CN112149351A - Microwave circuit physical dimension estimation method based on deep learning - Google Patents
Microwave circuit physical dimension estimation method based on deep learning Download PDFInfo
- Publication number
- CN112149351A CN112149351A CN202011000929.6A CN202011000929A CN112149351A CN 112149351 A CN112149351 A CN 112149351A CN 202011000929 A CN202011000929 A CN 202011000929A CN 112149351 A CN112149351 A CN 112149351A
- Authority
- CN
- China
- Prior art keywords
- microwave circuit
- layer
- neural network
- network model
- data set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013135 deep learning Methods 0.000 title claims abstract description 22
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000003062 neural network model Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 48
- 238000010586 diagram Methods 0.000 claims description 20
- 238000011176 pooling Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000005549 size reduction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 210000002569 neuron Anatomy 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000002945 steepest descent method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000611 regression analysis Methods 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Measurement Of Resistance Or Impedance (AREA)
- Design And Manufacture Of Integrated Circuits (AREA)
Abstract
The invention discloses a microwave circuit physical dimension estimation method based on deep learning, which comprises the following steps: step one, collecting S parameters of a plurality of groups of microwave circuits and physical dimensions of the plurality of groups of microwave circuit parameters as an initial data set, and constructing a training sample set according to the initial data set; training the convolutional neural network model according to the training sample set to obtain a microwave circuit size estimation neural network model; and step three, collecting S parameters of the target microwave circuit as input parameters, and inputting the S parameters into the microwave circuit size estimation neural network model to obtain the physical size of the target microwave circuit. The microwave circuit physical dimension estimation method based on deep learning provided by the invention has the advantages of high automation degree and high estimation accuracy, can effectively reduce intermediate links and manual intervention for microwave circuit physical dimension parameter estimation, can effectively reduce application cost and complexity, and can effectively improve the accuracy and real-time property for microwave circuit physical dimension parameter estimation.
Description
Technical Field
The invention belongs to the technical field of microwave circuit design simulation, and particularly relates to a microwave circuit physical dimension estimation method based on deep learning.
Background
In recent years, training neural networks to model the electrical performance of passive and active components/circuits for advanced simulations and designs has grown to be a method to provide a quick solution to tasks. Conventional methods of microwave circuit design in the industry today, such as numerical modeling methods, can be computationally expensive, while new analytical equipment, such as empirical models, can be difficult to obtain in a manner that is limited in scope and accuracy. Therefore, neural network technology has been widely used in various microwave applications, such as embedded passive devices, transmission line components, coplanar waveguide (CPW) components, spiral inductors, FETs.
The design means of the microwave circuit in the industry at present mainly is according to theoretical modeling, obtains roughly circuit size parameter after theoretical simulation, simulates in certain parameter range interval through actual simulation software, selects the microwave circuit size parameter that the effect is the closest to theoretical simulation result and corresponds through the contrast to the simulation result at last, but this kind of scheme exists inefficiency, and work load is big, does not have theoretical guidance scheduling problem, can not satisfy the efficiency demand in the industry at present.
Disclosure of Invention
The invention aims to provide a microwave circuit physical size estimation method based on deep learning, which can realize quick and accurate acquisition of the size parameters of a microwave circuit by carrying out regression analysis on the corresponding relation between the calculation theoretical electrical parameters and the circuit size parameters through a deep learning technology.
The technical scheme provided by the invention is as follows:
a microwave circuit physical dimension estimation method based on deep learning comprises the following steps:
step one, collecting S parameters of a plurality of groups of microwave circuits and physical dimensions of the plurality of groups of microwave circuit parameters as an initial data set, and constructing a training sample set according to the initial data set;
training the convolutional neural network model according to the training sample set to obtain a microwave circuit size estimation neural network model;
and step three, collecting S parameters of the target microwave circuit as input parameters, and inputting the S parameters into the microwave circuit size estimation neural network model to obtain the physical size of the target microwave circuit.
Preferably, in the second step, the convolutional neural network model is trained by a gradient descent method to obtain the microwave circuit size estimation neural network model.
