CN109635420B - A simulation method and system of a microwave microstrip hairpin filter - Google Patents
A simulation method and system of a microwave microstrip hairpin filter Download PDFInfo
- Publication number
- CN109635420B CN109635420B CN201811500423.4A CN201811500423A CN109635420B CN 109635420 B CN109635420 B CN 109635420B CN 201811500423 A CN201811500423 A CN 201811500423A CN 109635420 B CN109635420 B CN 109635420B
- Authority
- CN
- China
- Prior art keywords
- layer
- data
- simulation
- microwave microstrip
- filter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 230000004913 activation Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 22
- 230000006870 function Effects 0.000 description 20
- 230000008569 process Effects 0.000 description 10
- 210000002569 neuron Anatomy 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Measurement Of Resistance Or Impedance (AREA)
Abstract
The invention discloses a simulation method and a system of a microwave microstrip hairpin filter, wherein the method comprises the following steps: acquiring simulation data of the accumulated microwave microstrip filter; establishing a prediction model based on a BP neural network; training the prediction model by using the accumulated microwave microstrip filter simulation data as training data to obtain a trained prediction model; inputting the target scattering parameters of the microwave microstrip filter into the trained prediction model to obtain the microwave microstrip filter for predicting the scattering parameters; judging whether the microwave microstrip filter for predicting the scattering parameters meets simulation requirements or not, and if so, outputting the microwave microstrip filter for predicting the scattering parameters; if not, returning to the step of acquiring the simulation data of the accumulated microwave microstrip filter. The invention realizes the automatic simulation of the microwave microstrip hairpin filter and reduces manpower and material resources.
Description
Technical Field
The invention relates to the technical field of filter design, in particular to a simulation method and a simulation system of a microwave microstrip hairpin-type filter.
Background
The microwave microstrip filter is an important device in modern communication systems and plays a role in screening out irrelevant signals. The traditional microwave microstrip filter simulation method including single-port group delay, a space mapping method and the like needs a designer to carry out design and simulation operations before a computer from beginning to end, needs a certain simulation experience, is time-consuming and labor-consuming, has low automation degree, has design efficiency which is changed according to the level of the worker, and is difficult to be competent for a large amount of design work of the filter.
Disclosure of Invention
The invention aims to provide a simulation method and a simulation system for a microwave microstrip hairpin filter, so as to realize automatic simulation of the microwave microstrip hairpin filter and reduce manpower and material resources.
In order to achieve the above object, the present invention provides a method for simulating a microstrip hairpin filter, the method comprising:
acquiring simulation data of the accumulated microwave microstrip filter; the accumulated simulation data of the microwave microstrip filter is that a large amount of simulation is automatically completed by controlling electromagnetic simulation software through MATLAB, and all the simulation data of the microwave microstrip filter of the filter are returned;
establishing a prediction model based on a BP neural network;
training the prediction model by using the accumulated microwave microstrip filter simulation data as training data to obtain a trained prediction model;
inputting the target scattering parameters of the microwave microstrip filter into the trained prediction model to obtain the microwave microstrip filter for predicting the scattering parameters;
judging whether the microwave microstrip filter for predicting the scattering parameters meets simulation requirements or not, and if so, outputting the microwave microstrip filter for predicting the scattering parameters; if not, returning to the step of acquiring the simulation data of the accumulated microwave microstrip filter.
Optionally, the acquiring simulation data of the accumulated microwave microstrip filter specifically includes:
adjusting the size parameters of each strip in the microwave microstrip filter according to preset frequency in MATLAB control electromagnetic simulation software to ensure that the whole size of the microwave microstrip filter is fixed and unchanged, and obtaining a plurality of groups of microwave microstrip filters with scattering parameters; wherein the dimensional parameters include a length and a width of the strip.
