CN117725705B - Rib shape optimization method, device, equipment and storage medium - Google Patents
Rib shape optimization method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117725705B CN117725705B CN202410176880.1A CN202410176880A CN117725705B CN 117725705 B CN117725705 B CN 117725705B CN 202410176880 A CN202410176880 A CN 202410176880A CN 117725705 B CN117725705 B CN 117725705B
- Authority
- CN
- China
- Prior art keywords
- parameter vector
- round
- target
- hysteresis effect
- parameter
- 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 69
- 238000005457 optimization Methods 0.000 title claims abstract description 24
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 239000013598 vector Substances 0.000 claims abstract description 372
- 230000000694 effects Effects 0.000 claims abstract description 156
- 238000004088 simulation Methods 0.000 claims abstract description 127
- 230000006870 function Effects 0.000 claims description 28
- 230000003044 adaptive effect Effects 0.000 claims description 27
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000011161 development Methods 0.000 abstract description 11
- 238000002474 experimental method Methods 0.000 description 19
- 238000004422 calculation algorithm Methods 0.000 description 18
- 241000282461 Canis lupus Species 0.000 description 16
- 230000008569 process Effects 0.000 description 9
- 239000000463 material Substances 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 241000282421 Canidae Species 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009863 impact test Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000006461 physiological response Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a rib shape optimization method, a device, equipment and a storage medium, and relates to the technical field of computers, wherein the method comprises the following steps: acquiring a t-th round parameter vector set of the shape of the dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors; obtaining a plurality of groups of hysteresis effect simulation values according to a plurality of groups of parameter vectors and a predetermined hysteresis effect simulation function; determining a target hysteresis effect simulation value from a plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer; if the target hysteresis effect simulation value meets the preset condition, the rib shape is optimized according to the optimal parameter vector in the t-th round of target parameter vector. The method can shorten the development period of the dummy rib and reduce the time cost.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for optimizing a rib shape.
Background
The dummy is a detection device for evaluating the safety of the vehicle and a technical weight for measuring the safety of the vehicle. The dummy is used for replacing a real person to carry out a collision test, so that the damage condition of the human body under different conditions can be simulated. The consistency of the rib of the chest of the dummy with the real person will affect the collision result.
At present, whether the rib of the dummy meets the standard is verified through an impact experiment, but the verification mode based on the impact experiment is high in time cost, and if the rib does not meet the standard, the rib component proportion and/or the rib shape parameter of the dummy are manually adjusted, so that the impact experiment is performed again.
In the traditional scheme, the rib development period of the dummy is long, and the time cost is high.
Disclosure of Invention
The application provides a rib shape optimization method, a device, equipment and a storage medium, which can shorten the development period of a dummy rib and reduce the time cost.
In order to achieve the above purpose, the application adopts the following technical scheme:
In a first aspect, the present application provides a method for optimizing rib shape, the method comprising:
Acquiring a t-th round parameter vector set of the shape of a dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, the parameter vectors comprise a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, and t is a positive integer;
obtaining a plurality of groups of hysteresis effect simulation values according to a plurality of groups of the parameter vectors and a predetermined hysteresis effect simulation function;
Determining a target hysteresis effect simulation value from the plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer;
And if the target hysteresis effect simulation value meets a preset condition, optimizing the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors.
In some possible implementations, the method further includes:
and if the target hysteresis effect simulation value does not meet a preset condition and the t reaches the maximum iteration times, optimizing the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors.
In some possible implementations, the method further includes:
If the target hysteresis effect simulation value does not meet a preset condition and the t does not reach the maximum iteration number, acquiring a t-th round target distance influence factor corresponding to the t-th round target parameter vector;
and if the absolute value of the t-th round target distance influence factor is larger than 1, updating the t-th round parameter vector set by using the parameter vector randomly selected from the t-th round parameter vector set to obtain a t+1-th round parameter vector set.
In some possible implementations, the method further includes:
And if the absolute value of the t-th round target distance influence factor is smaller than or equal to 1, updating the t-th round parameter vector set according to the t-th round target parameter vector to obtain a t+1th round parameter vector set.
In some possible implementations, the updating the set of t-th round parameter vectors with a parameter vector randomly selected from the set of t-th round parameter vectors includes:
wherein, For the ith parameter vector randomly selected from the set of t-th round parameter vectors,/>Representing the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th round of parameter vector set,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>For a first random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors,Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
In some possible implementations, the updating the set of the t-th round parameter vector according to the t-th round target parameter vector includes
Wherein,For the nth parameter vector of the t-th round of target parameter vectors,/>Is the distance between the p-th parameter vector in the t-th round parameter vector set and the n-th parameter vector in the t-th round target parameter vector,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>Is the first random parameter vector different from the p-th parameter vector in the t-th round parameter vector set,/>Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
In some possible implementations, the method further includes:
Obtaining a hysteresis effect true value obtained by testing the rib corresponding to the optimized rib shape;
And if the difference value between the hysteresis effect actual value and the hysteresis effect simulation value corresponding to the optimal parameter vector is larger than a preset difference value threshold, updating the preset condition and/or the hysteresis effect simulation function.
In a second aspect, the present application provides a rib-shaped optimization apparatus, the apparatus comprising:
The acquisition module is used for acquiring a t-th round parameter vector set of the shape of the dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, the parameter vectors comprise a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, and t is a positive integer;
The simulation module is used for obtaining a plurality of groups of hysteresis effect simulation values according to a plurality of groups of the parameter vectors and a predetermined hysteresis effect simulation function; determining a target hysteresis effect simulation value from the plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer;
And the optimization module is used for optimizing the rib shape according to the optimal parameter vector in the t-th round target parameter vector if the target hysteresis effect simulation value meets the preset condition.
