A Novel Neural Network Model of Hysteresis Nonlinearities

Zhao, Tong; Sui, Shulin; Du, Changqing

doi:10.1109/isda.2006.72

Cited by 8 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tong et al [14] used artificial neural networks (ANNs) for this purpose. Their approach is based on representing the increasing (or decreasing) parts of the hysteresis curve as a parabola.…”

Section: Introductionmentioning

confidence: 99%

Compensation of hysteresis in a shape memory alloy wire system using linear parameter‐varying gain scheduling control

Kilicarslan¹,

Grigoriadis²,

Song³

2014

IET Control Theory & Applications

View full text Add to dashboard Cite

Robust tracking control of shape memory alloy (SMA) systems is a challenge because of their highly non-linear response, non-local memory and lack of differentiability. In this work, a linear parameter-varying (LPV) control method is proposed to compensate for the hysteretic behaviour of an SMA actuator. To provide information on the scheduling variable, the Preisach model of hysteresis is utilised. Parameter-dependent controller is updated based on the real-time computation of the instantaneous scheduling variable from the model. An H ∞ controller is also synthesised by representing the hysteresis as a parametric uncertainty. The controllers are implemented on an SMA actuated experimental system. Experimental validation is conducted for various types of reference inputs which can dramatically change the system's response. These reference signals are designed to excite major, minor and frequency dependent hysteresis loops. Trajectory tracking and disturbance rejection results show that the LPV controller has an improved response and the hysteresis is compensated for the full range of the scheduling variable. The tracking performances of both controllers are also compared when the system is under partial and persistent plant disturbances. For these cases, the LPV controller results in a more robust tracking response because of its less conservative structure.

show abstract

Section: Introductionmentioning

confidence: 99%

Compensation of hysteresis in a shape memory alloy wire system using linear parameter‐varying gain scheduling control

Kilicarslan¹,

Grigoriadis²,

Song³

2014

IET Control Theory & Applications

View full text Add to dashboard Cite

show abstract

“…Several attempts have been proposed recently using soft computing methodologies to model and control hysteretic systems. Tong et al (2006) used Artificial Neural Networks (ANNs) for this purpose. The analytical part of their approach is based on representing the monotonically increasing (or decreasing) segments of the data set as parabolas for both major and minor hysteresis loops (voltage vs. displacement characteristics).…”

Section: Introductionmentioning

confidence: 99%

Modeling and Hysteresis Compensation in a Thin SMA Wire Using ANFIS Methods

Kilicarslan

Song

Grigoriadis

2011

Journal of Intelligent Material Systems and Structures

View full text Add to dashboard Cite

Having a responsive behavior to applied voltage/current, shape memory alloy (SMA) wires are widely used as miniature, low mass, compact actuators for many applications. Due to the non-linear hysteretic behavior, SMA wires require advanced control techniques for precision control when used as actuators. In this article, an adaptive neuro-fuzzy inference system (ANFIS) is developed to compensate for the hysteretic non-linearity in a thin SMA wire. An experimental setup is designed to test the SMA wire, which can achieve an operating bandwidth of 1 Hz without an external cooling system. By using the data obtained from the experimental system, an ANFIS model is developed to model the major and minor hysteresis loops (voltage vs. displacement characteristics) and the hysteresis non-linearity at various driving frequencies. Results of numerical simulations based on the ANFIS model closely match the experimental data. Having demonstrated the ability of the ANFIS to account for the hysteretic behavior, an inverse ANFIS controller is devised to compensate for the hysteretic behavior. Finally a PI control action is included in the feedback loop to finetune the system response in real time.

show abstract

“…Tong et al use Neural Networks (NN) for this purpose. 7 Analytical part of their approach is based on representing the monotonically increasing (and decreasing) parts of the whole data set as a parabola. They use this parabola both for major and minor hysteretic loops.…”

Section: Introductionmentioning

confidence: 99%

ANFIS based modeling and inverse control of a thin SMA wire

2008

View full text Add to dashboard Cite

In this work, we propose an Adaptive Neuro Fuzzy Inference System (ANFIS) based hysteresis modeling and control strategy for a thin Shape Memory Alloy (SMA) wire. Controlling the SMA wire is a challenging problem because of its dynamic hysteretic behavior. By using a hybrid learning procedure ANFIS architectures are powerful tools for many applications, such as identifying nonlinear parameters in a controlled system, predicting chaotic time series and modeling nonlinear functions. We tested our ANFIS model by making it predict major and minor hysteresis loops in different driving frequencies and compared them with the experimental data. To compensate the hysteretic effect, we used an inverse ANFIS model and used it directly as a controller. After dramatically reducing the hysteretic effect, we implemented a PI control to fine tune the response.

show abstract

A Novel Neural Network Model of Hysteresis Nonlinearities

Cited by 8 publications

References 13 publications

Compensation of hysteresis in a shape memory alloy wire system using linear parameter‐varying gain scheduling control

Compensation of hysteresis in a shape memory alloy wire system using linear parameter‐varying gain scheduling control

Modeling and Hysteresis Compensation in a Thin SMA Wire Using ANFIS Methods

ANFIS based modeling and inverse control of a thin SMA wire

Contact Info

Product

Resources

About