Transcript 下載/瀏覽

授課教師:陳文山
學生:蘇修賢
 Neural Network Theory and eneralities
 Neural Network Applications in Microwave
Modeling and Design
 Conclusion
Neural Network Theory and Generalities

Basics of Neural Networks

General Neural Network Modeling Approach

Neural Networks for Inverse Modeling Problem
Basics of Neural Networks
1. A typical neural network structure comprises two types of basic components,the
processing elements and the interconnections between them.
2. The processing elements are called neurons and the connections between the
neurons are known as links or synapses.
3. Every link has a corresponding weight parameter associated with it. Each neuron
receives stimuli from other neurons connected to it, processes the information,
and produces an output.
4. Multilayer perceptron (MLP) is a popularly used neural network structure. In the
MLP neural network,
y1
1
y2
2
ym
…
Layer 3
(Output Layer)
m
1
2
3
…
q
Layer 2
(Hidden Layer)
1
2
3
…
n
Layer 1
(Input Layer)
x1
x2
x3
xn
Figure 1. A three-layer perceptron neural network structure with an input
layer, a hidden layer, and an output layer.
Neural Network Theory and Generalities

Basics of Neural Networks

General Neural Network Modeling Approach

Neural Networks for Inverse Modeling Problem
General Neural Network Modeling
Approach
1. To develop a neural network model, we first define the input and output variables
of a device or a structure. We then generate IO data using EM simulation,
physics-based simulation, or measurement.
2. The generated data, training data, are used to train the neural network. Once the
model is trained, it can be incorporated into a circuit simulator for fast and
accurate simulation and optimization.
3.
This allows circuit-level simulation speed with EM-level accuracy. This process
is illustrated in Figure 2. For a given component,
Figure 2. Illustration of fast circuit
optimization where
 a spiral inductor component is represented
by a neural network model, avoiding
repeated EM simulation when geometrical
parameters are changed.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Neural Network Theory and Generalities

