CN106844924A - Method based on Response Surface Method and genetic algorithm optimization PCB microstrip line constructions - Google Patents
Method based on Response Surface Method and genetic algorithm optimization PCB microstrip line constructions Download PDFInfo
- Publication number
- CN106844924A CN106844924A CN201710022783.7A CN201710022783A CN106844924A CN 106844924 A CN106844924 A CN 106844924A CN 201710022783 A CN201710022783 A CN 201710022783A CN 106844924 A CN106844924 A CN 106844924A
- Authority
- CN
- China
- Prior art keywords
- microstrip line
- return loss
- population
- factor
- groups
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Design And Manufacture Of Integrated Circuits (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method of use Response Surface Method genetic algorithm optimization PCB microstrip lines of the invention, including:The electromagnetic simulation model of PCB microstrip lines is set up based on HFSS softwares, the return loss and insertion loss of microstrip line are obtained based on the model, and with substrate thickness, micro belt line width, microstrip line thickness, with dielectric constant as design parameter, using return loss as desired value, design 29 groups of experiment calculation emulation, using response phase method to relation is fitted between return loss and its factor of influence under the conditions of experiment gained 5GHZ, advantage using the search globally optimal solution of genetic algorithm is optimized to gained fitting function, the minimum combination parameter of return loss is obtained.And it is subject to the checking of HFSS analogue simulations, it was confirmed that and the accuracy of optimum results, and the method also has directive function to other interconnection structure optimization designs.
Description
Technical field
The present invention relates to microelectronics Packaging signal integrity technical field, specifically based on Response Surface Method and genetic algorithm
The method for optimizing PCB microstrip line constructions.
Background technology
As large scale integrated circuit promptly develops to high speed, high-frequency, high density direction, clock frequency can
Hundreds of MHz or even number GHz are reached, data transfer rate reaches more than Gbps, even integrated tens thousand of electronic components above on circuit board.Letter
Transmission number between device and device, chip and chip be unable to do without interconnection structure, but with the increase of component closeness,
It is more compact that the density of interconnection structure becomes therewith, and especially the spacing of microstrip line has reached um ranks.Increasingly increase in frequency
High, interconnection structure density constantly increases interconnection, physical dimension also in the case of ever-reduced, the high speed that interconnection structure is transmitted
Pulse signal is in the same order of magnitude with the size of interconnection structure in the high-end corresponding wavelength of frequency spectrum, and signal pulse is in interconnection line
It is upper that obvious fluctuation effect is presented, now interconnection line be not simple connecting line and as many conductors biography with ghost effect
Defeated line treatment.Ghost effect can cause noise and interference in transmission signal so that high speed interconnection structure problems of Signal Integrity
Become increasingly to protrude.Microstrip line is used as key component in interconnection structure, it is necessary to ensure that the correct transmission of electric current and signal, in height
Under fast high frequency condition, if correct transmission of the signal in transmission line cannot be ensured, i.e., the decline of whole system performance can be caused,
Therefore the analysis for launching problems of Signal Integrity to microstrip line is extremely necessary.
Due to the complexity of engineering structure, the function of structure usually directly cannot do function with the stochastic variable of structure design
Expression, therefore directly can not be calculated with first-order reliability method method, then BOX and Wilson propose response phase method.Response surface
Method is also referred to as regression analysis, is the product that mathematical method and mathematical statistics are combined, and is that a kind of approximate functional relation is represented
The fitting method for designing of variable and target.The method is first with center is multiple, Box-Behnken designs, the experimental design such as uniform,
The uniform some test combinations for waiting experimental technique to set up factor, build to respectively carrying out acquisition respective objects value and then system of selection respectively
Some test combinations of vertical factor, then select suitable Mathematical Modeling that factor is represented with objective result, then with a most young waiter in a wineshop or an inn
Multiply principle and try to achieve middle unknowm coefficient, finally obtain the fitting function expression formula of variable and result.RSM can be by less experiment time
The functional relation that number is relatively accurately approached between factor and desired value within the specific limits, and shown with structure
Come, and Complex Response relation can be intended by the selection to regression model within the specific limits, with excellent robust performance, meter
It is relatively simple, it is that later stage Parameters Optimal Design brings great convenience.
