CN108268700A - A kind of RF power amplification temperature characterisitic modeling method based on BPNN - Google Patents
A kind of RF power amplification temperature characterisitic modeling method based on BPNN Download PDFInfo
- Publication number
- CN108268700A CN108268700A CN201711409317.0A CN201711409317A CN108268700A CN 108268700 A CN108268700 A CN 108268700A CN 201711409317 A CN201711409317 A CN 201711409317A CN 108268700 A CN108268700 A CN 108268700A
- Authority
- CN
- China
- Prior art keywords
- bpnn
- models
- test
- desired value
- bpnn models
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Amplifiers (AREA)
Abstract
The invention discloses a kind of RF power amplification temperature characterisitic modeling methods based on BPNN：The training data and test data of BPNN models are chosen according to the measured data of the radio-frequency power amplifier temperature characterisitic of acquisition；Determine the input variable and output variable of BPNN models；Training data is imported in BPNN models, BPNN models are trained；Test data is imported in trained BPNN models, compares BPNN models output result and test result and the error for calculating the two；Compare the size of test error MSE and BPNN the model accuracy desired value of BPNN models, if test error MSE is less than precision desired value, BPNN model trainings are completed；If test error MSE is more than precision desired value, adjusting parameter re -training, until MSE is less than precision desired value, training terminates.The present invention realizes the prediction to radio-frequency power amplifier performance indicator situation of change in given temperature section using BPNN.
Description
Technical field
The present invention relates to radio-frequency power amplifier temperature characterisitics to model field, more specifically, being to be related to one kind to be based on
The RF power amplification temperature characterisitic modeling method of BPNN.
Background technology
Radio-frequency power amplifier is the indispensable core circuit module of radio-frequency front-end, and the quality of performance directly determines
The good and the bad of performance in wireless communication systems.The performance of radio-frequency power amplifier is influenced by temperature huge, and the defect is in practical work
It can not be avoided during work.Literature survey the result shows that：Not yet establish complete device temperature model at present, cause it is designed go out
The radio-frequency power amplifier come can only be met the requirements within the scope of a certain specific temperature.When the work temperature of radio-frequency power amplifier
Degree change (especially temperature generation wide variation) when, the characteristic of radio-frequency power amplifier will become therewith
Change, and the performance and working condition that this will greatly influence entire communication system.Therefore, it is necessary to be directed to one to design penetrating for completion
Frequency power amplifier characterized about the behavior of temperature characterisitic, and to realize, radio-frequency power is put under a wide range of temperature variations
The prediction of big device characteristic.
Predict the characteristic of the radio-frequency power amplifier under a wide range of temperature variations, this just needs to carry out a large amount of
Actual test, and practical test process is extremely time-consuming, and practical test point is unlikely to be complete continuous covering again
All temperature.Therefore, in the case where predicting a wide range of temperature variations, the characteristic of radio-frequency power amplifier just faces one urgently
Demand：The characteristic of the radio-frequency power amplifier in entire temperature range is characterized according to a small number of crucial test points.
Invention content
The purpose of the invention is to overcome deficiency of the prior art, the present invention provides a kind of radio frequency work(based on BPNN
Temperature characterisitic modeling method is put, based on the measured data of radio-frequency power amplifier temperature characterisitic, using Back Propagation
Neural Network (BPNN), establish radio-frequency power amplifier performance indicator (such as：S parameter, output power, PAE etc.) it closes
In the correlation model of temperature, the prediction to radio-frequency power amplifier performance indicator situation of change in given temperature section is realized.
The purpose of the present invention is what is be achieved through the following technical solutions.
