CN106849882A - A kind of ultra-wideband low-noise amplifier based on artificial neural network - Google Patents

A kind of ultra-wideband low-noise amplifier based on artificial neural network Download PDF

Info

Publication number
CN106849882A
CN106849882A CN201710049060.6A CN201710049060A CN106849882A CN 106849882 A CN106849882 A CN 106849882A CN 201710049060 A CN201710049060 A CN 201710049060A CN 106849882 A CN106849882 A CN 106849882A
Authority
CN
China
Prior art keywords
data
input
artificial neural
neural network
control voltage
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
Application number
CN201710049060.6A
Other languages
Chinese (zh)
Other versions
CN106849882B (en
Inventor
刘洋
顾珣
莫雁杰
高宝玲
雷旭
于奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Electronic Science and Technology of China
Original Assignee
University of Electronic Science and Technology of China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Electronic Science and Technology of China filed Critical University of Electronic Science and Technology of China
Priority to CN201710049060.6A priority Critical patent/CN106849882B/en
Publication of CN106849882A publication Critical patent/CN106849882A/en
Application granted granted Critical
Publication of CN106849882B publication Critical patent/CN106849882B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F1/00—Details of amplifiers with only discharge tubes, only semiconductor devices or only unspecified devices as amplifying elements
    • H03F1/26—Modifications of amplifiers to reduce influence of noise generated by amplifying elements
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F1/00—Details of amplifiers with only discharge tubes, only semiconductor devices or only unspecified devices as amplifying elements
    • H03F1/42—Modifications of amplifiers to extend the bandwidth
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F3/00—Amplifiers with only discharge tubes or only semiconductor devices as amplifying elements
    • H03F3/20—Power amplifiers, e.g. Class B amplifiers, Class C amplifiers
    • H03F3/21—Power amplifiers, e.g. Class B amplifiers, Class C amplifiers with semiconductor devices only
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F3/00—Amplifiers with only discharge tubes or only semiconductor devices as amplifying elements
    • H03F3/20—Power amplifiers, e.g. Class B amplifiers, Class C amplifiers
    • H03F3/24—Power amplifiers, e.g. Class B amplifiers, Class C amplifiers of transmitter output stages
    • H03F3/245—Power amplifiers, e.g. Class B amplifiers, Class C amplifiers of transmitter output stages with semiconductor devices only
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F2200/00—Indexing scheme relating to amplifiers
    • H03F2200/294—Indexing scheme relating to amplifiers the amplifier being a low noise amplifier [LNA]
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F2200/00—Indexing scheme relating to amplifiers
    • H03F2200/372—Noise reduction and elimination in amplifier
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03F—AMPLIFIERS
    • H03F2200/00—Indexing scheme relating to amplifiers
    • H03F2200/451—Indexing scheme relating to amplifiers the amplifier being a radio frequency amplifier

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Amplifiers (AREA)

Abstract

A kind of ultra-wideband low-noise amplifier based on artificial neural network, belongs to field of radio frequency integrated circuits.Including control voltage generation module and ultra-wideband low-noise amplifier module, ultra-wideband low-noise amplifier module includes the variable resistor being made up of the second NMOS tube M3 and the second PMOS M4, control voltage generation module is by sensor, data selector, input data processing unit, artificial neural network and output data processing unit are constituted, using artificial neural network itself unintentional nonlinearity mapping ability, enable the network with highly precise approach nonlinear function, in the control voltage of non-linear relation and it is added to the grid of the second NMOS tube M3 and the second PMOS M4 and changes its variable resistor resistance so as to produces to frequency, so as to ensure bandwidth, the maximized noise data NF for improving circuit under conditions of gain and good fitting.