In some possible implementations, the optimization module is further configured to optimize the rib shape according to an optimal parameter vector in the t-th round of target parameter vector if the target hysteresis effect analog value does not meet a preset condition and the t reaches a maximum number of iterations.
In some possible implementations, the obtaining module is further configured to obtain a t-th round target distance influencing factor corresponding to the t-th round target parameter vector if the target hysteresis effect analog value does not meet a preset condition and the t does not reach the maximum iteration number; and if the absolute value of the t-th round target distance influence factor is larger than 1, updating the t-th round parameter vector set by using the parameter vector randomly selected from the t-th round parameter vector set to obtain a t+1-th round parameter vector set.
In some possible implementations, the obtaining module is further configured to update the set of t-th round of parameter vectors according to the t-th round of target parameter vector if the absolute value of the t-th round of target distance influencing factor is less than or equal to 1, to obtain a set of t+1-th round of parameter vectors.
In some possible implementations, the obtaining module is specifically configured to update the set of t-th round of parameter vectors by:
wherein, For the ith parameter vector randomly selected from the set of t-th round parameter vectors,/>Representing the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th round of parameter vector set,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>For a first random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors,Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
In some possible implementations, the obtaining module is specifically configured to update the set of t-th round of parameter vectors by the following formula:
wherein, For the nth parameter vector of the t-th round of target parameter vectors,/>Is the distance between the p-th parameter vector in the t-th round parameter vector set and the n-th parameter vector in the t-th round target parameter vector,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>Is the first random parameter vector different from the p-th parameter vector in the t-th round parameter vector set,/>Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
In some possible implementations, the apparatus further includes an update module; the acquisition module is also used for acquiring a hysteresis effect true value obtained by testing the rib corresponding to the optimized rib shape;
And the updating module is used for updating the preset condition and/or the hysteresis effect simulation function if the difference value between the hysteresis effect actual value and the hysteresis effect simulation value corresponding to the optimal parameter vector is greater than a preset difference value threshold.
In a third aspect, the present application provides a computing device comprising a memory and a processor;
Wherein one or more computer programs are stored in the memory, the one or more computer programs comprising instructions; the instructions, when executed by the processor, cause the computing device to perform the method of any of the first aspects.
In a fourth aspect, the present application provides a computer readable storage medium for storing a computer program for performing the method of any one of the first aspects.
According to the technical scheme, the application has at least the following beneficial effects:
The application provides an optimization method of rib shape, the method includes obtaining a t-th round parameter vector set of the shape of a dummy rib, the parameter vector set includes a plurality of groups of parameter vectors, the parameter vectors include a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, t is a positive integer, then a plurality of groups of hysteresis effect simulation values are obtained according to the plurality of groups of parameter vectors and a predetermined hysteresis effect simulation function, then a target hysteresis effect simulation value is determined from the plurality of groups of hysteresis effect simulation values, the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of groups of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to the t-th round target parameter vector, and N is a positive integer; and if the target hysteresis effect simulation value meets the preset condition, optimizing the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors. In the method, a plurality of groups of parameter vector sets are generated through an improved gray wolf algorithm, a real impact experiment is simulated through a preset function, and the rib shape is optimized by utilizing the corresponding target parameter vector under the condition that the simulation value meets the preset condition, so that the development period of the rib is shortened, and the time cost is reduced. Compared with the traditional method, the method does not need to truly manufacture rib materials and truly experiment, does not need to manually adjust component proportion and/or shape parameters of the rib materials, reduces workload of staff and improves efficiency.
It should be appreciated that the description of technical features, aspects, benefits or similar language in the present application does not imply that all of the features and advantages may be realized with any single embodiment. Conversely, it should be understood that the description of features or advantages is intended to include, in at least one embodiment, the particular features, aspects, or advantages. Therefore, the description of technical features, technical solutions or advantageous effects in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and advantageous effects described in the present embodiment may also be combined in any appropriate manner. Those of skill in the art will appreciate that an embodiment may be implemented without one or more particular features, aspects, or benefits of a particular embodiment. In other embodiments, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments.
Drawings
FIG. 1 is a flowchart of a method for optimizing rib shape according to an embodiment of the present application;
FIG. 2 is a schematic view of a rib shape according to an embodiment of the present application;
FIG. 3 is a flow chart of another method for optimizing rib shape according to an embodiment of the present application;
FIG. 4 is a schematic structural view of a rib-shaped optimizing apparatus according to an embodiment of the present application;
Fig. 5 is a schematic structural diagram of a computing device according to an embodiment of the present application.
Detailed Description
The terms "first," "second," and "third," and the like, in the description and in the drawings, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
For clarity and conciseness in the description of the following embodiments, a brief description of the related art will be given first:
The vehicle collision experiment is a method for testing the safety performance and the structural strength of a vehicle during collision by simulating traffic accident conditions. These experiments are typically conducted by the vehicle manufacturer or a separate safety organization to ensure that the vehicle provides optimal protection in the event of a collision.
In an automobile collision experiment, a bionic manikin called an "automobile collision test dummy" (also called a collision test model or a collision test manikin) is used. The purpose of this model is to simulate the physiological response of a real human body in a vehicle collision accident to evaluate the safety performance of the vehicle. In these dummy models, modeling of ribs is included in order to more fully understand the impact of collisions on the dummy body.
