Control of robots using radial basis function neural networks with dead‐zone

Ishihara, Abraham K.; Doornik, Johan van; Ben-Menahem, Shahar

doi:10.1002/acs.1226

Cited by 9 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is assumed that absolute value of is less than a small positive constant , that is, j j < . Then, the error dynamic equation from (11) can be rewritten as Then, the Lyapunov function is selected as…”

Section: Third Layer: Output Layermentioning

confidence: 99%

Adaptive recurrent Chebyshev neural network control for PM synchronous motor servo‐drive electric scooter with V‐belt continuously variable transmission

Lin

2014

Adaptive Control & Signal

View full text Add to dashboard Cite

Because of unknown nonlinearity and time-varying characteristics of electric scooter with V-belt continuously variable transmission (CVT) driven by permanent magnet synchronous motor (PMSM), its accurate dynamic model is difficult to establish for the design of the linear controller in whole system. In order to conquer this difficulty and raise robustness, an adaptive recurrent Chebyshev neural network (NN) control system is proposed to control for PMSM servo-drive electric scooter with V-belt CVT under lumped nonlinear external disturbances in this study. The adaptive recurrent Chebyshev NN control system consists of a recurrent Chebyshev NN control and a compensated control with estimation law. In addition, the online parameters tuning methodology of the recurrent Chebyshev NN and the estimation law of the compensated controller can be derived by using the Lyapunov stability theorem. Moreover, the two optimal learning rates of the recurrent Chebyshev NN based on a discrete-type Lyapunov function are proposed to guarantee the convergence of tracking error. Finally, comparative studies are demonstrated by experimental results in order to show the effectiveness of the proposed control scheme.

show abstract

Section: Third Layer: Output Layermentioning

confidence: 99%

Adaptive recurrent Chebyshev neural network control for PM synchronous motor servo‐drive electric scooter with V‐belt continuously variable transmission

Lin

2014

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…Furthermore, it is well known that dead-zone characteristic is frequently encountered in various engineering systems and can be a cause of instability. In this line, many effective control methods have been proposed to deal with dead-zone [26][27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Synchronization of Unknown Uncertain Chaotic Systems Via Adaptive Control Method

Aghababa

Hashtarkhani

2015

Journal of Computational and Nonlinear Dynamics

View full text Add to dashboard Cite

In this paper, an adaptive control scheme is offered to synchronize two different uncertain chaotic systems. It is assumed that the whole dynamics of both master and slave chaotic systems and their bounds are unknown and different. The error system stabilization is achieved in two cases: with input nonlinearities and without input nonlinearities. We design an adaptive control scheme based on the state boundedness property of the chaotic systems. The proposed method does not need any information about nonlinear/ linear terms of the chaotic systems. It only uses an adaptive feedback control strategy. The stability of the proposed controllers is proved by using the Lyapunov stability theory. Finally, the designed adaptive controllers are applied to synchronize two different pairs of the chaotic systems (Lorenz-Chen and electromechanical device-electrostatic transducer).

show abstract

“…Bursting can still occur when using e-mod, where the error goes up toward a large uniform bound rather than infinity. For a more contemporary survey of robust adaptive techniques see [4].…”

Section: Introductionmentioning

confidence: 99%

An Introspective Learning Algorithm that Achieves Robust Adaptive Control of a Quadrotor Helicopter

Masaud

Macnab

2012

Infotech@Aerospace 2012

View full text Add to dashboard Cite

This paper looks at applying a novel robust adaptive control algorithm to achieve stable adaptive control of a quadrotor helicopter. In direct adaptive control, drift of adaptive parameters to large magnitudes can lead to control signal chatter and bursting behavior. Drift is likely to happen when systems are affected by disturbances, for quadrotor helicopters when picking up payloads or flying in windy conditions. Traditional methods to stop weight drift rely on simple mathematical modifications of the parameter/weight update laws, by limiting or halting weight updates in a simplistic fashion. However, performance may be limited-for a quadrotor helicopter flying in windy conditions performance may be far from adequate. This paper proposes a design of an algorithm to supervise weight updates in a direct adaptive control scheme when using the Cerebellar Model Arithmetic Computer (CMAC) as the nonlinear approximator. The new algorithm makes an introspective decision on when to halt weight updates, based on the perceived affect of each weight update on the error within the local domain of each CMAC basis function. In fact, each domain casts a weighted vote as to whether it perceives a beneficial effect from the weight update. An addition of the weighted votes determines whether the update will be kept in permanent memory or not. Simulation results with a quadrotor helicopter show this novel approach can halt weight drift, achieving both high performance and stability, in the case of uncertain payload and large unmeasured sinusoidal disturbance -a situation where the common e-modification robust adaptive weight update cannot achieve a practical result.

show abstract

Control of robots using radial basis function neural networks with dead‐zone

Cited by 9 publications

References 47 publications

Adaptive recurrent Chebyshev neural network control for PM synchronous motor servo‐drive electric scooter with V‐belt continuously variable transmission

Adaptive recurrent Chebyshev neural network control for PM synchronous motor servo‐drive electric scooter with V‐belt continuously variable transmission

Synchronization of Unknown Uncertain Chaotic Systems Via Adaptive Control Method

An Introspective Learning Algorithm that Achieves Robust Adaptive Control of a Quadrotor Helicopter

Contact Info

Product

Resources

About