CN110728075A - Method for optimizing cryogenic process parameters by MOA algorithm - Google Patents
Method for optimizing cryogenic process parameters by MOA algorithm Download PDFInfo
- Publication number
- CN110728075A CN110728075A CN201911021776.0A CN201911021776A CN110728075A CN 110728075 A CN110728075 A CN 110728075A CN 201911021776 A CN201911021776 A CN 201911021776A CN 110728075 A CN110728075 A CN 110728075A
- Authority
- CN
- China
- Prior art keywords
- parameter
- local
- global
- optimal
- elements
- 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.)
- Pending
Links
Images
Landscapes
- Separation By Low-Temperature Treatments (AREA)
Abstract
The invention discloses a method for optimizing a cryogenic process parameter by utilizing an MOA algorithm, which comprises the following steps of: firstly, constructing a basic framework of an MOA optimal process parameter algorithm; according to the product quality characteristic, namely a search element in the process parameter diversified structure, a basic framework of an MOA optimal process parameter algorithm is used for parameter setting and code programming, the optimal value of a regression equation is searched, and an algorithm and a fitness change curve chart for searching the MOA optimal cryogenic process parameter of the product life are established; finally, the two are combined, and the optimum parameter combination of the cryogenic temperature and the heat preservation time is found out, so that the service life Y is optimized. The invention solves the problem of large mass loss caused by the design stage of the existing screw tap. The method can effectively relieve the mutual constraint between the global chain parameter elements and the local parameter elements, and has good applicability and superiority in the optimization process.
Description
Technical Field
The invention belongs to the field of product material design and research, and particularly relates to a method for optimizing cryogenic process parameters by utilizing an MOA algorithm.
Background
Social development drives the improvement of consumption capacity, and the requirement of users on cutter materials is higher. The service life is one of the key quality characteristics of the screw tap, the quality of the screw tap is directly determined by the service life, and the quality fault can seriously affect the service performance of the screw tap and even directly affect the safety of the screw tap, so that the screw tap loses the whole service function and becomes a waste product. The quality loss caused in the design stage of the screw tap is the largest and is more than the loss caused in the production and manufacturing links. The related problems of how to efficiently improve the quality and reduce the development cost from the design source have become the hot and difficult problems of the study of the scholars.
Disclosure of Invention
In order to overcome the defect of large mass loss caused by the design stage of the existing screw tap, the invention provides the method for optimizing the cryogenic process parameters by utilizing the MOA algorithm, which can effectively eliminate the mutual constraint between the global chain parameter elements and the local parameter elements and has good applicability and superiority in the optimization process.
The technical scheme adopted by the invention for realizing the purpose is as follows:
a method for optimizing a cryogenic process parameter by utilizing an MOA algorithm comprises the following steps: firstly, constructing a basic framework of an MOA optimal process parameter algorithm by a process parameter search element and a process parameter diversified structure; according to the product quality characteristic, namely a search element in the process parameter diversified structure, a basic framework of an MOA optimal process parameter algorithm is used for parameter setting and code programming, the optimal value of a regression equation is searched, the algorithm for searching the MOA optimal cryogenic process parameter of the product life is established, and the algorithm for searching the MOA optimal cryogenic process parameter is used for a fitness variation curve graph of the cryogenic process parameter; finally, the two are combined, and the optimal parameter combination of the cryogenic temperature and the heat preservation time is found out, so that the quality characteristic of the product is optimal.
Further, a basic framework of the MOA optimal process parameter algorithm is composed of process parameter search elements and a process parameter diversified structure; the technological parameter diversification structure is a platform and a carrier for carrying out global parameter search and local parameter search by a parameter search element, the parameter search element is organized, and a global optimal parameter combination is obtained after multiple times of number cycles through the global parameter search and the local parameter search, so that the optimization of the technological parameter combination is realized; according to different division, the technological parameter search elements of the MOA algorithm are divided into global parameter elements G (a, b) and local parameter elements L (a, b).
