Adaptive Neural Network Control with Backstepping for Surface Ships with Input Dead-Zone

Xia, Guoqing; Shao, Xingchao; Zhao, Ang; Wu, Huapeng

doi:10.1155/2013/530162

Cited by 9 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], a robust adaptive controller is investigated for the longitudinal dynamics of a generic hypersonic flight vehicle and command filters are used to compensate the actuator of the hypersonic aircraft. By introducing auxiliary design systems to analyze the effect of input constraints, an adaptive neural network control with backstepping is proposed for surface ships with input saturation in [17]. In [18], a robust adaptive control was proposed based on the backstepping technique and the special property of a hyperbolic tangent function and a Nussbaum function are used to deal with the input saturation.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Postcapture Backstepping Control for Tumbling Tethered Space Robot–Target Combination

Huang

Wang

Meng

et al. 2016

Journal of Guidance, Control, and Dynamics

136

View full text Add to dashboard Cite

Nomenclature a = positive parameter a tx a ty a tz T = linear acceleration due to the tether tension, m · s −2 a x a y a z T = linear acceleration of the gripper's thruster force, m · s −2 Ck = matrix in coordinated desaturation controller d = position vector of the capture position, m F l = tether tension, N I = inertia matrix of the combination, kg · m 2 I 0 = nominal value of combination's inertia matrix, kg · m 2 K ξ = positive-definite design matrix k 2 = positive-definite design matrix m = mass of tethered space robot-target combination, kg Ox l y l z l = space tether frame Ox p y p z p = space platform orbital frame Ox t y t z t = combination orbital frame Ox 0 t y 0 t z 0 t = combination body frame P = positive-definite design matrix R = transformation matrix from platform orbital frame to combination body frame Sk = constant positive weighting matrix T l = tether control torque, Nm x y z T = centroid position of the combination in the platform orbital frame, m ΔI = inertia matrix uncertainty, kg · m 2 ε = positive parameter λk = Lagrange multiplier λ L = upper bound of disturbancê λ L = estimation values of disturbance μ = positive design parameter ξ = state of the auxiliary design system σ = modified Rodrigues parameters σ d = desired modified Rodrigues parameters τk = vector of optimal thruster force and tether tension τ c = control torque of the combination, N · m τ d = disturbing torques, N · m τ t = control torque of the thruster, N · m τ l = control torque of the tether, N · m ω = absolute angular velocity of the combination, rad · s −1 ω d = desired angular velocity of the combination, rad · s −1

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Postcapture Backstepping Control for Tumbling Tethered Space Robot–Target Combination

Huang

Wang

Meng

et al. 2016

Journal of Guidance, Control, and Dynamics

136

View full text Add to dashboard Cite

show abstract

“…A good number of novel intelligent control methods such as fuzzy control and neural network (NN) control were proposed [11][12][13][14][15][16][17][18]. Owing to the approximation capability of learning and adaptation, there is no need to spend much effort on system modeling.…”

Section: Introductionmentioning

confidence: 99%

“…Pan et al presented similar work using a regressor to express the highly nonlinear dynamics of a vessel [15]. Both Dai et al and Xia et al employed a radial basis function in NN to estimate and compensate the uncertainties of ship dynamics and environmental disturbances [17,18]. According to the backstepping technique and the Lypunov theory, they succeeded to improve the control performance and reduce the tracking errors.…”

Section: Introductionmentioning

confidence: 99%

Online learning control of surface vessels for fine trajectory tracking

Li¹,

Li²,

Hildre³

et al. 2015

J Mar Sci Technol

View full text Add to dashboard Cite

This paper presents an adaptive neural network (NN) controller for fine trajectory tracking of surface vessels with uncertain environmental disturbances. Regarding to the new demands for fine trajectory tracking, especially to the requirement of high-accuracy tracking in limited working space, the proposed NN controller is designed to contain a tracking error control component and a velocity error control component, aiming to converge both types of error to zero, separately. It utilizes radial basis functions to approximate a vessel's unknown nonlinear dynamics. Therefore, there is no need of any explicit knowledge of the vessel. The online learning ability is obtained during the stability analysis using the backstepping technique and the Lyapunov theory. Theoretical results guarantee both the convergence of tracking error and velocity error and the boundedness of NN update. Through simulation and tracking performance study based on the CyberShip II model, the proposed controller is verified effective in fine trajectory tracking.

show abstract

“…Therefore, by expressing the system uncertainty in terms of neural networks, an adaptive neural controller is able to handle arbitrary nonlinearities through the tuning of its unknown network parameters. With this attractive feature, adaptive neural control has been extensively used in many controller design problems and practical applications [4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Control Using Fully Online Sequential-Extreme Learning Machine and a Case Study on Engine Air-Fuel Ratio Regulation

Wong

Vong

Gao

et al. 2014

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Most adaptive neural control schemes are based on stochastic gradient-descent backpropagation (SGBP), which suffers from local minima problem. Although the recently proposed regularized online sequential-extreme learning machine (ReOS-ELM) can overcome this issue, it requires a batch of representative initial training data to construct a base model before online learning. The initial data is usually difficult to collect in adaptive control applications. Therefore, this paper proposes an improved version of ReOS-ELM, entitled fully online sequential-extreme learning machine (FOS-ELM). While retaining the advantages of ReOS-ELM, FOS-ELM discards the initial training phase, and hence becomes suitable for adaptive control applications. To demonstrate its effectiveness, FOS-ELM was applied to the adaptive control of engine air-fuel ratio based on a simulated engine model. Besides, controller parameters were also analyzed, in which it is found that large hidden node number with small regularization parameter leads to the best performance. A comparison among FOS-ELM and SGBP was also conducted. The result indicates that FOS-ELM achieves better tracking and convergence performance than SGBP, since FOS-ELM tends to learn the unknown engine model globally whereas SGBP tends to “forget” what it has learnt. This implies that FOS-ELM is more preferable for adaptive control applications.

show abstract

Adaptive Neural Network Control with Backstepping for Surface Ships with Input Dead-Zone

Cited by 9 publications

References 19 publications

Adaptive Postcapture Backstepping Control for Tumbling Tethered Space Robot–Target Combination

Adaptive Postcapture Backstepping Control for Tumbling Tethered Space Robot–Target Combination

Online learning control of surface vessels for fine trajectory tracking

Adaptive Control Using Fully Online Sequential-Extreme Learning Machine and a Case Study on Engine Air-Fuel Ratio Regulation

Contact Info

Product

Resources

About