CN111144569A - Yield improvement applicable model optimization method based on genetic algorithm - Google Patents
Yield improvement applicable model optimization method based on genetic algorithm Download PDFInfo
- Publication number
- CN111144569A CN111144569A CN201911353118.1A CN201911353118A CN111144569A CN 111144569 A CN111144569 A CN 111144569A CN 201911353118 A CN201911353118 A CN 201911353118A CN 111144569 A CN111144569 A CN 111144569A
- Authority
- CN
- China
- Prior art keywords
- genetic algorithm
- model
- yield improvement
- steps
- fitness
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 46
- 230000002068 genetic effect Effects 0.000 title claims abstract description 40
- 230000006872 improvement Effects 0.000 title claims abstract description 23
- 238000005457 optimization Methods 0.000 title claims abstract description 19
- 239000013256 coordination polymer Substances 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims description 17
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 13
- 230000035772 mutation Effects 0.000 claims description 11
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 4
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 abstract description 5
- 239000010931 gold Substances 0.000 abstract description 5
- 229910052737 gold Inorganic materials 0.000 abstract description 5
- 230000006866 deterioration Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 108090000623 proteins and genes Proteins 0.000 description 5
- 238000012795 verification Methods 0.000 description 4
- 210000000349 chromosome Anatomy 0.000 description 3
- 238000001259 photo etching Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000000206 photolithography Methods 0.000 description 2
- 230000010076 replication Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010429 evolutionary process Effects 0.000 description 1
- 230000007614 genetic variation Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides an optimization method of yield improvement applicable model based on genetic algorithm, which optimizes parameters of the model, optimizes fitness function and perfects the model by optimizing the deception problem of the algorithm, simulates the biological evolution form of product passing by optimizing the established genetic algorithm model, on one hand, searches the gold route of the product passing, and simultaneously predicts the CP/Bin upper limit value of the product based on the organic condition, provides reference for the control and optimization of an online machine station, and improves the product quality; on the other hand, the machine with poor performance can be highlighted, the deterioration lower limit value of the product based on the CP/Bin under the current machine condition is predicted, reference is provided for online machine management and control and adjustment, the product quality is stable, the labor cost is saved, and meanwhile, the problem is solved more quickly and accurately.
Description
Technical Field
The invention relates to the field of industrial big data, in particular to an optimization method of a yield improvement applicable model based on a genetic algorithm.
Background
Genetic Algorithm (GA) is a self-organizing, self-adaptive artificial intelligence technology for simulating the natural biological evolution process and mechanism to solve the extreme value problem. The artificial neural network model simulates the natural evolution theory of Darwin and the genetic variation theory of Mongolian and has solid biological foundation; it provides a simulation of biological intelligence from the point of view of intelligent generation process, having clear cognitive meaning; it is suitable for any kind of function with or without expression, and has realizable parallel computing behavior; it can solve any kind of practical problem, and has wide application value. Genetic algorithms begin with a population representing a potential set of solutions to a problem, and a population is composed of a certain number of individuals that are genetically encoded. Each individual is actually a chromosome-bearing cadaver. Chromosomes, which are the main vector of genetic material, are a collection of genes whose internal expression (i.e., genotype) is a certain combination of genes that determines the external expression of an individual's shape, e.g., black hair, is characterized by a certain combination of genes in the chromosome that controls this characteristic. Therefore, mapping from phenotype to genotype, i.e., coding work, needs to be accomplished at the outset. Since the work of copying gene codes is complicated, simplification is generally performed, such as binary coding. After the initial generation population is generated, better and better approximate solutions are generated by generation evolution according to the principle that survival of suitable persons is superior or inferior. In each generation, individuals are selected according to the fitness of the individuals in the problem domain, and combined intersection and variation are carried out by means of genetic operators of natural genetics to generate a population representing a new solution set. The process leads the population of the later generation like the natural evolution to be more adaptive to the environment than the prior generation, and the optimal individual in the population of the later generation can be used as the approximate optimal solution of the problem after being decoded (reference documents: Wang Xiao Ming's parallel works' theory of genetic algorithm, application and software implementation 'and Zhang Wen Xie Liang's happy works 'mathematical basis of genetic algorithm').
