scholarly journals Actor Critic Neural Network-Based Adaptive Control for MEMS Gyroscopes Suffering from Multiresource Disturbances

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Chao Jing ◽  
Gangzhu Qiao
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Control Method ◽  
Control Policy ◽  
Dynamic Surface Control ◽  
Order System ◽  
Dynamic Surface ◽  
Control Approach ◽  
Mems Gyroscopes ◽  
Critic Neural Network

In this paper, an actor critic neural network-based adaptive control scheme for micro-electro-mechanical system (MEMS) gyroscopes suffering from multiresource disturbances is proposed. Faced with multiresource interferences consisting of parametric uncertainties, strong couplings between axes, Coriolis forces, and variable external disturbances, an actor critic neural network is introduced, where the actor neural network is employed to estimate the packaged disturbances and the critic neural network is utilized to supervise the system performance. Hence, strong robustness against uncertainties and better tracking properties can be derived for MEMS gyroscopes. Aiming at handling the nonlinearities inherent in gyroscopes without analytically differentiating the virtual control signals, dynamic surface control (DSC) rather than backstepping control method is employed to divide the 2nd order system into two 1st order systems and design the actual control policy. Moreover, theoretical analyses along with simulation experiments are conducted with a view to validate the effectiveness of the proposed control approach.

Concise leader-follower formation control of underactuated unmanned surface vehicle with output error constraints

2021 ◽  
pp. 014233122110471
Author(s):  
Meijiao Zhao ◽  
Yan Peng ◽  
Yueying Wang ◽  
Dan Zhang ◽  
Jun Luo ◽  
...  
Keyword(s):  
Neural Network ◽  
Formation Control ◽  
Control Method ◽  
Dynamic Surface Control ◽  
Small Range ◽  
Dynamic Surface ◽  
Unmanned Surface Vehicle ◽  
Control Approach ◽  
Output Error ◽  
Ocean Environment

In this paper, a concise leader-follower formation control approach is presented for a group of underactuated unmanned surface vehicle with dynamic system uncertainties and external environment disturbances, where the output errors are required to be within constraints. To settle the output error constraints, a standard barrier Lyapunov function (BLF) is incorporated into the backstepping control method. Furthermore, the “differential explosion” problem of virtual control laws is avoided by introducing the dynamic surface control. To estimate the unknown dynamic terms, an adaptive neural network is designed and a nonlinear disturbance observer is adopted to compensate for the approximation errors of neural network and ocean environment disturbances. Under the constraint of output error, the presented controller based on standard BLF has simpler structure and better control performance than depended on tan-type BLF. The presented controller can ensure that the formation errors converge to a small range around zero, while the output error constraint requirements are met. All signals in the closed-loop system are bounded, and the numerical simulation further shows the effectiveness of the presented control scheme.

scholarly journals Neural networks-based robust adaptive flight path tracking control of large transport

2018 ◽  
Vol 38 (3) ◽  
pp. 268-278
Author(s):  
Maolong Lv ◽  
Xiuxia Sun ◽  
G. Z. Xu ◽  
Z. T. Wang
Keyword(s):  
Neural Network ◽  
Control Method ◽  
Nonlinear Modeling ◽  
Dynamic Surface Control ◽  
Continuous Functions ◽  
Network Dynamic ◽  
Dynamic Surface ◽  
The Neural Network ◽  
Neural Network Dynamic ◽  
Robust Adaptive

For the ultralow altitude airdrop decline stage, many factors such as actuator nonlinearity, the uncertain atmospheric disturbances, and model unknown nonlinearity affect the precision of trajectory tracking. A robust adaptive neural network dynamic surface control method is proposed. The neural network is used to approximate unknown nonlinear continuous functions of the model, and a nonlinear robust term is introduced to eliminate the actuator’s nonlinear modeling error and external disturbances. From Lyapunov stability theorem, it is rigorously proved that all the signals in the closed-loop system are bounded. Simulation results confirm the perfect tracking performance and strong robustness of the proposed method.

scholarly journals A novel adaptive control design method for stochastic nonlinear systems using neural network

2021 ◽  
Author(s):  
Mohammad Mahdi Aghajary ◽  
Arash Gharehbaghi
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Nonlinear Systems ◽  
Stochastic Systems ◽  
Control Method ◽  
Dead Zone ◽  
Stochastic Nonlinear Systems ◽  
Adaptation Period ◽  
Dynamic Surface ◽  
Actuator Nonlinearity

AbstractThis paper presents a novel method for designing an adaptive control system using radial basis function neural network. The method is capable of dealing with nonlinear stochastic systems in strict-feedback form with any unknown dynamics. The proposed neural network allows the method not only to approximate any unknown dynamic of stochastic nonlinear systems, but also to compensate actuator nonlinearity. By employing dynamic surface control method, a common problem that intrinsically exists in the back-stepping design, called “explosion of complexity”, is resolved. The proposed method is applied to the control systems comprising various types of the actuator nonlinearities such as Prandtl–Ishlinskii (PI) hysteresis, and dead-zone nonlinearity. The performance of the proposed method is compared to two different baseline methods: a direct form of backstepping method, and an adaptation of the proposed method, named APIC-DSC, in which the neural network is not contributed in compensating the actuator nonlinearity. It is observed that the proposed method improves the failure-free tracking performance in terms of the Integrated Mean Square Error (IMSE) by 25%/11% as compared to the backstepping/APIC-DSC method. This depression in IMSE is further improved by 76%/38% and 32%/49%, when it comes with the actuator nonlinearity of PI hysteresis and dead-zone, respectively. The proposed method also demands shorter adaptation period compared with the baseline methods.