Damping material is an important component of the rib of the dummy. After the chest of the dummy is impacted by the load, the hysteresis effect of the rib damping material can reflect the similarity of the rib of the dummy and the real human body structure. In the field of automotive crash dummies, the rationality of the dummy rib design is generally assessed based on the hysteresis effects described above.
The response evaluation indexes of the dummy rib comprise rib impact force peak value, rib compression quantity peak value and rib hysteresis effect (represented by hysteresis rate), and the evaluation index limit values are different for different impact rates. Under the low-speed working condition, the impact force peak value is 2.38-2.73 KN, and the compression amount peak value is 21.5-26.5 mm. The hysteresis effect can be calculated by the two, and the hysteresis evaluation standard, namely the hysteresis rate, is 60% -75%.
In the traditional scheme, whether the dummy rib meets the standard is verified through an impact experiment. However, the time cost of the evaluation method based on the impact test is high, if the rib does not meet the standard, the component proportion or the shape and the size need to be manually adjusted, and then the impact test is performed until the dummy rib meets the standard. In the traditional scheme, the rib development period of the dummy is long, and the time cost is high.
In view of this, an embodiment of the present application provides a method for optimizing a rib shape, including: obtaining a t-th round parameter vector set of the shape of the dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, the parameter vectors comprise a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, t is a positive integer, then obtaining a plurality of groups of hysteresis effect simulation values according to the plurality of groups of parameter vectors and a predetermined hysteresis effect simulation function, then determining a target hysteresis effect simulation value from the plurality of groups of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of groups of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to the t-th round target parameter vector, N is a positive integer, and if the target hysteresis effect simulation value meets a preset condition, optimizing the shape of the rib according to an optimal parameter vector in the t-th round target parameter vector.
In the method, a plurality of groups of parameter vector sets are generated through a gray wolf algorithm, a real impact experiment is simulated through a preset function, and the rib shape is optimized by utilizing the corresponding target parameter vector under the condition that the simulation value meets the preset condition, so that the development period of the rib is shortened, and the time cost is reduced. Compared with the traditional method, the method does not need to actually manufacture rib materials and carry out real experiments, does not need to manually adjust the component proportion of the rib materials, reduces the workload of staff and improves the efficiency.
It should be noted that, the above-mentioned optimization method of the rib shape may be performed by an electronic device, and the electronic device may be a terminal or a server. The terminal comprises, but is not limited to, a computer, a notebook computer, a mobile phone and the like, and the server comprises, but is not limited to, an edge server and a cloud server.
In order to make the technical scheme of the application clearer and easier to understand, the method for optimizing the rib shape provided by the embodiment of the application is described below by combining the drawings from the angle of the electronic equipment. As shown in fig. 1, the method is a flowchart of a rib shape optimization method according to an embodiment of the present application, and the method includes:
S101, the electronic equipment acquires a t-th round parameter vector set of the shape of the dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, the parameter vectors comprise a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, and t is a positive integer.
Fig. 2 is a schematic view of a rib shape according to an embodiment of the present application. The parameter vector of the rib shape may be characterized by a first radius 201, a second radius 202, a lateral length 203, a longitudinal width 204, a thickness 205, a thread pitch 206, and a tilt angle 207 of the rib. The sets of parameter vectors form a set of parameter vectors.
When t=1, the electronic device may obtain the 1 st round of parameter vector set through the following formula:
wherein, For the q-th element in the p-group parameter vector, e.g. p=1, q=2,/>Representing the second radius 202 in the group 1 parameter vector. /(I)Is the total number of parameter vectors in the set of parameter vectors, e.g. 30. /(I)Representing the upper bound of the value of the q-th element,/>Representing the lower bound of the value of the q-th element,/>Representing a fifth random scalar.
When t is greater than 1, under different conditions, the electronic device generates a t+1 round of parameter vector set in different modes, and the description is subsequently performed.
S102, the electronic equipment obtains a plurality of groups of hysteresis effect simulation values according to a plurality of groups of parameter vectors and a predetermined hysteresis effect simulation function.
The hysteresis effect simulation function can be obtained by fitting sample rib data, wherein the sample rib data comprises a sample parameter vector of a rib shape and a hysteresis effect sample value corresponding to the rib shape after an impact experiment is carried out.
After the hysteresis effect simulation function is predetermined, the electronic device can use a plurality of groups of parameter vectors as the input of the hysteresis effect simulation function to obtain a plurality of groups of hysteresis effect simulation values. Therefore, a hysteresis effect value corresponding to the parameter vector of the rib shape can be obtained without carrying out a real impact experiment.
S103, the electronic equipment determines a target hysteresis effect simulation value from a plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer.
The electronic device outputs a hysteresis effect analog value corresponding to each set of parameter vectors, and after obtaining a hysteresis effect analog value corresponding to a plurality of sets (all) of parameter vectors, a target hysteresis effect analog value can be determined from the plurality of sets of hysteresis effect analog values, wherein the target hysteresis effect analog value is a top-ranked N analog value in the plurality of sets of hysteresis effect analog values, the target hysteresis effect analog value corresponds to a t-th round of target parameter vector, and N is a positive integer. For ease of understanding, the description will be given below taking n=3 as an example.
In some embodiments, the electronic device may filter the fitness of each hysteresis effect analog value, and the electronic device may calculate the fitness of the hysteresis effect analog value by the following formula:
wherein, Indicating the fitness of the p-th hysteresis effect analog value,/>Representing hysteresis effect analog value corresponding to the p-th parameter vector,/>Representing a hysteresis maximum, e.g. 0.75,/>Indicating a hysteresis minimum, for example 0.6.
