Professional Documents
Culture Documents
Bias-Dependent_Model_of_Microwave_FET_S-parameters_Based_on_Prior_Knowledge_ANNs
Bias-Dependent_Model_of_Microwave_FET_S-parameters_Based_on_Prior_Knowledge_ANNs
Abstract - The applications of artificial neural networks (Field-Effect Transistors) transistors. Almost all of the
(ANNs) in bias-dependent modeling of S-parameters of standard FET transistors, like MESFET (MEtal
microwave FETs have been proposed earlier. Here, a model Semiconductor FET) and HEMT (High Electron Mobility
based on an ANN with additional prior knowledge at its Transistor), have a very low-noise level, and therefore
inputs (PKI ANN) is introduced. S-parameters of the device
that belongs to the same class as the modeled device are used they are suitable to be applied to the low-noise
as the prior knowledge. The PKI concept allows ANN model microwave active circuits.
to be developed with less training data, which is very When operating under small-signal conditions, the
advantageous when training data is expensive or time microwave FETs can be characterized by the scattering
consuming to obtain. The proposed modeling concept is parameters. Processes of design, optimization and
illustrated by an appropriate modeling example. analyses of the microwave active circuits require accurate
and reliable models of S-parameters of the microwave
Keywords - Artificial neural network, microwave FETs,
prior knowledge input model, S-parameters. transistors. Most of the existing small-signal models are
based on an equivalent circuit representation of the
device. The equivalent circuit elements are extracted
usually from the measured S-parameters within a
I. INTRODUCTION microwave circuit simulator.
OWING to generalization capability, i.e. the capability Although the device S-parameters are bias-dependent,
of providing the correct response even for the input most of the small-signal models are valid for only one
values not used during the training process, artificial bias. For any other bias, it is necessary to repeat
neural networks (ANNs) have appeared as a good extraction of the equivalent circuit parameters from the
alternative to the conventional modeling in the field of measured S-parameters. That procedure can be very time-
microwaves. consuming in the case when models for various bias
Unlike complex and time-consuming electromagnetic conditions are required.
models, once developed model based on ANNs give Recently, a bias-dependent model of the FET S-
responses almost instantaneously, because response parameters has been proposed. It is a completely black-
providing is based on performing basic mathematical box model consisting of a single multilayer ANN that
operations and calculating elementary mathematic models S-parameters dependence on bias conditions and
functions (such as an exponential or hyperbolic tangent frequency, [3], [4] and [9]. Once developed, such model
function). ANNs have the capability of approximating enables prediction of S-parameters in the whole device
any nonlinear function. Therefore, it is possible to operating range without additional optimizations or
develop neural model from source-response data points. additional measurements.
ANNs have been applied to a wide range of modeling Here, a prior knowledge input (PKI) model is
problems in the area of microwaves, [1]-[11]. There are introduced. It is an extension of the basic model - its
ANN applications, either to passive devices, to active inputs are not only bias conditions and frequency, but
devices, or to whole systems. also prior knowledge about S-parameters. The main aim
This paper deals with ANN modeling of small-signal of this model is to increase the modeling accuracy and to
scattering parameters (S-parameters) of microwave FET achieve suitable modeling with as less training samples as
possible. In the proposed case, the ANN additional inputs
are S-parameters of the device that belongs to the same
This work was supported by Ministry of Science and Environmental class as the modeled device.
Protection of Republic of Serbia, under the project 1351. Validity of the proposed model is verified by the
Z. D. Marinkovic is with the Faculty of Electronic Engineering,
University of Nis, Aleksandra Medvedeva 14, 18000 Nis, Serbia, (phone appropriate modeling examples.
+381-18-529-303; fax: +381-18-588-399; e-mail:
zlaticaAelfak.ni.ac.yu). II. MICROWAVE TRANSISTOR S-PARAMETERS
0. R. Proni6 is with the Faculty of Electronic Engineering, University
of Nis, Serbia (e-mail: oljapAelfak.ni.ac.yu). Microwave FETs operating under small-signal
V. V. Markovic is with the Faculty of Electronic Engineering, conditions can be characterized by the scattering
University of Nis, Serbia (e-mail: veraAelfak.ni.ac.yu).
Fig. 1. Incident and reflected waves in a two-port network IV. BIAS-DEPENDENT PKI ANN MODEL
Prior knowledge (or existing models) can be used for
An element of the [S] matrix can be determined as reducing the complexity of the input/output relationships
that an ANN has to learn, as it was proposed in [5]. This
reduction of input/output complexity allows an accurate
U v Vk=O,zakj
i1k (3)
ANN model to be developed with less training data,
Sii is the reflection coefficient seen looking into the which is very advantageous when training data is
port i when all other ports are terminated in load matches. expensive or time consuming to obtain. Since the S-
S is the transmission coefficient from port j to port i parameters' measurements require complex equipment,
not available to most of the microwave designers, and
when all ports are terminated in matched loads. manufacturer given data are often not sufficient for
The S-parameters of microwave transistors are simple black-box ANN model development, a PKI ANN
frequency-, temperature- and bias-dependent. model is introduced, Fig. 3.