Optionally, the establishing a prediction model based on a BP neural network specifically includes:
setting the number of elements of an input layer and the number of elements of an output layer;
calculating the number of hidden layers according to the number of the input layer elements and the number of the output layer elements;
establishing a prediction model by taking a sigmoid function as an activation function;
optionally, the training of the prediction model by using the accumulated microwave microstrip filter simulation data as training data to obtain the trained prediction model specifically includes:
inputting the accumulated microwave microstrip filter simulation data into an input layer of the prediction model;
determining the connection weight of the input layer and the hidden layer and the connection weight of the hidden layer and the output layer by using a random gradient descent method;
determining hidden layer input data through input data of an input layer and connection weight of the input layer and the hidden layer;
inputting the hidden layer input data into an activation function to obtain hidden layer output data;
determining output layer input data according to the hidden layer output data and the connection weight of the hidden layer and the output layer;
inputting the input data of the output layer into the activation function for reverse processing, and outputting the data;
and transmitting the error between the output data and the target output data to the hidden layer as a feedback signal, and adjusting the connection weight between the input layer and the hidden layer and the connection weight between the hidden layer and the output layer in the hidden layer until the error is within a set threshold range to obtain a trained prediction model.
Optionally, the determining whether the microwave microstrip filter for predicting the scattering parameter meets the simulation requirement specifically includes:
judging whether the error between the predicted scattering parameter of the microwave microstrip filter of the predicted scattering parameter and the target scattering parameter is smaller than a set threshold value, if so, meeting the simulation requirement; if not, the simulation requirement is not met.
The invention also provides a simulation system of the microwave microstrip hairpin-type filter, which comprises:
the data acquisition unit is used for acquiring the accumulated microwave microstrip filter simulation data; the accumulated simulation data of the microwave microstrip filter is that a large amount of simulation is automatically completed by controlling electromagnetic simulation software through MATLAB, and all the simulation data of the microwave microstrip filter of the filter are returned;
the model establishing unit is used for establishing a prediction model based on a BP neural network;
the training unit is used for training the prediction model by using the accumulated microwave microstrip filter simulation data as training data to obtain a trained prediction model;
the prediction unit is used for inputting the target scattering parameters of the microwave microstrip filter into the trained prediction model to obtain the microwave microstrip filter with the predicted scattering parameters;
the judging unit is used for judging whether the microwave microstrip filter for predicting the scattering parameters meets the simulation requirements or not, and if so, outputting the microwave microstrip filter for predicting the scattering parameters; if not, returning to the step of acquiring the simulation data of the accumulated microwave microstrip filter.
Optionally, the data obtaining unit specifically includes:
the size adjusting subunit is used for adjusting the size parameters of each strip in the microwave microstrip filter according to the preset frequency in MATLAB control electromagnetic simulation software, so that the overall size of the microwave microstrip filter is fixed and unchanged, and the microwave microstrip filter with multiple groups of scattering parameters is obtained; wherein the dimensional parameters include a length and a width of the strip.
Optionally, the model establishing unit specifically includes:
the setting subunit is used for setting the number of elements of the input layer and the number of elements of the output layer;
a hidden layer number calculating subunit, configured to calculate the number of hidden layers according to the number of input layer elements and the number of output layer elements;
the device comprises a building subunit, a prediction unit and a prediction unit, wherein the building subunit is used for building a prediction model by taking a sigmoid function as an activation function;
optionally, the training unit specifically includes:
an input subunit, configured to input the accumulated microwave microstrip filter simulation data into an input layer of the prediction model;
the weight determining subunit is used for determining the connection weight of the input layer and the hidden layer and the connection weight of the hidden layer and the output layer by using a random gradient descent method;
the hidden layer input data determining subunit is used for determining hidden layer input data through input data of an input layer and the connection weight of the input layer and the hidden layer;
the hidden layer output data determining subunit is used for inputting the hidden layer input data into an activation function to obtain hidden layer output data;
the output layer input data determining subunit is used for determining output layer input data according to the hidden layer output data and the connection weight of the hidden layer and the output layer;
the reverse processing subunit is used for inputting the input data of the output layer into the activation function for reverse processing and then outputting the data;
and the weight adjusting subunit is used for transmitting the error between the output data and the target output data to the hidden layer as a feedback signal, adjusting the connection weight between the input layer and the hidden layer and the connection weight between the hidden layer and the output layer in the hidden layer until the error is within a set threshold range, and obtaining the trained prediction model.
