent variables of elastic components in the hinge and an optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force;
and determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model.
In a second aspect, an embodiment of the present invention further provides an optimization apparatus for a hinge structure, including:
the multi-body dynamic model building module is used for building a multi-body dynamic model of the hinge and the opening and closing piece;
the corresponding relation acquisition module is used for acquiring the corresponding relation between the independent variable of the elastic component in the hinge and the dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force;
the opening and closing force calculation module is used for establishing a neural network model according to the corresponding relation and calculating the opening and closing force corresponding to different pre-deformation amounts according to the neural network model;
the target opening and closing force determining module is used for determining the target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to the man-machine engineering principle;
the genetic algorithm model building module is used for building a multi-objective optimization genetic algorithm model according to the independent variable of the elastic component in the hinge and the optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force;
and the target pre-deformation amount determining module is used for determining the target pre-deformation amount of the elastic component according to the output result of the multi-objective optimization genetic algorithm model.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for optimizing a hinge structure provided by any of the embodiments of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the optimization method for the hinge structure provided in any embodiment of the present invention.
According to the embodiment of the invention, the corresponding relation between the pre-deformation amount of the elastic component in the hinge and the opening and closing force of the opening and closing piece is obtained by establishing the multi-body dynamic model of the hinge and the opening and closing piece, and the neural network model is established according to the corresponding relation so as to calculate the opening and closing force corresponding to different pre-deformation amounts. And then, determining a target opening and closing force from the opening and closing force corresponding to the predeformation amount with any size according to an ergonomic principle, constructing a multi-target optimization genetic algorithm model according to the predeformation amount of the elastic component in the hinge and the optimization target of the opening and closing piece, and determining the target predeformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model. The target predeformation amount is also the most ideal predeformation amount, so that the elastic component in the hinge can be set to the optimal predeformation amount, the operation comfort of the hinge structure is improved, the problem that the operation comfort of the hinge structure cannot be met in the existing universal design scheme of the hinge structure is solved, the application operation force of the hinge structure is optimized on the premise that the universality of the hinge structure is ensured, and the operation comfort of the hinge structure is improved.
Drawings
Fig. 1 is a flowchart of a method for optimizing a hinge structure according to an embodiment of the present invention;
FIG. 2 is a schematic view illustrating the connection effect of a hinge and a shutter according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for optimizing a hinge structure according to a second embodiment of the present invention;
fig. 4 is a schematic view of an optimization device of a hinge structure provided in the third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The terms "first" and "second," and the like in the description and claims of embodiments of the invention and in the drawings, are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not set forth for a listed step or element but may include steps or elements not listed.
Example one
Fig. 1 is a flowchart of an optimization method for a hinge structure according to an embodiment of the present invention, where the present embodiment is applicable to a situation where the operational comfort of the hinge structure is improved on the premise of ensuring the universality of the hinge structure, and the method may be performed by an optimization apparatus for the hinge structure, where the optimization apparatus may be implemented by software and/or hardware, and may be generally integrated in a computer device. Accordingly, as shown in fig. 1, the method comprises the following operations:
and S110, establishing a multi-body dynamic model of the hinge and the opening and closing piece.
The opening and closing member may be a component applied to various devices or homes, such as an automobile opening and closing member, including but not limited to an engine cover, a sunroof of a vehicle body, a door, a trunk lid, and the like. Alternatively, the shutter may also be a furniture shutter, including but not limited to doors, windows, doors, etc. The embodiment of the present invention does not limit the specific type of the opening and closing member.
Since the hinge is usually used in combination with the opening/closing member, in the embodiment of the present invention, a multi-body dynamic model between the hinge and the opening/closing member can be established, so that the hinge structure can be optimized by using the opening/closing force of the opening/closing member.
In an alternative embodiment of the present invention, the establishing a multi-body dynamic model of the hinge and the opening and closing member may include: and establishing an opening and closing process model of the hinge and the opening and closing piece as the multi-body dynamic model.
In a specific example, an opening and closing process model of the hinge and a new vehicle type connecting piece (such as a vehicle door or a vehicle cover) can be established, so that the hinge structure applied to the new vehicle type connecting piece can be optimized by utilizing the opening and closing process model of the hinge and the opening and closing piece.
S120, acquiring a corresponding relation between an independent variable of an elastic component in the hinge and a dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force.
Alternatively, the elastic member may be various types of springs. Accordingly, the amount of pre-deformation may be the amount of pre-compression of the spring. The number of the elastic components may be one or more, and the number of the elastic components in the hinge is not limited in the embodiment of the present invention. The opening and closing force may include two different types of forces, an opening force and a closing force.
Accordingly, after the multi-body dynamic model of the hinge and the opening and closing member is established, the correspondence between the amount of predeformation of the elastic member in the hinge and the opening and closing force of the opening and closing member can be obtained from the established multi-body dynamic model. In this correspondence relationship, the pre-deformation amount is an independent variable, and the opening/closing force is a dependent variable. The number of the corresponding relations can be set according to actual requirements, such as 100-group corresponding relations and the like. It can be understood that the more the number of the corresponding relations is, the more reliable the training result of the subsequent neural network model is, and the higher the accuracy of the neural network model is.
