2015
DOI: 10.1109/tmech.2015.2431819
|View full text |Cite
|
Sign up to set email alerts
|

An Inversion-free Predictive Controller for Piezoelectric Actuators Based on A Dynamic Linearized Neural Network Model

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
60
0
1

Year Published

2017
2017
2023
2023

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 82 publications
(61 citation statements)
references
References 39 publications
0
60
0
1
Order By: Relevance
“…With this inversion model, the desired position of the driving object can be determined by the predesigned reference of the end-effector. Third, the model predictive control method proposed in [ 30] is employed to control the PEA to let the driving object reach the desired position. This model predictive controller is able to handle the hysteresis nonlinearity well.…”
Section: Driving Objectmentioning
confidence: 99%
See 2 more Smart Citations
“…With this inversion model, the desired position of the driving object can be determined by the predesigned reference of the end-effector. Third, the model predictive control method proposed in [ 30] is employed to control the PEA to let the driving object reach the desired position. This model predictive controller is able to handle the hysteresis nonlinearity well.…”
Section: Driving Objectmentioning
confidence: 99%
“…In the sub-step control phase, it can be seen that the positioning control of PEAs is one crucial technique for PASS-Ds. Among the advanced control algorithms of PEAs, this paper employs the dynamic linearized neural network based model predictive control method proposed in [ 30] because this method requires no calculation of the inversion of hysteresis and has a satisfactory control performance by experiment validations. The next subsection gives a brief introduction to this model predictive control method.…”
Section: Preliminaries a Control Paradigm Of Passdsmentioning
confidence: 99%
See 1 more Smart Citation
“…In the hysteresis compensation of the PEA, Wang and Chen presented a novel Duhem model based on the neural network to describe the dynamic hysteresis of PEAs [26]. An inversion-free predictive controller was proposed based on a dynamic linearized multilayer feedforward neural network model [27]. A cerebellar model articulation controller neural network PID controller was also proposed [4].…”
Section: Introductionmentioning
confidence: 99%
“…Considerando que la mayoría de los modelos de histéresis sólo son válidos para ciertas frecuencias de señal de entrada, se suele utilizar un control feedforward combinado con control feedback, para conseguir un seguimiento más preciso del desplazamiento [5].Además, teniendo en cuenta que modelar la histéresis es un procedimiento complejo, frecuentemente se utilizan planteamientos basados en la identificación del modelo de la planta sin considerar la histéresis. Se suelen aplicar diferentes técnicas de control tales como control PID [6], control robusto H∞ [7], técnica basada en inversión [8], controladores basados en modelos de red neuronal dinámicos linealizados [9], o basados en redes neuronales fuzzy Pi-sigma [10]. Un enfoque alternativo en plataformas movidas por actuadores piezoeléctricos es considerar la histéresis como una perturbación y utilizar técnicas de control deslizante (sliding mode control, SMC) [3], [11].…”
unclassified