For a mature semiconductor process, the product quality (CP/FT) depends mainly on the performance of the process tools and their shipment paths. Generally, the method for evaluating the performance of the machine is to analyze some type of data, and determine the difference between the performance of the machine and the performance of the machine according to the commonness (common) and the experience of the engineer. For example: if the CP of lot passing through a certain machine is significantly lower than that of other machines, the machine is considered to have poor performance, the machine is highlighted (highlight), and an allocation engineer deals with an event/problem (case), so that the product quality is stable, and a gold route (gold path) cannot be obtained. Meanwhile, for a product, engineers do various methods to improve the yield, but no method can estimate the upper limit of the yield at present, and the problem searching machine is obtained by a series of data analysis and comprehensive experience judgment of the engineers, so that the time consumption is long, the requirements on the engineers for processing the problems are high, the time and labor cost investment is large, and when the problems are complex, the efficiency is obviously reduced.
Therefore, a new method is needed to solve the above problems.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide an optimization method for a yield improvement adaptive model based on a genetic algorithm, which is used to solve the problems of unstable product quality and high labor cost in the prior art.
In order to achieve the above and other related objects, the present invention provides a method for optimizing a yield improvement adaptive model based on a genetic algorithm, the method at least comprising the following steps: firstly, carrying out scale transformation of a fitness function according to an existing genetic algorithm model and a CP or WAT characteristic value of a product to optimize the deception problem of the algorithm; step two, optimizing a crossover operator, a mutation interval and a deletion operator in the genetic algorithm model; step three, introducing a population uniform scale to perform linear sequencing so as to optimize the fitness function; and step four, expanding the global search function and evolving characteristic values to perfect the genetic algorithm model.
Preferably, the scaling of the fitness function performed in step one is such that the average value of the original fitness is equal to the average value of the scaled fitness.
Preferably, the scale transformation of the fitness function performed in the step one is performed so that the maximum value of the transformed fitness is equal to a specified multiple of the average value of the original fitness.
Preferably, the crossover operator in step two is 0.25.
Preferably, the mutation operator in step two is 0.005.
Preferably, the variation range in the second step is 60 to 100.
Preferably, the deletion operator in step two is 0.005.
Preferably, the step three, the introducing the population uniformity scale for linear ranking includes providing a selection probability including an individual ranking number to optimize the fitness function.
Preferably, the expanding the global search function in the fourth step includes: the steps of the shipped product are evolved to the entire process flow.
Preferably, evolving the eigenvalue in step four includes inputting the failure rate of Bin as the eigenvalue.
As described above, the yield improvement adaptive model optimization method based on the genetic algorithm of the present invention has the following beneficial effects: according to the invention, by optimizing the established genetic algorithm model, the biological evolution form of product passing is simulated, on one hand, a gold route of the product passing is searched, and on the other hand, the CP/Bin upper limit value of the product based on the existing organic condition is predicted, so that a reference is provided for the control and optimization of an online machine, and the product quality is improved; on the other hand, the machine with poor performance can be highlighted, the deterioration lower limit value of the product based on the CP/Bin under the current machine condition is predicted, reference is provided for online machine control and adjustment, the product quality is stable, and the labor cost is saved.
Drawings
FIG. 1 is a schematic flow chart of the optimization method of the yield improvement adaptive model based on the genetic algorithm according to the present invention;
FIG. 2 is a diagram showing the evolution trend of CP after the scale transformation of fitness function according to the present invention;
FIG. 3a is a graph showing the evolutionary trend of CP before optimizing model parameters;
FIGS. 3b and 3d are graphs showing the evolution trend of CP after the model parameters are optimized according to the present invention;
FIG. 4a is a diagram showing the CP evolution trend of a tool that has only performed a photolithography process;
FIG. 4b is a CP evolution trend graph after the steps of the shipped product are evolved into the whole process flow in the present invention;
FIG. 4c is a diagram showing the evolution trend of the present invention after Bin is inputted as a feature value.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
Please refer to fig. 1 to 4 c. It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The invention provides a yield improvement adaptive model optimization method based on a genetic algorithm, and as shown in fig. 1, fig. 1 is a flow diagram of the yield improvement adaptive model optimization method based on the genetic algorithm. The method at least comprises the following steps:
firstly, carrying out scale transformation of a fitness function according to an existing genetic algorithm model and a CP or WAT characteristic value of a product to optimize the deception problem of the algorithm; in the initial stage of genetic evolution, some supernormal individuals are usually generated, and if a proportional selection method is adopted, the abnormal individuals control the selection process due to the fact that the competitiveness is too prominent, and the global optimization performance of an algorithm is influenced; in the later stage of genetic evolution, namely when the algorithm is close to convergence, as the individual fitness difference in the population is small, the potential of continuous optimization is reduced, and a certain local optimal solution can be obtained.