Furthermore, the global parameter element G (a, b) is a solution composed of n global parameter elements generated in the whole parameter solution field, and forms an n-dimensional global parameter linked list; the local parameter element L (a, b) is a feasible solution randomly generated in a local parameter solution neighborhood by taking a certain global parameter element as a center. The global parameter elements G (a, b) are exploration facing the whole parameter field, a valuable search area is determined, a potential optimal parameter solution field is found, and the local parameter elements L (a, b) are responsible for carrying out local exploration on each parameter solution field so as to find a parameter solution with better local quality; the local parameter search unit is to search the local parameter solution area again in more detail. The global parameter elements are randomly generated in the whole parameter field, and the local parameter elements are randomly generated in the parameter neighborhood taking the global parameter elements as the center. The process parameter diversified structure is formed according to the following principle: the fitness value of the global parameter element determines the orientation of the global parameter element in the global parameter linked list, and the value of the global parameter element is gradually increased from right to left. The local parameter linked list is hung on the global parameter searching element through a pointer, the depth of the local linked list is gradually increased from right to left along with the value of the global linked list, the position of the local parameter element in the local linked list is determined by the fitness of the local parameter element, and the value of the local parameter element is gradually increased from bottom to top.
Furthermore, the linked list in the process parameter diversified structure is realized by a pointer, and comprises a global parameter linked list and a local parameter linked list which are ordered structures taking parameter element fitness values as keywords; the first row in the parameter diversification structure is a global parameter linked list used for storing global parameter elements and memorizing and transferring global parameter search information, and each vertical column is a local parameter linked list used for storing local parameter elements and memorizing information of each local process parameter element.
Further, the algorithm for finding the MOA optimal cryogenic process parameter of the product life specifically comprises the following steps:
(1) carrying out initialization setting on parameters: the number of the global parameter elements is n, the parameters a1 and a2 are upper and lower limits of temperature, the parameters b1 and b2 are upper and lower limits of time, r1 is the radius of temperature, r2 is the radius of time, the radius of a local neighborhood of the parameter is 0.025, and the maximum adjusting times is 1000;
(2) generating global parameter elements, carrying out global exploration, constructing the global parameter elements describing temperature and time process influence factors, and evaluating the global parameter elements;
(3) adjusting the global parameter list: a plurality of process parameters with better time and temperature are reserved and used as a center of local development to lay a foundation for local development; time and temperature process parameters inferior to or similar to global parameter elements are eliminated; therefore, the global parameter elements can be prevented from being repeatedly explored in the same field, and the exploration efficiency and the exploration capacity of the global parameter elements are improved;
(4) generating local parameter elements: local parameter elements for describing time and temperature process influence factors are constructed, and the local parameter elements are locally searched and evaluated in a neighborhood taking the global parameter elements as the center; aims to obtain better time and temperature process parameters through local adjustment;
(5) adjusting the local parameter list: after the local parameter is adjusted, if a better time and temperature process parameter is found and the local parameter element is better than the global parameter element, the local parameter element replaces the global parameter element and is used as the basis for adjusting a local vertical list next time;
(6) judging whether the algorithm meets the preset requirement of the product, if so, stopping adjustment, otherwise, returning to the step (3) to continue the circular adjustment;
(7) and obtaining the optimal design of the product quality characteristics, wherein the obtained parameter search element is the optimal combination of the product process parameters at the upper left of the process parameter diversified structure.
Further, the step of finding the optimal value of the regression equation is as follows: according to the condition that the maximum of the product quality characteristic life Y is a target, the temperature A and the time B are used as parameters to be optimized and coded as search elements, under the feasible condition, the larger the response Y is, the more optimal the response Y is, the fitness function is determined by the formula (1), global and local parameter elements are evaluated through the fitness function,
Ysmall＝165.6+2.431A-35.56B+0.00832A2+5.44B2(1)
Namely, a group of optimal sub-zero treatment process parameter combinations (A, B) is obtained, so that the output service life Y is optimal.
