Article
Automation & Control Systems
Dan Bao, Xiaoling Liang, Shuzhi Sam Ge, Baolin Hou
Summary: This article proposes an adaptive neural trajectory tracking control scheme for n-DOF robotic manipulators subjected to parameter variations, unknown functions, and time-varying external disturbances. The computed torque control (CTC) method is used to reduce the system's nonlinearity. Radial basis function neural networks (RBFNNs) are constructed to approximate the uncertainties due to parameter variations and unknown functions. The effectiveness of the proposed method is validated through simulations on a seven-degrees of freedom robotic manipulator.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Hoai Vu Anh Truong, Manh Hung Nguyen, Duc Thien Tran, Kyoung Kwan Ahn
Summary: This paper presents an adaptive backstepping-based model-free control method for enhancing system tracking performance of general high-order nonlinear systems subject to disturbances and unstructured uncertainties. The proposed methodology combines backstepping control with radial basis function neural network-based time-delayed estimation to overcome the obstacle of unknown system dynamics. Command filtering is also used to address the complexity explosion in the design of backstepping control. New control laws are established to reduce the effects of approximation errors. The stability of the closed-loop system is guaranteed through the Lyapunov theorem, and the superiority of the proposed methodology is confirmed through comparative simulation with other model-free approaches.
Review
Acoustics
Amhmed M. Al Aela, Jean-Pierre Kenne, Honorine A. Mintsa
Summary: An adaptive neural network control system is proposed to stabilize a quarter car electrohydraulic active suspension system by handling dynamic nonlinearities and uncertainties. The control system can effectively handle model uncertainty and unknown smoothing functions, with the use of a combined adaptive radial basis function neural network and a backstepping control system.
JOURNAL OF VIBRATION AND CONTROL
(2022)
Article
Automation & Control Systems
Cuong Nguyen Manh, Tien Ngo Manh, Duyen Ha Thi Kim, Quyen Nguyen Van, Tung Lam Nguyen
Summary: This paper proposes an approach to address the problems arising from inaccurate elements in car driving simulators and the disadvantages of nonlinear model-based controllers. By constructing an adaptive and robust neural network-based controller, the proposed method ensures the high accuracy of the robot's motion under uncertain components and external factors, while mitigating the drawbacks of conventional controllers.
INTERNATIONAL JOURNAL OF CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Qinyi Wang, Yang Yu, Fan Zhang, Panfeng Huang
Summary: In this paper, a novel neural-network-based backstepping control method is designed for the post-capture tethered space combination system subjected to multi-source disturbances and actuator saturation. The unknown nonlinearities are estimated using radial basis function neural networks (RBFNNs). The anti-windup technique is employed to handle actuator saturation in the system. Sufficient conditions are derived to guarantee system stability during the non-cooperative target capture mission. Numerical simulations are conducted to validate the proposed methodology.
Article
Engineering, Aerospace
Prabhjeet Singh, Dipak K. Giri, Ajoy K. Ghosh
Summary: This paper proposes an asymptotic control method for the attitude and altitude of an aircraft using robust backstepping sliding mode control (BSMC) in combination with an adaptive radial basis function neural network (RBFNN). The control strategy relies on accurate knowledge of non-linear aerodynamic forces and moments, with the adaptive RBFNN used to approximate unknown non-linear functions. The proposed method demonstrates good control performance in a continuous dynamic environment.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Nuclear Science & Technology
Jiuwu Hui, Jun Ling, Kai Gu, Jingqi Yuan
Summary: An adaptive backstepping control strategy with extended state observer is proposed for load following of nuclear power plant. The extended state observer is designed to estimate unmeasured states of the system and output disturbances online, and the system uncertainties are approximated by using radial basis function neural network. Through Lyapunov stability theory, it is demonstrated that the overall control system is ultimately uniformly bounded.
PROGRESS IN NUCLEAR ENERGY
(2021)
Article
Computer Science, Artificial Intelligence
Yukun Zheng, Yixiang Liu, Rui Song, Xin Ma, Yibin Li
Summary: This study proposes an adaptive robust control strategy based on RBFNN and a state observer for a mobile manipulator with uncertain dynamics and external disturbances. The proposed method achieves precise position tracking in the task space by implementing virtual speed tracking control and control torque conversion. Theoretical analysis demonstrates the global asymptotic stability of the system under the control of the proposed method.
Article
Computer Science, Artificial Intelligence
Yiming Fei, Dongyu Li, Yanan Li, Jiangang Li
Summary: This paper proposes an adaptive phase compensator to improve the performance of the deterministic learning-based adaptive feedforward control system. By applying the adaptive phase compensator to the hidden layer of the neural network, the nonlinear approximation capability of the network is effectively improved, leading to better learning and control performance. Simulation studies confirm the effectiveness of the proposed phase compensation method.