The inputs of a PKI ANN model (ANN Devicel in Fig.
III. BIAS-DEPENDENT ANN MODEL 3) are not only bias conditions and frequency (as in the
ANN has been applied for modeling bias- and basic ANN model), but also S-parameters corresponding
frequency- dependence of microwave transistor S- to these input values. We propose that the approximate
parameters, [3], [4] and [9]. The model consists of an values are obtained by a basic ANN model of S-
MLP ANN trained to predict transistor S-parameters for parameters (ANN Device 0 in Fig. 3) developed earlier
given bias voltage, bias current and frequency at its for a device from the same class as the modeled device
inputs, Fig. 2. Therefore, the network has three input (reference device).
neurons corresponding to: In this way, as it will be presented in the following
* bias dc drain-to-source voltage, Vds, example, a sufficiently accurate model can be developed
* bias dc drain-to-source current, Ids' with reduced number of training data.
* frequency f.
WI g(i )
Ang(S )
*ng(Sl)
ANN
I
Mag($s2 )
1 Ang\(S2.)
186
Authorized licensed use limited to: University of Electronic Science and Tech of China. Downloaded on May 30,2023 at 13:30:52 UTC from IEEE Xplore. Restrictions apply.
V. PKI ANN MODELING EXAMPLE acceptable.
The proposed PKI ANN model was developed for TABLE 1. TESTING RESULTS FOR THE BIAS POINTS USED IN THE
TRAINING PROCESS
ATF34143 pHEMT device (Hewlett Packard). The
measured S-parameter data for this device available on
the manufacturer web-site, [13], refer only to four bias IS,,1 1.899 5.874 0.99646
points (Vds Ids) in (0.5-18) GHz frequency range (23 Ang(Sll) 0.811 2.943 0.99968
frequency points per one bias point). Although, it is
possible to train an ANN to learn these data accurately, it IS211 1.546 5.077 0.99796
is not possible to achieve any acceptable generalization. Ang(S21) 0.741 2.495 0.99969
Therefore, the PKI ANN model was developed. The prior
knowledge input values were those obtained by the basic
IS121 1.228 6.717 0.99864
Ang(S12) 0.708 2.772 0.99979
ANN model (ANNO) developed for ATF35143 pHEMT
device, which belongs to the same class, [9]. The ANN IS221 1.565 6.311 0.99862
model of ATF35143 device has 10 neurons in each of two Ang(S22) 0.662 4.038 0.99963
hidden layers.
The available S-parameters' data for the modeled TABLE 2. TESTING RESULTS FOR THE BIAS POINTS NOT USED IN
device were divided in two subsets: the data referring to THE TRAINING PROCESS
three bias points were used as the ANN (ANNI) training
data and the data for the remaining bias point were used
as the validation test data. The angles of S-parameters IS,,1 14.201 39.758 0.89106
were expressed in one of (0°.360°) or (-180°.180°) Ang(S1l) 2.825 7.588 0.99901
ranges. The criterion for the range selection, for the angle
of each S-parameter, is the angle frequency dependence
IS211 8.014 18.392 0.98909
without sharp changes, in order to help ANN to increase Ang(S2l) 4.223 10.642 0.99942
modeling accuracy.
ANNs with 11 input, 8 output and different number of
IS121 3.957 14.370 0.98386
hidden neurons were trained. The prediction of S- Ang(S12) 7.353 17.555 0.99775
parameters by all of the obtained ANNs was tested for the IS221 8.672 18.155 0.97255
corresponding training and test sets. After comparison of |Ang(S22) 6.191 12.696 0.99835
the test results, the ANN with two hidden layers, with 10
neurons in each hidden layer, was chosen as the best
model. This can be confirmed from results in Fig 4, where
For the purpose of quantifying accuracy of the ANN prediction of the S-parameters for the remaining bias
model, average test error (ATE [0Io]), worst-case error point is shown. The PKI ANN obtained S-parameters are
(WCE [0/O]), and correlation coefficient, r, between the represented by lines and the reference (measured) values
referent and the modeled data are calculated, [1]. are represented by symbols. It can be observed that
The Pearson Product-Moment correlation coefficient r modeled values match well to the reference ones.
is defined by:
187
Authorized licensed use limited to: University of Electronic Science and Tech of China. Downloaded on May 30,2023 at 13:30:52 UTC from IEEE Xplore. Restrictions apply.
help ANN to extract input-output dependences.