And S130, establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model.
Correspondingly, after the corresponding relation between the multiple groups of pre-deformation amounts and the opening and closing force is obtained, the neural network model can be trained according to the obtained corresponding relation. After the neural network model is trained successfully, the opening and closing forces corresponding to different pre-deformation quantities can be calculated by using the successfully trained neural network model.
And S140, determining a target opening and closing force from the opening and closing forces corresponding to the pre-deformation amount with any size according to an ergonomic principle.
Among them, ergonomics is a cross discipline of multiple disciplines, and the core problem of research is the coordination among people, machines and environment in different operations. The target opening-closing force may be an optimal opening-closing force.
In the embodiment of the present invention, in order to enable the hinge structure to satisfy the ergonomic condition, after the opening/closing force corresponding to the pre-deformation amount of any size is calculated and obtained through the neural network model, the optimal opening/closing force can be further determined as the target opening/closing force from the opening/closing force corresponding to the pre-deformation amount of any size according to the ergonomic principle.
S150, constructing a multi-objective optimization genetic algorithm model according to independent variables of elastic components in the hinge and the optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force.
And S160, determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model.
The target amount of pre-deformation is the optimal amount of pre-deformation. The use of a target amount of pre-deformation of the resilient components in the hinge structure may improve the operational comfort of the hinge structure.
In the embodiment of the invention, after the target opening and closing force is determined according to the ergonomic principle, the difference value between the opening and closing force of the opening and closing member and the target opening and closing force can be used as an optimization target, and a multi-target optimization genetic algorithm model is constructed according to the established optimization target and the pre-deformation amount of the elastic component in the hinge. The multi-objective optimization genetic algorithm model can realize multi-objective optimization on the opening force and the closing force simultaneously. Correspondingly, after the multi-objective optimization genetic algorithm model is constructed, the optimal pre-deformation amount of the elastic component can be determined as the target pre-deformation amount according to the output result of the multi-objective optimization genetic algorithm model, so that the hinge structure can be optimized.
Fig. 2 is a schematic view illustrating a connection effect of a hinge and an opening/closing member according to an embodiment of the present invention. In a specific example, as shown in fig. 2, the hinge 10 may include a first spring 11 and a second spring 12, and is connected to the opening and closing member of the cover 20, and the hinge 10 may be fixed to the fixing surface 30. When the operator operates cover 20, cover 20 may be operated by an operation force F to open or close cover 20. By adopting the optimization method of the hinge structure provided by the embodiment of the invention, the optimal pre-deformation amount of the two springs can be determined as the target pre-deformation amount for the hinge 10, so that the optimization of the hinge structure is realized.
Therefore, the optimization method of the hinge structure does not need to change the specifications of the main body structure and the elastic part of the hinge, and can realize optimization of the application operating force of the hinge structure only by adjusting the pre-deformation amount of the elastic part in the hinge, so that the operation comfort of the hinge structure can be improved, and the application cost of the hinge can be reduced. Meanwhile, the hinge structure obtained by the optimization method of the hinge structure can meet the requirements of human engineering, and the universality and the operation comfort of the hinge structure can be ensured at the same time.
According to the embodiment of the invention, the corresponding relation between the pre-deformation amount of the elastic component in the hinge and the opening and closing force of the opening and closing piece is obtained by establishing the multi-body dynamic model of the hinge and the opening and closing piece, and the neural network model is established according to the corresponding relation so as to calculate the opening and closing force corresponding to different pre-deformation amounts. And then, determining a target opening and closing force from the opening and closing force corresponding to the predeformation amount with any size according to an ergonomic principle, constructing a multi-target optimization genetic algorithm model according to the predeformation amount of the elastic component in the hinge and the optimization target of the opening and closing piece, and determining the target predeformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model. The target predeformation amount is also the most ideal predeformation amount, so that the elastic component in the hinge can be set to the optimal predeformation amount, the operation comfort of the hinge structure is improved, the problem that the operation comfort of the hinge structure cannot be met in the existing universal design scheme of the hinge structure is solved, the application operation force of the hinge structure is optimized on the premise that the universality of the hinge structure is ensured, and the operation comfort of the hinge structure is improved.
Example two
Fig. 3 is a flowchart of an optimization method for a hinge structure according to a second embodiment of the present invention, which is embodied on the basis of the second embodiment, and in this embodiment, a specific implementation manner of constructing a multi-objective optimization genetic algorithm model according to the independent variables of the elastic component in the hinge and the optimization goal of the opening/closing element is given. Accordingly, as shown in fig. 3, the method of the present embodiment may include:
s310, establishing a multi-body dynamic model of the hinge and the opening and closing piece.
S320, acquiring the corresponding relation between the independent variable of the elastic component in the hinge and the dependent variable of the opening and closing piece.
S330, establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model.
And S340, determining the target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to an ergonomic principle.
And S350, constructing a multi-objective optimization genetic algorithm model according to the independent variable of the elastic component in the hinge and the optimization target of the opening and closing piece.