Optionally, the determining unit specifically includes:
the parameter judgment subunit is used for judging whether the error between the predicted scattering parameter of the microwave microstrip filter of the predicted scattering parameter and the target scattering parameter is smaller than a set threshold value, and if so, the simulation requirement is met; if not, the simulation requirement is not met.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
1. the filter design and simulation are combined with the machine learning, so that the design and simulation of the filter can be automatically completed by a computer by utilizing the machine learning, and the design efficiency is greatly improved.
2. From low order filter design to high order filter design, this can be done by machine learning. In the conventional filter design, the higher the filter order is, the higher the labor cost is, and the more obvious the advantage of machine learning in the high-order filter design is.
3. The design of high frequency filters, e.g. 8GHz to 30GHz, is more complex than low frequency filters. The method can be popularized and applied to high-frequency filters, even terahertz frequency band filters (100 GHz).
In summary, the simulation method and system for the microstrip hairpin-type filter provided by the invention apply artificial intelligence based on machine learning to the filter design and optimization, for a computer, the whole process can be completely and automatically completed, the improvement of the order only means the increase of the output parameters, the design difficulty existing in manual design does not exist, and the design of the filter with any order can be completed only with enough calculation power theoretically, which means that the invention greatly saves manpower and improves the design efficiency. The design cost is reduced. In addition, aiming at the filter with a complex configuration, the invention can complete the design and simulation work which is hard to be competed by a designer.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a simulation method of a microstrip hairpin filter according to an embodiment of the present invention;
fig. 2 is a system block diagram of a simulation system of a microstrip hairpin filter according to an embodiment of the present invention;
FIG. 3 is a block diagram of a first order filter obtained by simulation using the present invention;
FIG. 4 is a graph of a first order filter target scattering parameter to be simulated;
FIG. 5 is a graph comparing predicted scattering parameters and target scattering parameters of a first order filter obtained by simulation according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the simulation method of the microstrip hairpin filter provided in this embodiment includes:
step 101: acquiring simulation data of the accumulated microwave microstrip filter; the accumulated simulation data of the microwave microstrip filter is that a large amount of simulation is automatically completed by controlling electromagnetic simulation software through MATLAB, and all the simulation data of the microwave microstrip filter of the filter are returned.
Specifically, the step 101 specifically includes:
adjusting the size parameters of each strip in the microwave microstrip filter according to preset frequency in MATLAB control electromagnetic simulation software to ensure that the whole size of the microwave microstrip filter is fixed and unchanged, and obtaining a plurality of groups of microwave microstrip filters with scattering parameters; wherein the dimensional parameters include a length and a width of the strip.
That is, before simulation, the MATLAB controls the electromagnetic simulation software to edit codes, and then the MATLAB controls the electromagnetic simulation software to run to automatically realize the automatic design of the microwave microstrip filter, thereby acquiring a large amount of accumulated simulation data of all the microwave microstrip filters. In the simulation, the changed parameters are the physical dimensions of each strip (see the black strip structure in fig. 3) in the layout of the microwave microstrip filter, that is, the length and width (fixed thickness) of each strip, the changed frequency range is 3-8GHz (preset frequency), the size of the whole size of the filter is fixed, and finally, a large amount of data of different physical dimensions of the filter and corresponding different S parameters (scattering parameters) are obtained.
Step 102: establishing a prediction model based on a BP neural network;
the calculation process of the BP neural network consists of a forward calculation process and a backward calculation process. And in the forward propagation process, the input mode is processed layer by layer from the input layer through the hidden unit layer and is transferred to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output can not be obtained at the output layer, the reverse propagation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal.
Forward propagation: the input samples are processed from the input layer through the hidden layer by layer, and are transmitted to the output layer after passing through all the hidden layers; during the layer-by-layer process, the state of each layer of neurons only affects the state of the next layer of neurons. The present output is compared with the expected output at the output layer and if the present output is not equal to the expected output, the back propagation process is entered.
And (3) back propagation: the error signal is transmitted back according to the original forward propagation path, and the weight coefficient of each neuron of each hidden layer is modified so as to expect the error signal to tend to be minimum.
The step 102 specifically includes:
setting the number of elements of an input layer and the number of elements of an output layer;
calculating the number of hidden layers according to the number of the input layer elements and the number of the output layer elements;
and establishing a prediction model by taking the sigmoid function as an activation function.