Genetic algorithm is a kind of global optimization approach in computational mathematics, is especially suitable for solving large-scale Combinatorial Optimization asking
Topic.The layout of electronic component belongs to travelling salesman (TSP) problem in Combinatorial Optimization, in recent years scholar by genetic algorithm application
To in the area research, therefore, being optimized using standard genetic algorithm can obtain relatively good result, easily realize optimization
Effect.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, and provide a kind of Response Surface Method-genetic algorithm optimization
The method of PCB microstrip line constructions, the method has excellent robust performance, calculates relatively simple, is later stage Parameters Optimal Design band
Greatly to facilitate, the result of calculation after optimization is ideal.
Realizing the technical scheme of the object of the invention is:
Method based on Response Surface Method and genetic algorithm optimization PCB microstrip line constructions, 29 are designed first with response phase method
Group test combinations, according to this 29 groups of experiment parameters, set up corresponding 29 groups of simulation models, obtain 5GHZ using Response Surface Method
Under return loss S11 and key factor functional relation, carry out variance analysis in the functional expression to being obtained, it is determined that return
Return the validity of equation;Recycle genetic algorithm to optimize regression equation, initial population generation is performed successively, intersected, become
It is different to be operated with reverse of evolving, the optimum combination most beneficial for microstrip line signal transmission is obtained, emulate mould finally by HFSS is set up
Type and making are tested exemplar measurement and are verified, specifically include following steps:
Step 1:Set up HFSS microstrip line signal integrity analysis models;
Step 2:Obtain the return loss and insertion loss of microstrip line;
Step 3:Establish the influence factor of influence return loss;
Step 4:Establish the parameter level value of influence factor;
Step 5:The 29 groups of experiment samples needed using the center combination design modelling of BOX-Behnken;
Step 6:Obtain the functional relation of influence factor and return loss;
Step 7:It is to carry out variance analysis to gained functional relation;
Step 8:Establish the correctness of gained functional relation;
Step 9:Initial population is generated using random fashion;
Step 10:Obtain current evolutionary generation gen and adaptive optimal control angle value;
Step 11:Crossover operation is implemented to population respectively;
Step 12:Mutation operation is implemented to population respectively;
Step 13:Respectively population is implemented to evolve and reversed;
Step 14:Using population as overall calculation fitness function value, and optimized individual is selected using optimum maintaining strategy;
Step 15:Rejudged after population recruitment, if gen values are more than 0 less than 50 and num values, local is implemented to population
Catastrophe.
In the step 1, the size of model is PCB substrate a length of 15-20mm, a width of 5-15mm, a height of 5-15mm, PCB
Baseplate material is FR4, and dielectric constant is 4.4;The a length of 15-20mm of microstrip line, a width of 0.1-0.2mm, thickness is 0.03-0.04mm;
Reference layer thickness 0.2-0.4mm.
In the step 2, the frequency range of return loss and insertion loss is 1GHz~5GHz.
In the step 3, influence factor is substrate thickness, micro belt line width, microstrip line thickness and substrate dielectric constant.
In the step 4, the number of levels of parameter level value is 3, and factor number is 4.
It is the 29 groups of experiment samples needed using the center combination design modelling of BOX-Behnken in the step 5
This, wherein 24 groups is analysis factor, 5 groups is the zero point factor, i.e. parameter level combination is identical, estimates for experimental error.
In the step 6, the analyzing influence factor is carried out with the relation of return loss under the conditions of signal frequency is 5GHZ.
In the step 9, population scale is set to 40.
The step 10, genetic algebra is set to 50.
Beneficial effect:The method relatively accurately approaches factor and target within the specific limits by less experiment number
Functional relation between value, and shown with structure, and by the selection to regression model within the specific limits
Complex Response relation can be intended, with excellent robust performance, calculate relatively simple, be that later stage Parameters Optimal Design brings very big side
Just.