The smaller the fitness of the hysteresis effect analog value is, the better the parameter vector corresponding to the hysteresis effect analog value is represented, and after the fitness of each hysteresis effect analog value is obtained, the sequence can be from small to large, so that the analog value of N before ranking is obtained, namely, the target hysteresis effect analog value is obtained.
It should be noted that, the electronic devices may also be ranked from large to small, and the target hysteresis effect analog value is determined based on a similar principle, and the specific manner is not repeated.
And S104, if the target hysteresis effect simulation value meets the preset condition, the electronic equipment optimizes the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors.
The preset condition may be a preset condition, for example, in this embodiment, the preset condition may be that the fitness corresponding to the target hysteresis effect analog value is within a preset range, for example, within a section [ [ And (c) inner.
If the target hysteresis effect simulation meets the preset condition, the electronic equipment optimizes the rib shape according to the optimal parameter vector in the t-th round of target parameter vector. Therefore, the component proportion and/or shape parameters of the rib are not required to be manually adjusted, the development period of the rib is shortened, and the efficiency is improved.
S105, if the target hysteresis effect simulation value does not meet the preset condition and t reaches the maximum iteration times, the electronic equipment optimizes the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors.
If the target hysteresis effect simulation value does not meet the preset condition and t reaches the maximum iteration times, the electronic equipment optimizes the rib shape according to the optimal parameter vector in the t-wheel target parameter vector.
And S106, if the target hysteresis effect simulation value does not meet the preset condition and t does not reach the maximum iteration times, the electronic equipment acquires a t-th round target distance influence factor corresponding to the t-th round target parameter vector.
If the target hysteresis effect simulation value does not meet the preset condition and t does not reach the maximum iteration number, the electronic equipment acquires a t-th round target distance influence factor corresponding to the t-th round target parameter vector.
In some embodiments, the electronic device may calculate the t-th round target distance impact factor by the following formula:
wherein, Representing the target distance influence factor of the t-th round,/>Representing the linear influence factor of the t-th round,Representing the maximum number of iterations,/>Is a first random scalar. In some examples, t=1 may result in/>，May be a random number of-2 to 2.
And S107, if the absolute value of the target distance influence factor of the t-th round is larger than 1, the electronic equipment updates the parameter vector set of the t-th round by utilizing the parameter vector randomly selected from the parameter vector set of the t-th round to obtain the parameter vector set of the t+1-th round.
After the target distance influence factor of the t-th round is obtained, the magnitude relation between the absolute value of the target distance influence factor and 1 can be compared, and if the absolute value of the target distance influence factor of the t-th round is larger than 1, the electronic equipment updates the parameter vector set of the t-th round by using the parameter vector randomly selected from the parameter vector set of the t-th round to obtain the parameter vector set of the t+1-th round.
In this case, the characterization of the wolf algorithm is in the exploration phase, and the wolf individuals will escape away from some random individual (rather than the optimal solution), thus providing more exploration directions, enhancing the global search capability of the algorithm, and helping to break through the local optimal stagnation.
Specifically, the electronic device updates the t-th round parameter vector set by using a parameter vector randomly selected from the t-th round parameter vector set, which can be implemented by the following formula:
wherein, For the ith parameter vector randomly selected from the set of t-th round parameter vectors,/>Representing the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th round of parameter vector set,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>For a first random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors,Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors. N may be equal to 3 in the above example.
The electronic device may calculate the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th parameter vector set by the following formula：
Wherein,Representing the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th round of parameter vector set,/>Representation/>Random influence factor of/>For the ith parameter vector randomly selected from the set of t-th round parameter vectors,/>Is the p-th parameter vector in the t-th parameter vector.
In some examples, the electronic device may determine the first adaptive coefficient by the following formulaAnd a second adaptive coefficient/>：
Wherein,For the first adaptive coefficient,/>For the second adaptive coefficient, t is the iteration number,/>Is the maximum number of iterations.
After the parameter vector set of the t+1th round is obtained, the parameter vector set of the t+1th round is used for replacing the parameter vector set of the t round, and the process returns to S101 to iterate.
S108, if the absolute value of the target distance influence factor of the t round is smaller than or equal to 1, the electronic equipment updates the parameter vector set of the t round according to the target parameter vector of the t round to obtain the parameter vector set of the t+1 round.
If the absolute value of the target distance influence factor of the t-th round is smaller than or equal to 1, the electronic equipment updates the parameter vector set of the t-th round according to the target parameter vector of the t-th round to obtain the parameter vector set of the t+1-th round. In this case, the wolf algorithm is in a development stage, and the individual wolves converge towards the optimal solution, ensuring the local searching capability and convergence performance of the algorithm.
Specifically, the electronic device updates the t-th round of parameter vector set according to the t-th round of target parameter vector, which can be realized by the following formula:
wherein, For the nth parameter vector of the t-th round of target parameter vectors,/>Is the distance between the p-th parameter vector in the t-th round parameter vector set and the n-th parameter vector in the t-th round target parameter vector,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>Is the first random parameter vector different from the p-th parameter vector in the t-th round parameter vector set,/>Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
The electronic device may calculate the distance between the p-th parameter vector in the t-th parameter vector set and the n-th parameter vector in the t-th target parameter vector by the following formula：
Wherein,Representing the distance between the p-th parameter vector in the t-th round parameter vector set and the n-th parameter vector in the t-th round target parameter vector,/>Representation/>Random influence factor of/>For the nth parameter vector of the t-th round of target parameter vectors,/>Is the p-th parameter vector in the t-th parameter vector.