Description

A kind of ultra-wideband low-noise amplifier based on artificial neural network
Technical field
The invention belongs to field of radio frequency integrated circuits, and in particular to a kind of superwide band low noise based on artificial neural network Amplifier.
Background technology
With the development of short-distance wireless communication, requirement more and more higher of the people to high-speed radiocommunication system performance, more Large Copacity, faster speed and safer communication are the inevitable development trend of short-distance wireless communication.And radio communication system System be unable to do without receiver, and the radio-frequency module in receiver foremost is low-noise amplifier LNA, and it is to whole receiver and entirely Communication system has important influence.In order to meet the demand of high-speed transfer, it is desirable to which low-noise amplifier LNA can be in frequency band wide Operated within range, so having triggered the research to ultra-wideband low-noise amplifier.
In addition, low-noise amplifier LNA is used as the larger module of power consumption in whole receiver, in order to ensure that its is continued a journey Ability is, it is necessary to make it have low power consumption.For UWB (ultra wideband) system is radio ultra wide band system, low-power consumption is Its basic demand.But, due to there is very big noise in input signal, it can be seen from system noise cascading equations, in receiving terminal Low-noise amplifier must provide for enough gains to ensure that rear class noise will not cause excessive influence to systematic function, together When, enough gains need consumption high power consumption could realize.Therefore low-noise amplifier LNA gain requirement and power consumption requirements it Between exist certain relation contradiction, how reduce power consumption while increase as far as possible gain be in being applied to UWB systems it is low The important topic of noise amplifier LNA designs.
The realization of ultra wide band low noise amplifier circuit generally has 3 kinds of modes：The first is using such as article " A The distribution that Monolithic DC-70-GHz Broadband Distributed Amplifier Using 90-nm " are reported Formula structure expands bandwidth；Second is using such as article " Bandwidth extension techniques for CMOS The inductor peaking technology that amplifiers " is reported；The third is using article " Wide-Band CMOS Low-Noise The resistive degeneration noise cancellation technique that Amplifier Exploiting Thermal Noise Canceling " are reported. However, the first implementation can take very big chip area, and power consumption is big, noiseproof feature is poor；The second way is difficult Realize broadband input matching；The third mode is difficult to realize flat gain high.To solve this problem, patent A kind of ultra wide band low-power consumption noise amplifier of automatic biasing is refer in CN10479919A, is realized in 0.2-6GHz frequency models Enclose interior work LNA and keep 16 ± 1.3dB gains,<The noise coefficient of 2.8dB and good input matching.But it is traditional Circuit design has the limitation of itself technique and design all the time, how further to improve the bandwidth of LNA, reduces noise, improves increasing Benefit, reduction power consumption and maintenance good gain flatness, are the key points of ultra-wideband low-noise amplifier design.
The content of the invention
For existing ultra-wideband low-noise amplifier because traditional handicraft and design limitation cannot provide work where it Make the shortcoming of the optimum noise data NF of frequency range, put the invention provides a kind of superwide band low noise based on artificial neural network Big device.
Technical scheme is as follows：
A kind of ultra-wideband low-noise amplifier based on artificial neural network, including control voltage generation module and ultra wide band Low noise amplifier module,
The ultra-wideband low-noise amplifier module includes low-frequency gain amplifying circuit and high-frequency gain amplifying circuit, described The input of high-frequency gain amplifying circuit connects the output end of the low-frequency gain amplifying circuit, and its output end is used as the ultra-wide Output end with low noise amplifier module, the low-frequency gain amplifying circuit is included by the second NMOS tube M3 and the second PMOS The variable resistor that M4 is constituted；
The control voltage generation module includes sensor, data selector, input data processing unit, ANN Network and output data processing unit,
The input of sensor connects the output end of the ultra-wideband low-noise amplifier module, gathers the ultra wide band low The frequency data f of noise amplifier module, noise data NF, matched data S11 and gain data S21；
Data selector, its first input end is connected with the output end of sensor, the second input connection control voltage letter Number Contr, data selector is selected the data that sensor is collected under the control of control voltage signal Contr Pre-input data；
