Force Control of a Shape Memory Alloy Spring Actuator Based on Internal Electric Resistance Feedback and Artificial Neural Networks

Sarmento, Nathan L.D.; Basílio, José Marques; Cunha, Maxsuel Ferreira; Souto, Cícero da Rocha; Ries, Andreas

doi:10.1080/08839514.2021.2015106

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, accurate control of the electrical resistance is difficult due to complex non-linear characteristics such as hysteresis and saturation. Therefore, a resistance control system with additional hysteresis compensators has been proposed for the non-linear characteristics of SMA [9][10][11][12]. A feedforward hysteresis compensator can effectively compensate for non-linear phenomena.…”

Section: Introductionmentioning

confidence: 99%

Modelling of a shape memory alloy actuator for feedforward hysteresis compensator considering load fluctuation

Saito

Oka

Onodera

2022

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

This paper presents a hysteresis mathematical model of a shape memory alloy (SMA) actuator for feedforward hysteresis compensator. The hysteresis model represents the relation between temperature, stress, and electric resistance. Firstly, based on the laws of thermodynamics, the hysteresis model of the SMA actuator is built. Secondly, the inverse of the hysteresis model is obtained to produce a compensator for non‐linear characteristics such as hysteresis and saturation. Thirdly, the parameters of the hysteresis model are obtained from each experiment under constant load and constant temperature, and the model validity is confirmed by comparing experimentally obtained results. Finally, the inverse model is applied to a part of feedforward hysteresis compensator. In order to verify the effectiveness of the proposed model as hysteresis compensator, an electrical resistance control using feedback–feedforward control was conducted by numerical simulation. The simulation results indicate advantages of the proposed mathematical model in hysteresis compensation of SMA actuator, and demonstrate that the model is capable of handling load fluctuation.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling of a shape memory alloy actuator for feedforward hysteresis compensator considering load fluctuation

Saito

Oka

Onodera

2022

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

“…The use of electrical resistance (E.R.) as a sensor is investigated in a few references (Karimi and Konh, 2020; Prechtl et al, 2020; Sarmento et al, 2022; Simone et al, 2017; Urata et al, 2007). These studies focus on a SMA that undergoes a constant stress value.…”

Section: Introductionmentioning

confidence: 99%

Accurate sensorless displacement control based on the electrical resistance of the shape memory actuator

Berhil

Barati

Bernard

et al. 2022

Journal of Intelligent Material Systems and Structures

View full text Add to dashboard Cite

This paper aims to implement the controllable deformation of a structure using Shape Memory Alloys (SMA) actuators. A sensorless displacement estimation method is proposed. This method is tested on a prototype composed of a disc, beams, and SMA actuators. By measuring the variation of electrical resistivity in SMA springs, as a feedback signal in the closed-loop position control, the surface displacement is obtained without any external displacement sensor. The proposed method is validated by comparing the displacement values estimated by the electrical resistivity measurement with those measured by a laser sensor. The estimated displacement and the measured displacement follow the reference displacement with steady-state errors, respectively of 1.14% and 0.42%.

show abstract

“…An adaptive Q-Learning controller was proposed for controlling an SMA actuated humanoid robotic finger [25]. The resistance feedback control of an SMA spring actuator was investigated and artificial neural networks were used instead of constitutive models [26]. With the development of RL theory, the DeepMind team added a neural network into RL instead of the original reward table, which developed into deep reinforcement learning (DRL) [27].…”

Section: Introductionmentioning

confidence: 99%

A new model-free control method for SMA wire actuators based on DRL

Lu¹,

Xu²,

Jiang³

et al. 2022

Eng. Res. Express

View full text Add to dashboard Cite

Shape memory alloy (SMA) has been widely used in different applications due to its unique shape memory property. However, when used as an actuator, it exhibits a hysteresis behavior in its relation between temperature and strain, which is highly nonlinear and difficult to control. Although studies have been conducted on establishing various constitutive models of SMA, it is still difficult to achieve the precise control of the SMA wire with the existing models. In this work, a new promising approach regarding the SMA control task as a reinforcement learning (RL) problem is proposed to address this issue, which does not require accurate mathematical models. Both RL and an improved method named deep reinforcement learning (DRL) are used to solve the problem of precise control of a 1-D SMA wire actuator, respectively. The simulation results indicate that with the DRL method, the agent can precisely control the output deformation of the SMA wire after only ten episodes of training. Compared with the DRL method, the RL agent can also achieve the same training target but with hundreds of training.

show abstract

Force Control of a Shape Memory Alloy Spring Actuator Based on Internal Electric Resistance Feedback and Artificial Neural Networks

Cited by 7 publications

References 15 publications

Modelling of a shape memory alloy actuator for feedforward hysteresis compensator considering load fluctuation

Modelling of a shape memory alloy actuator for feedforward hysteresis compensator considering load fluctuation

Accurate sensorless displacement control based on the electrical resistance of the shape memory actuator

A new model-free control method for SMA wire actuators based on DRL

Contact Info

Product

Resources

About