Brief description of the drawings
Fig. 1 is gained return loss plot after basic model of the invention emulation;
Fig. 2 is gained return loss plot after basic model of the invention emulation;
Fig. 3 is regression equation by Change in Mean figure after Neural Network Optimization;
Fig. 4 is variation diagram of the regression equation by optimal solution after Neural Network Optimization;
Fig. 5 is the HFSS simulation result figures of optimum combination;
Fig. 6 is the experiment results figure of optimum combination.
Specific embodiment
The present invention is further elaborated with reference to the accompanying drawings and examples, but is not limitation of the invention.
Embodiment:
Method based on Response Surface Method and genetic algorithm optimization PCB microstrip line constructions, specifically includes following steps:
(1) the microstrip line simulation analysis model of HFSS is set up, model substrate size is as shown in table 1;
(2) it is the return loss S11 and insertion loss S21 under 1GHz -5GHz to obtain frequency, as shown in Figure 1, 2;
(3) influence factor of acquisition influence microstrip line is:Substrate thickness H1, micro belt line width t, microstrip line thickness H2 and
Substrate dielectric constant E;3 level values are chosen to each factor respectively, its factor level table is as shown in table 2;
(4) using the center combination design model of BOX-Behnken, there are 29 groups of simulation model horizontal combinations, wherein 24 groups
It is analysis factor, 5 groups is the zero point factor, i.e. parameter level combination is identical, estimates for experimental error;
(5) according to calculus knowledge, any function all by several polynomial pieces approximate representations, therefore can actually asked
In topic, regardless of relation complexity between variable and result, always can be with polynomial regression come analytical calculation, due to setting herein
For 4 and between variable and target, functional relation is non-linear to meter variable, with reference to the experiment sample number of table 2, from based on Taylor
The second order polynomial model of expansion:
(A) formula includes constant term α0, linear termLinear crossingQuadratic termαi
It is linear term coefficient;αijIt is linear crossing term coefficient;αiiIt is secondary term coefficient;ε is random error;X is design variable;Y is mesh
Scale value;N is variable number.
(6) secondary multiple regression fitting is carried out to testing combinations of factors and its result in table 2, obtains return loss (Y) right
Substrate height (X1), micro belt line width (X2), microstrip line thickness (X3), dielectric constant (X4) quadratic polynomial regression equation be:
(7) in order to ensure regression equation is credible, data in table 2 have been carried out with variance analysis and the conspicuousness checking of model,
Regression equation relevant evaluation index is obtained, as a result as shown in table 3;
(8) model " Preb that response surface analysis is obtained>F " represents this significantly less than 0.0001, generally less than 0.05,
That is response surface model regression effect is particularly evident;Regression equation coefficients R-Squared is 0.956, shows regression equation degree of fitting
It is very high;Regression equation regulation coefficient Adj R-Squared are 0.946, more accurately reflect that the degree of fitting of equation is very high;Return
Prediction equation FACTOR P red R-Squared are 0.912, show that the prediction equation degree of accuracy is good;Result above coefficient all shows
(B) formula can highly be fitted the experimental result in table 2, therefore regression equation is accurately credible;
(9) appeal regression equation is optimized using genetic algorithm, the algorithm is random true one group first from domain of definition
The optimal or algorithm of object function random true one group of initial solution first from domain of definition, enters in the range of initial solution, and then search neck
And search for the optimal or suboptimal solution of object function in the range of neck;
Described genetic algorithm optimization regression equation, step specific as follows:
Step a:Initial population is generated using random fashion;
Step b:Obtain current evolutionary generation gen and adaptive optimal control angle value;
Step c:Crossover operation is implemented to population respectively;
Step d:Mutation operation is implemented to population respectively;
Step e:Respectively population is implemented to evolve and reversed;
Step f:Using population as overall calculation fitness function value, and optimized individual is selected using optimum maintaining strategy;
Step g:Rejudged after population recruitment, if gen values are more than 0 less than 50 and num values, local calamity is implemented to population
Become, be then back to step b, otherwise direct return to step b;The maximum genetic algebra of algorithm was set to for 50 generations, and gen values are more than 50 ends
Only evolve.