Neural network formation control of a team of tractor–trailer systems

Robotica ◽  
2017 ◽  
Vol 36 (1) ◽  
pp. 39-56 ◽  
Author(s):  
Khoshnam Shojaei
Keyword(s):  
Neural Network ◽  
Formation Control ◽  
Network Formation ◽  
Direct Method ◽  
Dynamic Surface Control ◽  
Loop Formation ◽  
Dynamic Surface ◽  
Control Approach ◽  
On Line ◽  
Virtual Leader

SUMMARYThis paper addresses the formation tracking control of a group of tractor–trailer systems in the presence of model uncertainties. A virtual leader–follower formation technique is used to design a controller in order to force a team of tractor–trailer systems to construct a desired formation configuration. Since tractor–trailer systems have a nonlinear multi-input multi-output model with strong couplings, multi-layer neural networks are employed to overcome unknown nonlinearities and uncertain parameters by using on-line weight tuning algorithms. Neural network approximation errors and external disturbances are also compensated with adaptive robust signals. The dynamic surface control approach has been used to reduce the complexity of the proposed controller effectively. Lyapunov’s direct method proves that all signals in the closed-loop formation control system are bounded and tracking errors converge to a neighborhood of the origin whose size is adjustable. Finally, simulation results will be provided to illustrate the efficiency of the proposed controller.

Adaptive neural network control for course-keeping of ships with input constraints

2017 ◽  
Vol 41 (4) ◽  
pp. 1010-1018 ◽  
Author(s):  
Qingling Wang ◽  
Changyin Sun ◽  
Yangyang Chen
Keyword(s):  
Neural Network ◽  
Control Method ◽  
Dynamic Surface Control ◽  
Backstepping Technique ◽  
Input Constraints ◽  
Adaptive Neural Network ◽  
Dynamic Surface ◽  
Controlled System ◽  
Surface Control ◽  
Adaptive Neural Network Control

In this paper, an adaptive neural network (NN) control method is proposed for the problem of nonlinear course control of ships with input constraints and unknown direction control gains. Specifically, dynamic surface control is used to overcome the problem of explosion of complexity inherent in the backstepping technique, and the Nussbaum function is employed to deal with the unknown signs of control gains. It is proved that the proposed adaptive NN control method, which is composed of dynamic surface control and a backstepping technique with the Nussbaum gain function, is able to guarantee uniform ultimate boundedness of all the signals in the controlled system. In addition, the tracking error between the output of the controlled system and a desired trajectory is shown to converge to a small neighbourhood of the origin. Finally, one example is introduced to illustrate the proposed theoretical results.

scholarly journals A Novel Adaptive Control Approach Based on Available Headroom of the VSC-HVDC for Enhancement of the AC Voltage Stability

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3222
Author(s):  
Duc Nguyen Huu
Keyword(s):  
Adaptive Control ◽  
Voltage Stability ◽  
Reactive Power ◽  
Control Method ◽  
Offshore Wind ◽  
Voltage Source ◽  
Long Distance ◽  
Control Approach ◽  
Hvdc System ◽  
Voltage Support

Increasing offshore wind farms are rapidly installed and planned. However, this will pose a bottle neck challenge for long-distance transmission as well as inherent variation of their generating power outputs to the existing AC grid. VSC-HVDC links could be an effective and flexible method for this issue. With the growing use of voltage source converter high-voltage direct current (VSC-HVDC) technology, the hybrid VSC-HVDC and AC system will be a next-generation transmission network. This paper analyzes the contribution of the multi VSC-HVDC system on the AC voltage stability of the hybrid system. A key contribution of this research is proposing a novel adaptive control approach of the VSC-HVDC as a so-called dynamic reactive power booster to enhance the voltage stability of the AC system. The core idea is that the novel control system is automatically providing a reactive current based on dynamic frequency of the AC system to maximal AC voltage support. Based on the analysis, an adaptive control method applied to the multi VSC-HVDC system is proposed to realize maximum capacity of VSC for reactive power according to the change of the system frequency during severe faults of the AC grid. A representative hybrid AC-DC network based on Germany is developed. Detailed modeling of the hybrid AC-DC network and its proposed control is derived in PSCAD software. PSCAD simulation results and analysis verify the effective performance of this novel adaptive control of VSC-HVDC for voltage support. Thanks to this control scheme, the hybrid AC-DC network can avoid circumstances that lead to voltage instability.

Sign in / Sign up

Export Citation Format

Share Document