Wherein, S350 may specifically include the following operations:
s351, initializing a first generation population of the multi-objective optimization genetic algorithm model and initialization parameters of the first generation population.
In an optional embodiment of the present invention, the initializing the first generation population of the multi-objective optimization genetic algorithm model and the initialization parameters of the first generation population may include: adopting binary coding to randomly generate a first generation population with the chromosome length as the target length and the individual number as the target number; the chromosomes of the first generation population include a set number of genes that characterize the amount of predeformation of the elastic members; calculating the average distance of the first generation population individuals; and determining the cross probability and the mutation probability of the first generation population.
The target length may be set according to a set number of genes, the set number of genes may be determined according to the number of elastic members included in the hinge structure, and specific values of the target length and the set number are not limited in the embodiments of the present invention. The target number is also set according to the actual requirement, and in order to ensure the effect of the algorithm, the target number can be selected to be between 200 and 300.
In creating the multiobjective optimization genetic algorithm model, the characteristics of the elastic components in the hinge structure may be used as gene characteristics. Each individual in the population may represent a pre-compression of an elastic member included in one of the hinge structures. Specifically, binary coding, random, may be used firstAnd generating a first generation population with the chromosome length of chromonlength and the number of individuals of N. Each individual in the population may include a chromosome, and each chromosome may include one or more genes. For example, assuming that the number of springs in the hinge structure is 2, the number of genes may be 2, which are the precompression amounts of the first spring and the second spring, respectively. That is, the first half of the chromosome represents the magnitude of the precompression for the first spring and the second half of the chromosome represents the magnitude of the precompression for the second spring. Alternatively, when calculating the average distance of the individuals of the first generation population, the average distance of the euclidean distances between the individuals may be calculated. Optionally, when determining the cross probability and the mutation probability of the first generation population, the cross probability may be set to pcSetting the mutation probability as pm. Wherein p iscAnd pmCan be set according to actual requirements, such as pc＝0.6，pm0.005. The embodiment of the invention does not limit the specific values of the cross probability and the mutation probability.
And S352, taking the first generation population as a current population.
And S353, calculating the fitness of the current population.
Accordingly, after the first generation population is established, iterative computation can be started for the population until the optimal population is obtained. Specifically, the first generation population may be used as the current population, and the fitness of the current population may be calculated.
In an optional embodiment of the present invention, the calculating the fitness of the current population may include: calculating individual target values corresponding to all individuals in the current population according to the neural network model; wherein the individual target value is an absolute value of a difference between an opening-closing force and a target opening-closing force; and taking the reciprocal of the individual target value as the fitness of the current population.
In the embodiment of the present invention, in order to make the opening and closing force and the optimal opening and closing force as close as possible, an absolute value of a difference between the opening and closing force and the optimal opening and closing force corresponding to all individuals in the current population may be calculated according to a trained neural network model, and a reciprocal of the absolute value of the difference between the opening and closing force and the optimal opening and closing force is taken as the fitness of the current population.
Illustratively, assume an optimal opening/closing force of 10N, a first opening/closing force of 8N, and a second opening/closing force of 9N. Accordingly, the reciprocal of the absolute value of the difference between the first opening/closing force and the optimum opening/closing force is 1/2, and the reciprocal of the absolute value of the difference between the second opening/closing force and the optimum opening/closing force is 1. It can be seen that the second opening/closing force is closest to the optimum opening/closing force, and therefore the second opening/closing force has a higher fitness value than the first opening/closing force. It follows that the closer the opening and closing force is to the optimum opening and closing force, the greater its fitness value.
S354, selecting and mutating the current population according to the fitness, and crossing the current population to obtain an updated population.
The update population may be a new population obtained by performing operations such as selection, variation, and crossing on the current population.
After the fitness of the current population is obtained, the current population can be selected and varied according to the fitness, and the current population is crossed, so that an updated population is obtained.
In an optional embodiment of the present invention, the selecting the current population according to the fitness may include: sequentially calculating Euclidean distances between the current individual and other individuals in the current population; sequentially selecting an individual with the maximum fitness value of the current individual within a set distance range as a target individual; storing the target individual and the fitness corresponding to the target individual in a fitness matrix; if the target individual is the current individual, marking the current individual as a superior individual, and storing the superior individual and the fitness corresponding to the superior individual in a superior individual matrix.
Wherein the set distance range can be set according to actual requirements, such as k1Multiple average distance range, where k1The specific value of (a) may be set according to actual requirements, such as 3, and the embodiment of the present invention does not limit this. The fitness matrix may be used to store selected target individualsBody and its corresponding fitness. The excellent individual matrix is used for storing excellent individuals and fitness thereof.