Wherein the first adaptive coefficientAnd a second adaptive coefficient/>See S107, which is not described here. After the parameter vector set of the t+1st round is obtained, the parameter vector set of the t+1st round is then replaced with the parameter vector set of the t+1st round, and the process returns to S101.
In some embodiments, the electronic device may further obtain a hysteresis effect actual value obtained by testing the rib corresponding to the optimized rib shape, and if a difference between the hysteresis effect actual value and a hysteresis effect analog value corresponding to the optimal parameter vector is greater than a preset difference threshold, update the preset condition and/or the hysteresis effect simulation function, so as to further optimize.
For example, the electronic device may optimize the preset condition by the following formula:
wherein, Is the difference value of hysteresis effect simulation value corresponding to the hysteresis effect true value and the optimal parameter vector,/>Is the true value of hysteresis effect,/>Is a hysteresis effect analog value; /(I)For the adjusted hysteresis maximum,/>For the minimum value of hysteresis after adjustment,/>Represents a hysteresis maximum,/>Indicating a hysteresis minimum.
In some examples, the electronic device may also be based on the aboveAnd optimizing the hysteresis effect simulation function, thereby improving the accuracy of the hysteresis effect simulation function.
Based on the description, the embodiment of the application provides a rib shape optimization method, which comprises the steps of obtaining a t-th round parameter vector set of the shape of a dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, each parameter vector comprises a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclined angle of the dummy rib, t is a positive integer, obtaining a plurality of groups of hysteresis effect simulation values according to the plurality of groups of parameter vectors and a predetermined hysteresis effect simulation function, and then determining a target hysteresis effect simulation value from the plurality of groups of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of groups of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to the t-th round target parameter vector, and N is a positive integer; and if the target hysteresis effect simulation value meets the preset condition, optimizing the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors. In the method, a plurality of groups of parameter vector sets are generated through a gray wolf algorithm, a real impact experiment is simulated through a preset function, and the rib shape is optimized by utilizing the corresponding target parameter vector under the condition that the simulation value meets the preset condition, so that the development period of the rib is shortened, and the time cost is reduced. Compared with the traditional method, the method does not need to truly manufacture rib materials and truly perform experiments, does not need to manually adjust component proportion and/or shape parameters of the rib materials, reduces workload of staff and improves efficiency.
Furthermore, the application improves the traditional wolf algorithm, and introduces two new mechanisms: adaptive wrapping mechanisms and random discrete mechanisms. The self-adaptive surrounding mechanism automatically adjusts the updating mode of the position (parameter vector) of the gray wolf according to the value of the absolute value |A| of the distance influence factor of the algorithm, so that the searching direction is diversified, and the global searching performance of the algorithm is enhanced; the random discrete mechanism introduces the influence of two random wolves on the basis of the population updating formula of the traditional wolf algorithm, and automatically adjusts the searching tendency of the algorithm through the self-adaptive coefficient so as to balance the local searching performance and the global searching performance of the algorithm. Compared with the traditional wolf algorithm, the improved wolf algorithm provided by the application has higher convergence accuracy and is more suitable for optimization of the rib shape of the automobile collision dummy.
Furthermore, in the application, the gray wolf algorithm is firstly applied to rib shape optimization of the automobile collision dummy, and the parameter configuration of the optimal rib shape is searched in the computer simulation layer, so that the rib can meet the design requirement on the premise of not manually changing the rib component proportion, thereby obviously reducing the development period and the development cost. In addition, the stopping condition of the algorithm optimization process is adjusted and modified by combining the actual experimental analysis result, so that the optimization efficiency and accuracy are improved, and the optimization result accords with the actual expectation. Unlike traditional optimization methods based on experiments only, the experimental analysis of the method is only used for adjusting the hysteresis evaluation criteria to correct the hysteresis effect simulation function. After the hysteresis effect simulation function and the impact experiment tend to be consistent, analysis is performed through the hysteresis effect simulation function, so that the impact experiment is replaced. Therefore, the method can effectively reduce the implementation times of the impact experiment.
As shown in fig. 3, the method is a flowchart of another method for optimizing a rib shape according to an embodiment of the present application, and the method includes:
s301, initializing the parameters of the gray wolf algorithm and the population.
In some examples, electronic device initialization、/>、/>、/>Exemplary, A is a random number from-2 to 2, C is a random number from 0 to 2,/>Is 0,/>1. The user may input the size P of the population (e.g., the total number of parameter vectors) and the problem dimension Q, which in this embodiment may be 30 and Q may be 7. The formula for initializing population can be seen in the above embodiment) And will not be described in detail herein. /(I)
S302, calculating the fitness of each gray wolf individual.
After the initialized population is obtained, namely a parameter vector set of the first round, firstly calculating hysteresis effect simulation values corresponding to each parameter vector in the parameter vector set, and then calculating the fitness based on the hysteresis effect simulation values. Specific calculation process refers to the above example, and will not be described herein.
S303, selecting three gray wolf individuals with the fitness of 3.
After the fitness of the complete parameter vector is calculated, three optimal fitness 3 parameter vectors are obtained,、/>、/>The optimal, suboptimal and third optimal parameter vectors in the population are respectively.
S304, judging whether a preset condition is met.