Preferably, in the first step, constructing a training sample set according to the initial data set includes:
converting and adjusting the size of the S parameter of the microwave circuit to a format of 3 multiplied by 1; and expanding the data volume of the initial data set by adopting a data enhancement method, and taking a part of the expanded initial data set as a training sample set.
Preferably, the data in the augmented initial data set is divided into three parts, including:
training sample set 60%, validation data set 20% and test data set 20%.
Preferably, the microwave circuit size estimation neural network model comprises, connected in sequence: the device comprises an input layer, a processing module, a Dropout layer, a full connection layer and a regression prediction output layer.
Preferably, the processing module comprises at least four processing units connected in sequence, wherein,
the first processing unit to the third processing unit respectively comprise a convolution layer, a batch standardization BN layer, a correction linear unit ReLU layer and a pooling layer which are connected in sequence, and the fourth processing unit comprises a convolution layer, a batch standardization BN layer and a correction linear unit ReLU layer which are connected in sequence.
Preferably, the sizes of convolution kernels in the convolution layers of the four processing units are all 2 × 2; the number of convolution kernels of the four processing units is increased in sequence according to the connection order.
Preferably, in the third step, obtaining the physical size of the target microwave circuit includes the following steps:
step 1, sequentially processing and transmitting input data in four processing units in the processing module based on a gradient descent algorithm until a target characteristic diagram is output in the four processing units;
step 2, the full connection layer converts the target characteristic diagram into a one-dimensional vector;
and 3, outputting a physical size estimation result of the target microwave circuit by the regression prediction output layer according to the one-dimensional vector.
Preferably, in the step 1, the method includes:
the convolutional layer extracts a characteristic diagram of the input data according to the following formula;
in the formula (I), the compound is shown in the specification,
a feature map of the ith output of the jth convolutional layer in the convolutional neural network model; m is the number of the input characteristic graphs of the jth convolutional layer in the convolutional neural network model;
the batch standardization BN layer is used for carrying out normalization processing on the characteristic diagram;
carrying out nonlinear transformation on the normalized characteristic diagram of the ReLU layer;
the pooling layer performs size reduction processing on the received nonlinear-converted characteristic diagram according to the following formula;
in the formula (I), the compound is shown in the specification,
is a down-sampling function; f is the size of the down-sampling filter; s is down sampling step length。
Preferably, in the step 3, the full connection layer converts the target feature map into a one-dimensional vector according to the following formula;
vj＝f(wjvj-1+bj)；
in the formula, vjOutputting a one-dimensional vector for the jth fully-connected layer; w is ajThe weight matrix of the jth full connection layer; bjBias term of jth fully-connected layer; f (-) is a nonlinear activation function.
The invention has the beneficial effects that:
the microwave circuit physical dimension estimation method based on deep learning provided by the invention has the advantages of high automation degree and high estimation accuracy, can effectively reduce intermediate links and manual intervention for microwave circuit physical dimension parameter estimation, can effectively reduce application cost and complexity, and can effectively improve the accuracy and real-time property for microwave circuit physical dimension parameter estimation.
Drawings
Fig. 1 is a flowchart of a microwave circuit physical dimension parameter estimation method based on a convolutional neural network according to the present invention.
FIG. 2 is a flow chart of the present invention for building a convolutional neural network model.
Fig. 3 is a schematic structural diagram of a convolutional neural network model according to the present invention.
Fig. 4 is a flowchart of a microwave circuit physical dimension parameter estimation method based on a convolutional neural network according to the present invention.
FIG. 5 is a schematic flow chart of embodiment 1 of the present invention.
Fig. 6 is a block diagram of a system for estimating physical size parameters of a microwave circuit based on a convolutional neural network in embodiment 1 of the present invention.
Fig. 7 is a schematic structural diagram of an electronic device in embodiment 1 of the present invention.