Input data processing unit, its first input end connects the output end of data selector, the connection control of the second input Voltage signal Contr processed, its output end is connected with the first input end of artificial neural network, and pre-input data are carried out to process To the input data X that artificial neural network can be processed directly；
Artificial neural network, its second input connection control voltage signal Contr, at its output end connection output data The input of unit is managed, to input data X it is anticipated that the nonlinear function of setting under the control of control voltage signal Contr Nonlinear response is made in conversion V=g (X), produces the data signal of non-linear control voltage；
Output data processing unit, its input links the output end of artificial neural network, and artificial neural network is exported The data signal of non-linear control voltage be converted to voltage signal, i.e. control voltage V, it is low that its output end connects the ultra wide band The grid of the second NMOS tube M3 and the second PMOS M4 adjusts the resistance of the variable resistor of its composition in noise amplifier module, together When feed back to input data processing unit.
Specifically, the control voltage signal Contr is state switching signal, control artificial neural network, data selection Device and input data processing unit switch between learning state and working condition.
Specifically, when control voltage signal Contr control inputs data processing unit is in learning state, being input to defeated The data for entering data processing unit include frequency data f, control voltage V, noise data NF, matched data S11 and gain data S21, then input data X=(f, V, NF, S11, S21)；When control voltage signal Contr control datas selector is in work shape During state, the data for being input to data selector only have frequency data f, then input data X=(f).
Specifically, the low-frequency gain amplifying circuit includes the first NMOS tube M1, the first PMOS M2, the second NMOS tube M3, the second PMOS M4 and the first inductance L1,
The one of the grid of the first PMOS M2, the drain electrode of the second NMOS tube M3 and the second PMOS M4 and the first inductance L1 End is connected and constitutes the input of the ultra-wideband low-noise amplifier module, and the other end of the first inductance L1 connects the first NMOS tube The grid of M1,
The grid of the second NMOS tube M3 and the second PMOS M4 connects the output end of the output data processing unit, second The source electrode of NMOS tube M3 and the second PMOS M4 is connected and as described with the drain electrode of the first NMOS tube M1 and the first PMOS M2 The output end of low-frequency gain amplifying circuit,
The source ground GND of the first NMOS tube M1, the source electrode of the first PMOS M2 meets supply voltage VDD.
Specifically, the high-frequency gain amplifying circuit includes the second inductance L2, the 3rd inductance L3, the 3rd NMOS tube M5, the Three PMOS M6,
The output end of the one termination low-frequency gain amplifying circuit of the second inductance L2, its other end connects the 3rd NMOS tube The grid of M5 and the 3rd PMOS M6,
One end of the 3rd inductance L3 of drain electrode connection of the 3rd PMOS M6 is used as the ultra-wideband low-noise amplifier module Output end and be connected with the input of the sensor of the control voltage generation module, its source electrode meets supply voltage VDD,
The drain electrode of the 3rd NMOS tube M5 connects the other end of the 3rd inductance L3, its source ground GND.
A kind of course of work of ultra wide band low noise amplifier based on artificial neural network proposed by the present invention is divided into three Stage, specially：
First stage：Collecting training data
Under each different frequency fi, i is temperature label, is constituted by the second PMOS M4 and the second NMOS tube M3 Variable resistor two ends apply the grid connection positive controling voltage of control voltage right ± Vi, the second NMOS tube M3, the second PMOS The grid connection negative control voltage of M4 so that in different Frequency point fi, circuit meets matching and gain requirement under this frequency When reach minimum noise data NF, record data (Vi, fi) obtains training sample Y=(Vi, fi)；Now training sample Y is Two-dimensional array, wherein f as artificial neural network input, V as artificial neural network target export.
Second stage：The training (study) of artificial neural network
The stage, control voltage signal Contr control artificial neural networks are in learning state, while control passes through data The data of selector are the noise data NF obtained in the collecting training data stage.The training sample data Y of first stage collection =(Vi, fi) is input to artificial neural network after input data processing unit processes, and artificial neural network is to input variable X= (f, V, NF, S11, S21) is responded, and produces network output, then network output and target output V is compared, when both Error when being unsatisfactory for default required precision, artificial neural network adjustment network weight W, until error is less than default essence Degree, training terminates.
