A Bidirectional Deep Learning Approach for Designing MEMS Sensors

Abstract
To achieve the desired characteristics for MEMS sensors, the traditional
design process obtains the geometrical parameters based on complex
theoretical calculations and interactive finite
are time consuming and data consumin
data-driven bidirectional design approach based on the deep learning (DL)
method is introduced to improve the design efficiency of MEMS sensors in this
work. By using the piezoresistive acceleration sensor as a design exam
the forward artificial neural network (ANN) with the sensor geometrical
parameters as the input and the sensor performance as the output is trained
and realized by using 1000 groups of data collected through FE simulation.
This forward ANN can accurat
the measurement range, sensitivity, and resonant frequency. In addition, the
inverse ANN with the sensor performance as the input and the sensor
geometrical parameters as the output is also achieved by using a
finite-element (FE) simulations, which
consuming. To solve the above problems, a
accurately predict the sensor performance, including
g. example,
ely tandem
network. This inverse ANN can provide the geometrical parameters directly
and instantly according to the target performance. Both the forward and
inverse networks cost only about 6 ms for each task and the mean relative
errors are less than 3%. The high efficiency and low relative error indicate that
DL is a promising approach to improve the design efficiency for MEMS
sensors.