Fig. 8 is a comparison graph of the theoretical simulation result of the physical dimension parameter of the microwave circuit and the simulation result of the physical dimension parameter of the microwave circuit obtained in example 1.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
As shown in fig. 1, the present invention provides a method for estimating physical dimensions of a microwave circuit based on deep learning, which comprises:
In step 101, the microwave circuit electrical parameter acquisition unit in the microwave circuit physical dimension parameter estimation system based on the convolutional neural network automatically receives the acquired electrical parameters of the target microwave circuit, and the specific way of acquiring the electrical parameters of the target microwave circuit can invoke an operation interface provided by electromagnetic simulation software sonet through MATLAB to perform operation automatic acquisition, and send the acquired electrical parameters to the microwave circuit electrical parameter acquisition unit.
In step 102, after automatically receiving the collected electrical parameter data of the target microwave circuit, the microwave circuit electrical parameter collecting unit sends the electrical parameter data of the target microwave circuit to the convolutional neural network model establishing unit in the microwave circuit physical dimension parameter estimation system based on the convolutional neural network, and the convolutional neural network model establishing unit receives the electrical parameters of the microwave circuit, takes an input data set corresponding to the electrical parameters of the microwave circuit as the input of the model, and establishes a convolutional neural network model specially used for estimating the physical dimension parameters of the target microwave circuit according to the characteristics of the input data set, such as the dimension and the like. It can be understood that, in addition to the input layer, the fully connected layer and the output layer which are connected in sequence, the convolutional layer (convolutional layer) and the pooling layer (pooling layer) connected between the input layer and the fully connected layer are arranged in a manner and the number of layers depends on the characteristics of the size and the like of the input data set corresponding to the microwave electrical parameter data. It is understood that convolutional neural network cnn (convolutional neural network) is a kind of feed-forward neural network whose artificial neurons can respond to a part of the surrounding cells within the coverage.
On the other hand, the embodiment further provides a microwave circuit physical size parameter estimation system based on a convolutional neural network, including:
the microwave circuit electrical parameter and physical dimension parameter acquisition unit is used for continuously acquiring the target microwave circuit and constructing a corresponding input data set according to the electrical parameters of the target microwave circuit;
the parameter estimation unit is used for inputting the input data set into a trained convolutional neural network model to obtain an estimation result of the physical size parameter of the target microwave circuit; the trained convolutional neural network model is obtained by taking a training data set as input and utilizing a gradient descent method for training.
The embodiment further comprises a processor, a communication interface, a memory and a bus, wherein the processor, the communication interface and the memory complete mutual communication through the bus, and the processor can call the deep learning training model stored in the memory to execute the method for estimating the physical size parameters of the microwave circuit based on the convolutional neural network provided by the first aspect.
Meanwhile, the present embodiment also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method for estimating physical dimension parameters of a microwave circuit based on a convolutional neural network provided in the first aspect.
And the estimation unit of the microwave circuit physical dimension parameter in the microwave circuit physical dimension parameter estimation system based on the convolutional neural network performs model training, verification and test on the convolutional neural network model according to a gradient descent algorithm and the test data set to obtain an estimation result of the target microwave circuit physical dimension parameter.
It will be appreciated that the gradient descent algorithm is an optimization algorithm, also commonly referred to as the steepest descent method. The steepest descent method uses the negative gradient direction as the search direction, and the closer the steepest descent method is to the target value, the smaller the step length is, the slower the progress is.
In this embodiment, as shown in fig. 2, before inputting the input data set into a trained convolutional neural network model to obtain an estimation result of the physical size parameter of the target microwave circuit, the method further includes:
step 201, using an input data set corresponding to the electrical parameters of the target microwave circuit as the input of the input layer of the convolutional neural network;
step 202, establishing a processing module of the convolutional neural network model according to the size of the data in the input data set;
and 203, sequentially connecting the input layer, the processing module, a Dropout layer for preventing the output of the processing module from being over-fitted, a full connection layer for converting the output of the processing module into a one-dimensional vector and a regression prediction output layer for outputting the estimation result of the physical size parameter of the target microwave circuit, and completing the establishment of the convolutional neural network model.
In the above steps 201 to 203, an overall architecture of the convolutional neural network model is as shown in fig. 3, the processing module at least includes four processing units connected in sequence, and each of the first processing unit to the third processing unit includes a convolutional Layer, a Batch Normalization Layer (BN Layer), a modified linear unit ReLU Layer, and a pooling Layer connected in sequence, and the fourth processing unit includes the convolutional Layer, the Batch Normalization BN Layer, and the modified linear unit ReLU Layer connected in sequence;
the sizes of convolution kernels in each convolution layer in the four sequentially connected processing units are not changed, and the number of convolution kernels is increased gradually.