The selecting operation is used for selecting individuals from the current population according to the size of the fitness value. Classical genetic algorithms use roulette methods for selection, which can achieve a greater probability of an individual being selected for a greater fitness value. However, for a multi-peak function, the multi-peak function is easy to fall into a local better solution, and further becomes early, so that a global optimal solution cannot be searched. In the embodiment of the invention, the problem of trapping in a local better solution is effectively avoided by adopting the niche technology, and then the global optimal solution is searched. The niche technology is to divide each generation of individuals into a plurality of classes, select a plurality of individuals with high fitness in each class as excellent representatives of one class to form a group, cross in the group, and generate new generation of individuals through mutation, and specific examples are as follows:
sequentially calculating Euclidean distances between the current individual and other individuals in the current population. And after the current individual completes the calculation, updating the next individual into the current individual, and returning to execute the operation of sequentially calculating the Euclidean distances between the current individual and other individuals in the current population until the calculation of the Euclidean distances between all the individuals and other individuals is completed. Then, all individuals are sequentially subjected to traversal calculation, and the current individual is sequentially selected to be in k1And taking the individual with the maximum fitness value in the double average distance range as a target individual, and storing the selected target individual and the fitness corresponding to the target individual in a fitness matrix. If the target individual is the current individual, the target individual is marked as a superior individual, and the superior individual and the fitness corresponding to the superior individual are stored in a superior individual matrix.
It can be understood that, every time the population is updated, the fitness matrix and the excellent individual matrix corresponding to the current population are also updated.
In an optional embodiment of the present invention, the mutating the current population according to the fitness may include: sequentially calculating Euclidean distances between the current individual and other individuals in the current population; sequentially comparing the fitness values of the current individual and other individuals within a set distance range; if the fitness of a first number of individuals in the set distance range exceeds the fitness of the current individual, increasing a first multiple of the variation probability of the current individual; if a second number of subsequent individuals are coincident with the current individual in position within the set distance range, increasing the variation probability of the current individual by a second multiple; the mutation probability of the current individual is the sum of the initial mutation probability and the newly increased mutation probability; and if the value of the random function is smaller than the mutation probability of the current individual, mutating the random gene position in the chromosome, and halving the mutation probability of the current individual until the value of the random function is larger than or equal to the mutation probability of the current individual.
The first quantity and the second quantity may be set according to actual requirements, and the specific numerical values of the first quantity and the second quantity are not limited in the embodiment of the present invention. Similarly, the first multiple and the second multiple may also be set according to actual requirements, and the embodiments of the present invention do not limit specific values of the first multiple and the second multiple. The random gene location may be the location of a randomly selected one of the genes in the chromosome.
In a specific example, when performing mutation operation on the current population, euclidean distances between the current individual and other individuals in the current population may be sequentially calculated. And after the current individual completes the calculation, updating the next individual into the current individual, and returning to execute the operation of sequentially calculating the Euclidean distances between the current individual and other individuals in the current population until the calculation of the Euclidean distances between all the individuals and other individuals is completed. Then, the current individual is compared with k sequentially1Fitness values of other individuals within a multiple average distance range. If it is k1If the fitness of n individuals in the double average distance range exceeds the fitness of the current individual, increasing n x k to the variation probability of the current individual2Multiple times. For example, assume that the current population is the first generation population and the initial variation probability of the current individual is pmThen the initial mutation probability p of the current individual can bemOn the basis of (2), n x k is added2Pm. If it is k1There are m subsequent individuals within the double mean distance range(determined according to the ordering sequence of the individuals) is coincident with the position of the current individual, the mutation probability of the current individual is increased by m x k3And (4) doubling. For example, assume that the current population is the first generation population and the initial variation probability of the current individual is pmThen the initial mutation probability p of the current individual can bemOn the basis of the formula (II), m is increased by k3Pm. Wherein k is2And the method represents the weak variation coefficient, is characterized in a specific range, and increases the variation probability of the individual under the condition of competitive weakness if the fitness value is small. k is a radical of3And representing the coincidence variation coefficient, and representing the increasing amplitude of the variation probability of the individual under the condition that the m individuals in the sequence behind the coincidence coefficient coincide with the coordinates of the individual. In order to avoid that all the overlapping individuals increase the variation probability and further that all the overlapping individuals are likely to be varied, it is specified that only the individuals with the sequence behind the overlapping individuals increase the variation probability of the individuals, and the last individual does not increase the overlapping variation probability.
On the basis of the mutation operation, if the value of the random function rand is smaller than the mutation probability of the current individual, the mutation can be performed on a random gene position in the chromosome, and the mutation probability of the current individual is halved until the value of the random function rand is larger than or equal to the mutation probability of the current individual, and the compiling cycle of the current individual is skipped.
In an alternative embodiment of the invention, the number of genes is 2; the crossing the current population may include: setting the end position of the first gene as a cross point; and if the value of the random function is less than the crossover probability, performing crossover operation on the genes in the chromosome.
Wherein the cross point may be a point at which each gene in the chromosome crosses.
In the present embodiment, the number of genes may be 2, i.e., one chromosome may include two genes. Correspondingly, when the current population is subjected to the crossover operation, the last position of the first gene can be set as a crossover point, and when the value of the random function rand is determined to be smaller than the crossover probability, the genes in the chromosome are subjected to the crossover operation. Illustratively, assuming that the chromosome of the individual 1 includes the gene 1 and the gene 2, and the chromosome of the individual 2 includes the gene 3 and the gene 4, when the individual 1 and the individual 2 are crossed, the gene 2 and the gene 4 may be crossed with each other, so that the chromosome of the individual 1 includes the gene 1 and the gene 4, and the chromosome of the individual 2 includes the gene 3 and the gene 2. The gene crossing in the chromosome may be performed by crossing the genes in the chromosomes of two individuals selected randomly, or by sequentially selecting two individuals and crossing the genes in the chromosomes, which is not limited in the embodiments of the present invention.