Phase III：Work
The stage, control voltage signal Contr control artificial neural networks are in running order.Control voltage signal Contr control inputs are X=(f) to the data of input data processing unit, and artificial neural network is according in second stage training Good network weight W is to input data X=(f) it is anticipated that the non-linear function transformation V=g (X) of setting makes non-linear sound Should, produce non-linear control voltage V=g (f), the control voltage controlled after output data processing unit the second PMOS M4, The grid end voltage of the second NMOS tube M3, so that the variable resistor resistance being made up of the second PMOS M4 and the second NMOS tube M3 becomes Change and cause that circuit is met the optimal noise data NF under gain, matching condition.
Beneficial effects of the present invention are：Artificial neural network is used for low-noise amplifier by the present invention, overcomes tradition super Wideband low noise amplifier is designed due to the immutable shortcoming that further cannot be lifted to circuit performance of feedback resistance, is passed through Artificial neural network itself unintentional nonlinearity mapping ability enables the network with high accuracy in control voltage generation module Nonlinear Function Approximation, thus produce to frequency in nonlinear function control voltage, the voltage is by controlling the 2nd PMOS brilliant The grid end voltage of body pipe M4 and the second nmos pass transistor M3, so that the second PMOS transistor M4 and the second nmos pass transistor M3 groups Into variable resistor change in resistance so that circuit is met the optimal noise under gain, matching condition at respective frequencies Coefficient NF；Second level high-frequency gain amplifying circuit is effectively opened up using the inductor peaking effect of the second inductance L2 and the 3rd inductance L3 This circuit high-frequency gain bandwidth is again opened up.
Brief description of the drawings
Fig. 1 is the structural representation of the ultra-wideband low-noise amplifier for having been based on artificial neural network proposed by the present invention Figure.
Fig. 2 is the training schematic diagram of artificial neural network.
Fig. 3 is proposed by the present invention to have been based on ultra wide band low noise in the ultra-wideband low-noise amplifier of artificial neural network The topology diagram of acoustic amplifier module.
Fig. 4 is the small-signal simplification figure of ultra-wideband low-noise amplifier modular circuit.
Fig. 5 is a kind of gain of ultra-wideband low-noise amplifier based on artificial neural network proposed by the present invention, matching With noise factor simulation curve.
Specific embodiment
The present invention is further detailed explanation below in conjunction with the accompanying drawings and apart from implementation method.
Core of the invention is that employment artificial neural networks are produced by the second PMOS transistor M4 and the second nmos pass transistor Control voltage needed for the variable resistor two ends that M3 is constituted.Artificial neural network itself unintentional nonlinearity mapping ability causes this Network can with highly precise approach nonlinear function so that produce to frequency in nonlinear function control voltage, the voltage lead to The second PMOS transistor M4 of control, the second nmos pass transistor M3 gate voltages are crossed, so that variable resistor change in resistance causes circuit It is met the optimal noise coefficient NF under gain, matching condition.
It is as shown in Figure 1 the structure of the ultra-wideband low-noise amplifier for having been based on artificial neural network proposed by the present invention Schematic diagram, including control voltage generation module and ultra-wideband low-noise amplifier module.Wherein, control voltage generation module is by passing Sensor, data selector, input data processing unit, artificial neural network and output data processing unit are constituted, and its effect is Produce to frequency in non-linear relation control voltage；The control voltage is low by output data processing unit output control ultra wide band The grid end voltage of the second PMOS M4 and the second NMOS tube M3 in noise amplifier module, so that by the second PMOS M4 and The variable resistor change in resistance that two NMOS tube M3 are constituted causes that circuit is met the optimal NF under gain, matching condition.
In the control voltage generation module, sensor is connected with input data processing unit, for detecting and transmits super The frequency data f of wideband low noise amplifier module, noise data NF, matched data S11 and gain data S21.