As can be seen from the above description, the method for estimating physical size parameters of a microwave circuit based on a convolutional neural network provided in this embodiment provides an effective and reliable method for establishing a convolutional neural network model for estimating physical size parameters of a microwave circuit, where the convolutional neural network model for estimating physical size parameters of a microwave circuit has an accurate structure and strong pertinence, and can estimate the physical size parameters of the microwave circuit more accurately.
In this embodiment, as shown in fig. 4, inputting the input data set into a trained convolutional neural network model to obtain an estimation result of the physical size parameter of the target microwave circuit, which specifically includes:
In step 401, the convolutional layer in the processing module extracts a feature map of the received input data set, including:
the convolutional layer extracts a feature map of the received input data set according to formula one:
in the formula (1), the first and second groups,
a feature map of the ith output of the jth convolutional layer in the convolutional neural network model; m is the number of the input characteristic graphs of the jth convolutional layer in the convolutional neural network model;
Correspondingly, the pooling layer performs size reduction processing on the received nonlinear-converted feature map, and the size reduction processing comprises the following steps:
and the pooling layer performs size reduction treatment on the received nonlinear converted characteristic diagram according to a formula II:
in the formula (2), the first and second groups,
is a down-sampling function; f is the size of the down-sampling filter; and S is a down-sampling step length.
the full connection layer converts the target characteristic diagram into a one-dimensional vector according to a formula III:
vj＝f(wjvj-1+bj)#(3)
in the formula (3), vjOutputting a one-dimensional vector for the jth fully-connected layer; w is ajThe weight matrix of the jth full connection layer; bjBias term of jth fully-connected layer; f (-) is a nonlinear activation function.
And 403, outputting a physical size parameter estimation result of the target microwave circuit by the regression prediction layer according to the one-dimensional vector.
Example 1
For further explanation, the present invention further provides an application example of the microwave circuit physical dimension parameter estimation method based on the convolutional neural network, and with reference to fig. 5, the method specifically includes the following contents:
501. acquiring microwave circuit electrical parameter data and preprocessing the data;
in particular, the pre-processing comprises resizing the microwave circuit electrical parameter data, for example to a 3 x 1 format. Constructing an initial data set by the electrical parameters of the preprocessed microwave circuit, and expanding the data volume of the initial data set by adopting a data enhancement method;
the data set is divided into training data set, validation data set and test data set 3 parts.
502. Constructing a convolutional neural network model structure, and training, verifying and testing the convolutional neural network model according to the expanded data set and a gradient descent method;
specifically, the convolutional neural network model takes the electrical parameters of the microwave circuit as input and takes the estimated physical size parameters of the microwave circuit as output, and comprises five modules in total. The first to fourth modules each include 1 convolutional layer, 1 BN layer, 1 RELU layer, and 1 pooling layer. The convolution layer has a convolution kernel size of 2 × 2, and is used to acquire the features of the input image. The RELU layer carries out nonlinear transformation on the characteristic diagram generated by the convolutional layer, so that the sparsity of the network is realized, the interdependence relation of parameters is reduced, and the occurrence of the over-fitting problem is relieved. The RELU layer does not change the feature size. The convolution kernel size of the pooling layer is 2 × 2, the step size is 1, the pooling is maximum, and the feature size is reduced to 1/2. The number of convolution kernels in the four module convolution layers is gradually increased and is 32, 64, 128 and 256 in sequence. The size of convolution kernel of the fifth module and the function of each layer are the same as those of the first four modules, and the fifth module comprises 1 convolution layer, 1 BN layer and 1 RELU layer, wherein the number of convolution kernels in the convolution layer is 512. The last module comprises 2 full-connection layers and 1 regression output layer, wherein the first full-connection layer in the 2 full-connection layers contains 500 neurons, and the second full-connection layer contains 1 neuron. The regression output layer estimates the physical size parameters of the microwave circuit.