And S355, replacing the excellent individuals screened out when the current population is selected with the updated population.
In the embodiment of the invention, after the current population is selected, mutated and crossed, excellent individuals screened during the selection of the current population can be replaced into the updated population. That is, the individuals with the smallest fitness in the updated population are sequentially replaced by the excellent individuals in the excellent individual matrix.
And S356, taking the updated population as the current population.
S357, judging whether the iteration times of the multi-objective optimization genetic algorithm model reach the target iteration times, if so, executing S358; otherwise, return to execute S353.
And S358, ending the iterative calculation process.
And S360, determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model.
The target iteration number may be a maximum iteration number set for the multi-objective optimization genetic algorithm model.
Correspondingly, after the current population is selected, subjected to variation crossover and excellent individual replacement to obtain an updated population, the updated population can be updated to the current population, and the operation of calculating the fitness of the current population is executed again until the iteration number of the multi-target optimization genetic algorithm model reaches the maximum iteration number, namely the optimal population is obtained. After the iterative computation of the multi-objective optimization genetic algorithm model is completed, the optimal individual and the opening and closing force corresponding to the optimal individual can be output. The calculated opening and closing force is close to the optimal opening and closing force, and the gene characteristics of the chromosome in the optimal individual, namely the optimal pre-deformation amount of the elastic component.
According to the embodiment of the invention, the corresponding relation between the pre-deformation amount of the elastic component in the hinge and the opening and closing force of the opening and closing piece is obtained by establishing the multi-body dynamic model of the hinge and the opening and closing piece, and the neural network model is established according to the corresponding relation so as to calculate the opening and closing force corresponding to different pre-deformation amounts. And then, determining a target opening and closing force from the opening and closing force corresponding to the predeformation amount with any size according to an ergonomic principle, constructing a multi-target optimization genetic algorithm model according to the predeformation amount of the elastic component in the hinge and the optimization target of the opening and closing piece, and determining the target predeformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model. The target predeformation amount is also the most ideal predeformation amount, so that the elastic component in the hinge can be set to the optimal predeformation amount, the operation comfort of the hinge structure is improved, the problem that the operation comfort of the hinge structure cannot be met in the existing universal design scheme of the hinge structure is solved, the application operation force of the hinge structure is optimized on the premise that the universality of the hinge structure is ensured, and the operation comfort of the hinge structure is improved.
It should be noted that any permutation and combination between the technical features in the above embodiments also belong to the scope of the present invention.
EXAMPLE III
Fig. 4 is a schematic view of an optimized device of a hinge structure according to a third embodiment of the present invention, as shown in fig. 4, the device includes: the multi-body dynamics model building module 410, the corresponding relation obtaining module 420, the opening and closing force calculating module 430, the target opening and closing force determining module 440, the genetic algorithm model building module 450, and the target pre-deformation amount determining module 460, wherein:
a multi-body dynamics model building module 410 for building a multi-body dynamics model of the hinge and the opening and closing member;
a correspondence obtaining module 420, configured to obtain a correspondence between an independent variable of an elastic component in the hinge and a dependent variable of the opening/closing member; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force;
the opening and closing force calculation module 430 is used for establishing a neural network model according to the corresponding relation and calculating the opening and closing force corresponding to different pre-deformation amounts according to the neural network model;
a target opening/closing force determination module 440 for determining the target opening/closing force from the opening/closing force corresponding to the pre-deformation amount of any magnitude according to the ergonomic principle;
a genetic algorithm model construction module 450, configured to construct a multi-objective optimized genetic algorithm model according to the independent variable of the elastic component in the hinge and the optimization target of the opening and closing member; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force;
and a target pre-deformation amount determining module 460, configured to determine a target pre-deformation amount of the elastic component according to an output result of the multi-objective optimization genetic algorithm model.
According to the embodiment of the invention, the corresponding relation between the pre-deformation amount of the elastic component in the hinge and the opening and closing force of the opening and closing piece is obtained by establishing the multi-body dynamic model of the hinge and the opening and closing piece, and the neural network model is established according to the corresponding relation so as to calculate the opening and closing force corresponding to different pre-deformation amounts. And then, determining a target opening and closing force from the opening and closing force corresponding to the predeformation amount with any size according to an ergonomic principle, constructing a multi-target optimization genetic algorithm model according to the predeformation amount of the elastic component in the hinge and the optimization target of the opening and closing piece, and determining the target predeformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model. The target predeformation amount is also the most ideal predeformation amount, so that the elastic component in the hinge can be set to the optimal predeformation amount, the operation comfort of the hinge structure is improved, the problem that the operation comfort of the hinge structure cannot be met in the existing universal design scheme of the hinge structure is solved, the application operation force of the hinge structure is optimized on the premise that the universality of the hinge structure is ensured, and the operation comfort of the hinge structure is improved.