According to the invention, the optimal process parameters of the screw tap are solved by utilizing the characteristic that an MOA intelligent method realizes global search of a solution space through efficient communication and cooperation among different search elements, and finally, the optimal combination of the process parameters is determined by an MOA intelligent optimization method, so that the product life of the screw tap can be effectively prolonged, and a new thinking method is provided for the optimization design of quality characteristics.
According to the invention, programming operation software is designed on a computer, the MOA intelligent method operates in a technological parameter diversified structure in a parameter coding form, parameter solving is not needed, complex calculation is effectively avoided, and the MOA intelligent method has good applicability and superiority in an optimization process; the MOA intelligent method utilizes the technological parameter diversified structure to conduct division and cooperation of the parameter search elements, the exploration characteristic effectively relieves the mutual constraint between the global chain parameter elements and the local parameter elements, and the parameter search elements can be prevented from falling into the optimal limitation in advance.
Drawings
The invention will now be further described with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a process parameter diversification structure using an optimized process memory algorithm (MOA) for a cryogenic process;
FIG. 2 is a flow chart of an optimization process memory algorithm (MOA) for cryogenic process parameters;
FIG. 3 is a graph of the optimization process memory algorithm (MOA) applied to the change of the parameter fitness of the cryogenic process.
Detailed Description
As shown in fig. 1 to 3, the method for optimizing the cryogenic process parameters by using the MOA algorithm of the present embodiment includes the following steps: firstly, constructing a basic framework of an MOA optimal process parameter algorithm by a process parameter search element and a process parameter diversified structure; according to the product quality characteristic, namely a search element in the process parameter diversified structure, a basic framework of an MOA optimal process parameter algorithm is used for parameter setting and code programming, the optimal value of a regression equation is searched, the algorithm for searching the MOA optimal cryogenic process parameter of the product life is established, and the algorithm for searching the MOA optimal cryogenic process parameter is used for a fitness variation curve graph of the cryogenic process parameter; finally, the two are combined, and the optimal parameter combination of the cryogenic temperature and the heat preservation time is found out, so that the quality characteristic of the product is optimal.
Further, a basic framework of the MOA optimal process parameter algorithm is composed of process parameter search elements and a process parameter diversified structure; the technological parameter diversification structure is a platform and a carrier for carrying out global parameter search and local parameter search by a parameter search element, the parameter search element is organized, and a global optimal parameter combination is obtained after multiple times of number cycles through the global parameter search and the local parameter search, so that the optimization of the technological parameter combination is realized; according to different division, the technological parameter search elements of the MOA algorithm are divided into global parameter elements G (a, b) and local parameter elements L (a, b).
Furthermore, the global parameter element G (a, b) is a solution composed of n global parameter elements generated in the whole parameter solution field, and forms an n-dimensional global parameter linked list; the local parameter element L (a, b) is a feasible solution randomly generated in a local parameter solution neighborhood by taking a certain global parameter element as a center. The global parameter elements G (a, b) are exploration facing the whole parameter field, a valuable search area is determined, a potential optimal parameter solution field is found, and the local parameter elements L (a, b) are responsible for carrying out local exploration on each parameter solution field so as to find a parameter solution with better local quality; the local parameter search unit is to search the local parameter solution area again in more detail. The global parameter elements are randomly generated in the whole parameter field, and the local parameter elements are randomly generated in the parameter neighborhood taking the global parameter elements as the center. The process parameter diversified structure is formed according to the following principle: the fitness value of the global parameter element determines the orientation of the global parameter element in the global parameter linked list, and the value of the global parameter element is gradually increased from right to left. The local parameter linked list is hung on the global parameter searching element through a pointer, the depth of the local linked list is gradually increased from right to left along with the value of the global linked list, the position of the local parameter element in the local linked list is determined by the fitness of the local parameter element, and the value of the local parameter element is gradually increased from bottom to top.
Furthermore, the linked list in the process parameter diversified structure is realized by a pointer, and comprises a global parameter linked list and a local parameter linked list which are ordered structures taking parameter element fitness values as keywords; the first row in the parameter diversification structure is a global parameter linked list used for storing global parameter elements and memorizing and transferring global parameter search information, and each vertical column is a local parameter linked list used for storing local parameter elements and memorizing information of each local process parameter element.