503. According to the convolutional neural network model, estimating physical size parameters of an input microwave circuit data set;
the microwave circuit physical size parameter estimation method based on the convolutional neural network can directly use microwave circuit electrical parameters as input of an estimation model, expand input data quantity through data enhancement, construct a convolutional neural network model, train, verify and test, realize quick estimation of microwave circuit physical size parameters, improve estimation accuracy and realize practical application of the microwave circuit physical size parameter estimation method.
As shown in fig. 6, the microwave circuit physical dimension parameter estimation system based on the convolutional neural network comprises: a microwave circuit electrical parameter acquisition unit 601 and a microwave circuit physical dimension parameter estimation unit 602. Wherein:
the microwave circuit electrical parameter acquisition unit 601 is configured to continuously acquire electrical parameters of a target microwave circuit, and construct a corresponding input data set according to the electrical parameters of the target microwave circuit. The microwave circuit physical size parameter estimation unit 602 is configured to input the input data set into a trained convolutional neural network model to obtain an estimation result of the target microwave circuit physical size parameter; the trained convolutional neural network model is obtained by taking a training data set as input and utilizing a gradient descent method for training.
Specifically, the acquisition unit 601 may acquire microwave circuit electrical parameter data, and perform preprocessing on the microwave electrical parameter data, where the preprocessing includes adjusting the size of the input data.
Furthermore, an initial data set is constructed according to the preprocessed data, and the size of the initial data set is expanded by adopting a data enhancement method. Dividing the data set into a training data set, a verification data set and a test data set 3, wherein the proportion is respectively as follows: 60%, 20% and 20%.
The microwave circuit physical dimension parameter estimation unit 602 is used for constructing the convolutional neural network structure of the present invention. The convolution neural network model takes the electrical parameter data of the microwave circuit as input and takes the estimated physical dimension parameter of the microwave circuit as output, and comprises 5 modules in total. The first to fourth modules each include 1 convolutional layer, 1 BN layer, 1 RELU layer, and 1 pooling layer. The convolution layer has a convolution kernel size of 2 × 2, and is used to acquire the features of the input image. The RELU layer carries out nonlinear transformation on the characteristic diagram generated by the convolutional layer, so that the sparsity of the network is realized, the interdependence relation of parameters is reduced, and the occurrence of the over-fitting problem is relieved. The RELU layer does not change the feature size. The convolution kernel size of the pooling layer is 2 × 2, the step size is 2, the pooling is maximum, and the feature size is reduced to 1/2. The number of convolution kernels in the four module convolution layers is gradually increased and is 32, 64, 128 and 256 in sequence. The size of convolution kernel of the fifth module and the function of each layer are the same as those of the first four modules, and the fifth module comprises 1 convolution layer, 1 BN layer and 1 RELU layer, and the number of convolution kernels of the convolution layers is 512. The last module comprises 2 dropouts, 2 full-connection layers and 1 regression output layer, the discarding rate of the 2 dropouts is 0.5, the first full-connection layer in the 2 full-connection layers comprises 500 neurons, and the second full-connection layer comprises 1 neuron. And the regression output layer estimates the physical size parameters of the microwave circuit. The microwave circuit physical size parameter estimation unit 602 performs training, verification, and testing of a convolutional neural network based on the expanded data set and the gradient descent algorithm, and estimates the microwave circuit physical size parameter of the input electrical parameter of the microwave circuit based on the tested convolutional neural network model.
As can be seen from the above description, the estimation of the physical size parameter of the microwave circuit based on the convolutional neural network provided in the embodiment of the present invention can directly use the electrical parameter of the microwave circuit as the input of the identification model, expand the input data amount through data enhancement, construct the convolutional neural network model, and perform training, verification and testing, thereby realizing the estimation of the physical size parameter of the microwave circuit, improving the estimation accuracy, and realizing the practical application of the estimation of the physical size parameter of the microwave circuit.
