Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network

Aiming at the problem of nonlinear coupling error in the measurement of parallel six-axis accelerometers, this study improves the back propagation (BP) neural network and proposes an improved BP neural network decoupling model that introduces the gradient descent with momentum and the Levenberg–Marq...

Full description

Saved in:
Bibliographic Details
Main Authors: Jialin Zhang, Chunzhan Yu, Chengxin Du, Zhe Hao, Zhibo Sun
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2280
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730360112316416
author Jialin Zhang
Chunzhan Yu
Chengxin Du
Zhe Hao
Zhibo Sun
author_facet Jialin Zhang
Chunzhan Yu
Chengxin Du
Zhe Hao
Zhibo Sun
author_sort Jialin Zhang
collection DOAJ
description Aiming at the problem of nonlinear coupling error in the measurement of parallel six-axis accelerometers, this study improves the back propagation (BP) neural network and proposes an improved BP neural network decoupling model that introduces the gradient descent with momentum and the Levenberg–Marquardt (LM) algorithm. By introducing the momentum factor in the model updating stage, the LM algorithm is used in the local learning stage to improve the convergence speed and shock resistance of the network, and to enhance the accuracy of the algorithm. Based on the mid-frequency standard vibration device APS 129 ELECTRO-SEIS (SPEKTRA, Stuttgart, Baden-Württemberg, Germany), the calibration data are obtained and the improved BP neural network decoupling model is trained to complete the nonlinear decoupling of the test set. Compared with the linear decoupling method, the decoupled six-axis accelerometers with the improved BP neural network model have acceleration measurement accuracies of 0.035%, 0.018% and 0.039% along the x, y and z axes, respectively, which indicates that the model has high decoupling accuracy, and it can significantly improve the measurement accuracy of the sensors. The research results can provide theoretical support for high-precision inertial navigation.
format Article
id doaj-art-cf7ba6dd0f1e4736add812b18fbc69e2
institution DOAJ
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-cf7ba6dd0f1e4736add812b18fbc69e22025-08-20T03:08:54ZengMDPI AGSensors1424-82202025-04-01257228010.3390/s25072280Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural NetworkJialin Zhang0Chunzhan Yu1Chengxin Du2Zhe Hao3Zhibo Sun4The School of Technology, Beijing Forestry University, Beijing 100083, ChinaThe School of Technology, Beijing Forestry University, Beijing 100083, ChinaThe School of Technology, Beijing Forestry University, Beijing 100083, ChinaThe School of Technology, Beijing Forestry University, Beijing 100083, ChinaBeihang School, Beihang University, Beijing 100191, ChinaAiming at the problem of nonlinear coupling error in the measurement of parallel six-axis accelerometers, this study improves the back propagation (BP) neural network and proposes an improved BP neural network decoupling model that introduces the gradient descent with momentum and the Levenberg–Marquardt (LM) algorithm. By introducing the momentum factor in the model updating stage, the LM algorithm is used in the local learning stage to improve the convergence speed and shock resistance of the network, and to enhance the accuracy of the algorithm. Based on the mid-frequency standard vibration device APS 129 ELECTRO-SEIS (SPEKTRA, Stuttgart, Baden-Württemberg, Germany), the calibration data are obtained and the improved BP neural network decoupling model is trained to complete the nonlinear decoupling of the test set. Compared with the linear decoupling method, the decoupled six-axis accelerometers with the improved BP neural network model have acceleration measurement accuracies of 0.035%, 0.018% and 0.039% along the x, y and z axes, respectively, which indicates that the model has high decoupling accuracy, and it can significantly improve the measurement accuracy of the sensors. The research results can provide theoretical support for high-precision inertial navigation.https://www.mdpi.com/1424-8220/25/7/2280six-axis accelerometerparallel mechanismimproved BP neural networkgradient descent with momentumnonlinear decoupling
spellingShingle Jialin Zhang
Chunzhan Yu
Chengxin Du
Zhe Hao
Zhibo Sun
Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network
Sensors
six-axis accelerometer
parallel mechanism
improved BP neural network
gradient descent with momentum
nonlinear decoupling
title Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network
title_full Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network
title_fullStr Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network
title_full_unstemmed Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network
title_short Nonlinear Decoupling Study of Six-Axis Acceleration Sensor Based on Improved BP Neural Network
title_sort nonlinear decoupling study of six axis acceleration sensor based on improved bp neural network
topic six-axis accelerometer
parallel mechanism
improved BP neural network
gradient descent with momentum
nonlinear decoupling
url https://www.mdpi.com/1424-8220/25/7/2280
work_keys_str_mv AT jialinzhang nonlineardecouplingstudyofsixaxisaccelerationsensorbasedonimprovedbpneuralnetwork
AT chunzhanyu nonlineardecouplingstudyofsixaxisaccelerationsensorbasedonimprovedbpneuralnetwork
AT chengxindu nonlineardecouplingstudyofsixaxisaccelerationsensorbasedonimprovedbpneuralnetwork
AT zhehao nonlineardecouplingstudyofsixaxisaccelerationsensorbasedonimprovedbpneuralnetwork
AT zhibosun nonlineardecouplingstudyofsixaxisaccelerationsensorbasedonimprovedbpneuralnetwork