Further, the algorithm for finding the MOA optimal cryogenic process parameter of the product life specifically comprises the following steps:
(1) carrying out initialization setting on parameters: the number of the global parameter elements is n, the parameters a1 and a2 are upper and lower limits of temperature, the parameters b1 and b2 are upper and lower limits of time, r1 is the radius of temperature, r2 is the radius of time, the radius of a local neighborhood of the parameter is 0.025, and the maximum adjusting times is 1000;
(2) generating global parameter elements, carrying out global exploration, constructing the global parameter elements describing temperature and time process influence factors, and evaluating the global parameter elements;
(3) adjusting the global parameter list: a plurality of process parameters with better time and temperature are reserved and used as a center of local development to lay a foundation for local development; time and temperature process parameters inferior to or similar to global parameter elements are eliminated; therefore, the global parameter elements can be prevented from being repeatedly explored in the same field, and the exploration efficiency and the exploration capacity of the global parameter elements are improved;
(4) generating local parameter elements: local parameter elements for describing time and temperature process influence factors are constructed, and the local parameter elements are locally searched and evaluated in a neighborhood taking the global parameter elements as the center; aims to obtain better time and temperature process parameters through local adjustment;
(5) adjusting the local parameter list: after the local parameter is adjusted, if a better time and temperature process parameter is found and the local parameter element is better than the global parameter element, the local parameter element replaces the global parameter element and is used as the basis for adjusting a local vertical list next time;
(6) judging whether the algorithm meets the preset requirement of the product, if so, stopping adjustment, otherwise, returning to the step (3) to continue the circular adjustment;
(7) and obtaining the optimal design of the product quality characteristics, wherein the obtained parameter search element is the optimal combination of the product process parameters at the upper left of the process parameter diversified structure.
Further, the step of finding the optimal value of the regression equation is as follows: under feasible conditions, the larger the response Y is, the better the response Y is, the fitness function is determined by the formula (1), global and local parameter elements are evaluated through the fitness function,
Ysmall＝165.6+2.431A-35.56B+0.00832A2+5(44)B2
Namely, a group of optimal sub-zero treatment process parameter combinations (A, B) is obtained, so that the output service life Y is optimal.
According to the invention, an optimization process memory algorithm (MOA) is used for the cryogenic process parameters, and the influence of the tap cryogenic process on the life of the tap is taken as an example to carry out research through the optimization process memory algorithm (MOA), wherein the method comprises the following steps:
firstly, constructing a basic framework of an MOA optimal process parameter algorithm by a process parameter search element and a process parameter diversified structure; according to the fact that the product quality characteristic life Y is the maximum target, the temperature A and the time B are used as parameters to be optimized and coded as search elements, any possible group (A, B) is one search element in the technological parameter diversified structure, a basic framework of an MOA optimal technological parameter algorithm is used for parameter setting and code programming, an optimal value of a regression equation is searched, and an algorithm for searching the MOA optimal cryogenic technological parameter of the product life and a cryogenic technological parameter adaptability change curve graph are established; finally, the two are combined, and the optimum parameter combination of the cryogenic temperature and the heat preservation time is found out, so that the service life Y is optimized.
And (3) searching the optimal value of the regression equation by utilizing an MOA algorithm, wherein the larger the response Y is, the better the response Y is, the fitness function is determined by the formula (1), and the global and local parameter elements are evaluated by the fitness function, namely, a group of optimal cryogenic treatment process parameter combinations (A, B) are solved, so that the output life Y is optimal.
YSmall＝165.6+2.431A-35.56B+0.00832A2+5.44B2(1)
The flow of the algorithm for establishing the optimal cryogenic process parameter for finding the service life of the screw tap by using the MOA is as follows, and the method is specifically completed by the following steps.