In this embodiment, a total of 4 hidden layers are used in the training process, each layer including 20 neurons. The BP neural network is a neural network with data forward propagation and error backward propagation, in the training process, a sigmoid function is adopted as an activation function, the number of input layer elements x of the neural network is 501, the number of output layer elements y of the neural network is 4, and the BP neural network is based on a formula
The number of hidden layers n can be calculated, where a is an integer between 1 and 10.
Step 103: and training the prediction model by using the accumulated microwave microstrip filter simulation data as training data to obtain the trained prediction model.
The step 103: the method specifically comprises the following steps:
inputting the accumulated microwave microstrip filter simulation data into an input layer of the prediction model;
determining the connection weight of the input layer and the hidden layer and the connection weight of the hidden layer and the output layer by using a random gradient descent method;
determining hidden layer input data through input data of an input layer and connection weight of the input layer and the hidden layer;
inputting the hidden layer input data into an activation function to obtain hidden layer output data;
determining output layer input data according to the hidden layer output data and the connection weight of the hidden layer and the output layer;
inputting the input data of the output layer into the activation function for reverse processing, and outputting the data;
and transmitting the error between the output data and the target output data to the hidden layer as a feedback signal, and adjusting the connection weight between the input layer and the hidden layer and the connection weight between the hidden layer and the output layer in the hidden layer until the error is within a set threshold range to obtain a trained prediction model.
During the training process, the loss function used is:
each training sample is weighted toward its negative gradient by using a stochastic gradient descent method, and the gradient of L to the connecting weight w is
Calculating the derivative of L to the input s as
Is marked as
Then the hidden layer δ is
Output layer δ is
Wherein y represents an output; s represents an input; l represents a loss function; SSE denotes the sum of the residual squares; SST denotes the sum of the squares; SSR represents regression sum of squares;
represents the square of the mathematical expectation for the jth element of the output layer y; e.g. of the typeiRepresents the mathematical expectation for the ith element of the output layer y;
represents the average of the jth element of the output layer; y isjCurrent value representing jth element of output layer; x is the number ofiAn ith element representing an input;
an input representing a jth node of the hidden layer;
an input representing an ith node of the output layer;
representing the connection weight from the jth node of the hidden layer to the ith node of the output layer; θ' () represents the value of the coefficient derivative in parentheses;
representing the connection weight from the ith node of the input layer to the jth node of the hidden layer;
error representing the ith input of the hidden layer;
error representing the jth output of the hidden layer;
representing the error of the ith input of the output layer.
After the training model is obtained through the steps, the prediction capability of the training model, namely the accuracy of the automatic design and simulation filter can be evaluated according to the following formula:
wherein SST is the sum of the squares of the total squares, SSR is the sum of the squares of the regression, and SSE is the sum of the squares of the residuals. Calculated R2A closer to 1 indicates a better fit. After the expected requirements are met, the model can be used for automatic design and simulation of the filter.
Step 104: and inputting the target scattering parameters of the microwave microstrip filter into the trained prediction model to obtain the microwave microstrip filter with the predicted scattering parameters.
Step 105: judging whether the microwave microstrip filter for predicting the scattering parameters meets simulation requirements or not, and if so, outputting the microwave microstrip filter for predicting the scattering parameters; if not, returning to the step of acquiring the simulation data of the accumulated microwave microstrip filter.
The step 105 specifically includes:
judging whether the error between the predicted scattering parameter of the microwave microstrip filter of the predicted scattering parameter and the target scattering parameter is smaller than a set threshold value, if so, meeting the simulation requirement; if not, the simulation requirement is not met.