The input of input data processing unit is also connected with the control voltage in ultra-wideband low-noise amplifier module, defeated Go out and be connected with the input of artificial neural network, its effect is to receive input data, and artificial neural network is processed into it can be with The data for directly processing.
The output termination output data processing unit of artificial neural network, effect is in control voltage signal Contr controls Under to input data x it is anticipated that non-linear function transformation V=g (x) of setting makes nonlinear response, produce nonlinear Control Voltage；
The output of output data processing unit meets the second NMOS tube M3 and second in ultra-wideband low-noise amplifier module The control voltage of PMOS M4, its effect is the treatment of the output data of artificial neural network to be followed by the second NMOS tube M3 and the The grid of two PMOS M4, by controlling the second NMOS tube M3 and the second PMOS M4 right to realize in the resistance in linear work area The regulation of circuit noise.
Wherein control voltage signal Contr is artificial neural network and data selector and input data processing unit State switching signal, signal control artificial neural network and data selector and input data processing unit are in learning state Switch and working condition between.
When control voltage signal Contr control artificial neural networks are in learning state, control voltage signal Contr controls The data that system is input to input data processing unit are 5 dimensions, including frequency f, control voltage v, noise NF, gain S21, matching S11, both X=(V, f, NF, S21, S11)；And it is in running order to work as control voltage signal Contr control artificial neural networks When, control voltage signal Contr control inputs only have frequency data f to the data of input data processing unit, i.e.,：X=(f).
The course of work for being based on the ultra wide band low noise amplifier of artificial neural network is divided into three phases, specially：
First stage：Collecting training data
Under each different frequency fi, i is temperature label, is constituted by the second PMOS M4 and the second NMOS tube M3 Variable resistor two ends apply the grid connection positive controling voltage of control voltage right ± Vi, the second NMOS tube M3, the second PMOS The grid connection negative control voltage of M4 so that in different Frequency point fi, circuit meets matching and gain requirement under this frequency When reach minimum noise data NF, record data (Vi, fi) obtains training sample Y=(Vi, fi)；Now training sample Y is Two-dimensional array, wherein f as artificial neural network input, V as artificial neural network target export.
Second stage：The training (study) of artificial neural network
The stage, control voltage signal Contr control artificial neural networks are in learning state, while control passes through data The data of selector are the noise data NF obtained in the collecting training data stage.The training sample data Y of first stage collection =(Vi, fi) is input to artificial neural network after input data processing unit processes, and artificial neural network is to input variable X= (f, V, NF, S11, S21) is responded, and produces network output, then network output and target output V is compared, when both Error when being unsatisfactory for default required precision, artificial neural network adjustment network weight W, until error is less than default essence Degree, training terminates.
Phase III：Work
The stage, control voltage signal Contr control artificial neural networks are in running order.Control voltage signal Contr control inputs are X=(f) to the data of input data processing unit, and artificial neural network is according in second stage training Good network weight W makes nonlinear response to input data X=(f), produces the numeral letter of non-linear control voltage V=g (f) Number, the data signal of the control voltage is converted to voltage signal after output data processing unit and controls the second PMOS M4, the The grid end voltage of two NMOS tube M3, so that the variable resistor change in resistance being made up of the second PMOS M4 and the second NMOS tube M3 So that circuit is met the optimal noise data NF under gain, matching condition.
Ultra-wideband low-noise amplifier module ultra-wideband low-noise amplifier modular circuit of the invention as shown in figure 3, by The low-frequency gain amplifying circuit of the first order and the high-frequency gain amplifying circuit composition of the second level；