The electronic device can judge、/>、/>Whether the respective corresponding hysteresis effect analog values meet the preset conditions. If not, S305 is performed, and if yes, S310 is performed.
S305, judging whether the iteration times t reach the maximum iteration times max_iter.
If not, S306 is performed, and if so, S310 is performed.
S306, judgingWhether the absolute value of (c) is greater than 1.
If yes, then execution S307; if not, S308 is performed.
S307, updating the t-th round seed group by using the gray wolves randomly selected from the t-th round seed group.
And S308, updating the t-th round of seed group according to the t-th round of target wolf.
Wherein, the individual wolves can be characterized by a parameter vector, and the target wolves can be characterized by a target parameter vector.
S309, updating parameters、/>、/>、/>、/>。
After updating the completion parameter, the process returns to S302.
S310, output。
It should be noted that the description of this embodiment is relatively simple, and a specific implementation may be referred to the above embodiment.
The method for optimizing the rib shape according to the embodiment of the present application is described in detail above with reference to fig. 1 to 3, and the apparatus and the device according to the embodiments of the present application are described below with reference to the accompanying drawings.
As shown in fig. 4, the structure of a rib-shaped optimizing device according to an embodiment of the present application is shown, where the device includes:
An obtaining module 401, configured to obtain a set of t-th round parameter vectors of a shape of a dummy rib, where the set of parameter vectors includes a plurality of sets of parameter vectors, the parameter vectors include a first radius, a second radius, a lateral length, a longitudinal width, a thickness, a pitch of threads, and an inclination angle of the dummy rib, and t is a positive integer;
The simulation module 402 is configured to obtain a plurality of sets of hysteresis effect simulation values according to a plurality of sets of the parameter vectors and a predetermined hysteresis effect simulation function; determining a target hysteresis effect simulation value from the plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer;
And an optimizing module 403, configured to optimize the rib shape according to an optimal parameter vector in the t-th round of target parameter vectors if the target hysteresis effect analog value meets a preset condition.
In some possible implementations, the optimizing module 403 is further configured to optimize the rib shape according to an optimal parameter vector in the t-th round of target parameter vector if the target hysteresis effect analog value does not meet a preset condition and the t reaches a maximum number of iterations.
In some possible implementations, the obtaining module 401 is further configured to obtain a t-th round target distance influencing factor corresponding to the t-th round target parameter vector if the target hysteresis effect analog value does not meet a preset condition and the t does not reach the maximum iteration number; and if the absolute value of the t-th round target distance influence factor is larger than 1, updating the t-th round parameter vector set by using the parameter vector randomly selected from the t-th round parameter vector set to obtain a t+1-th round parameter vector set.
In some possible implementations, the obtaining module 401 is further configured to update the set of t-th round of parameter vectors according to the t-th round of target parameter vector if the absolute value of the t-th round of target distance influencing factor is less than or equal to 1, to obtain a set of t+1-th round of parameter vectors.
In some possible implementations, the obtaining module 401 is specifically configured to update the set of t-th round of parameter vectors by:
wherein, For the ith parameter vector randomly selected from the set of t-th round parameter vectors,/>Representing the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th round of parameter vector set,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>For a first random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors,Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
In some possible implementations, the obtaining module 401 is specifically configured to update the set of t-th round parameter vectors by the following formula:
wherein, For the nth parameter vector of the t-th round of target parameter vectors,/>Is the distance between the p-th parameter vector in the t-th round parameter vector set and the n-th parameter vector in the t-th round target parameter vector,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>Is the first random parameter vector different from the p-th parameter vector in the t-th round parameter vector set,/>Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
In some possible implementations, the apparatus further includes an update module; the acquiring module 401 is further configured to acquire a hysteresis effect true value obtained by testing a rib corresponding to the optimized rib shape;
And the updating module is used for updating the preset condition and/or the hysteresis effect simulation function if the difference value between the hysteresis effect actual value and the hysteresis effect simulation value corresponding to the optimal parameter vector is greater than a preset difference value threshold.
The rib-shaped optimizing device according to the embodiment of the present application may correspond to performing the method described in the embodiment of the present application, and the above and other operations and/or functions of each module/unit of the rib-shaped optimizing device are respectively for implementing the corresponding flow of each method in the embodiment shown in fig. 1, and are not repeated herein for brevity.
The embodiment of the application also provides a computing device. The computing device is particularly adapted to implement the functionality of the rib-shaped optimizing means in the embodiment shown in fig. 4.
As shown in fig. 5, which is a schematic structural diagram of a computing device according to an embodiment of the present application, the computing device 700 includes a bus 701, a processor 702, a communication interface 703, and a memory 704. Communication between processor 702, memory 704 and communication interface 703 is via bus 701.
Bus 701 may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.
The processor 702 may be any one or more of a central processing unit (central processing unit, CPU), a graphics processor (graphics processing unit, GPU), a Microprocessor (MP), or a digital signal processor (DIGITAL SIGNAL processor, DSP).
The communication interface 703 is used for communication with the outside.
The memory 704 may include volatile memory (RAM), such as random access memory (random access memory). The memory 704 may also include a non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, a hard disk drive (HARD DISK DRIVE, HDD) or a solid state drive (SSD STATE DRIVE).
The memory 704 has stored therein executable code that the processor 702 executes to perform the rib shape optimization method described previously.