(10) the minimum targets of S11 are lost with clawback by MATLAB GAs Toolboxes carries out parameter optimization;Problem
Average and optimal solution change are as shown in Figure 3, Figure 4.
(11) according to the span that factor of influence is set in appeal factor parameter list, acquisition optimum combination is PCB substrate
H1 is 0.5mm, and micro belt line width is 0.4mm, and microstrip line thickness is 0.075mm, and dielectric constant E is 4.4, now obtains 5GHZ pre-
Survey return loss value is -13.006dB.
(12) combined according to above-mentioned obtained final parameter, set up corresponding HFSS microstrip lines simulation model, its emulation knot
Fruit curve is extremely connect with genetic algorithm predicted value as shown in figure 5, return loss value S11 under the conditions of its 5GHZ is -12.8dB
Closely, it was demonstrated that the validity of genetic algorithm optimization microstrip line construction.
(13) according to above-mentioned obtained best parameter group, the experiment exemplar of best parameter group is made, measurement obtains reality
Survey curve map approximate trend and return loss value S11 is closer to, as shown in Figure 6, it was confirmed that the microstrip line based on HFSS is imitated
The correctness of true mode has been based on the accuracy of response surface design-genetic algorithm.
The moulded dimension figure of table 1
The factor level table of table 2
3 29 groups of parameter combination results of table
The response surface analysis result of table 4
Claims (9)
1. the method for Response Surface Method and genetic algorithm optimization PCB microstrip line constructions is based on, it is characterised in that first with response surface
Method designs 29 groups of test combinations, according to this 29 groups of experiment parameters, corresponding 29 groups of simulation models is set up, using Response Surface Method
The functional relation of the return loss S11 and key factor under 5GHZ is obtained, variance analysis is carried out in the functional expression to being obtained,
The validity of regression equation is determined;Recycle genetic algorithm regression equation is optimized, successively perform initial population generation,
Intersect, variation and evolve and reverse operation, the optimum combination most beneficial for microstrip line signal transmission is obtained, finally by setting up HFSS
Simulation model and making are tested exemplar measurement and are verified, specifically include following steps:
Step 1:Set up HFSS microstrip line signal integrity analysis models;
Step 2:Obtain the return loss and insertion loss of microstrip line;
Step 3:Establish the influence factor of influence return loss;
Step 4:Establish the parameter level value of influence factor;
Step 5:The 29 groups of experiment samples needed using the center combination design modelling of BOX-Behnken;
Step 6:Obtain the functional relation of influence factor and return loss;
Step 7:It is to carry out variance analysis to gained functional relation;
Step 8:Establish the correctness of gained functional relation;
Step 9:Initial population is generated using random fashion;
Step 10:Obtain current evolutionary generation gen and adaptive optimal control angle value;
Step 11:Crossover operation is implemented to population respectively;
Step 12:Mutation operation is implemented to population respectively;
Step 13:Respectively population is implemented to evolve and reversed;
Step 14:Using population as overall calculation fitness function value, and optimized individual is selected using optimum maintaining strategy;
Step 15:Rejudged after population recruitment, if gen values are more than 0 less than 50 and num values, local catastrophe is implemented to population.
2. the method according to right 1, it is characterised in that, the size of model is PCB substrate a length of 15-20mm, a width of 5-
15mm, a height of 5-15mm, PCB substrate material are FR4, and dielectric constant is 4.4;Microstrip line a length of 15-20mm, a width of 0.1-
0.2mm, thickness is 0.03-0.04mm;Reference layer thickness 0.2-0.4mm.
3. the method according to right 1, it is characterised in that in the step 2, the frequency range of return loss and insertion loss
It is 1 GHz~5 GHz.