Wherein, low-frequency gain amplifying circuit includes the first NMOS tube M1, the first PMOS M2, the second NMOS tube M3, second PMOS M4 and the first inductance L1, the grid of the first PMOS M2, the drain electrode of the second NMOS tube M3 and the second PMOS M4 and One end of first inductance L1 is connected and constitutes the input of the ultra-wideband low-noise amplifier module, the other end of the first inductance L1 The grid of the first NMOS tube M1 is connected, the grid of the second NMOS tube M3 and the second PMOS M4 connects the output data treatment list The output end of unit, the drain electrode of the source electrode and the first NMOS tube M1 and the first PMOS M2 of the second NMOS tube M3 and the second PMOS M4 Connect and as the output end of the low-frequency gain amplifying circuit, the source ground GND, the first PMOS M2 of the first NMOS tube M1 Source electrode meet supply voltage VDD.
This structural reference article A DC-11.5GHz Low-Power, Wideband of Shih-Fong Chao Amplifier Using Splitting-Load Inductive Peaking Technique, and carried out in its structure Optimization, the ultra wide band low noise amplifier circuit of present invention design make use of the design that automatic biasing has avoided biasing circuit to simplify Circuit design and constrain the power consumption of circuit.
Wherein, high-frequency gain amplifying circuit includes the second inductance L2, the 3rd inductance L3, the 3rd NMOS tube M5, the 3rd PMOS The output end of the one termination low-frequency gain amplifying circuit of pipe M6, the second inductance L2, its other end connects the 3rd NMOS tube M5 With the grid of the 3rd PMOS M6, one end of the 3rd inductance L3 of drain electrode connection of the 3rd PMOS M6 is used as the ultra wide band low noise The output end of acoustic amplifier module is simultaneously connected with the input of the sensor of the control voltage generation module, and its source electrode connects power supply Voltage VDD, the drain electrode of the 3rd NMOS tube M5 connects the other end of the 3rd inductance L3, its source ground GND.
Second level high-frequency gain amplifying circuit is effective using the inductor peaking effect of the second inductance L2 and the 3rd inductance L3 This circuit high-frequency gain bandwidth is again expanded.
The small-signal model of circuit can be obtained by Fig. 3, as shown in figure 4, Cgs1, Cgs2, Cgs5, Cgs6 are respectively in figure The first NMOS tubes of NMOS M1, the first PMOS M2, the parasitic capacitance between the 3rd NMOS tube M5, the grid source of the 3rd PMOS M6, Cgd1, Cgd2, Cgd3, Cgd4 are respectively the first NMOS tube M1, the first PMOS M2, the 3rd NMOS tube M5, the 3rd PMOS M6 Parasitic capacitance between grid leak, R ˊ are the variable resistors being made up of the second PMOS M4, the second NMOS tube M3, ro1, ro2, ro5, Ro6 is respectively the first NMOS tube M1, the first PMOS M2, the 3rd NMOS tube M5, the output resistance of the 3rd PMOS M6, gm1, Gm2, gm3, gm4 are respectively the first NMOS tube M1, the first PMOS M2, the 3rd NMOS tube M5, the small-signal of the 3rd PMOS M6 Mutual conductance.
By small signal circuit figure, we can be derived by the input resistance R of circuitin
And first order circuit gain
Wherein s=jw=j2 π f
For secondary structure, the overall noise factor of circuit
Wherein NF1It is the noise coefficient of first order circuit, NF2It is the noise coefficient of second level circuit, AP1It is first order electricity The available power gain on road.The noise coefficient of the first order plays leading role in the overall noise factor of circuit as can be seen here.The In stage circuit, R ˊ play an important role as feedback resistance in extension low-noise amplifier bandwidth, but resistance feedback Network can produce the thermal noise of itself, therefore can also adjust the noise coefficient of circuit by adjusting R ˊ sizes.
Control voltage needed for producing variable resistor two ends by artificial neural network, artificial neural network itself is intrinsic Non-linear mapping capability enables the network with highly precise approach nonlinear function, so that it is in nonlinear function to produce to frequency Control voltage, the voltage by control the second PMOS transistor M4, the second nmos pass transistor M3 gate voltages so that second The variable resistor change in resistance of PMOS transistor M4, the second nmos pass transistor M3 composition causes that circuit is met gain, matching Under the conditions of optimal noise coefficient NF.
Fig. 5 illustrates optimum results of the ultra-wideband low-noise amplifier based on artificial neural network for circuit.
It can be seen that, instant invention overcomes legacy ultra-wideband low-noise amplifier design due to feedback resistance is immutable cannot The shortcoming for further being lifted to circuit performance, can be reached at respective frequencies most by the control of artificial neural network Low noise causes that circuit performance is greatly improved.
One of ordinary skill in the art can make various not departing from originally according to these technical inspirations disclosed by the invention Other various specific deformations and combination of essence are invented, these deformations and combination are still within the scope of the present invention.