For FAB, the difference between the abnormal value and the normal value of the actual event (case) characteristic value (CP/WAT) is small, supernormal individuals exist, namely, obvious deception problem exists in the evolution result, and scale transformation, namely linear transformation, of the fitness function is performed for optimizing the algorithm model. Further, the scale transformation of the fitness function in the step one makes the average value of the original fitness equal to the average value of the calibrated fitness. Furthermore, the fitness function is subjected to scale transformation in the step one, so that the maximum value of the transformed fitness is equal to a specified multiple of the average value of the original fitness.
Assuming that the original fitness function is f and the transformed fitness function is f ', the linear transformation can be expressed by the following formula, f ' is α xf + β, the coefficient determination is satisfied that the average value of the original fitness is equal to the average value of the scaled fitness so as to ensure that the expected replication number of the individual with the average value of the fitness in the next generation is 1, namely f ' _ avg is f _ avg, and the maximum value of the transformed fitness is equal to the specified multiple of the average value of the original fitness so as to control the replication number of the individual with the maximum fitness in the next generation, namely:
f'_max＝c×f_avg；
α＝((c-1)×f_avg)/(f_max-f_avg)；
β＝((f_max-c×f_avg)×f_avg)/(f_max-f_avg)。
referring to fig. 2, fig. 2 is a diagram showing the evolution trend of CP after the scale transformation of the fitness function is performed according to the present invention; is the CP evolution trend of the product 0025 in the variation interval 3/1-6/1. Therefore, the linear transformation method transforms the difference between the fitness, keeps the diversity in the population and has more referential significance to the result.
Step two, optimizing a crossover operator, a mutation interval and a deletion operator in the genetic algorithm model; in the initial stage of building the traditional model, the value of a crossover operator is 0.75, the value of a mutation operator is 0.005, the value of a mutation interval is 94-100, the value of a deletion operator is 0.01, and the evolution result shows rapid convergence, as shown in fig. 3a, which is a graph showing the evolution trend of the CP before optimizing the model parameters; the CP evolution trend of a product 0060 in variation intervals 1/1-7/1 shows that the setting of each parameter is more rapid. Further, the crossover operator in the second step is 0.25, the mutation operator is 0.005, the mutation interval is 60-100, and further, the deletion operator is 0.005, and the CP evolution trend graph as shown in fig. 3b and 3c is obtained by adjusting parameters. The trend of the CP evolution of the product 0025 in the variation range 3/1-3/15 is shown, and the CP evolution tends to be smooth by adjusting parameters. But the convergence number is still less than 50, for further verification, the CP variation range of (product) lot (150) is randomly defined to be 60-100, and the algorithm is performed: wherein the crossover operator is 0.25, the mutation operator is 0.005, the mutation interval is 60-100, and the deletion operator is 0.005, as shown in fig. 3d, the visible convergence time is less than 50, which indicates that the sample property is determined, the parameter adjustment is reasonable, and the model has practical reference significance.
Step three, introducing a population uniform scale to perform linear sequencing so as to optimize the fitness function; further, the step three of introducing the population uniformity scale for linear ranking includes providing a selection probability containing individual ranking sequence numbers to optimize the fitness function. Rank-based fitness assignment: in rank-based fitness allocation, populations are ranked by target value. Fitness depends only on the rank of the individual in the population, not the actual target value. The ranking method overcomes the scaling problem of the proportional fitness calculation, in case the selection pressure is too small, and premature convergence resulting from the rapid narrowing of the search band. The population uniformity scale is introduced to carry out linear sequencing so as to optimize the fitness function.
The linear sorting has the calculation formula of p _ i ═ 1/N [ η ^ + - (η ^ η ^ -) (i-1)/(N-1) ], wherein i is an individual sorting sequence number, 1 is not more than η ^ 2, and η ^ is 2- η ^ so that the first individual has the highest selection probability, namely the highest fitness.
And step four, expanding the global search function and evolving characteristic values to perfect the genetic algorithm model. Furthermore, the expanding global search function in the fourth step of the invention comprises: the steps of the shipped product are evolved to the entire process flow.