The RF power amplification temperature characterisitic modeling method based on BPNN of the present invention, includes the following steps：
Step 1 chooses the training of BPNN models according to the measured data of the radio-frequency power amplifier temperature characterisitic obtained
Data and test data；
Step 2 determines the input variable (input power, frequency and temperature) of BPNN models and output variable (output work
Rate, S parameter and PAE)；
Training data is imported in BPNN models, BPNN models is trained by step 3；
Step 4 imports test data in trained BPNN models, compares BPNN models output result and survey
The test error MSE of test result and the error, i.e. BPNN models that both calculate：
Wherein, miRepresent the test result of BPNN models, i.e., the preferable output of BPNN models is as a result, oiRepresent BPNN models
Output as a result, i.e. BPNN models reality output as a result, n represent sample size；
Step 5 compares the size of test error MSE and BPNN the model accuracy desired value of BPNN models, if test misses
Poor MSE is less than precision desired value, then BPNN model trainings are completed；If test error MSE is more than precision desired value, need to lead to
It crosses adjusting parameter (excitation function F (￡), hiding number of plies L and hidden neuron number N) and carries out re -training, until MSE is less than
Precision desired value, training terminate.
Compared with prior art, advantageous effect caused by technical scheme of the present invention is：
BPNN models are applied to the modeling of radio-frequency power amplifier temperature characterisitic by the present invention for the first time, can be met and be closed by minority
The test point of key characterizes the current demand of radio-frequency power amplifier characteristic in entire temperature range, has filled up radio-frequency power amplification
Device temperature characterisitic models the blank in field.The application of BPNN models realize radio-frequency power amplifier input variable (input power,
Frequency and temperature) and output variable (output power, S parameter and PAE) Nonlinear Mapping, and when new data enter BPNN moulds
When being trained in type, model can be by adjusting weighted value to adapt to more data.In addition, by adjusting BPNN moulds
The transmission function of last in type layer neuron can flexibly change the last output of the output variable of entire model, i.e. model
Variable can be arbitrary value.
In addition, the model and its modeling procedure may be equally applied to other RF/Microwave Integrated Circuits temperature characterisitics analysis and
Prediction has very strong practical guided significance to the design of actual radio frequency/microwave circuit.
Description of the drawings
Fig. 1 is the modeling procedure schematic diagram based on BPNN；
Fig. 2 is radio-frequency power amplifier temperature property test circuit diagram；
Fig. 3 is radio-frequency power amplifier output power and the modeling result schematic diagram of PAE；
Fig. 4 is the modeling result schematic diagram of radio-frequency power amplifier S21 and S22.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
The RF power amplification temperature characterisitic modeling method based on BPNN of the present invention, as shown in Figure 1, including the following steps：
Step 1 chooses the training of BPNN models according to the measured data of the radio-frequency power amplifier temperature characterisitic obtained
Data and test data；
Step 2 determines the input variable (input power, frequency and temperature) of BPNN models and output variable (output work
Rate, S parameter and PAE)；
Training data is imported in BPNN models, BPNN models is trained by step 3；
Step 4 imports test data in trained BPNN models, compares BPNN models output result and survey
The test error MSE of test result and the error, i.e. BPNN models that both calculate：
Wherein, miRepresent the test result of BPNN models, i.e., the preferable output of BPNN models is as a result, oiRepresent BPNN models
Output as a result, i.e. BPNN models reality output as a result, n represent sample size；
Step 5 compares the size of test error MSE and BPNN the model accuracy desired value of BPNN models, if test misses
Poor MSE is less than precision desired value, then BPNN model trainings are completed；If test error MSE is more than precision desired value, need to lead to
It crosses adjusting parameter (excitation function F (￡), hiding number of plies L and hidden neuron number N) and carries out re -training, until MSE is less than
Precision desired value, training terminate.
Embodiment：0.1-1.2GHzCMOS radio-frequency power amplifiers
Step 1 is carried out using environment testing case and tested, and Range of measuring temp is -25~125 DEG C, and supply voltage is
3.3V, scan frequency are 100MHz to 1.2GHz, and radio-frequency power amplifier temperature is recorded using vector network analyzer and frequency spectrograph
The measured data of characteristic is spent, test circuit figure is as shown in Figure 2；
According to the measured data of radio-frequency power amplifier temperature characterisitic obtained, measured data is divided into 2 groups, is made respectively
Training data and test data for BPNN models.
Step 2 determines the input variable (input power, frequency and temperature) of BPNN models and output variable (output work
Rate, S parameter and PAE).
Selected training data is imported in BPNN models, BPNN models is trained by step 3.