(1) And carrying out initialization setting on the parameters. The number of global parameter elements is 10, parameters a1 and a2 are upper and lower limits of temperature, parameters b1 and b2 are upper and lower limits of time, r1 is the radius of temperature, r2 is the radius of time, the radius of a local neighborhood of the parameter is 0.025, and the maximum adjustment frequency is 1000.
(2) A global parameter element is generated. And performing global exploration, constructing global parameter elements for describing temperature and time process influence factors, and evaluating the global parameter elements.
(3) The global parameter list is adjusted. A plurality of process parameters with better time and temperature are reserved and used as the center of local development to lay a foundation for local development. Time and temperature process parameters which are inferior to or similar to the global parameter elements are eliminated, so that the global parameter elements can be prevented from being repeatedly explored in the same field, and the exploration efficiency and the exploration capacity of the global parameter elements are improved.
(4) Local parameter elements are generated. And local parameter elements for describing time and temperature process influence factors are constructed, and the local parameter elements are locally developed and evaluated in a neighborhood taking the global parameter elements as the center, so that better time and temperature process parameters are obtained through local adjustment.
(5) The local parameter list is adjusted. After the local adjustment, if a better time and temperature process parameter is found and the local parameter element is better than the global parameter element, it will replace the global parameter element and be used as the basis for the next adjustment of the local vertical list.
(6) And judging whether the algorithm meets the preset requirement. If the preset requirement is met, stopping the adjustment, otherwise returning to (3) and continuing the cycle adjustment.
(7) And obtaining the optimal design of the quality characteristic of the screw tap. And the obtained parameter searching element is the optimal combination of the screw tap process parameters at the upper left of the process parameter diversified structure.
Further, the code programming is carried out through an MOA optimal process parameter algorithm
The structure body adopts a process parameter diversified structure, the number of global parameter elements in the global parameter linked list is 10, the number of local parameter elements in the local parameter linked list is increased from right to left, the length of the local parameter linked list corresponding to the jth global parameter element is 10-j, the total number of search elements in the process parameter diversified structure is 65, the radius of a local neighborhood of the parameter is set to be 0.025, and the maximum adjustment times is 1000 times.
The MOA optimal process parameter code is programmed as follows:
results of MOA optimal Process parameters
The optimal influence factors A of the MOA algorithm optimization are-146.094 ℃ and B of 3.268h, namely the cryogenic temperature A is-146.094 ℃, the heat preservation time is 3.268h, the number of the machining holes is 75.6179, and the quality characteristic service life Y of the screw tap is optimal.
Claims (6)
1. A method for optimizing a cryogenic process parameter by utilizing an MOA algorithm is characterized by comprising the following steps: firstly, constructing a basic framework of an MOA optimal process parameter algorithm by a process parameter search element and a process parameter diversified structure; according to the product quality characteristic, namely a search element in the process parameter diversified structure, a basic framework of an MOA optimal process parameter algorithm is used for parameter setting and code programming, the optimal value of a regression equation is searched, the algorithm for searching the MOA optimal cryogenic process parameter of the product life is established, and the algorithm for searching the MOA optimal cryogenic process parameter is used for a fitness variation curve graph of the cryogenic process parameter; finally, the two are combined, and the optimal parameter combination of the cryogenic temperature and the heat preservation time is found out, so that the quality characteristic of the product is optimal.
2. The method for optimizing cryogenic process parameters by utilizing MOA algorithm according to claim 1, wherein the basic framework of the MOA optimal process parameter algorithm is composed of process parameter search elements and process parameter diversified structures; the technological parameter diversification structure is a platform and a carrier for carrying out global parameter search and local parameter search by a parameter search element, the parameter search element is organized, and a global optimal parameter combination is obtained after multiple times of number cycles through the global parameter search and the local parameter search, so that the optimization of the technological parameter combination is realized; according to different division, the technological parameter search elements of the MOA algorithm are divided into global parameter elements G (a, b) and local parameter elements L (a, b).
3. The method for optimizing cryogenic process parameters by utilizing MOA algorithm according to claim 2, wherein the global parameter element G (a, b) is a solution consisting of n global parameter elements generated in the whole parameter solution field, and forms an n-dimensional global parameter linked list; the local parameter element L (a, b) is a feasible solution randomly generated in a local parameter solution neighborhood by taking a certain global parameter element as a center.
