RBF neural network-based sliding mode control for a ballistic missile

Zhao, Hongchao; Gu, Wenjin; Zhang, Ruchuan

doi:10.1504/ijmic.2009.029022

Cited by 9 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its structure is relatively simple, with only one hidden layer, and its learning efficiency is high. 22 Since the relationship between the output moment u and angular momentum H b g of the MSCSG pyramid configu-…”

Section: Design Of Rbf Neural Network Adaptive Sliding Mode Control S...mentioning

confidence: 99%

See 1 more Smart Citation

Spacecraft attitude control and vibration suppression using magnetically suspended control & sensitive gyroscope and radial basis function network adaptive sliding mode control

Ren

Chen

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

For the sake of improving the agility and super-static performance of spacecraft under external disturbances, this paper puts forward an idea for using pyramid configuration of the Magnetically Suspended Control & Sensitive Gyroscope to realize dual control of attitude maneuver and vibration suppression of spacecraft. The RBF neural network is used to reduce the chattering in sliding mode control through adaptively learning the non-linear part of the system. A band-pass filter is designed to divide the attitude deviation signal fed back by the sensors into high-frequency and low-frequency parts. The control laws of gyro gimbal and magnetic suspension rotor are designed, respectively, to realize the attitude maneuver and vibration suppression simultaneously. The adaptive laws of parameters avoid the saturation of rotor deflection angle while speeding up the attitude maneuver process of spacecraft. Compared with the traditional sliding mode control methods, the proposed one not only improves the accuracy and speed of attitude control but also improves the robustness of the spacecraft attitude control and vibration suppression system. Semi-physical simulation results show the effectiveness and superiority of the proposed method.

show abstract

Section: Design Of Rbf Neural Network Adaptive Sliding Mode Control S...mentioning

confidence: 99%

“…Its structure is relatively simple, with only one hidden layer, and its learning efficiency is high. 22…”

Section: Design and Optimization Of Rbf Neural Network Adaptive Slidi...mentioning

confidence: 99%

Spacecraft attitude control and vibration suppression using magnetically suspended control & sensitive gyroscope and radial basis function network adaptive sliding mode control

Ren

Chen

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

show abstract

“…Liu, et al [8] used some decentralized BP neural networks to approximate the uncertain upper bounds of a class of large scale nonlinear highorder interconnect subsystems, and SMC is applied to compensate for the approximation error. H.C. Zhao, et al [9] designed a neural network sliding mode controller for each channel thrust vectoring system of three-channel ballistic missile, and RBF neural network was applied to estimate the upper bound of the overall uncertainty. L. Qin and M. Yang [10] discussed the problem of accurate real-time tracking of the satellite using terminal sliding mode control combined with RBF neural network to study the upper bound of uncertainty adaptively.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Neural Network Sliding Mode Control based on Particle Swarm Optimization for Rotary Steering Drilling Stabilized Platform

Zhang¹,

Li²,

Jiang³

2012

IJACT

View full text Add to dashboard Cite

This study focuses on the robust control of stabilized platform of rotary steering drilling system. Firstly, the uncertain and nonlinear mathematical model of stabilized platform is given by considering the outside interference, drilling technology and geometrical parameter perturbation of the borehole on stabilized platform under work condition. Then, an adaptive neural network sliding mode control strategy is introduced,, which uses sliding mode control to guarantee system robustness, makes the uncertain upper bound adjust adaptively with RBF neural network to nonlinear approximate the upper bound of overall uncertainty, reduces chattering by quasi-sliding mode control method. Finally, particle swarm optimization algorithm is applied to search the optimal controller parameters, including adaptive parameter of neural network weight, boundary layer thickness and switching function coefficient. Simulation results demonstrate that the control strategy proposed can make stabilized platform get optimal control performance and robustness.

show abstract

“…Sliding mode control requires that the system uncertainty upper bound value must be known, while the upper bound of the actual system generally cannot be measured. Therefore neural network can be used to reduce chattering by study the uncertain upper bound adaptively [4,5]. Particle swarm optimization algorithm to optimize the parameters of sliding mode controller is superior to conventional experience to select the parameters, which can further enhance the performance of the sliding mode control system [6,7].…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Sliding Mode Control Scheme for Stabilized Platform of Rotary Steering Drilling Tool

Zhang

Jiang

2012

AMM

View full text Add to dashboard Cite

Considering the nonlinear and uncertain influencing factors on stabilized platform of rotary steering drilling tool under work condition, a new intelligent sliding mode control strategy is presented for stabilized platform. The system robustness is ensured by sliding mode control. The upper bound of overall uncertainty is nonlinear approximated by RBF neural network, which can make the uncertain upper bound adjust adaptively. The chattering is reduced by quasi-sliding mode method. Finally, particle swarm optimization algorithm is applied to search the optimal controller parameters, including boundary layer thickness, switching function coefficient and adaptive parameter of neural network weight, Simulation results show that this control scheme can make stabilized platform get a good control performance and robustness.

show abstract

RBF neural network-based sliding mode control for a ballistic missile

Cited by 9 publications

References 0 publications

Spacecraft attitude control and vibration suppression using magnetically suspended control & sensitive gyroscope and radial basis function network adaptive sliding mode control

Spacecraft attitude control and vibration suppression using magnetically suspended control & sensitive gyroscope and radial basis function network adaptive sliding mode control

Adaptive Neural Network Sliding Mode Control based on Particle Swarm Optimization for Rotary Steering Drilling Stabilized Platform

An Intelligent Sliding Mode Control Scheme for Stabilized Platform of Rotary Steering Drilling Tool

Contact Info

Product

Resources

About