In particular, in the case where the embodiment shown in fig. 4 is implemented, and each module or unit of the rib-shaped optimizing apparatus described in the embodiment of fig. 4 is implemented by software, software or program code required to perform the functions of each module/unit in fig. 4 may be partially or entirely stored in the memory 704. The processor 702 executes the program codes corresponding to the respective units stored in the memory 704, and performs the above-described rib shape optimization method.
The embodiment of the application also provides a computer readable storage medium. The computer readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), etc. The computer-readable storage medium includes instructions that instruct a computing device to perform the above-described method of optimizing a rib shape applied to a device for optimizing a rib shape.
Embodiments of the present application also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the processes or functions in accordance with embodiments of the present application are fully or partially developed.
The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.).
The computer program product, when executed by a computer, performs any of the methods of optimization of rib shape described above. The computer program product may be a software installation package which may be downloaded and executed on a computer in case any one of the aforementioned rib shape optimization methods is required.
The descriptions of the processes or structures corresponding to the drawings have emphasis, and the descriptions of other processes or structures may be referred to for the parts of a certain process or structure that are not described in detail.
The foregoing is merely illustrative of specific embodiments of the present application, and the scope of the present application is not limited thereto, but any changes or substitutions within the technical scope of the present application should be covered by the scope of the present application.
Claims (7)
1. A method for optimizing rib shape, comprising:
Acquiring a t-th round parameter vector set of the shape of a dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, the parameter vectors comprise a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, and t is a positive integer;
obtaining a plurality of groups of hysteresis effect simulation values according to a plurality of groups of the parameter vectors and a predetermined hysteresis effect simulation function;
Determining a target hysteresis effect simulation value from the plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer;
if the target hysteresis effect simulation value meets a preset condition, optimizing the rib shape according to the optimal parameter vector in the t-th round target parameter vector;
The method further comprises the steps of:
if the target hysteresis effect simulation value does not meet a preset condition and the t reaches the maximum iteration number, optimizing the rib shape according to the optimal parameter vector in the t-th round of target parameter vectors;
The method further comprises the steps of:
If the target hysteresis effect simulation value does not meet a preset condition and the t does not reach the maximum iteration number, acquiring a t-th round target distance influence factor corresponding to the t-th round target parameter vector;
If the absolute value of the t-th round target distance influence factor is larger than 1, updating the t-th round parameter vector set by using a parameter vector randomly selected from the t-th round parameter vector set to obtain a t+1-th round parameter vector set;
The method further comprises the steps of:
And if the absolute value of the t-th round target distance influence factor is smaller than or equal to 1, updating the t-th round parameter vector set according to the t-th round target parameter vector to obtain a t+1th round parameter vector set.
2. The method of claim 1, wherein updating the set of t-th round parameter vectors with a parameter vector randomly selected from the set of t-th round parameter vectors comprises:
wherein, For the ith parameter vector randomly selected from the set of t-th round parameter vectors,/>Representing the distance between the p-th parameter vector and the randomly selected i-th parameter vector in the t-th round of parameter vector set,/>Not equal to 0,/>Representation/>At/>Distance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>Is the first random parameter vector different from the p-th parameter vector in the t-th round parameter vector set,/>Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
3. The method of claim 1, wherein updating the set of t-th round parameter vectors based on the t-th round target parameter vector comprises
Wherein,For the nth parameter vector of the t-th round of target parameter vectors,/>Is the distance between the p-th parameter vector in the t-th round parameter vector set and the n-th parameter vector in the t-th round target parameter vector,/>Not equal to 0,/>Representation/>At the position ofDistance of movement under influence,/>For/>A corresponding distance influencing factor; /(I)Is the p-th parameter vector in the t+1-th parameter vector,/>For the first adaptive coefficient,/>For the second adaptive coefficient,/>Is a third random scalar,/>Is a fourth random scalar,/>Is the first random parameter vector different from the p-th parameter vector in the t-th round parameter vector set,/>Is a second random parameter vector that is different from the p-th parameter vector in the set of t-th round parameter vectors.
4. A method according to any one of claims 1-3, wherein the method further comprises:
Obtaining a hysteresis effect true value obtained by testing the rib corresponding to the optimized rib shape;
And if the difference value between the hysteresis effect actual value and the hysteresis effect simulation value corresponding to the optimal parameter vector is larger than a preset difference value threshold, updating the preset condition and/or the hysteresis effect simulation function.
5. A rib-shaped optimization device, the device comprising:
The acquisition module is used for acquiring a t-th round parameter vector set of the shape of the dummy rib, wherein the parameter vector set comprises a plurality of groups of parameter vectors, the parameter vectors comprise a first radius, a second radius, a transverse length, a longitudinal width, a thickness, a thread pitch and an inclination angle of the dummy rib, and t is a positive integer;
The simulation module is used for obtaining a plurality of groups of hysteresis effect simulation values according to a plurality of groups of the parameter vectors and a predetermined hysteresis effect simulation function; determining a target hysteresis effect simulation value from the plurality of sets of hysteresis effect simulation values, wherein the target hysteresis effect simulation value is a simulation value of N before ranking in the plurality of sets of hysteresis effect simulation values, the target hysteresis effect simulation value corresponds to a t-th round target parameter vector, and N is a positive integer;
the optimization module is used for optimizing the rib shape according to the optimal parameter vector in the t-th round target parameter vector if the target hysteresis effect simulation value meets the preset condition;
the optimization module is further configured to optimize the rib shape according to an optimal parameter vector in the t-th round of target parameter vectors if the target hysteresis effect simulation value does not meet a preset condition and the t reaches a maximum iteration number;
The acquisition module is further configured to acquire a t-th round target distance influence factor corresponding to the t-th round target parameter vector if the target hysteresis effect simulation value does not meet a preset condition and the t does not reach the maximum iteration number; if the absolute value of the t-th round target distance influence factor is larger than 1, updating the t-th round parameter vector set by using a parameter vector randomly selected from the t-th round parameter vector set to obtain a t+1-th round parameter vector set;
the obtaining module is further configured to update the t-th round of parameter vector set according to the t-th round of target parameter vector if the absolute value of the t-th round of target distance influence factor is less than or equal to 1, to obtain a t+1-th round of parameter vector set.
