Citation: Guo, G.; Chai, B.; Cheng, R.;
Wang, Y. Temperature Drift
Compensation of a MEMS
Accelerometer Based on DLSTM and
ISSA. Sensors 2023, 23, 1809.
https://doi.org/10.3390/s23041809
Academic Editors: Yangquan Chen,
Subhas Mukhopadhyay, Nunzio
Cennamo, M. Jamal Deen, Junseop
Lee, Simone Morais
Received: 5 January 2023
Revised: 2 February 2023
Accepted: 3 February 2023
Published: 6 February 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Temperature Drift Compensation of a MEMS Accelerometer
Based on DLSTM and ISSA
Gangqiang Guo * , Bo Chai, Ruichu Cheng and Yunshuang Wang
Xi’an Microelectronics Technology Institute, Xi’an 710054, China
* Correspondence: guogangqiang9352@163.com
Abstract:
In order to improve the performance of a micro-electro-mechanical system (MEMS) ac-
celerometer, three algorithms for compensating its temperature drift are proposed in this paper,
including deep long short-term memory recurrent neural network (DLSTM-RNN, short DLSTM),
DLSTM based on sparrow search algorithm (SSA), and DLSTM based on improved SSA (ISSA). More-
over, the piecewise linear approximation (PLA) method is employed in this paper as a comparison
to evaluate the impact of the proposed algorithm. First, a temperature experiment is performed to
obtain the MEMS accelerometer’s temperature drift output (TDO). Then, we propose a real-time
compensation model and a linear approximation model for neural network methods compensation
and PLA method compensation, respectively. The real-time compensation model is a recursive
method based on the TDO at the last moment. The linear approximation model considers the MEMS
accelerometer’s temperature and TDO as input and output, respectively. Next, the TDO is analyzed
and optimized by the real-time compensation model and the three algorithms mentioned before.
Moreover, the TDO is also compensated by the linear approximation model and PLA method as a
comparison. The compensation results show that the three neural network methods and the PLA
method effectively compensate for the temperature drift of the MEMS accelerometer, and the DL-
STM + ISSA method achieves the best compensation effect. After compensation by
DLSTM + ISSA
,
the three Allen variance coefficients of the MEMS accelerometer that bias instability, rate random
walk, and rate ramp are improved from 5.43
×
10
−4
mg
, 4.33
×
10
−5
mg/s
1
2
, 1.18
×
10
−6
mg/s
to
2.77
×
10
−5
mg
, 1.14
×
10
−6
mg/s
1
2
, 2.63
×
10
−8
mg/s
, respectively, with an increase of 96.68%
on average.
Keywords:
MEMS accelerometer; temperature drift; real-time compensation model; DLSTM + ISSA
1. Introduction
The MEMS accelerometer is one of the essential measurement elements of an Inertial
Measurement Unit (IMU), which inherits the advantages of MEMS technology, such as
small size, light weight, low cost, low power consumption, etc. MEMS accelerometers
can be used in various fields, such as aerospace, healthcare, gait analysis, sport science,
activity recognition, and portable devices [
1
–
9
]. However, existing manufacturing defects,
such as manufacturing tolerances, always degrade its performance. In addition, MEMS
accelerometers are extremely sensitive to ambient temperature, causing their performance
to degrade dramatically with temperature, which limits their application in high-precision
fields. In recent years, researchers have proposed many different approaches to address the
effects of temperature on MEMS accelerometers. In general, they are mainly divided into
two methods: hardware method and software method.
The hardware method improves the temperature characteristics of MEMS accelerom-
eters mainly through circuit control and structural optimization, which always require
additional time and economic costs. Wang proposed a temperature compensation method
for a high-performance resonant MEMS accelerometer based on a control circuit and struc-
tural design [
10
]. Liu used parasitic resistance to compensate for the temperature drift of
Sensors 2023, 23, 1809. https://doi.org/10.3390/s23041809 https://www.mdpi.com/journal/sensors