Claims (5)

1. a kind of ultra-wideband low-noise amplifier based on artificial neural network, including control voltage generation module and ultra wide band are low Noise amplifier module, it is characterised in that
The ultra-wideband low-noise amplifier module includes low-frequency gain amplifying circuit and high-frequency gain amplifying circuit, the high frequency The input of gain amplifying circuit connects the output end of the low-frequency gain amplifying circuit, and its output end is low as the ultra wide band The output end of noise amplifier module, the low-frequency gain amplifying circuit is included by the second NMOS tube (M3) and the second PMOS (M4) variable resistor for constituting；
The control voltage generation module include sensor, data selector, input data processing unit, artificial neural network and Output data processing unit,
The input of sensor connects the output end of the ultra-wideband low-noise amplifier module, gathers the superwide band low noise The frequency data f of amplifier module, noise data NF, matched data S11 and gain data S21；
Data selector, its first input end is connected with the output end of sensor, the second input connection control voltage signal Contr, the data that data selector is collected under the control of control voltage signal Contr to sensor carry out selecting to obtain pre- Input data；
Input data processing unit, its first input end connects the output end of data selector, the second input connection control electricity Pressure signal Contr, its output end is connected with the first input end of artificial neural network, in the control of control voltage signal Contr It is lower pre-input data process obtain the input data X that artificial neural network can be processed directly；
Artificial neural network, its second input connection control voltage signal Contr, its output end connection output data treatment is single The input of unit, to input data X it is anticipated that the non-linear function transformation of setting under the control of control voltage signal Contr V=g (X) makes nonlinear response, produces the data signal of non-linear control voltage；
Output data processing unit, its input connects the output end of artificial neural network, by the non-of artificial neural network output The data signal of Linear Control voltage is converted to voltage signal, i.e. control voltage V, and its output end connects the superwide band low noise The grid of the second NMOS tube (M3) and the second PMOS (M4) adjusts the resistance of the variable resistor of its composition in amplifier module, together When feed back to input data processing unit.
2. a kind of ultra-wideband low-noise amplifier based on artificial neural network according to claim 1, it is characterised in that The control voltage signal Contr is state switching signal, control artificial neural network, data selector and input data treatment Unit switches between learning state and working condition.
3. a kind of ultra-wideband low-noise amplifier based on artificial neural network according to claim 1 and 2, its feature exists In when control voltage signal Contr control inputs data processing unit is in learning state, being input to input data treatment single The data of unit include frequency data f, control voltage V, noise data NF, matched data S11 and gain data S21, then be input into number According to X=(f, V, NF, S11, S21)；When control voltage signal Contr control data selectors are in running order, it is input to The data of data selector only have frequency data f, then input data X=(f).
4. a kind of ultra-wideband low-noise amplifier based on artificial neural network according to claim 1, it is characterised in that The low-frequency gain amplifying circuit includes the first NMOS tube (M1), the first PMOS (M2), the second NMOS tube (M3), the 2nd PMOS Pipe (M4) and the first inductance (L1),
The grid of the first PMOS (M2), the drain electrode of the second NMOS tube (M3) and the second PMOS (M4) and the first inductance (L1) One end be connected and constitute the input of the ultra-wideband low-noise amplifier module, the other end connection first of the first inductance (L1) The grid of NMOS tube (M1),
The grid of the second NMOS tube (M3) and the second PMOS (M4) connects the output end of the output data processing unit, second The source electrode of NMOS tube (M3) and the second PMOS (M4) is connected simultaneously with the drain electrode of the first NMOS tube (M1) and the first PMOS (M2) As the output end of the low-frequency gain amplifying circuit,
The source ground (GND) of the first NMOS tube (M1), the source electrode of the first PMOS (M2) connects supply voltage (VDD).
5. a kind of ultra-wideband low-noise amplifier based on artificial neural network according to claim 1 or 4, its feature exists In the high-frequency gain amplifying circuit includes the second inductance (L2), the 3rd inductance (L3), the 3rd NMOS tube (M5), the 3rd PMOS Pipe (M6),
The output end of the one termination low-frequency gain amplifying circuit of the second inductance (L2), its other end connects the 3rd NMOS tube (M5) and the 3rd PMOS (M6) grid,
The drain electrode of the 3rd PMOS (M6) connects one end of the 3rd inductance (L3) as the ultra-wideband low-noise amplifier module Output end and be connected with the input of the sensor of the control voltage generation module, its source electrode connects supply voltage (VDD),
The drain electrode of the 3rd NMOS tube (M5) connects the other end of the 3rd inductance (L3), its source ground (GND).
CN201710049060.6A 2017-01-23 2017-01-23 A kind of ultra-wideband low-noise amplifier based on artificial neural network Active CN106849882B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710049060.6A CN106849882B (en) 2017-01-23 2017-01-23 A kind of ultra-wideband low-noise amplifier based on artificial neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710049060.6A CN106849882B (en) 2017-01-23 2017-01-23 A kind of ultra-wideband low-noise amplifier based on artificial neural network