Article
Computer Science, Artificial Intelligence
Jinzhu Peng, Rickey Dubay, Shuai Ding
Summary: This paper proposes an adaptive neural output feedback control scheme for controlling an electrically driven robotic manipulator system by using a neural network-based adaptive observer and a backstepping design technique. The proposed scheme can achieve the desired tracking effectiveness and estimation capability with prescribed errors constraint.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Mechanical
Xin Ma, Jian Xu, Hongbin Fang, Yang Lv, Xiaoxu Zhang
Summary: This paper proposes a new gait coordination-oriented adaptive neural sliding mode control (GC-ANSMC) for lower limb amputees using prostheses, addressing the difficulties in adapting to complex tasks. The approach combines a homotopy algorithm for trajectory generation with a radial basis function neural network for modeling uncertainties, achieving fast motion tracking and global convergence. Applications show that GC-ANSMC outperforms traditional methods in control accuracy, convergence speed, torque control, and gait coordination performance, demonstrating promising potential for adaptive control in nonlinear human-prosthesis dynamics.
INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES
(2022)
Article
Computer Science, Hardware & Architecture
Xiuping Wang, Yiming Wang, Shunyu Yao, Chunyu Qu, Hai Wang
Summary: This paper investigates the control of displacement and speed in a primary permanent magnet linear motor (PPMLM) considering unmodelled load interference, time-varying parameters, and end effects. The authors propose an adaptive backstepping control algorithm to maintain system stability in the presence of time-varying parameters during motor movements. Additionally, a radial basis function (RBF) neural network is used to compensate for unmodelled load disturbance, and a command filter is implemented to counteract the differential expansion phenomenon. Simulation results demonstrate the superiority of the proposed control strategy compared to other existing controllers.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Kojo Sarfo Gyamfi, James Brusey, Elena Gaura
Summary: The study introduces a differential radial basis function network to enhance the robustness of RBF networks in sequential data, and demonstrates its superior performance in multiple experiments.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Engineering, Multidisciplinary
Zhijiang Gao, Pak Kin Wong, Jing Zhao, Xingqi Hua, Xinbo Ma, Zhengchao Xie
Summary: This study proposes a compensatory backstepping strategy for the magnetorheological fluid suspension system, which utilizes a normalized phenomenological model to simulate the nonlinear characteristics of the magnetorheological fluid damper and employs an adaptive radial-basis function neural network to construct the inverse model of the damper. By calculating the reference state using the filter performance function, the trade-off between vehicle handling stability and ride comfort is achieved. Finally, a voltage-force compensator is constructed to improve the robustness of the controller, and simulations demonstrate the effectiveness of the proposed compensatory backstepping controller under various conditions.
APPLIED MATHEMATICAL MODELLING
(2023)
Article
Mathematics, Interdisciplinary Applications
Yi Yang, Haiyan H. Zhang
Summary: This paper presents an original radial basis function neural network-based adaptive fractional-order backstepping controller for reliable quadrotor operations in the presence of uncertain modeling parameters and unknown time-delayed inputs. The proposed controller eliminates the nonlinearity of time-delayed inputs by introducing an augmented state variable via Pade's approximation method. It ensures the semi-globally uniformly ultimately boundedness of all state variables and estimation error of uncertain parameters and demonstrates superior tracking accuracy and robustness compared to previous controllers.
FRACTAL AND FRACTIONAL
(2023)
Article
Engineering, Aerospace
Bowen Su, Fan Zhang, Panfeng Huang
Summary: This article researches the control and nonlinear state observer design for triangular tethered satellite formation (TTSF) system when the velocity vector is unmeasured. Linear feedback control and nonlinear control are designed to improve system performance, with the latter having a global stability domain. In the case of unmeasured velocity states, a nonlinear state observer is designed to regulate observation bias. Simulation results show that the proposed nonlinear control and state observer have better global stability and reduced chattering compared to linear control and general observer, making them promising for practical applications.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2022)
Article
Engineering, Aerospace
Bowen Su, Fan Zhang, Panfeng Huang
Summary: This article investigates the stability of a triangular tethered satellite formation (TTSF) and the performance improvement by filtering and virtual control. The equation of motion is formulated, and the state space equation (SSE) is derived with decoupled second-order terms. The stability of SSE is discussed with nonstretched and stretched tethers, and the effect of initial conditions on the system stability is explored. A state filter and a virtual control law with relay property are designed to smooth the system response and enhance its robustness. Simulation results validate the theoretical analyses.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2022)