4. the method according to right 1, it is characterised in that in the step 3, influence factor is substrate thickness, micro-strip line width
Degree, microstrip line thickness and substrate dielectric constant.
5. the method according to right 1, it is characterised in that in the step 4, the number of levels of parameter level value is 3, factor number
It is 4.
6. the method according to right 1, it is characterised in that in the step 5, is using the center combination of BOX-Behnken
29 groups of experiment samples that the design that designs a model needs, wherein 24 groups is analysis factor, 5 groups is the zero point factor, i.e. parameter level group
Close identical, estimate for experimental error.
7. the method according to right 1, it is characterised in that in the step 6, the relation of the analyzing influence factor and return loss
Carried out under the conditions of signal frequency is 5GHZ.
8. the method according to right 1, it is characterised in that in the step 9, population scale is set to 40.
9. the method according to right 1, it is characterised in that the step 10, genetic algebra is set to 50.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710022783.7A CN106844924B (en) | 2017-01-12 | 2017-01-12 | Method for optimizing PCB microstrip line structure based on response surface method and genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710022783.7A CN106844924B (en) | 2017-01-12 | 2017-01-12 | Method for optimizing PCB microstrip line structure based on response surface method and genetic algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106844924A true CN106844924A (en) | 2017-06-13 |
CN106844924B CN106844924B (en) | 2021-02-23 |
Family
ID=59123454
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710022783.7A Active CN106844924B (en) | 2017-01-12 | 2017-01-12 | Method for optimizing PCB microstrip line structure based on response surface method and genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106844924B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107832526A (en) * | 2017-11-09 | 2018-03-23 | 桂林电子科技大学 | A kind of method of optimization BGA solder joint return losses |
CN108829937A (en) * | 2018-05-24 | 2018-11-16 | 郑州云海信息技术有限公司 | A method of optimization PCB high speed signal via hole |
CN109002644A (en) * | 2018-08-10 | 2018-12-14 | 桂林电子科技大学 | A kind of optimization method of multi-chip module fluid channel radiator structure |
CN109063298A (en) * | 2018-07-23 | 2018-12-21 | 桂林电子科技大学 | A kind of structure parameter optimizing method improving fluid channel heat dissipation performance |
CN109190152A (en) * | 2018-07-23 | 2019-01-11 | 桂林电子科技大学 | A kind of CSP welding spot structure parameter optimization method reducing the stress under power cycle-Harmony response coupling |
CN109376372A (en) * | 2018-08-29 | 2019-02-22 | 桂林电子科技大学 | A kind of optimization optical interconnection module key position postwelding coupling efficiency method |
CN111159921A (en) * | 2020-01-17 | 2020-05-15 | 安徽瑞迪微电子有限公司 | IGBT design method |
CN112016243A (en) * | 2020-07-30 | 2020-12-01 | 东南大学 | Traffic flow prediction model parameter calibration method based on response surface |
CN112257373A (en) * | 2020-11-13 | 2021-01-22 | 江苏科技大学 | Snake-shaped PCB antenna return loss prediction method based on three-body training algorithm |
CN113051856A (en) * | 2021-03-24 | 2021-06-29 | 西安电子科技大学 | Optimization method of integrated circuit design data |
CN113095677A (en) * | 2021-04-13 | 2021-07-09 | 北京工业大学 | Machining process quantitative control method based on reverse derivation of machining quality |
US20230016096A1 (en) * | 2021-07-15 | 2023-01-19 | Montage Electronics (Shanghai) Co., Ltd. | Method for obtaining board parameters of printed circuit board |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030126562A1 (en) * | 2001-12-27 | 2003-07-03 | Hamlin Christopher L. | System and method for coevolutionary circuit design |
