An adaptive self-organizing fuzzy sliding mode controller for a 2-DOF rehabilitation robot actuated by pneumatic muscle actuators

Chang, Ming-Kun

doi:10.1016/j.conengprac.2009.08.005

Cited by 100 publications

(50 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…w (3) ij (i = 1, 2, 3, 4, j = 1, 2, 3) measures the influence of output from ith node in second layer on input of jth node in third layer. More details are described in [22].…”

Section: Bp Neural Network Structure For Online Tuning Pid Parametersmentioning

confidence: 99%

“…As a flexible actuator, pneumatic artificial muscle (PAM) has been widely used in medical robots [3,4]. However, strong hysteresis exists within PAM.…”

Section: Introductionmentioning

confidence: 99%

“…Rehabilitation robots have been studied in recently years [1][2][3][4]. As a flexible actuator, pneumatic artificial muscle (PAM) has been widely used in medical robots [3,4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

Fan¹,

Zhong²,

Zhao³

et al. 2015

THC

View full text Add to dashboard Cite

Abstract. BACKGROUND: Although Pneumatic Artificial Muscle (PAM) has a promising future in rehabilitation robots, it's difficult to realize accurate position control due to its highly nonlinear properties. OBJECTIVE: This paper deals with position control of PAM. METHODS: To describe the hysteresis inside PAM, a polynomial based phenomenological function is developed. Based on the phenomenological model for PAM and analysis of pressure dynamics within PAM, an adaptive cascade controller is proposed. Both outer loop and inner loop employ BP Neural Network tuned PID algorithm. The outer loop is to handle high nonlinearities and unmodeled dynamics of PAM, while the inner loop is responsible for nonlinearities caused by pressure dynamics. RESULTS: Experimental results show high tracking accuracy as compared with a convention PID controller. CONCLUSION: The proposed controller is effective in improving performance of PAM and will be implemented in a rehabilitation robot.

show abstract

“…w (3) ij (i = 1, 2, 3, 4, j = 1, 2, 3) measures the influence of output from ith node in second layer on input of jth node in third layer. More details are described in [22].…”

Section: Bp Neural Network Structure For Online Tuning Pid Parametersmentioning

confidence: 99%

“…As a flexible actuator, pneumatic artificial muscle (PAM) has been widely used in medical robots [3,4]. However, strong hysteresis exists within PAM.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

Fan¹,

Zhong²,

Zhao³

et al. 2015

THC

View full text Add to dashboard Cite

show abstract

“…Over the years, SMC has been developed and found wide applications in process of control, aerospace and biology (Wang, 2004), (Hess, 2003), (Chang, 2010). The central concept of SMC is the sliding variable , which is a linear combination of the tracking error and its temporal derivatives.…”

Section: Introductionmentioning

confidence: 99%

Robust Sliding Mode Controller for Uncertain Nonlinear Systems with Fast Transient

Chinte¹,

Abu-Ayyad²,

Dubay³

2014

International Journal of Automation and Control Engineering

View full text Add to dashboard Cite

This paper proposes an improved self-tuning sliding mode control for nonlinear uncertain systems. The proposed approach is based on the principle of approximating the gradient of cost-to-go using the dynamics of the sliding variable and a modified error. Validity of the proposed control design is established through Lyapunov analysis. The effectiveness of the proposed control design with fast transient response was demonstrated on a second order and 2-joint robot manipulator nonlinear systems with uncertainties. The results showed that the robustness of the method is guaranteed and the system arrived at the sliding manifold rapidly.

show abstract

“…in automotive industry (Hung and Chen, 2006), aeronautics (Bao et al, 2006;, transportation (Luo et al, 2008), mobile robotics Lian, 2012), manipulators (Chang, 2010;Amer et al, 2011), position control of induction and DC servomotors (Shahnazi et al, 2008), power systems (Nechadi et al, and Essounbouli, 2012), underwater vehicles (Javadi-Moghaddam and Bagheri, 2010; Bessa et al, 2010), compressors (JavadiMoghaddam and Madani, 2011), electro-hydraulic servo mechanism (Cerman and Hušek, 2012).…”

Section: Introductionmentioning

confidence: 99%

Design of an Adaptive Fuzzy Sliding Mode Control Using Supervisory Fuzzy Control for Micro-Electro-Mechanical Systems (MEMS) Z-Axis Gyroscope

Moghanni-Bavil-Olyaei

Gholami

2014

Journal of Low Frequency Noise, Vibration and Active Control

View full text Add to dashboard Cite

This paper presents a novel robust adaptive control strategy for MEMS gyroscope, based on the coupling of the fuzzy logic control with sliding mode control (SMC) approach and adaptive laws. The drawbacks of the conventional SMC include chattering phenomenon and requirement of a priori knowledge of the bounds of uncertainties. In this paper, these problems are suitably attenuated by adopting an adaptive fuzzy sliding mode control (AFSMC) approach which uses two additional fuzzy self-tuning controllers as supervisory fuzzy systems to adaptively tune the output control gain, sliding gain of the AFSMC in order to speed up the convergence rates of the tracking errors and parameter estimations with a desired level of attenuation. Control system stability is proved by Lyapunov method. Numerical simulations using the MEMS gyroscope model with uncertainties demonstrate the effectiveness of this approach in high speed trajectory tracking problems and robustness in estimating the gyroscope parameters and the angular velocity. Numerical simulations show that the chattering is effectively attenuated by this method. Convergence rate of tracking errors and the gyroscope parameters is better than convergence rates in the literature.

show abstract

An adaptive self-organizing fuzzy sliding mode controller for a 2-DOF rehabilitation robot actuated by pneumatic muscle actuators

Cited by 100 publications

References 19 publications

BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

Robust Sliding Mode Controller for Uncertain Nonlinear Systems with Fast Transient

Design of an Adaptive Fuzzy Sliding Mode Control Using Supervisory Fuzzy Control for Micro-Electro-Mechanical Systems (MEMS) Z-Axis Gyroscope

Contact Info

Product

Resources

About