6. A computing device comprising a memory and a processor;
Wherein one or more computer programs are stored in the memory, the one or more computer programs comprising instructions; the instructions, when executed by the processor, cause the computing device to perform the method of any of claims 1 to 4.
7. A computer readable storage medium for storing a computer program for performing the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410176880.1A CN117725705B (en) | 2024-02-08 | 2024-02-08 | Rib shape optimization method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410176880.1A CN117725705B (en) | 2024-02-08 | 2024-02-08 | Rib shape optimization method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117725705A CN117725705A (en) | 2024-03-19 |
| CN117725705B true CN117725705B (en) | 2024-05-31 |
Family
ID=90200200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410176880.1A Active CN117725705B (en) | 2024-02-08 | 2024-02-08 | Rib shape optimization method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117725705B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112989502A (en) * | 2019-12-12 | 2021-06-18 | 厦门雅迅网络股份有限公司 | Method for calculating gear number and transmission ratio of gearbox and storage medium |
| CN113923737A (en) * | 2021-10-11 | 2022-01-11 | 中铁二院工程集团有限责任公司 | Intelligent handover switching method for LTE-M system |
| CN113987938A (en) * | 2021-10-27 | 2022-01-28 | 北京百度网讯科技有限公司 | Process parameter optimization method, device, equipment and storage medium |
| CN115758922A (en) * | 2022-10-26 | 2023-03-07 | 同济大学 | Wind field digital twin system for construction of wind environment test field |
| CN115857311A (en) * | 2022-11-02 | 2023-03-28 | 盐城工学院 | Hysteresis compensation control method of micro-vibration suppression platform |
| CN116992738A (en) * | 2023-08-29 | 2023-11-03 | 西南石油大学 | High-voltage pulse rock breaking numerical simulation method |
-
2024
- 2024-02-08 CN CN202410176880.1A patent/CN117725705B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112989502A (en) * | 2019-12-12 | 2021-06-18 | 厦门雅迅网络股份有限公司 | Method for calculating gear number and transmission ratio of gearbox and storage medium |
| CN113923737A (en) * | 2021-10-11 | 2022-01-11 | 中铁二院工程集团有限责任公司 | Intelligent handover switching method for LTE-M system |
| CN113987938A (en) * | 2021-10-27 | 2022-01-28 | 北京百度网讯科技有限公司 | Process parameter optimization method, device, equipment and storage medium |
| CN115758922A (en) * | 2022-10-26 | 2023-03-07 | 同济大学 | Wind field digital twin system for construction of wind environment test field |
| CN115857311A (en) * | 2022-11-02 | 2023-03-28 | 盐城工学院 | Hysteresis compensation control method of micro-vibration suppression platform |
| CN116992738A (en) * | 2023-08-29 | 2023-11-03 | 西南石油大学 | High-voltage pulse rock breaking numerical simulation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117725705A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021233069A1 (en) | Quantization training and image processing methods and devices, and storage medium | |
| KR20190028531A (en) | Training machine learning models for multiple machine learning tasks | |
| WO2019018375A1 (en) | Neural architecture search for convolutional neural networks | |
| CN110597878A (en) | Cross-modal retrieval method, device, equipment and medium for multi-modal data | |
| EP3944105A1 (en) | Systems and methods for design parameter selection | |
| CN104573277A (en) | Vehicle suspension system performance analysis method | |
| US20220229640A1 (en) | Systems and methods for design parameter selection | |
| CN112288124A (en) | Information processing program, information processing method, and information processing apparatus | |
| CN110580897B (en) | Audio verification method and device, storage medium and electronic equipment | |
| US9098673B2 (en) | Structural optimization for vehicle crashworthiness | |
| CN117725705B (en) | Rib shape optimization method, device, equipment and storage medium | |
| CN109960841B (en) | Fluid surface tension simulation method, terminal equipment and storage medium | |
| JP2022003423A (en) | Learning method, learning device and program | |
| US20220019869A1 (en) | Hardware-optimized neural architecture search | |
| US8700686B1 (en) | Robust estimation of time varying parameters | |
| CN112417463A (en) | Software vulnerability prediction method and device, computer equipment and storage medium | |
| CN116306879A (en) | Data processing method, device, electronic equipment and storage medium | |
| CN116011071A (en) | Method and system for analyzing structural reliability of air building machine based on active learning | |
| CN113554097B (en) | Model quantization method and device, electronic equipment and storage medium | |
| CN115062777A (en) | Method for quantizing convolutional neural network, device, and storage medium | |
| CN114595627A (en) | Model quantization method, device, equipment and storage medium | |
| CN114358260A (en) | Neural network model building method, device, equipment and storage medium | |
| EP4189606A1 (en) | Neural architecture and hardware accelerator search | |
| CN116152907A (en) | Gesture reconstruction method and device and electronic equipment | |
| CN115809695A (en) | Model training method based on physical information neural network and related device |
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 |