Publications (2)

Publication Number Publication Date
CN106849882A true CN106849882A (en) 2017-06-13
CN106849882B CN106849882B (en) 2019-11-01

Family

ID=59119735

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710049060.6A Active CN106849882B (en) 2017-01-23 2017-01-23 A kind of ultra-wideband low-noise amplifier based on artificial neural network

Country Status (1)

Country Link
CN (1) CN106849882B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115977592A (en) * 2023-03-01 2023-04-18 电子科技大学 Speed-frequency self-adaptive clock applied to wireless perforation system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1139213A (en) * 1995-01-13 1997-01-01 特克特朗尼克公司 Split-path linear isolation circuit apparatus and method
CN1208282A (en) * 1998-05-25 1999-02-17 中国石油天然气总公司地球物理勘探局 Amplifier noise reducing method and ultralow-noise pre-amplifier
CN101465618A (en) * 2007-12-19 2009-06-24 中国科学院微电子研究所 Ultra-wideband low-noise amplifier with double input routes
CN104779919A (en) * 2015-05-04 2015-07-15 中国电子科技集团公司第五十四研究所 Self-biased ultra wideband low-power-consumption low-noise amplifier (LNA)
CN105141263A (en) * 2015-09-29 2015-12-09 株洲宏达天成微波有限公司 Multi-band low-noise amplification method and multi-band low-noise amplifier

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1139213A (en) * 1995-01-13 1997-01-01 特克特朗尼克公司 Split-path linear isolation circuit apparatus and method
CN1208282A (en) * 1998-05-25 1999-02-17 中国石油天然气总公司地球物理勘探局 Amplifier noise reducing method and ultralow-noise pre-amplifier
CN101465618A (en) * 2007-12-19 2009-06-24 中国科学院微电子研究所 Ultra-wideband low-noise amplifier with double input routes
CN104779919A (en) * 2015-05-04 2015-07-15 中国电子科技集团公司第五十四研究所 Self-biased ultra wideband low-power-consumption low-noise amplifier (LNA)
CN105141263A (en) * 2015-09-29 2015-12-09 株洲宏达天成微波有限公司 Multi-band low-noise amplification method and multi-band low-noise amplifier

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115977592A (en) * 2023-03-01 2023-04-18 电子科技大学 Speed-frequency self-adaptive clock applied to wireless perforation system
CN115977592B (en) * 2023-03-01 2024-05-17 电子科技大学 Speed-frequency self-adaptive clock applied to wireless perforation system

Also Published As

Publication number Publication date
CN106849882B (en) 2019-11-01

Similar Documents

Publication Publication Date Title
CN101741316B (en) Gain variable broadband radio frequency low-noise amplifier
CN103051298B (en) Programmable Gain Amplifier Circuit and programmable gain amplifier
TWI323555B (en) Low noise amplifier and related method
CN103051299B (en) Programmable gain amplifier applicable to transmitting end of communication system
CN105978515B (en) The wide transformer coupled radio-frequency power amplifier of adjusting range high integration
KR20090084349A (en) Reconfigurable low noise amplifier using capacitor dividing feedback
CN102790595B (en) Single ended differential gain amplifier with configurable radio frequency broadband gain
CN101997489A (en) Amplifier and implementation method thereof
CN105305979B (en) A kind of distributed amplifier circuit for improving the linearity
CN107592082A (en) A kind of bimodulus double frequency secondary current is multiplexed low-noise amplifier
CN101951229A (en) Multi-gain mode low-noise amplifier
CN103117711A (en) Monolithic integrated radio frequency high-gain low-noise amplifier
CN103532497A (en) Ultra-wide-band low-noise amplifier adopting inductance compensation technology
WO2023226581A1 (en) Class-j distributed power amplifier based on harmonic regulation and control, and optimization method for class-j distributed power amplifier
CN1141787C (en) Variable-gain single-ended-to-difference radio-frequency low-noise amplifier
CN106849881A (en) A kind of Band Monolithic Integrated integrated low-noise amplifier
CN106385239B (en) A kind of CMOS wideband low noise amplifier of adjustable gain
CN111478671A (en) Novel low-noise amplifier applied to Sub-GHz frequency band
CN106849882B (en) A kind of ultra-wideband low-noise amplifier based on artificial neural network
CN102176657A (en) Positive-feedback-broadband LNA (low noise amplifier) for millimeter wave frequency range
CN116108794B (en) Broadband matching method suitable for radio frequency microwave power amplifier chip
CN103701412B (en) Circuit for realizing high and low power of linear power amplifier by taking CMOS (complementary metal-oxide-semiconductor) transistors as switches
CN103944518B (en) Wideband low-noise amplifier
CN108574463A (en) Low-noise amplifier and RF front-end circuit
CN108649912A (en) A kind of distributed power amplifier based on feedback-type three-level Darlington transistor

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