0.9 - 0.16 - 120
360
0.8 - 0.14 - -Q
0.7 -
9: , ** 300 --------------------------------------- 60
240 0.12 -
0.6 - O 0
180 Z
0.5- ----------------- ---- ------- -------------- ---------------------- ----- -----------
-----
--,.- - - - -.., .;-... ... .... ... ... ... ... ... 0.10- '''''''''''/------- ----------- o-------,. . . . . . . . .
120 c -60 t
0.4 - '@./ *~~~~~~~~ " 0.08- =1
60 < --,,S,,,,,.,,,,.,,,,,,----'----------- '''''-'''''''''''''
0------'---- ---------------------- - -I- -& ------ ''
0.3 - ---
-
0 -120
0.06 -
0.2 - -60
symbols - reference values - 0.04 - ----------- symbols - reference values|--------' -180
0.1 -
lie neural
-,erl
li-nes model
o e ------------- --------------------------------- --------.. -120
lines - neural model
0.0 - - Is(t 02- , . . . . . "-
-240
2 4 6 8 10 12 14 16 18 0 2 4 6 8 10 12 14 16 18
f [GHz] f [GHz]
a) b)
11 - 180 0.81 360
I
10 - ---------------- symbols - reference values 120
lines neural model 300
9- -
.(
8-
.,,.,,,,,,.,,,,,,,,,,,,---O- ----- -----,------------ ----------------- -----,---------------''.'''''''''''''''','
60 0.6- o ,0 / 240
7-
-----------------
0 Z 180 _
6-
''----------- --------- -------------- ---------- ---,............. -----------'''' '''''''''''''''''''''''''
120
0~~~~~~~~~~~ -60 c 0.4-
5- 0~~~~~~~~~~
60 =
4- -120 <
0
*
.,,.,,.,,.,,,,,,,,,,, -----n-----------.
--------------
-.,o
3- -180 0.2- -60
2- \ o ~ S lines@ nera model
1- -240 -120
U .-JUU 0.0A
2 4 6 8 10 12 14 16 18 2 4 6 8 10 12 14
1
16
.,
-l18-180
f [GHz] f[GHz]
C) d)
Fig. 4. Scattering parameters for bias points not used for the training process: a)SI1 b) S12 c) S21 d) S22
S-parameters of the device belonging to the same class as [6] M. Vai, S. Prasad, Neural networks in microwave circuit design-
the modeled device (reference device) are used as prior beyond black box models, Int. J. RF and Microwave Computer-
Aided Eng., Special issue on Applications of Artificial Neural
knowledge. In that way, in the case when there are no networks to RF and Microwave Design, 1999, pp. 187-197.
enough training data, applying the PKI concept, it is [7] F. Giannini, G. Leuzzi, G. Orengo, M. Albertini, "Artificial neural
possible to achieve sufficiently good generalization of the network approach for MMIC passive and active device
ANN model. This is due to reducing the complexity of characterization" Proc. of Gallium Arsenide applications
the input/output relationships that an ANN has to learn symposium GAAS 2000, 2000, Paris.
-
[3] F.Gunes, H.Torpi, F.Gurgen, "Multidimensional signal-noise Vol. 23 No.2, 2004, pp.426-435.
neural network model", Circuits, Devices and Systems, IEE [11] V. Markovic, 0. Pronic, Z. Marinkovic, "Noise Wave Modeling of
Proceedings, Vol.145, Iss.2, Apr 1998, pp. 111-1 17. Microwave Transistors Based on Neural Networks", Microwave
[4] P.M. Watson, M. Weatherspoon, L. Dunleavy, G.L. Creech, and Optical Technology Letters, Vol. 41 No. 4, 2004, pp. 294-297.
"Accurate and Efficient Small-Signal Modelling of Active Devices [12] D. Pozar, Microwave Engineering, John Wiley & Sons, Inc., New
Using Artificial Neural Networks", GAAS IC Symp.Technical York, 1998.
Digest, 1998, pp 95-98.
[5] P. M. Watson, K. C. Gupta, R. L. Majahan, "Development of [13]
Knowledge Based Artificial Neural Network Models for
Microwave Compnents"IEEE Trans. Microwave Symp. Digest,
Baltimore, MD, vol. 44, pp. 9-12, Dec. 1998.
188Downloaded on May 30,2023 at 13:30:52 UTC from IEEE Xplore. Restrictions apply.
Authorized licensed use limited to: University of Electronic Science and Tech of China.