The present embodiment provides a system corresponding to the simulation method for a microstrip hairpin filter provided in the foregoing embodiment, where the system includes:
a data obtaining unit 201, configured to obtain simulation data of the accumulated microwave microstrip filter; the accumulated simulation data of the microwave microstrip filter is that a large amount of simulation is automatically completed by controlling electromagnetic simulation software through MATLAB, and all the simulation data of the microwave microstrip filter of the filter are returned;
a model establishing unit 202, configured to establish a prediction model based on a BP neural network;
the training unit 203 is configured to train the prediction model by using the accumulated microwave microstrip filter simulation data as training data to obtain a trained prediction model;
the prediction unit 204 is configured to input the target scattering parameter of the microwave microstrip filter to the trained prediction model to obtain a microwave microstrip filter with a predicted scattering parameter;
a judging unit 205, configured to judge whether the microwave microstrip filter for predicting the scattering parameter meets the simulation requirement, and if so, output the microwave microstrip filter for predicting the scattering parameter; if not, returning to the step of acquiring the simulation data of the accumulated microwave microstrip filter.
The data obtaining unit 201 specifically includes:
the size adjusting subunit is used for adjusting the size parameters of each strip in the microwave microstrip filter according to the preset frequency in MATLAB control electromagnetic simulation software, so that the overall size of the microwave microstrip filter is fixed and unchanged, and the microwave microstrip filter with multiple groups of scattering parameters is obtained; wherein the dimensional parameters include a length and a width of the strip.
The model establishing unit 202 specifically includes:
the setting subunit is used for setting the number of elements of the input layer and the number of elements of the output layer;
a hidden layer number calculating subunit, configured to calculate the number of hidden layers according to the number of input layer elements and the number of output layer elements;
the device comprises a building subunit, a prediction unit and a prediction unit, wherein the building subunit is used for building a prediction model by taking a sigmoid function as an activation function;
the training unit 203 specifically includes:
an input subunit, configured to input the accumulated microwave microstrip filter simulation data into an input layer of the prediction model;
the weight determining subunit is used for determining the connection weight of the input layer and the hidden layer and the connection weight of the hidden layer and the output layer by using a random gradient descent method;
the hidden layer input data determining subunit is used for determining hidden layer input data through input data of an input layer and the connection weight of the input layer and the hidden layer;
the hidden layer output data determining subunit is used for inputting the hidden layer input data into an activation function to obtain hidden layer output data;
the output layer input data determining subunit is used for determining output layer input data according to the hidden layer output data and the connection weight of the hidden layer and the output layer;
the reverse processing subunit is used for inputting the input data of the output layer into the activation function for reverse processing and then outputting the data;
and the weight adjusting subunit is used for transmitting the error between the output data and the target output data to the hidden layer as a feedback signal, adjusting the connection weight between the input layer and the hidden layer and the connection weight between the hidden layer and the output layer in the hidden layer until the error is within a set threshold range, and obtaining the trained prediction model.
The determining unit 205 specifically includes:
the parameter judgment subunit is used for judging whether the error between the predicted scattering parameter of the microwave microstrip filter of the predicted scattering parameter and the target scattering parameter is smaller than a set threshold value, and if so, the simulation requirement is met; if not, the simulation requirement is not met.
For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The practical effects of the present invention will be described below with reference to a specific embodiment:
fig. 3 shows a first order filter obtained by the method of the present invention. Fig. 4 is a graph of a first order filter target scattering parameter to be simulated. Fig. 5 is a comparison graph of the predicted scattering parameter and the target scattering parameter of the first-order filter obtained by simulation of the present invention, and it can be seen that the S parameter of the first-order filter is well matched with the target S parameter, which indicates that the accuracy of the prediction model obtained by the present invention can meet the actual use requirement, the center frequency of the filter is 6450MHz, the 3dB bandwidth is 35MHz, the used dielectric substrate is rogers RO4003C, the dielectric constant is 3.38, the tangent loss is 0.0038, and the thickness is 0.508 mm.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811500423.4A CN109635420B (en) | 2018-12-10 | 2018-12-10 | A simulation method and system of a microwave microstrip hairpin filter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811500423.4A CN109635420B (en) | 2018-12-10 | 2018-12-10 | A simulation method and system of a microwave microstrip hairpin filter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109635420A CN109635420A (en) | 2019-04-16 |