As shown in fig. 7, the electronic apparatus includes: the system comprises a processor (processor), a communication Interface (communication Interface), a memory (memory) and a bus, wherein the processor, the communication Interface and the memory are communicated with each other through the bus. The processor may call logic instructions in the memory to perform a method, for example, comprising: continuously acquiring electrical parameters of a target microwave circuit, and constructing a corresponding input data set according to the electrical parameters of the target microwave circuit; inputting the input data set into a trained convolutional neural network model to obtain an estimation result of the physical size parameter of the target microwave circuit; the trained convolutional neural network model is obtained by taking a training data set as input and utilizing a gradient descent method for training.
The logic instructions in the memory may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
All or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above-described embodiments of the communication device and the like are merely illustrative, and units illustrated as separate components may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
As shown in table 1, a table of results obtained by comparing the accuracy of the deep learning-based microwave circuit physical dimension parameter estimation method with other Regression prediction methods such as linear Regression and SVM RF Regression in example 1 shows that the results are obtained in MSE, MAE, R2On the evaluation standard commonly used by the three regression analyses, the method has the characteristics of higher precision, better fitting degree of regression curves and the like.
TABLE 1 comparison table of the accuracy of the physical dimension results of microwave circuits estimated by different methods
FIG. 8 is a comparison of the simulation result of the theoretical physical dimension parameter of the circuit and the simulation result of the physical dimension parameter predicted by the method, and it can be seen that the two are substantially identical at the equal waviness, which means that the circuit prepared by the physical dimension parameter predicted by the method can obtain the performance which is nearly equal to that obtained by the theoretical calculation.
In summary, the estimation method provided by the present invention includes automatically collecting the electrical parameters of the target microwave circuit, and constructing an input data set; taking an input data set corresponding to the electrical parameters of the target microwave circuit as the input of a model, and establishing a convolutional neural network model for estimating the physical size parameters of the target microwave circuit; and carrying out model training, verification and testing on the convolutional neural network model according to a gradient descent algorithm and a test data set to obtain an estimation result of the physical size parameter of the target microwave circuit. The method has high automation degree and estimation accuracy, can effectively reduce intermediate links and manual uncertainty of microwave circuit design simulation, reduces the application cost and complexity of microwave circuit design, and effectively improves the accuracy of estimation of physical dimension parameters of the microwave circuit.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (10)
1. A microwave circuit physical dimension estimation method based on deep learning is characterized by comprising the following steps:
step one, collecting S parameters of a plurality of groups of microwave circuits and physical dimensions of the plurality of groups of microwave circuit parameters as an initial data set, and constructing a training sample set according to the initial data set;
training the convolutional neural network model according to the training sample set to obtain a microwave circuit size estimation neural network model;
and step three, collecting S parameters of the target microwave circuit as input parameters, and inputting the S parameters into the microwave circuit size estimation neural network model to obtain the physical size of the target microwave circuit.
2. The microwave circuit physical dimension estimation method based on deep learning of claim 1, wherein in the second step, the convolutional neural network model is trained through a gradient descent method to obtain the microwave circuit dimension estimation neural network model.
3. The deep learning-based microwave circuit physical dimension estimation method according to claim 2, wherein in the step one, a training sample set is constructed from the initial data set, and the method comprises:
adjusting the size of the S parameter of the microwave circuit to a 3 x 1 format; and expanding the data volume of the initial data set by adopting a data enhancement method, and taking a part of the expanded initial data set as a training sample set.
4. The deep learning based microwave circuit physical dimension estimation method of claim 3, wherein the data in the expanded initial data set is divided into three parts, including:
training sample set 60%, validation data set 20% and test data set 20%.
5. The microwave circuit physical dimension estimation method based on deep learning of claim 3 or 4, wherein the microwave circuit dimension estimation neural network model comprises sequentially connected: the device comprises an input layer, a processing module, a Dropout layer, a full connection layer and a regression prediction output layer.
6. The deep learning based microwave circuit physical dimension estimation method of claim 5, wherein the processing module comprises at least four processing units connected in sequence, wherein,
the first processing unit to the third processing unit respectively comprise a convolution layer, a batch standardization BN layer, a correction linear unit ReLU layer and a pooling layer which are connected in sequence, and the fourth processing unit comprises a convolution layer, a batch standardization BN layer and a correction linear unit ReLU layer which are connected in sequence.