GB2479662A (en) * | 2006-01-17 | 2011-10-19 | Halliburton Energy Serv Inc | A control method predicting a flow rate between a reservoir and a wellbore |
CN103745029A (en) * | 2013-12-12 | 2014-04-23 | 西安电子工程研究所 | High-power isolation resistor of microwave power divider and design method of isolation resistor |
CN106096125A (en) * | 2016-06-08 | 2016-11-09 | 湖南大学 | One not uniform thickness tailor welded weld line optimization method |
-
2017
- 2017-01-12 CN CN201710022783.7A patent/CN106844924B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030126562A1 (en) * | 2001-12-27 | 2003-07-03 | Hamlin Christopher L. | System and method for coevolutionary circuit design |
GB2479662A (en) * | 2006-01-17 | 2011-10-19 | Halliburton Energy Serv Inc | A control method predicting a flow rate between a reservoir and a wellbore |
CN103745029A (en) * | 2013-12-12 | 2014-04-23 | 西安电子工程研究所 | High-power isolation resistor of microwave power divider and design method of isolation resistor |
CN106096125A (en) * | 2016-06-08 | 2016-11-09 | 湖南大学 | One not uniform thickness tailor welded weld line optimization method |
Non-Patent Citations (2)
Title |
---|
LEI LIU等: ""Numerical Techniques for Multi-Objective Synthesis of an Inverted-S Antenna"", 《PROCEEDINGS OF THE 17TH CONFERENCE ON THE COMPUTATION OF ELECTROMAGNETIC FIELDS》 * |
傅厦龙等: ""基于响应曲面和遗传算法的工艺参数优化"", 《高分子材料科学与工程》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107832526A (en) * | 2017-11-09 | 2018-03-23 | 桂林电子科技大学 | A kind of method of optimization BGA solder joint return losses |
CN107832526B (en) * | 2017-11-09 | 2020-11-17 | 桂林电子科技大学 | Method for optimizing return loss of BGA welding spot |
CN108829937A (en) * | 2018-05-24 | 2018-11-16 | 郑州云海信息技术有限公司 | A method of optimization PCB high speed signal via hole |
CN108829937B (en) * | 2018-05-24 | 2022-02-18 | 郑州云海信息技术有限公司 | Method for optimizing PCB high-speed signal via hole |
CN109063298A (en) * | 2018-07-23 | 2018-12-21 | 桂林电子科技大学 | A kind of structure parameter optimizing method improving fluid channel heat dissipation performance |
CN109190152A (en) * | 2018-07-23 | 2019-01-11 | 桂林电子科技大学 | A kind of CSP welding spot structure parameter optimization method reducing the stress under power cycle-Harmony response coupling |
CN109190152B (en) * | 2018-07-23 | 2023-04-07 | 桂林电子科技大学 | CSP welding spot structural parameter optimization method for reducing stress under power cycle-harmonic response coupling |
CN109002644A (en) * | 2018-08-10 | 2018-12-14 | 桂林电子科技大学 | A kind of optimization method of multi-chip module fluid channel radiator structure |
CN109376372A (en) * | 2018-08-29 | 2019-02-22 | 桂林电子科技大学 | A kind of optimization optical interconnection module key position postwelding coupling efficiency method |
CN109376372B (en) * | 2018-08-29 | 2022-11-18 | 桂林电子科技大学 | Method for optimizing postweld coupling efficiency of key position of optical interconnection module |
CN111159921A (en) * | 2020-01-17 | 2020-05-15 | 安徽瑞迪微电子有限公司 | IGBT design method |
CN111159921B (en) * | 2020-01-17 | 2023-06-16 | 安徽瑞迪微电子有限公司 | IGBT design method |
CN112016243A (en) * | 2020-07-30 | 2020-12-01 | 东南大学 | Traffic flow prediction model parameter calibration method based on response surface |
CN112257373A (en) * | 2020-11-13 | 2021-01-22 | 江苏科技大学 | Snake-shaped PCB antenna return loss prediction method based on three-body training algorithm |
CN112257373B (en) * | 2020-11-13 | 2022-05-17 | 江苏科技大学 | Snake-shaped PCB antenna return loss prediction method based on three-body training algorithm |
CN113051856A (en) * | 2021-03-24 | 2021-06-29 | 西安电子科技大学 | Optimization method of integrated circuit design data |
CN113051856B (en) * | 2021-03-24 | 2024-01-19 | 西安电子科技大学 | Optimization method for integrated circuit design data |
CN113095677A (en) * | 2021-04-13 | 2021-07-09 | 北京工业大学 | Machining process quantitative control method based on reverse derivation of machining quality |