Basics of Neural Networks

General Neural Network Modeling Approach

Neural Networks for Inverse Modeling Problem
Neural Networks for Inverse Modeling
Problem
1. To train the neural network inverse model, we swap the generated data so that
electrical parameters become training data for neural network inputs and geometric
parameters become training data for neural network outputs.
2.
Using these data, the trained neural network becomes a direct inverse model. The
model is then used to obtain values of geometric design variables from an electrical
parameter in a single model evaluation.
3. Unlike the forward model in which the input to output mapping (from geometric
parameter to electrical parameter) is usually a one-to-one mapping, the inverse model
often encounters the problem of nonunique solutions.
4. This problem also causes difficulties during training, because the same input values
to the inverse model will lead to different values at the output (multivalued solutions).
Neural Networks for Inverse Modeling
Problem
 Development of Neural Network Inverse Models for Waveguide Filter
 Waveguide Filter Design Using Inverse Models
 Neural Network for Parametric Modeling of a Complete Microwave Filter
 Neural Network for Correction of Nonlinear Device Models
 Neural Network Theory and eneralities
 Neural Network Applications in Microwave
Modeling and Design
 Conclusion
Development of Neural Network Inverse
Models for Waveguide Filter
1. We develop neural network inverse models for waveguide filter. These
inverse models will be used to design filters with the inverse approach.
2. The filter is decomposed into three different modules, each representing a
separate filter junction. The three models are the IO iris, the internal
coupling iris, and the tuning screws.
3. Figure 3 shows a diagram of a waveguide filter revealing various
dimensions of the models. Symbol M12 represents the coupling term
between cavity 1 and cavity 2. ther coupling terms are also defined
similarly.
Figure 3. Diagram of a circular
waveguide filter showing
 arious geometrical variables.
M12 represents the coupling
term between cavity 1 and cavity
2.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Lr
Pv
CD
Ph
w0
(a)
Pin
R
Lv
CD
Lh
w0
(b)
Pv
M23
Ph
M14
Ph
CD
Lh
w0
Lc
M12
(c)
Figure 4. Neural network inverse models representing junctions of a waveguide filter. (a)
Input-output iris model, (b) internal coupling iris model, and (c) tuning screw model.
Symbols CD and vo represent cavity diameter and center frequency, respectively.
P
Neural Networks for Inverse Modeling
Problem
 Development of Neural Network Inverse Models for Waveguide Filter
 Waveguide Filter Design Using Inverse Models
 Neural Network for Parametric Modeling of a Complete Microwave Filter
 Neural Network for Correction of Nonlinear Device Models
Waveguide Filter Design Using Inverse
Models
1. The filter’s center frequency is 12.155 GHz, bandwidth is 64 MHz and
cavity diameter is chosen to be 1.072 in. The normalized ideal coupling
values are obtained from coupling matrix synthesis, as shown in Figure 5.
2. Figure 6 presents the response of the tuned filter and compares with the
ideal one showing a perfect match between each other.
Geometrical Dimensions of Filter
Neural Inverse Model for Filter
Ideal Coupling Values
Coupling Matrix Synthesis
Filter Specification
Figure 4. Design approach using advanced
neural network inverse models.
Figure 5. Comparison of the 6pole filter response with ideal
filter response.
 The filter was designed,
fabricated, tuned and then
measured to obtain the
dimensions.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Neural Networks for Inverse Modeling
Problem
 Development of Neural Network Inverse Models for Waveguide Filter
 Waveguide Filter Design Using Inverse Models
 Neural Network for Parametric Modeling of a Complete Microwave Filter
 Neural Network for Correction of Nonlinear Device Models
Neural Network for Parametric Modeling
of a Complete Microwave Filter
1. A parametric model for a complete filter requires that the model has many
geometric variables. In the conventional approach, change of a geometric variable
requires EM resimulation of the whole filter.
2. Here, we develop a fast neural network model for this purpose. The geometric
variables will be formulated as neural network input neurons.
Figure 6. Diagram of a side-coupled filter. (a)
Side view. (b) Top view. From
 This type of filter offers significant
performance improvement and finds its
application in the satellite multiplexers with
extremely stringent mass, size, and thermal
requirements.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Figure 7. Comparisons of reflection coefficients of a sidecoupled circular waveguide
dual-mode filter obtained using the neural network model and the EM model.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Neural Networks for Inverse Modeling
Problem
 Development of Neural Network Inverse Models for Waveguide Filter
 Waveguide Filter Design Using Inverse Models
 Neural Network for Parametric Modeling of a Complete Microwave Filter
 Neural Network for Correction of Nonlinear Device Models
Neural Network for Correction of
Nonlinear Device Models
1. Another useful application of neural network is to map or repair an existing model
to match a new device. This process is called Neuro–Space Mapping (Neuro-SM).
2. The starting point for the Neuro-SM is when the existing/available device model
(coarse model) cannot match the data of a new device (fine model).
Figure 8. (a) The physical structure of a HEMT
device used for the physics-based device
simulator (the fine model). (b) The Neuro-SM
HEMT intrinsic nonlinear model.
 The coarse model is an existing/available
equivalent circuit model. The neural network
mapping is incorporated as the controlling
functions of the controlled sources.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Figure 9. Comparison between the HEMT
device data from the fine model (MINIMOS),
the existing model (without mapping), and the
Neuro-SM model in the HEMT example .
(a) dc and (b) S-parameters at four different
bias combinations of gate and drain voltages.
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
Figure 10. Doherty amplifier module used to generate training data for neural networks
for power amplifier behavioral modeling: the transistor package contains two separate
transistors, which are configured as a Doherty amplifier .
資料來源:
H. Kabir, Z. Lei, Y. Ming, P. Aaen, J. Wood, and Q. J. Zhang, “Smart Modeling of Microwave” Devices IEEE Microwave Magazine , Vol. 11 (2009 ) 105-108
 Neural Network Theory and eneralities
 Neural Network Applications in Microwave
Modeling and Design
 Conclusion
Conclusion
 Neural networks are fast to evaluate, and the neural network formulas are easy
to implement into microwave CAD.
 The simplicity of adding input neurons or hidden neurons makes neural network
flexible in handling functions of different dimensions and of different degree of
nonlinearity.
 Neural networks are helpful in developing parametric or scalable models for
passive and active microwave devices.
心得
 關於此濾波器讓我學系到了類神經網路的相關知識。
 此濾波器在類神經網路之應用，有著不錯的增益。