Quasi-static self-sensing piezoelectric actuator position control with complex permittivity-enhanced hybrid neural network
Lin, Chuhang ; Wang, Yanbo ; Sasamura, Tatsuki LU
; Chee, Sze Keat
and Morita, Takeshi
(2026)
In Precision Engineering
99.
p.214-220
- Abstract
This paper proposes a high-precision self-sensing method for piezoelectric actuators using a hybrid neural network that integrates complex permittivity information. The proposed method addresses the limitations of conventional permittivity-based self-sensing, which typically exhibits approximately 1% remaining hysteresis. A knowledge-based polynomial model is first employed to capture the primary displacement–permittivity relationship. To enhance accuracy, a neural network is then introduced to compensate for residual nonlinearity using the input voltage, permittivity, and leakage current as its inputs. Experimental validation was conducted on a one-degree-of-freedom (1-DOF) push–pull stage with a stroke of approximately 9 μm. The... (More)
This paper proposes a high-precision self-sensing method for piezoelectric actuators using a hybrid neural network that integrates complex permittivity information. The proposed method addresses the limitations of conventional permittivity-based self-sensing, which typically exhibits approximately 1% remaining hysteresis. A knowledge-based polynomial model is first employed to capture the primary displacement–permittivity relationship. To enhance accuracy, a neural network is then introduced to compensate for residual nonlinearity using the input voltage, permittivity, and leakage current as its inputs. Experimental validation was conducted on a one-degree-of-freedom (1-DOF) push–pull stage with a stroke of approximately 9 μm. The results demonstrate that the proposed framework achieves a root mean square (RMS) prediction error of 9 nm across the entire stroke. Furthermore, the trained estimator is deployed in a closed-loop proportional–integral(PI) controller for completely sensorless step positioning, maintaining steady-state errors within ±25 nm. These results represent a significant improvement over conventional permittivity-based and other existing self-sensing approaches, confirming the effectiveness of integrating piezoelectric self-sensing with machine learning for high-precision displacement estimation and real-time control.
(Less)
- author
- Lin, Chuhang
; Wang, Yanbo
; Sasamura, Tatsuki
LU
; Chee, Sze Keat
and Morita, Takeshi
- organization
- publishing date
- 2026-01-08
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Complex permittivity, Neural networks, Piezoelectric actuators, Self-sensing
- in
- Precision Engineering
- volume
- 99
- pages
- 7 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:105027421473
- ISSN
- 0141-6359
- DOI
- 10.1016/j.precisioneng.2026.01.010
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2026
- id
- 88a76184-9464-4720-8329-58c52f6b7171
- date added to LUP
- 2026-03-10 15:27:42
- date last changed
- 2026-03-11 03:54:08
@article{88a76184-9464-4720-8329-58c52f6b7171,
abstract = {{<p>This paper proposes a high-precision self-sensing method for piezoelectric actuators using a hybrid neural network that integrates complex permittivity information. The proposed method addresses the limitations of conventional permittivity-based self-sensing, which typically exhibits approximately 1% remaining hysteresis. A knowledge-based polynomial model is first employed to capture the primary displacement–permittivity relationship. To enhance accuracy, a neural network is then introduced to compensate for residual nonlinearity using the input voltage, permittivity, and leakage current as its inputs. Experimental validation was conducted on a one-degree-of-freedom (1-DOF) push–pull stage with a stroke of approximately 9 μm. The results demonstrate that the proposed framework achieves a root mean square (RMS) prediction error of 9 nm across the entire stroke. Furthermore, the trained estimator is deployed in a closed-loop proportional–integral(PI) controller for completely sensorless step positioning, maintaining steady-state errors within ±25 nm. These results represent a significant improvement over conventional permittivity-based and other existing self-sensing approaches, confirming the effectiveness of integrating piezoelectric self-sensing with machine learning for high-precision displacement estimation and real-time control.</p>}},
author = {{Lin, Chuhang and Wang, Yanbo and Sasamura, Tatsuki and Chee, Sze Keat and Morita, Takeshi}},
issn = {{0141-6359}},
keywords = {{Complex permittivity; Neural networks; Piezoelectric actuators; Self-sensing}},
language = {{eng}},
month = {{01}},
pages = {{214--220}},
publisher = {{Elsevier}},
series = {{Precision Engineering}},
title = {{Quasi-static self-sensing piezoelectric actuator position control with complex permittivity-enhanced hybrid neural network}},
url = {{http://dx.doi.org/10.1016/j.precisioneng.2026.01.010}},
doi = {{10.1016/j.precisioneng.2026.01.010}},
volume = {{99}},
year = {{2026}},
}