Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network

Piezoelectric actuators (PEAs) are extensively used for scanning and positioning in scanning probe microscopy (SPM) due to their high precision, simple construction, and fast response. However, there are significant challenges for instrument designers due to their nonlinear properties. Nonlinear pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Thi Thu Nguyen, Luke Oduor Otieno, Oyoo Michael Juma, Thi Ngoc Nguyen, Yong Joong Lee
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/13/10/391
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205940917207040
author Thi Thu Nguyen
Luke Oduor Otieno
Oyoo Michael Juma
Thi Ngoc Nguyen
Yong Joong Lee
author_facet Thi Thu Nguyen
Luke Oduor Otieno
Oyoo Michael Juma
Thi Ngoc Nguyen
Yong Joong Lee
author_sort Thi Thu Nguyen
collection DOAJ
description Piezoelectric actuators (PEAs) are extensively used for scanning and positioning in scanning probe microscopy (SPM) due to their high precision, simple construction, and fast response. However, there are significant challenges for instrument designers due to their nonlinear properties. Nonlinear properties make precise and accurate control difficult in cases where position feedback sensors cannot be employed. However, the performance of PEA-driven scanners can be significantly improved without position feedback sensors if an accurate mathematical model with low computational costs is applied to reduce hysteresis and other nonlinear effects. Various methods have been proposed for modeling PEAs, but most of them have limitations in terms of their accuracy and computational efficiencies. In this research, we propose a variant DenseNet-type neural network (NN) model for modeling PEAs in an AFM scanner where position feedback sensors are not available. To improve the performance of this model, the mapping of the forward and backward directions is carried out separately. The experimental results successfully demonstrate the efficacy of the proposed model by reducing the relative root-mean-square (RMS) error to less than 0.1%.
format Article
id doaj-art-69f2b6447c8a43dda6ecc36a1ed38021
institution OA Journals
issn 2076-0825
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-69f2b6447c8a43dda6ecc36a1ed380212025-08-20T02:10:57ZengMDPI AGActuators2076-08252024-10-01131039110.3390/act13100391Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural NetworkThi Thu Nguyen0Luke Oduor Otieno1Oyoo Michael Juma2Thi Ngoc Nguyen3Yong Joong Lee4School of Mechanical Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, Republic of KoreaDepartment of Electrical and Electronic Engineering, Dedan Kimathi University of Technology, Private Bag-10143, Dedan Kimathi, Nyeri 10143, KenyaSchool of Mechanical Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, Republic of KoreaSchool of Mechanical Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, Republic of KoreaDepartment of Smart Mobility Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, Republic of KoreaPiezoelectric actuators (PEAs) are extensively used for scanning and positioning in scanning probe microscopy (SPM) due to their high precision, simple construction, and fast response. However, there are significant challenges for instrument designers due to their nonlinear properties. Nonlinear properties make precise and accurate control difficult in cases where position feedback sensors cannot be employed. However, the performance of PEA-driven scanners can be significantly improved without position feedback sensors if an accurate mathematical model with low computational costs is applied to reduce hysteresis and other nonlinear effects. Various methods have been proposed for modeling PEAs, but most of them have limitations in terms of their accuracy and computational efficiencies. In this research, we propose a variant DenseNet-type neural network (NN) model for modeling PEAs in an AFM scanner where position feedback sensors are not available. To improve the performance of this model, the mapping of the forward and backward directions is carried out separately. The experimental results successfully demonstrate the efficacy of the proposed model by reducing the relative root-mean-square (RMS) error to less than 0.1%.https://www.mdpi.com/2076-0825/13/10/391high-speed atomic force microscopy (HS-AFM)hysteresisnonlinear systemDenseNet-type neural network
spellingShingle Thi Thu Nguyen
Luke Oduor Otieno
Oyoo Michael Juma
Thi Ngoc Nguyen
Yong Joong Lee
Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network
Actuators
high-speed atomic force microscopy (HS-AFM)
hysteresis
nonlinear system
DenseNet-type neural network
title Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network
title_full Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network
title_fullStr Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network
title_full_unstemmed Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network
title_short Nonlinear Modeling of a Piezoelectric Actuator-Driven High-Speed Atomic Force Microscope Scanner Using a Variant DenseNet-Type Neural Network
title_sort nonlinear modeling of a piezoelectric actuator driven high speed atomic force microscope scanner using a variant densenet type neural network
topic high-speed atomic force microscopy (HS-AFM)
hysteresis
nonlinear system
DenseNet-type neural network
url https://www.mdpi.com/2076-0825/13/10/391
work_keys_str_mv AT thithunguyen nonlinearmodelingofapiezoelectricactuatordrivenhighspeedatomicforcemicroscopescannerusingavariantdensenettypeneuralnetwork
AT lukeoduorotieno nonlinearmodelingofapiezoelectricactuatordrivenhighspeedatomicforcemicroscopescannerusingavariantdensenettypeneuralnetwork
AT oyoomichaeljuma nonlinearmodelingofapiezoelectricactuatordrivenhighspeedatomicforcemicroscopescannerusingavariantdensenettypeneuralnetwork
AT thingocnguyen nonlinearmodelingofapiezoelectricactuatordrivenhighspeedatomicforcemicroscopescannerusingavariantdensenettypeneuralnetwork
AT yongjoonglee nonlinearmodelingofapiezoelectricactuatordrivenhighspeedatomicforcemicroscopescannerusingavariantdensenettypeneuralnetwork