Optionally, the genetic algorithm model building module 450 is specifically configured to initialize a first generation population of the multi-objective optimization genetic algorithm model and initialization parameters of the first generation population; taking the first generation population as a current population, and calculating the fitness of the current population; selecting and varying the current population according to the fitness, and crossing the current population to obtain an updated population; replacing the excellent individuals screened out when the current population is selected into the updated population; and taking the updated population as the current population, and returning to execute the operation of calculating the fitness of the current population until the iteration times of the multi-objective optimization genetic algorithm model reach the target iteration times.
Optionally, the genetic algorithm model building module 450 is specifically configured to randomly generate a first generation population with a chromosome length as a target length and an individual number as a target number by using binary coding; the chromosomes of the first generation population include a set number of genes that characterize the amount of predeformation of the elastic members; calculating the average distance of the first generation population individuals; and determining the cross probability and the mutation probability of the first generation population.
Optionally, the genetic algorithm model building module 450 is specifically configured to calculate individual target values corresponding to all individuals in the current population according to the neural network model; wherein the individual target value is an absolute value of a difference between an opening-closing force and a target opening-closing force; and taking the reciprocal of the individual target value as the fitness of the current population.
Optionally, the genetic algorithm model building module 450 is specifically configured to sequentially calculate euclidean distances between the current individual and other individuals in the current population; sequentially selecting an individual with the maximum fitness value of the current individual within a set distance range as a target individual; storing the target individual and the fitness corresponding to the target individual in a fitness matrix; if the target individual is the current individual, marking the current individual as a superior individual, and storing the superior individual and the fitness corresponding to the superior individual in a superior individual matrix.
Optionally, the genetic algorithm model building module 450 is specifically configured to sequentially calculate euclidean distances between the current individual and other individuals in the current population; sequentially comparing the fitness values of the current individual and other individuals within a set distance range; if the fitness of a first number of individuals in the set distance range exceeds the fitness of the current individual, increasing a first multiple of the variation probability of the current individual; if a second number of subsequent individuals are coincident with the current individual in position within the set distance range, increasing the variation probability of the current individual by a second multiple; the mutation probability of the current individual is the sum of the initial mutation probability and the newly increased mutation probability; and if the value of the random function is smaller than the mutation probability of the current individual, mutating the random gene position in the chromosome, and halving the mutation probability of the current individual until the value of the random function is larger than or equal to the mutation probability of the current individual.
Optionally, the number of genes is 2; a genetic algorithm model construction module 450, specifically configured to set a last position of the first gene as a cross point; and if the value of the random function is less than the crossover probability, performing crossover operation on the genes in the chromosome.
The optimization device of the hinge structure can execute the optimization method of the hinge structure provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to a method for optimizing a hinge structure according to any embodiment of the present invention.
Since the above-described optimization device for a hinge structure is a device that can perform the optimization method for a hinge structure in the embodiment of the present invention, based on the optimization method for a hinge structure described in the embodiment of the present invention, a person skilled in the art can understand the specific implementation of the optimization device for a hinge structure in the embodiment of the present invention and various modifications thereof, and therefore, a detailed description of how the optimization device for a hinge structure implements the optimization method for a hinge structure in the embodiment of the present invention is not provided here. The scope of the present application is intended to cover any apparatus that can be used by those skilled in the art to implement the method for optimizing the hinge structure in the embodiments of the present invention.
Example four
Fig. 5 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 5 illustrates a block diagram of a computer device 512 suitable for use in implementing embodiments of the present invention. The computer device 512 shown in FIG. 5 is only an example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 5, computer device 512 is in the form of a general purpose computing device. Components of computer device 512 may include, but are not limited to: one or more processors 516, a storage device 528, and a bus 518 that couples the various system components including the storage device 528 and the processors 516.
The processor 516 executes programs stored in the storage device 528 to execute various functional applications and data processing, for example, to implement the optimization method of the hinge structure provided by the above-described embodiment of the present invention.
That is, the processing unit implements, when executing the program: establishing a multi-body dynamic model of the hinge and the opening and closing piece; acquiring a corresponding relation between an independent variable of an elastic component in the hinge and a dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force; establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model; determining a target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to an ergonomic principle; constructing a multi-objective optimization genetic algorithm model according to independent variables of elastic components in the hinge and an optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force; and determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model.
EXAMPLE five
An embodiment five of the present invention further provides a computer storage medium storing a computer program, which when executed by a computer processor is configured to perform the method for optimizing a hinge structure according to any one of the above embodiments of the present invention: establishing a multi-body dynamic model of the hinge and the opening and closing piece; acquiring a corresponding relation between an independent variable of an elastic component in the hinge and a dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force; establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model; determining a target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to an ergonomic principle; constructing a multi-objective optimization genetic algorithm model according to independent variables of elastic components in the hinge and an optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force; and determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM) or flash Memory), an optical fiber, a portable compact disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method of optimizing a hinge structure, comprising:
establishing a multi-body dynamic model of the hinge and the opening and closing piece;
acquiring a corresponding relation between an independent variable of an elastic component in the hinge and a dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force;
establishing a neural network model according to the corresponding relation, and calculating opening and closing forces corresponding to different pre-deformation amounts according to the neural network model;
determining a target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to an ergonomic principle;
constructing a multi-objective optimization genetic algorithm model according to independent variables of elastic components in the hinge and an optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force;
and determining the target pre-deformation amount of the elastic component according to the output result of the multi-target optimization genetic algorithm model.