In the traditional initial modeling, for performing deduction and display (demo) quickly and conveniently, the adopted process flow is the steps of all photoetching processes, namely, photoetching machines are selected, and for further optimizing the model and expanding the global search function, the evolutionary steps are expanded to the steps of all process flows, namely, the evolutionary process of all machines. As shown in fig. 4a and 4b, fig. 4a is a CP trend graph of a machine tool which only performs a photolithography process; shown as the CP evolution trend of product 0060 between evolution intervals 1/1-7/1; FIG. 4b is a CP evolution trend chart showing the CP evolution trend of 0098 product during the evolution interval 1/1-12/1(1 year period), after the steps of the shipped product are evolved into the whole process flow. The comparison shows that the evolution of all the machines is similar to the result graph of only the evolution of the photoetching machine, but the whole model is more complete, so that the method has the function of global search for the optimum.
Furthermore, the method comprises the step of evolving the characteristic value in the fourth step, wherein the failure rate of Bin is used as the characteristic value input. In the traditional initial modeling, the CP is used as a characteristic value to be input, a golden route and a poor-performance machine are analyzed, and a certain result is obtained. However, the CP value is influenced by multiple factors and simultaneously acted by multiple bins, so that the analysis of a machine with poor performance is complicated and the verification is troublesome. Therefore, the model is further accurate, the failure rate of Bin is improved to be input as the characteristic value by inputting the CP as the characteristic value, and the model verification is quicker and more convenient.
As shown in fig. 4c, fig. 4c is a graph showing the evolution trend of the present invention after Bin is input as a feature value. The evolution of Bin is consistent with the evolution trend chart of CP after the improvement, which shows that the modified model is applicable. Because the influence factor of Bin is less, and single, the problem board scope is narrower, is convenient for utilize the model to carry out experimental verification.
In conclusion, the continuous improvement and optimization process of the genetic algorithm model is mainly introduced, the deception problem of the optimization algorithm, the parameters of the optimization model, the optimization fitness function and the improvement of the model are mainly solved, the established genetic algorithm model is optimized, the product passing is simulated in the biological evolution form, on one hand, the gold route of the product passing is searched, and on the other hand, the CP/Bin upper limit value of the product based on the organic condition is predicted, so that the reference is provided for the control and optimization of an online machine, and the product quality is improved; on the other hand, the machine with poor performance can be highlighted, the deterioration lower limit value of the product based on the CP/Bin under the current machine condition is predicted, reference is provided for online machine management and control and adjustment, the product quality is stable, the labor cost is saved, and meanwhile, the problem is solved more quickly and accurately. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A yield improvement applicable model optimization method based on a genetic algorithm is characterized by at least comprising the following steps:
firstly, carrying out scale transformation of a fitness function according to an existing genetic algorithm model and a CP or WAT characteristic value of a product to optimize the deception problem of the algorithm;
step two, optimizing a crossover operator, a mutation interval and a deletion operator in the genetic algorithm model;
step three, introducing a population uniform scale to perform linear sequencing so as to optimize the fitness function;
and step four, expanding the global search function and evolving characteristic values to perfect the genetic algorithm model.
2. The method of claim 2, wherein the yield improvement adaptive model is optimized based on the genetic algorithm, and comprises: and the scale transformation of the fitness function in the step one enables the average value of the original fitness to be equal to the average value of the calibrated fitness.
3. The method of claim 3, wherein the yield improvement adaptive model is optimized based on the genetic algorithm, and comprises: and the scale transformation of the fitness function in the step one enables the maximum value of the transformed fitness to be equal to the specified multiple of the average value of the original fitness.
4. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: the crossover operator in step two is 0.25.
5. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: the mutation operator in step two is 0.005.
6. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: and the variation range in the second step is 60-100.
7. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: the delete operator in step two is 0.005.
8. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: the step three, introducing the population uniformity scale for linear sorting, includes providing a selection probability containing individual sorting sequence numbers to optimize the fitness function.
9. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: expanding the global search function in the fourth step comprises the following steps: the steps of the shipped product are evolved to the entire process flow.
