GA-based neuro-fuzzy controller for flexible-link manipulator

Siddique, M. N. H.; Tokhi, M. O.

doi:10.1109/cca.2002.1040231

Cited by 18 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimization of the rule-base corresponds to partially learning it. 15,16 It is evident from di®erent implementation of FLCs that learning or optimizing the MFs is computationally less complex than the adaptation of the rule-base. 17 MFs can easily be described by parameters, which can then be optimized with respect to a global error measure.…”

Section: And A2 In Appendix Amentioning

confidence: 99%

Evolutionary Tuning of Modular Fuzzy Controller for Two-Wheeled Wheelchair

Ahmad

Siddique

Tokhi

2012

Int. J. Comp. Intel. Appl.

View full text Add to dashboard Cite

In this work, an optimization technique is adopted to manipulate the input and output scaling factors of a modular fuzzy logic controller (MFC) for lifting and stabilizing the front wheels of a wheelchair in two-wheeled mode. A virtual wheelchair (WC) model is developed within Visual Nastran (VN) software environment where the model is further linked with Matlab/Simulink for control purposes. The lifting of the chair is done by transforming the¯rst link (Link1), attached to the front wheels (casters) to the upright position while maintaining stability of the second link (Link2) where the payload is attached. General rules of thumb allow heuristic tuning (trial and error) of the parameters but such heuristic method does not guarantee that the system tuned with current data set will represent future system states. A global optimization mechanism such as genetic algorithm is necessary to improve the system performance. Due to its signi¯cant advantages over other searching methods, a genetic algorithm approach is used to optimize the scaling factors of the MFC and results show that the optimized parameters give better system performance for such a complex, highly nonlinear two-wheeled wheelchair system.

show abstract

Section: And A2 In Appendix Amentioning

confidence: 99%

Evolutionary Tuning of Modular Fuzzy Controller for Two-Wheeled Wheelchair

Ahmad

Siddique

Tokhi

2012

Int. J. Comp. Intel. Appl.

View full text Add to dashboard Cite

show abstract

“…Oke and Istefanopulos [11] applied fuzzy logic control with gravity compensation for the point-to-point control of a two link flexible manipulator, and utilized a gradient descent method off-line for the trajectory planning. Siddique and Tokhi [12] used the direct inverse neural control using genetic learning to control a single-link flexible manipulator.…”

Section: Introductionmentioning

confidence: 99%

Application of adaptive neural network based interval type-2 fuzzy logic control on a nonlinear system

Önen

Kalyoncu

Tınkır

et al. 2011

2011 3rd International Conference on Computer Research and Development

View full text Add to dashboard Cite

In this study, four adaptive neural network based fuzzy logic controllers (ANNFL) are designed and used as two controllers in terms of interval type-2 fuzzy logic control. The new controllers are called as adaptive neural network based interval type-2 fuzzy logic controller (ANNIT2FL) and applied to a rigid-flexible robot manipulator. Initially dynamic model of the manipulator is obtained by using Lagrange equations and assumed modes method. ANNFL controllers are used for tracking and vibration control of system. The training and testing data of ANNFLs are obtained from the conventional PD control of the manipulator system. The performances of four ANFLCs are tested for different type and different number of membership functions and combined to create two ANNIT2FL controllers. Finally simulation results are obtained according to rotation and vibration control performances of ANNIT2FL controllers. Results demonstrate the remarkable performance of the proposed control technique.

show abstract

“…Over the last two decades, the control of FJMs has also benefited from strategies that seek to reduce the impact of modeling difficulties on controller performance, instead making use such nonmodel intensive strategies as genetic algorithms, particle swarm optimization methods, fuzzy logic, neural networks [11][12][13][14][15][16][17], and more recently, the so-called iPI and iPID strategies [18][19][20]. These pseudomodel based control strategies have enabled a compromise between the cost of real-time controller implementation and the need for highly accurate models in model-based control.…”

Section: Introductionmentioning

confidence: 99%

Trajectory and Vibration Control of a Single-Link Flexible-Joint Manipulator Using a Distributed Higher-Order Differential Feedback Controller

Agee

Bingül

Kizir

2017

Journal of Dynamic Systems, Measurement, and Control

View full text Add to dashboard Cite

The trajectory tracking in the flexible-joint manipulator (FJM) system becomes complicated since the flexibility of the joint of the FJM superimposes vibrations and nonminimum phase characteristics. In this paper, a distributed higher-order differential feedback controller (DHODFC) using the link and joint position measurement was developed to reduce joint vibration in step input response and to improve tracking behavior in reference trajectory tracking control. In contrast to the classical higher-order differential (HOD), the dynamics of the joint and link are considered separately in DHODFC. In order to validate the performance of the DHODFC, step input, trajectory tracking, and disturbance rejection experiments are conducted. In order to illustrate the differences between classical HOD and DHODFC, the performance of these controllers is compared based on tracking errors and energy of control signal in the tracking experiments and fundamental dynamic characteristics in the step response experiments. DHODFC produces better tracking errors with almost same control effort in the reference tracking experiments and a faster settling time, less or no overshoot, and higher robustness in the step input experiments. Dynamic behavior of DHODFC is examined in continuous and discontinues inputs. The experimental results showed that the DHODFC is successful in the elimination of the nonminimum phase dynamics, reducing overshoots in the tracking of such discontinuous input trajectories as step and square waveforms and the rapid damping of joint vibrations.

show abstract

GA-based neuro-fuzzy controller for flexible-link manipulator

Cited by 18 publications

References 14 publications

Evolutionary Tuning of Modular Fuzzy Controller for Two-Wheeled Wheelchair

Evolutionary Tuning of Modular Fuzzy Controller for Two-Wheeled Wheelchair

Application of adaptive neural network based interval type-2 fuzzy logic control on a nonlinear system

Trajectory and Vibration Control of a Single-Link Flexible-Joint Manipulator Using a Distributed Higher-Order Differential Feedback Controller

Contact Info

Product

Resources

About