2. The method of claim 1, wherein constructing a multiobjective optimization genetic algorithm model based on the independent variables of the elastic components in the hinge and the optimization objectives of the opening and closing member comprises:
initializing a first generation population of the multi-objective optimization genetic algorithm model and initialization parameters of the first generation population;
taking the first generation population as a current population, and calculating the fitness of the current population;
selecting and varying the current population according to the fitness, and crossing the current population to obtain an updated population;
replacing the excellent individuals screened out when the current population is selected into the updated population;
and taking the updated population as the current population, and returning to execute the operation of calculating the fitness of the current population until the iteration times of the multi-objective optimization genetic algorithm model reach the target iteration times.
3. The method of claim 2, wherein initializing the first generation population of the multiobjective optimization genetic algorithm model and initialization parameters of the first generation population comprises:
adopting binary coding to randomly generate a first generation population with the chromosome length as the target length and the individual number as the target number; the chromosomes of the first generation population include a set number of genes that characterize the amount of predeformation of the elastic members;
calculating the average distance of the first generation population individuals;
and determining the cross probability and the mutation probability of the first generation population.
4. The method of claim 2, wherein the calculating the fitness of the current population comprises:
calculating individual target values corresponding to all individuals in the current population according to the neural network model; wherein the individual target value is an absolute value of a difference between an opening-closing force and a target opening-closing force;
and taking the reciprocal of the individual target value as the fitness of the current population.
5. The method of claim 2, wherein selecting the current population according to the fitness comprises:
sequentially calculating Euclidean distances between the current individual and other individuals in the current population;
sequentially selecting an individual with the maximum fitness value of the current individual within a set distance range as a target individual;
storing the target individual and the fitness corresponding to the target individual in a fitness matrix;
if the target individual is the current individual, marking the current individual as a superior individual, and storing the superior individual and the fitness corresponding to the superior individual in a superior individual matrix.
6. The method of claim 2, wherein said mutating said current population according to said fitness comprises:
sequentially calculating Euclidean distances between the current individual and other individuals in the current population;
sequentially comparing the fitness values of the current individual and other individuals within a set distance range;
if the fitness of a first number of individuals in the set distance range exceeds the fitness of the current individual, increasing a first multiple of the variation probability of the current individual;
if a second number of subsequent individuals are coincident with the current individual in position within the set distance range, increasing the variation probability of the current individual by a second multiple; the mutation probability of the current individual is the sum of the initial mutation probability and the newly increased mutation probability;
and if the value of the random function is smaller than the mutation probability of the current individual, mutating the random gene position in the chromosome, and halving the mutation probability of the current individual until the value of the random function is larger than or equal to the mutation probability of the current individual.
7. The method of claim 3, wherein the number of genes is 2;
the crossing the current population includes:
setting the end position of the first gene as a cross point;
and if the value of the random function is less than the crossover probability, performing crossover operation on the genes in the chromosome.
8. An apparatus for optimizing a hinge structure, comprising:
the multi-body dynamic model building module is used for building a multi-body dynamic model of the hinge and the opening and closing piece;
the corresponding relation acquisition module is used for acquiring the corresponding relation between the independent variable of the elastic component in the hinge and the dependent variable of the opening and closing piece; wherein the independent variable comprises a pre-deformation amount, and the dependent variable comprises an opening and closing force;
the opening and closing force calculation module is used for establishing a neural network model according to the corresponding relation and calculating the opening and closing force corresponding to different pre-deformation amounts according to the neural network model;
the target opening and closing force determining module is used for determining the target opening and closing force from the opening and closing force corresponding to the pre-deformation amount with any size according to the man-machine engineering principle;
the genetic algorithm model building module is used for building a multi-objective optimization genetic algorithm model according to the independent variable of the elastic component in the hinge and the optimization target of the opening and closing piece; wherein the optimization target is a difference between an opening/closing force of the opening/closing member and the target opening/closing force;
and the target pre-deformation amount determining module is used for determining the target pre-deformation amount of the elastic component according to the output result of the multi-objective optimization genetic algorithm model.
9. A computer device, characterized in that the computer device comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of optimizing a hinge structure according to any one of claims 1-7.