10. The method of claim 1, wherein the yield improvement adaptive model is optimized based on a genetic algorithm, and the method comprises the following steps: evolving the eigenvalue in step four includes inputting the failure rate of Bin as the eigenvalue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353118.1A CN111144569A (en) | 2019-12-25 | 2019-12-25 | Yield improvement applicable model optimization method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353118.1A CN111144569A (en) | 2019-12-25 | 2019-12-25 | Yield improvement applicable model optimization method based on genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144569A true CN111144569A (en) | 2020-05-12 |
Family
ID=70519744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911353118.1A Pending CN111144569A (en) | 2019-12-25 | 2019-12-25 | Yield improvement applicable model optimization method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144569A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112904821A (en) * | 2021-01-28 | 2021-06-04 | 上海华力微电子有限公司 | Data analysis method and device based on genetic algorithm model |
| CN117036112A (en) * | 2023-10-09 | 2023-11-10 | 石家庄坤垚科技有限公司 | Geographic information system and method for land planning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1900956A (en) * | 2006-07-11 | 2007-01-24 | 南京大学 | Design method for improved mixed genetic algorithm optimizing water quality model parameter |
| CN110516807A (en) * | 2019-08-29 | 2019-11-29 | 上海华力集成电路制造有限公司 | Semiconductor product yields extreme value calculation method and its extreme value computing system |
-
2019
- 2019-12-25 CN CN201911353118.1A patent/CN111144569A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1900956A (en) * | 2006-07-11 | 2007-01-24 | 南京大学 | Design method for improved mixed genetic algorithm optimizing water quality model parameter |
| CN110516807A (en) * | 2019-08-29 | 2019-11-29 | 上海华力集成电路制造有限公司 | Semiconductor product yields extreme value calculation method and its extreme value computing system |
Non-Patent Citations (1)
| Title |
|---|
| 朱会霞, 东北大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112904821A (en) * | 2021-01-28 | 2021-06-04 | 上海华力微电子有限公司 | Data analysis method and device based on genetic algorithm model |
| CN117036112A (en) * | 2023-10-09 | 2023-11-10 | 石家庄坤垚科技有限公司 | Geographic information system and method for land planning |
| CN117036112B (en) * | 2023-10-09 | 2023-12-22 | 石家庄坤垚科技有限公司 | Geographic information system and method for land planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | A discrete multi-objective fireworks algorithm for flowshop scheduling with sequence-dependent setup times | |
| Wang et al. | A bi-population based estimation of distribution algorithm for the flexible job-shop scheduling problem | |
| Zhou et al. | Hyper-heuristic coevolution of machine assignment and job sequencing rules for multi-objective dynamic flexible job shop scheduling | |
| CN113805545B (en) | Flexible flow shop combined scheduling rule generation method considering batch processing | |
| CN105929690B (en) | A kind of Flexible Workshop Robust Scheduling method based on decomposition multi-objective Evolutionary Algorithm | |
| CN110571792A (en) | Analysis and evaluation method and system for operation state of power grid regulation and control system | |
| Salimpour et al. | Semi-robust layout design for cellular manufacturing in a dynamic environment | |
| CN110119558B (en) | Circuit parameter optimization method based on differential optimization algorithm | |
| CN108154003B (en) | Blasting vibration prediction method based on Spark gene expression optimization | |
| CN105447509A (en) | Short-term power prediction method for photovoltaic power generation system | |
| CN111144569A (en) | Yield improvement applicable model optimization method based on genetic algorithm | |
| CN112862380A (en) | Project type product assembly workshop personnel scheduling method and device based on hybrid algorithm and storage medium | |
| CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
| Kim et al. | Tire mixing process scheduling using particle swarm optimization | |
| CN115470862A (en) | Dynamic self-adaptive load prediction model combination method | |
| Tynchenko et al. | The parallel genetic algorithm for construction of technological objects neural network models | |
| Asokan et al. | Machine-cell grouping in cellular manufacturing systems using non-traditional optimisation techniques-A comparative study | |
| CN104281917A (en) | Fuzzy job-shop scheduling method based on self-adaption inheritance and clonal selection algorithm | |
| CN105427058A (en) | Engine test wire station distribution optimization method based on genetic algorithm | |
| CN110516807B (en) | Semiconductor product yield extreme value calculating method and extreme value calculating system thereof | |
| JAVIDI et al. | Research in random parameters of genetic algorithm and its application on TSP and optimization problems | |
| CN115115119A (en) | OA-GRU short-term power load prediction method based on grey correlation | |
| CN115659800A (en) | Multi-objective optimization method for chip development | |
| Boulas et al. | A hybrid evolutionary algorithm approach for estimating the throughput of short reliable approximately balanced production lines | |
| CN114089699A (en) | Method for solving hybrid flow shop scheduling based on cellular membrane calculation model |
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: 20200512 |
|
| RJ01 | Rejection of invention patent application after publication |