4. The method for optimizing cryogenic process parameters by utilizing MOA algorithm according to claim 2, wherein the linked lists in the process parameter diversification structure are realized by pointers, and comprise a global parameter linked list and a local parameter linked list which are ordered structures taking parameter element fitness values as keywords; the first row in the parameter diversification structure is a global parameter linked list used for storing global parameter elements and memorizing and transferring global parameter search information, and each vertical column is a local parameter linked list used for storing local parameter elements and memorizing information of each local process parameter element.
5. The method for optimizing cryogenic process parameters by utilizing MOA algorithm according to claim 1, wherein the establishing of the MOA optimal cryogenic process parameter algorithm for finding the product life specifically comprises the following steps:
(1) carrying out initialization setting on parameters: the number of the global parameter elements is n, the parameters a1 and a2 are upper and lower limits of temperature, the parameters b1 and b2 are upper and lower limits of time, r1 is the radius of temperature, r2 is the radius of time, the radius of a local neighborhood of the parameter is 0.025, and the maximum adjusting times is 1000;
(2) generating global parameter elements, carrying out global exploration, constructing the global parameter elements describing temperature and time process influence factors, and evaluating the global parameter elements;
(3) adjusting the global parameter list: a plurality of process parameters with better time and temperature are reserved and used as a center of local development to lay a foundation for local development; time and temperature process parameters inferior to or similar to global parameter elements are eliminated;
(4) generating local parameter elements: local parameter elements for describing time and temperature process influence factors are constructed, and the local parameter elements are locally searched and evaluated in a neighborhood taking the global parameter elements as the center;
(5) adjusting the local parameter list: after the local parameter is adjusted, if a better time and temperature process parameter is found and the local parameter element is better than the global parameter element, the local parameter element replaces the global parameter element and is used as the basis for adjusting a local vertical list next time;
(6) judging whether the algorithm meets the preset requirement of the product, if so, stopping adjustment, and if not, returning to the step (3) to continue the circular adjustment;
(7) and obtaining the optimal design of the product quality characteristics, wherein the obtained parameter search element is the optimal combination of the product process parameters at the upper left of the process parameter diversified structure.
6. The method for optimizing cryogenic process parameters using MOA algorithm according to claim 1, wherein the step of finding the optimal value of the regression equation is as follows: according to the condition that the maximum of the product quality characteristic life Y is a target, the temperature A and the time B are used as parameters to be optimized and coded as search elements, under the feasible condition, the larger the response Y is, the more optimal the response Y is, the fitness function is determined by the formula (1), global and local parameter elements are evaluated through the fitness function,
Ysmall＝165.6+2.431A-35.56B+0.00832A2+5.44B2(1)
Namely, a group of optimal sub-zero treatment process parameter combinations (A, B) is obtained, so that the output service life Y is optimal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911021776.0A CN110728075A (en) | 2019-10-25 | 2019-10-25 | Method for optimizing cryogenic process parameters by MOA algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911021776.0A CN110728075A (en) | 2019-10-25 | 2019-10-25 | Method for optimizing cryogenic process parameters by MOA algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110728075A true CN110728075A (en) | 2020-01-24 |
Family
ID=69222034
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911021776.0A Pending CN110728075A (en) | 2019-10-25 | 2019-10-25 | Method for optimizing cryogenic process parameters by MOA algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728075A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112965722A (en) * | 2021-03-03 | 2021-06-15 | 深圳华大九天科技有限公司 | Verilog-A model optimization method, electronic device and computer readable storage medium |