| CN109635420B true CN109635420B (en) | 2021-07-30 |
Family
ID=66072295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811500423.4A Active CN109635420B (en) | 2018-12-10 | 2018-12-10 | A simulation method and system of a microwave microstrip hairpin filter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635420B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111791103B (en) * | 2020-06-30 | 2022-04-29 | 北京百度网讯科技有限公司 | Filter debugging method and device, electronic equipment and readable storage medium |
| CN113505529B (en) * | 2021-06-30 | 2024-02-06 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Terahertz transmission performance relation model establishment method |
| CN116401964B (en) * | 2023-06-08 | 2023-09-29 | 深圳飞骧科技股份有限公司 | Method, system and related equipment for acquiring simulation parameters of elastic wave device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880945A (en) * | 2015-03-31 | 2015-09-02 | 成都市优艾维机器人科技有限公司 | Self-adaptive inverse control method for unmanned rotorcraft based on neural networks |
| CN105787558A (en) * | 2016-04-11 | 2016-07-20 | 江苏科技大学 | Knowledge-based neural network micro-strip filter design method based on ADS |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101425152B (en) * | 2008-12-12 | 2011-09-28 | 湖南大学 | Design method for FIR filter based on learning rate changing neural net |
| US8700541B2 (en) * | 2012-02-02 | 2014-04-15 | I-Shou University | Modeling method of neuro-fuzzy system |
| CN107565932A (en) * | 2017-09-26 | 2018-01-09 | 天津工业大学 | A kind of FIR ptototype filter design methods based on linear neural network |
| CN108959728B (en) * | 2018-06-12 | 2023-04-07 | 杭州法动科技有限公司 | Radio frequency device parameter optimization method based on deep learning |
-
2018
- 2018-12-10 CN CN201811500423.4A patent/CN109635420B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880945A (en) * | 2015-03-31 | 2015-09-02 | 成都市优艾维机器人科技有限公司 | Self-adaptive inverse control method for unmanned rotorcraft based on neural networks |
| CN105787558A (en) * | 2016-04-11 | 2016-07-20 | 江苏科技大学 | Knowledge-based neural network micro-strip filter design method based on ADS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109635420A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635420B (en) | A simulation method and system of a microwave microstrip hairpin filter | |
| CN108170950A (en) | Multilayer Frequency-Selective Surfaces absorbing material modeling optimization method based on neural network | |
| CN105787558B (en) | Knowledge neural network microstrip filter design method based on ADS | |
| CN111460665B (en) | Antenna design method based on kriging agent model and multi-target genetic algorithm | |
| CN108650131B (en) | Processing system for multi-controller deployment in SDN network | |
| CN115086992A (en) | Distributed semantic communication system and bandwidth resource allocation method and device | |
| CN119135551A (en) | A network information age optimization method and system based on meta-deep reinforcement learning | |
| CN119005639B (en) | A distributed power distribution management method and platform for power distribution cabinet | |
| CN110851911B (en) | Terminal state calculation model training method, control sequence search method and device | |
| CN109473122A (en) | Mood analysis method, device and terminal device based on detection model | |
| CN109117545B (en) | Neural network-based antenna rapid design method | |
| CN114093178A (en) | Traffic signal control method and device, electronic equipment and storage medium | |
| CN118378094A (en) | Chip layout model training and application method, device, electronic device and storage medium | |
| CN118804381A (en) | Network resource configuration plan generation, network migration method, device, medium, product and equipment | |
| CN116111984B (en) | Filter design optimization method and device, filter, equipment, medium | |
| CN116911245B (en) | Layout method, system, equipment and storage medium of integrated circuit | |
| CN114339855B (en) | Wireless network coverage evaluation method, device and computing equipment | |
| CN113076699A (en) | Antenna optimization method based on multi-output Gaussian process Bayesian optimization | |
| CN114401192A (en) | Multi-SDN controller collaborative training method | |
| CN112134631A (en) | Method and system for evaluating average capacity of wireless communication system | |
| CN117375753A (en) | Parametric modeling processing methods, devices, equipment and media for wireless propagation environment | |
| CN116683944A (en) | Carrier communication signal attenuation simulator, system, method and storage medium | |
| CN110084511B (en) | A UAV matching method, device, equipment and readable storage medium | |
| CN118972900B (en) | Space-sky-ground network traffic unloading decision-making method and system based on graph neural network | |
| CN114692484B (en) | Microwave window design method based on neural network |
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 |