Step 4 imports selected test data in trained BPNN models, compares the output of BPNN models
As a result it with the test error MSE of test result and the error, i.e. BPNN models that both calculate, is calculated by formula (1), wherein n=
156。
Step 5 compares the test error MSE and BPNN model accuracy desired value (10 of BPNN models-3) size, if
Test error MSE is less than precision desired value (10-3), then BPNN model trainings are completed；If test error MSE it is expected more than precision
Value (10-3), then it needs to carry out again by adjusting parameter (excitation function F (￡), hiding number of plies L and hidden neuron number N)
Training, until MSE is less than precision desired value (10-3), training terminates.
In the present embodiment, selected BPNN models, it is 2 to hide layer parameter, and hidden neuron number is 15, and test misses
Poor MSE=7.7011 × 10-4。
The RF power amplification temperature characteristics based on BPNN is drawn, as shown in Figures 3 and 4.It can be seen that from Fig. 3 and 4
BPNN models and measured result substantially completely coincide, and illustrate that the BPNN models can effectively represent 0.1-1.2GHz completely
CMOS radio-frequency power amplifiers output and input between non-linear relation, can be realized completely to radio frequency in given temperature section
The prediction of power amplifier properties index situation of change.
In conclusion the data based on a small number of key testpoints, and BPNN models are applied, it can realize that characterization is entire completely
The characteristic of radio-frequency power amplifier in temperature range, and can greatly shorten the testing time, so as to fulfill to a wide range of temperature
The quick analysis and prediction of radio-frequency power amplifier temperature characterisitic under situation of change.
Although the function and the course of work of the present invention are described above in conjunction with attached drawing, the invention is not limited in
Above-mentioned concrete function and the course of work, above-mentioned specific embodiment is only schematical rather than restricted, ability
The those of ordinary skill in domain is not departing from present inventive concept and scope of the claimed protection situation under the enlightenment of the present invention
Under, many forms can also be made, these are belonged within the protection of the present invention.
Claims (1)
1. a kind of RF power amplification temperature characterisitic modeling method based on BPNN, which is characterized in that include the following steps：
Step 1 chooses the training data of BPNN models according to the measured data of the radio-frequency power amplifier temperature characterisitic obtained
And test data；
Step 2 determines the input variable (input power, frequency and temperature) of BPNN models and output variable (output power, S ginsengs
Number and PAE)；
Training data is imported in BPNN models, BPNN models is trained by step 3；
Step 4 imports test data in trained BPNN models, compares BPNN models output result and test is tied
Fruit and the test error MSE of the error, i.e. BPNN models that both calculate：
Wherein, miRepresent the test result of BPNN models, i.e., the preferable output of BPNN models is as a result, oiRepresent the defeated of BPNN models
Go out as a result, i.e. the reality output of BPNN models is as a result, n represents sample size；
Step 5 compares the size of test error MSE and BPNN the model accuracy desired value of BPNN models, if test error
MSE is less than precision desired value, then BPNN model trainings are completed；If test error MSE is more than precision desired value, need to pass through
Adjusting parameter (excitation function F (￡), hiding number of plies L and hidden neuron number N) carries out re -training, until MSE is less than essence
Desired value is spent, training terminates.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711409317.0A CN108268700A (en) | 2017-12-22 | 2017-12-22 | A kind of RF power amplification temperature characterisitic modeling method based on BPNN |
| LU100963A LU100963B1 (en) | 2017-12-22 | 2018-10-10 | A BPNN-based method for modeling temperature characteristics of a radio frequency power amplifier |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711409317.0A CN108268700A (en) | 2017-12-22 | 2017-12-22 | A kind of RF power amplification temperature characterisitic modeling method based on BPNN |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108268700A true CN108268700A (en) | 2018-07-10 |
Family