7. The deep learning-based microwave circuit physical size estimation method according to claim 6, wherein the sizes of convolution kernels in the convolution layers of the four processing units are all 2 x 2; the number of convolution kernels of the four processing units is increased in sequence according to the connection order.
8. The method for estimating the physical size of the microwave circuit based on the deep learning of claim 7, wherein in the third step, obtaining the physical size of the target microwave circuit comprises the following steps:
step 1, sequentially processing and transmitting input data in four processing units in the processing module based on a gradient descent algorithm until a target characteristic diagram is output in the four processing units;
step 2, the full connection layer converts the target characteristic diagram into a one-dimensional vector;
and 3, outputting a physical size estimation result of the target microwave circuit by the regression prediction output layer according to the one-dimensional vector.
9. The deep learning-based microwave circuit physical dimension estimation method according to claim 8, wherein in the step 1, the method comprises:
the convolutional layer extracts a characteristic diagram of the input data according to the following formula;
in the formula (I), the compound is shown in the specification,
a feature map of the ith output of the jth convolutional layer in the convolutional neural network model; m is the number of the input characteristic graphs of the jth convolutional layer in the convolutional neural network model;
the batch standardization BN layer is used for carrying out normalization processing on the characteristic diagram;
carrying out nonlinear transformation on the normalized characteristic diagram of the ReLU layer;
the pooling layer performs size reduction processing on the received nonlinear-converted characteristic diagram according to the following formula;
in the formula (I), the compound is shown in the specification,
is a down-sampling function; f is the size of the down-sampling filter; and S is a down-sampling step length.
10. The deep learning-based microwave circuit physical dimension estimation method according to claim 9, wherein in the step 3, the full connection layer converts the target feature map into a one-dimensional vector according to the following formula;
vj＝f(wjvj-1+bj)；
in the formula, vjOutputting a one-dimensional vector for the jth fully-connected layer; w is ajThe weight matrix of the jth full connection layer; bjBias term of jth fully-connected layer; f (-) is a nonlinear activation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011000929.6A CN112149351B (en) | 2020-09-22 | 2020-09-22 | Microwave circuit physical dimension estimation method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011000929.6A CN112149351B (en) | 2020-09-22 | 2020-09-22 | Microwave circuit physical dimension estimation method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112149351A true CN112149351A (en) | 2020-12-29 |
| CN112149351B CN112149351B (en) | 2023-04-18 |
Family
ID=73893658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011000929.6A Expired - Fee Related CN112149351B (en) | 2020-09-22 | 2020-09-22 | Microwave circuit physical dimension estimation method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149351B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454756A (en) * | 2023-10-23 | 2024-01-26 | 广州航海学院 | Microstrip antenna modeling method and device, electronic equipment and medium |
| EP4421671A1 (en) * | 2023-02-23 | 2024-08-28 | RTX Corporation | Method for designing architecture for microwave communication and power networks |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040239452A1 (en) * | 2001-11-02 | 2004-12-02 | Fred Bassali | Circuit board microwave filters |
| CN101539137A (en) * | 2009-04-17 | 2009-09-23 | 北京航空航天大学 | Residual life gray prediction method of aerospace hydraulic pump based on delta filter |
| CN106528975A (en) * | 2016-11-01 | 2017-03-22 | 电子科技大学 | Fault prognostics and health management method applied to circuits and systems |
| CN106560691A (en) * | 2016-10-20 | 2017-04-12 | 中国计量大学 | Identification method for producing area of Wuyi rock tea and with deep learning function |
| CN107645287A (en) * | 2017-05-24 | 2018-01-30 | 南京大学 | A kind of size based on 6 parallel rapid finite impact response filter cascade structures can configure convolution hardware and realize |
| CN109670509A (en) * | 2019-01-04 | 2019-04-23 | 中国农业大学 | Winter wheat seedling stage growing way parameter evaluation method and system based on convolutional neural networks |