10. A computer storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a method of optimizing a hinge construction according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010814004.9A CN111950204B (en) | 2020-08-13 | 2020-08-13 | Hinge structure optimization method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010814004.9A CN111950204B (en) | 2020-08-13 | 2020-08-13 | Hinge structure optimization method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111950204A CN111950204A (en) | 2020-11-17 |
| CN111950204B true CN111950204B (en) | 2022-04-19 |
Family
ID=73343351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010814004.9A Active CN111950204B (en) | 2020-08-13 | 2020-08-13 | Hinge structure optimization method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111950204B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104765916A (en) * | 2015-03-31 | 2015-07-08 | 西南交通大学 | Dynamics performance parameter optimizing method of high-speed train |
| CN105243172A (en) * | 2015-07-22 | 2016-01-13 | 湖南大学 | Engine suspension system optimization method capable of considering dynamic rigidity and damping |
| CN106202755A (en) * | 2016-07-15 | 2016-12-07 | 西安交通大学 | Electric main shaft structure Optimization Design based on kinetic model and genetic algorithm |
| CN108416178A (en) * | 2018-05-02 | 2018-08-17 | 南京航空航天大学 | A kind of mechanical elastic vehicle wheel Design of Structural parameters method |
| CN109376493A (en) * | 2018-12-17 | 2019-02-22 | 武汉理工大学 | A kind of radial base neural net car speed tracking of particle group optimizing |
| CN110990961A (en) * | 2020-03-04 | 2020-04-10 | 江西昌河汽车有限责任公司 | Method for calculating opening and closing force of air spring of automobile tail door |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPWO2004033159A1 (en) * | 2002-10-11 | 2006-02-09 | 富士通株式会社 | Robot control algorithm construction device, robot control algorithm construction program robot control device, robot control program, and robot |
-
2020
- 2020-08-13 CN CN202010814004.9A patent/CN111950204B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104765916A (en) * | 2015-03-31 | 2015-07-08 | 西南交通大学 | Dynamics performance parameter optimizing method of high-speed train |
| CN105243172A (en) * | 2015-07-22 | 2016-01-13 | 湖南大学 | Engine suspension system optimization method capable of considering dynamic rigidity and damping |
| CN106202755A (en) * | 2016-07-15 | 2016-12-07 | 西安交通大学 | Electric main shaft structure Optimization Design based on kinetic model and genetic algorithm |
| CN108416178A (en) * | 2018-05-02 | 2018-08-17 | 南京航空航天大学 | A kind of mechanical elastic vehicle wheel Design of Structural parameters method |
| CN109376493A (en) * | 2018-12-17 | 2019-02-22 | 武汉理工大学 | A kind of radial base neural net car speed tracking of particle group optimizing |
| CN110990961A (en) * | 2020-03-04 | 2020-04-10 | 江西昌河汽车有限责任公司 | Method for calculating opening and closing force of air spring of automobile tail door |
Non-Patent Citations (3)
| Title |
|---|
| "A comparative study between artificial neural network and linear regression for optimizing a hinged blade cross axis turbine";Arvin H. Fernando 等;《2015 International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management (HNICEM)》;20160128;第1-4页 * |
| "基于Excel的行李箱盖扭杆弹簧计算研究";李超帅 等;《汽车实用技术》;20180415(第7期);第94-97,107页 * |
| "考虑多个铰链间隙的开环机构动力学特性研究";杨丽新;《中国优秀博硕士学位论文全文数据库(博士)工程科技Ⅱ辑》;20190115;第C029-3页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111950204A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bai et al. | A model-based reinforcement learning with adversarial training for online recommendation | |
| US10971142B2 (en) | Systems and methods for robust speech recognition using generative adversarial networks | |
| Weisz et al. | Sample efficient deep reinforcement learning for dialogue systems with large action spaces | |
| CN110366734B (en) | Optimizing neural network architecture | |
| Sriram et al. | Robust speech recognition using generative adversarial networks | |
| US20180260714A1 (en) | Global optimization, search and machine learning method based on the lamarckian principle of inheritance of acquired characteristics | |
| US11610108B2 (en) | Training of student neural network with switched teacher neural networks | |
| WO2019177951A1 (en) | Hybrid quantum-classical generative modes for learning data distributions | |
| JP4201012B2 (en) | Data processing apparatus, data processing method, and program | |
| CN110766044A (en) | Neural network training method based on Gaussian process prior guidance | |
| Muratore et al. | Neural posterior domain randomization | |
| JPWO2018062265A1 (en) | Acoustic model learning device, method thereof and program | |
| CN111506814A (en) | Sequence recommendation method based on variational self-attention network | |
| CN114219360A (en) | Monitoring safety prediction method and system based on model optimization | |
| CN111860364A (en) | Training method and device of face recognition model, electronic equipment and storage medium | |
| CN115293227A (en) | Model training method and related equipment | |
| Xavier-Júnior et al. | A novel evolutionary algorithm for automated machine learning focusing on classifier ensembles | |
| WO2024120504A1 (en) | Data processing method and related device | |
| CN114386580A (en) | Decision model training method and device, decision method and device, electronic equipment and storage medium | |
| CN111950204B (en) | Hinge structure optimization method and device, computer equipment and storage medium | |
| McDermott et al. | A derivation of minimum classification error from the theoretical classification risk using Parzen estimation | |
| US11797769B1 (en) | Artificial intelligence system using hybrid technique for task-oriented dialog management | |
| Fernández et al. | VQQL. Applying vector quantization to reinforcement learning | |
| Yu et al. | Hidden Markov models and the variants | |
| Marwala | Finite-element-model updating using a Bayesian approach |
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 |