ID=62772307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711409317.0A Pending CN108268700A (en) | 2017-12-22 | 2017-12-22 | A kind of RF power amplification temperature characterisitic modeling method based on BPNN |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108268700A (en) |
| LU (1) | LU100963B1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135010A (en) * | 2019-04-23 | 2019-08-16 | 天津大学 | The design method of RF power amplifier intervalve matching circuit is instructed using modeling |
| CN110907704A (en) * | 2018-09-14 | 2020-03-24 | 天津大学青岛海洋技术研究院 | Method for extracting unique values of microwave complex dielectric constant and complex permeability of material |
-
2017
- 2017-12-22 CN CN201711409317.0A patent/CN108268700A/en active Pending
-
2018
- 2018-10-10 LU LU100963A patent/LU100963B1/en active IP Right Grant
Non-Patent Citations (4)
| Title |
|---|
| CHENG-YU ZHANG等: "Extreme learning machine for the behavioral modeling of RF power amplifiers", 《2017 IEEE MTT-S INTERNATIONAL MICROWAVE SYMPOSIUM (IMS)》 * |
| QIAN LIN等: "Interconnect Reliability Analysis for Power Amplifier Based on Artificial Neural Networks", 《JOURNAL OF ELECTRONIC TESTING》 * |
| 林倩等: "宽带功率放大器温度可靠性研究", 《天津理工大学学报》 * |
| 王祯祥等: "GaN HEMT高效功率放大器电路温度特性研究", 《南开大学学报（自然科学版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110907704A (en) * | 2018-09-14 | 2020-03-24 | 天津大学青岛海洋技术研究院 | Method for extracting unique values of microwave complex dielectric constant and complex permeability of material |
| CN110135010A (en) * | 2019-04-23 | 2019-08-16 | 天津大学 | The design method of RF power amplifier intervalve matching circuit is instructed using modeling |
Also Published As
| Publication number | Publication date |
|---|---|
| LU100963B1 (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977535A (en) | A kind of RF power amplification temperature characterisitic modeling method based on ELM | |
| Cai et al. | Padé-approximation-based behavioral modeling | |
| CN101256214A (en) | Self-adapting testing system and method for radio-frequency power amplifier | |
| CN105353226A (en) | EMI noise source impedance equivalent parameter extraction method based on scattering parameter and intelligent algorithm | |
| US20210173011A1 (en) | Physics-Based Artificial Intelligence Integrated Simulation and Measurement Platform | |
| CN109142865B (en) | Frequency domain spectrum identification method considering polarization equivalent circuit parameters of oiled paper insulation interface | |
| CN108268700A (en) | A kind of RF power amplification temperature characterisitic modeling method based on BPNN | |
| CN108287941A (en) | A kind of RF power amplification temperature characterisitic modeling method based on DNN | |
| Cai et al. | A new nonlinear behavioral modeling technique for RF power transistors based on Bayesian inference | |
| CN111898320A (en) | Radio frequency power amplifier scattering parameter extraction method and device based on neural network | |
| CN104573216A (en) | Antenna performance optimizing method and device | |
| CN108446451A (en) | A kind of low-noise amplifier temperature characterisitic modeling method based on ELM | |
| CN114567386B (en) | High-precision channel group delay characteristic fitting and simulation implementation method, system, storage medium and communication system | |
| CN111880003B (en) | Method for extracting harmonic balance parameters of radio frequency power amplifier based on neural network | |
| US20220029719A1 (en) | Simulation Model Fitting for Radio Frequency Matching-Network Optimization | |
| Wang et al. | A comparison of second‐order derivative based models for time domain reflectometry waveform analysis | |
| Lin et al. | X-parameter modeling investigation for microwave power devices | |
| Cai et al. | An improved quadratic poly-harmonic distortion behavioral model | |
| CN113486617A (en) | Line loss value evaluation model generation method, system, device and medium | |
| Geng et al. | Integrating field measurements into a model-based simulator for industrial communication networks | |
| CN109190207A (en) | A kind of radio-frequency power amplifier temperature performance prediction technique based on ELM | |
| CN116596061B (en) | Power amplifier harmonic prediction method based on transfer learning | |
| CN110658436A (en) | Characterization method for MOS transistor performance degradation under radio frequency stress | |
| CN109697302A (en) | The behavior modeling method of radio-frequency power amplifier based on OP-ELM | |
| CN115589267B (en) | Circuit analysis and prediction method for intermodulation power frequency characteristics of passive component |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180710 |
|
| RJ01 | Rejection of invention patent application after publication |