| CN110765704A (en) * | 2019-11-28 | 2020-02-07 | 北京工业大学 | Novel automatic deep neural network modeling method applied to microwave device |
-
2020
- 2020-09-22 CN CN202011000929.6A patent/CN112149351B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040239452A1 (en) * | 2001-11-02 | 2004-12-02 | Fred Bassali | Circuit board microwave filters |
| CN101539137A (en) * | 2009-04-17 | 2009-09-23 | 北京航空航天大学 | Residual life gray prediction method of aerospace hydraulic pump based on delta filter |
| CN106560691A (en) * | 2016-10-20 | 2017-04-12 | 中国计量大学 | Identification method for producing area of Wuyi rock tea and with deep learning function |
| CN106528975A (en) * | 2016-11-01 | 2017-03-22 | 电子科技大学 | Fault prognostics and health management method applied to circuits and systems |
| CN107645287A (en) * | 2017-05-24 | 2018-01-30 | 南京大学 | A kind of size based on 6 parallel rapid finite impact response filter cascade structures can configure convolution hardware and realize |
| CN109670509A (en) * | 2019-01-04 | 2019-04-23 | 中国农业大学 | Winter wheat seedling stage growing way parameter evaluation method and system based on convolutional neural networks |
| CN110765704A (en) * | 2019-11-28 | 2020-02-07 | 北京工业大学 | Novel automatic deep neural network modeling method applied to microwave device |
Non-Patent Citations (3)
| Title |
|---|
| G.L. CREECH等: "Artificial neural networks for accurate microwave CAD applications", 《1996 IEEE MTT-S INTERNATIONAL MICROWAVE SYMPOSIUM DIGEST》 * |
| JING JIN 等: "Deep Neural Network Technique for High-Dimensional Microwave Modeling and Applications to Parameter Extraction of Microwave Filters", 《IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES》 * |
| 张淑娥 等: "遗传神经网络在腔体滤波器结构参数优化中的应用", 《中国新通信》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4421671A1 (en) * | 2023-02-23 | 2024-08-28 | RTX Corporation | Method for designing architecture for microwave communication and power networks |
| CN117454756A (en) * | 2023-10-23 | 2024-01-26 | 广州航海学院 | Microstrip antenna modeling method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112149351B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110926782B (en) | Circuit breaker fault type judgment method and device, electronic equipment and storage medium | |
| CN111860588A (en) | Training method for graph neural network and related equipment | |
| CN110472695B (en) | Abnormal working condition detection and classification method in industrial production process | |
| CN107784180B (en) | Design method of time-varying convex quadratic programming solver | |
| CN112149351B (en) | Microwave circuit physical dimension estimation method based on deep learning | |
| CN111126481A (en) | Training method and device of neural network model | |
| CN110222718B (en) | Image processing method and device | |
| CN110689183B (en) | Cluster photovoltaic power probability prediction method, system, medium and electronic device | |
| CN113541985B (en) | Internet of things fault diagnosis method, model training method and related devices | |
| CN114490065A (en) | Load prediction method, device and equipment | |
| CN113011532B (en) | Classification model training method, device, computing equipment and storage medium | |
| WO2023159756A1 (en) | Price data processing method and apparatus, electronic device, and storage medium | |
| CN115860100A (en) | Neural network model training method and device and computing equipment | |
| CN117454756B (en) | Microstrip antenna modeling method and device, electronic equipment and medium | |
| CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
| CN117454750A (en) | Temperature prediction method, device, equipment and storage medium | |
| CN110288002B (en) | Image classification method based on sparse orthogonal neural network | |
| CN116186534B (en) | Pre-training model updating method and device and electronic equipment | |
| CN116826734A (en) | Photovoltaic power generation power prediction method and device based on multi-input model | |
| CN116912483A (en) | Target detection method, electronic device and storage medium | |
| CN114372539B (en) | Machine learning framework-based classification method and related equipment | |
| CN115983362A (en) | Quantization method, recommendation method and device | |
| CN116362301A (en) | Model quantization method and related equipment | |
| Yu et al. | Fault diagnosis of wearable temperature sensors based on multi-scale feature extraction | |
| CN116701857B (en) | Method and device for predicting water content and drying energy consumption of target object in drying process |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20230418 |