US20230016096A1 (en) * | 2021-07-15 | 2023-01-19 | Montage Electronics (Shanghai) Co., Ltd. | Method for obtaining board parameters of printed circuit board |
US11782086B2 (en) * | 2021-07-15 | 2023-10-10 | Montage Electronics (Shanghai) Co., Ltd. | Method for obtaining board parameters of printed circuit board |
Also Published As
Publication number | Publication date |
---|---|
CN106844924B (en) | 2021-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106844924A (en) | Method based on Response Surface Method and genetic algorithm optimization PCB microstrip line constructions | |
CN107832526A (en) | A kind of method of optimization BGA solder joint return losses | |
Wu et al. | Machine-learning-assisted optimization and its application to antenna designs: Opportunities and challenges | |
Rayas-Sanchez et al. | EM-based Monte Carlo analysis and yield prediction of microwave circuits using linear-input neural-output space mapping | |
CN111639447B (en) | Random high-order mixed grid time domain discontinuous Galerkin method of multistage local time stepping technology | |
CN110728034B (en) | Antenna rapid multi-target modeling method using multistage cooperative machine learning | |
CN110941896B (en) | Design method of ultra-wideband antenna based on PGP | |
CN109408844A (en) | The optimization method of chip package solder joint Random vibration and return loss | |
CN109190152A (en) | A kind of CSP welding spot structure parameter optimization method reducing the stress under power cycle-Harmony response coupling | |
Marinkovis et al. | Artificial neural network based design of RF MEMS capacitive shunt switches | |
Chen et al. | Multibranch machine learning-assisted optimization and its application to antenna design | |
Bandler et al. | A space-mapping design framework | |
CN118013928A (en) | Method for constructing parasitic parameter mode library of integrated circuit based on self-adaptive incremental learning | |
Fedi et al. | Profiled corrugated circular horns analysis and synthesis via an artificial neural network | |
Liu et al. | Application of Chaos Mind Evolutionary Algorithm in Antenna Arrays Synthesis. | |
Aoad et al. | Development of knowledge based response correction for a reconfigurable N-shaped microstrip antenna design | |
Sahu et al. | An Automated Machine Learning Approach to Inkjet Printed Component Analysis: A Step Toward Smart Additive Manufacturing | |
Sánchez-Masís et al. | FNNs Models for Regression of S-Parameters in Multilayer Interconnects with Different Electrical Lengths | |
Wu et al. | Machine-learning-assisted two-step antenna modelling method | |
Cao et al. | Modeling and synthesis of on-chip multi-layer spiral inductor for millimeter-wave regime based on ANN method | |
Wang et al. | Studying the effect of drilling uncertainty on signal propagation through vias | |
Tian et al. | A structure and circuit coupling modeling method for flexible interconnection points and transmission performance of gold belt in microwave modules | |
Demming-Janssen et al. | 3D Field simulation of sparse arrays using various solver techniques within CST MICROWAVE STUDIO® | |
Na et al. | Parallel EM optimization using improved pole‐residue‐based neuro‐TF surrogate and isomorphic orthogonal DOE sampling for microwave components design | |
Geng et al. | Millimetre wave channel modeling based on grey genetic optimization 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170613 Assignee: Guilin Gaopu Electronic Technology Co.,Ltd. Assignor: GUILIN University OF ELECTRONIC TECHNOLOGY Contract record no.: X2022450000412 Denomination of invention: Optimization of PCB Microstrip Line Structure Based on Response Surface Methodology and Genetic Algorithm Granted publication date: 20210223 License type: Common License Record date: 20221227 |