| CN116415434A (en) * | 2023-04-07 | 2023-07-11 | 平湖市山特螺纹工具有限公司 | Screw tap processing technique and system for high-strength steel |
| CN117407817A (en) * | 2023-10-25 | 2024-01-16 | 国网四川省电力公司绵阳供电公司 | Abnormality monitoring system of power distribution automation machine room |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202461727U (en) * | 2011-12-23 | 2012-10-03 | 成都发动机（集团）有限公司 | Three assembly tap for optimizing allowance |
| CN103164709A (en) * | 2012-12-24 | 2013-06-19 | 天津工业大学 | Method for optimizing support vector machine based on tabu search algorithm |
-
2019
- 2019-10-25 CN CN201911021776.0A patent/CN110728075A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202461727U (en) * | 2011-12-23 | 2012-10-03 | 成都发动机（集团）有限公司 | Three assembly tap for optimizing allowance |
| CN103164709A (en) * | 2012-12-24 | 2013-06-19 | 天津工业大学 | Method for optimizing support vector machine based on tabu search algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 郭映霞: "丝锥质量特性的稳健设计", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅰ辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112965722A (en) * | 2021-03-03 | 2021-06-15 | 深圳华大九天科技有限公司 | Verilog-A model optimization method, electronic device and computer readable storage medium |
| CN116415434A (en) * | 2023-04-07 | 2023-07-11 | 平湖市山特螺纹工具有限公司 | Screw tap processing technique and system for high-strength steel |
| CN116415434B (en) * | 2023-04-07 | 2024-05-24 | 平湖市山特螺纹工具有限公司 | Screw tap processing technique and system for high-strength steel |
| CN117407817A (en) * | 2023-10-25 | 2024-01-16 | 国网四川省电力公司绵阳供电公司 | Abnormality monitoring system of power distribution automation machine room |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728075A (en) | Method for optimizing cryogenic process parameters by MOA algorithm | |
| CN105955190B (en) | A kind of holes machining path planning method based on cuckoo searching algorithm | |
| Zhang et al. | A matrix cube-based estimation of distribution algorithm for the energy-efficient distributed assembly permutation flow-shop scheduling problem | |
| CN103676645A (en) | Mining method for association rules in time series data flows | |
| CN113537592B (en) | Oil and gas reservoir yield prediction method and device based on long-short-term memory network | |
| Seo et al. | Evolutionary genetic algorithm for efficient clustering of wireless sensor networks | |
| CN102799682A (en) | Massive data preprocessing method and system | |
| CN103793577A (en) | Method for optimizing and controlling little-cutting fluid processing technology in machining process | |
| John et al. | A survey of energy-aware cluster head selection techniques in wireless sensor network | |
| CN113157694A (en) | Database index generation method based on reinforcement learning | |
| CN116307533B (en) | Reservoir group flood control dispatching intelligent method, system and medium | |
| CN106503092A (en) | A kind of method using multidimensional technique construction Spatial Multi-Dimensional degree search tree | |
| CN103150336B (en) | A kind of skyline on-line calculation method based on user clustering | |
| Ducange et al. | Multi-objective evolutionary fuzzy systems | |
| CN110119408A (en) | Mobile object continuous-query method under geographical space real-time streaming data | |
| Fang | [Retracted] An Effective Hybrid Multiobjective Flexible Job Shop Scheduling Problem Based on Improved Genetic Algorithm | |
| CN114066014A (en) | Time sequence prediction method for machine learning based on asynchronous parallel multi-arm slot machine | |
| CN109543921A (en) | The production scheduled production method of oil pipes Flow Shop based on improved adaptive GA-IAGA | |
| Qi et al. | A method for stochastic L-BFGS optimization | |
| CN111985162A (en) | Replacement flow shop control method and system based on deep learning | |
| CN103336829B (en) | query optimization method based on simulated annealing algorithm | |
| CN113554216B (en) | Kfold-LSTM hybrid variation optimizing polymer hybrid manufacturing multi-objective optimizing method | |
| CN103020767A (en) | Method for intelligently manufacturing steel assembly and device for achieving method | |
| Jo et al. | BitGourmet: Deterministic Approximation via Optimized Bit Selection. | |
| CN104570759B (en) | The quick Binomial Trees of control system midpoint orientation problem |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200124 |
|
| RJ01 | Rejection of invention patent application after publication |