scholarly journals Path following of underactuated surface ships based on model predictive control with neural network

2020 ◽  
Vol 17 (4) ◽  
pp. 172988142094595
Author(s):  
Ronghui Li ◽  
Ji Huang ◽  
Xinxiang Pan ◽  
Qionglei Hu ◽  
Zhenkai Huang
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Input Saturation ◽  
Path Following ◽  
Environmental Disturbances ◽  
Control Approach ◽  
Underactuated Ship ◽  
Mmg Model ◽  
The Mathematical Model

A model predictive control approach is proposed for path following of underactuated surface ships with input saturation, parameters uncertainties, and environmental disturbances. An Euler iterative algorithm is used to reduce the calculation amount of model predictive control. The matter of input saturation is addressed naturally and flexibly by taking advantage of model predictive control. The mathematical model group (MMG) model as the internal model improves the control accuracy. A radial basis function neural network is also applied to compensate the total unknowns including parameters uncertainties and environmental disturbances. The numerical simulation results show that the designed controller can force an underactuated ship to follow the desired path accurately in the case of input saturation and time-varying environmental disturbances including wind, current, and wave.

Nonlinear output path following control using a two-loop robust model predictive control approach

2021 ◽  
pp. 014233122097142
Author(s):  
Mohammad Ghassem Farajzadeh-Devin ◽  
Seyed Kamal Hosseini Sani
Keyword(s):  
Model Predictive Control ◽  
Predictive Control ◽  
Robot Manipulator ◽  
Path Following ◽  
Uncertain System ◽  
Loop Model ◽  
Control Approach ◽  
Output Tracking ◽  
Path Following Control ◽  
Nonlinear Uncertain System

In this paper, output tracking of a geometric path for a nonlinear uncertain system with input and state constraints is considered. We propose an enhanced two-loop model predictive control approach for output tracking of a nonlinear uncertain system. Additionally, we propose an optimal version of output path following control problem to improve the controller synthesis. Satisfaction of the dynamical constraints of a system such as velocity, acceleration and jerk limitations is added to the problem introducing a new augmented system. The recursive feasibility of the proposed method is demonstrated, and its robust stability is guaranteed such that relaxation on the terminal constraint and penalty are achieved. To validate the theoretical benefits of the proposed controller, it is simulated on a SCARA robot manipulator and the results are compared with a two-loop model predictive controller successfully.

A combined neural network and model predictive control approach for ball transfer unit–magnetorheological elastomer–based vibration isolation of lightweight structures

2020 ◽  
Vol 26 (19-20) ◽  
pp. 1668-1682 ◽  
Author(s):  
Renato Brancati ◽  
Giandomenico Di Massa ◽  
Stefano Pagano ◽  
Alberto Petrillo ◽  
Stefania Santini
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Smart Devices ◽  
Magnetorheological Elastomer ◽  
Isolation System ◽  
Control Approach ◽  
Lightweight Structures ◽  
Transfer Unit ◽  
Lightweight Structure

This study addresses the possibility of adopting semi-active magnetorheological elastomers–based isolators for protecting lightweight structures from ground vibration. The exploitation of these smart devices has the main advantage of controlling their stiffness and damping features by acting on the magnetic field generated by a coil on the basis of the actual conditions of both the lightweight structure and the surrounding environment. This allows for combining the reliability of passive devices with the benefits of active control methods. Both mechanical and control system designs could play a crucial role in the challenging problem of improving isolation performances. To solve this issue, we (i) suggest a novel ball transfer unit–magnetorheological elastomer–based isolation system prototype to obtain an improved isolation response of the lightweight structure with respect to the exclusive use of an magnetorheological elastomer and (ii) propose a novel robust combined neural network and model-predictive control approach, allowing proper functioning of the ball transfer unit–magnetorheological elastomer–based isolation system. The effectiveness of the proposed semi-active isolator in guaranteeing vibrational isolation of lightweight structures is evaluated by considering a rack cabinet composed of three storeys and subject to an El Centro earthquake. Numerical simulations confirm and disclose the efficacy of the proposed approach.

Nonlinear Model Predictive Tracking Control for Nonholonomic AGV Based on Bio-Inspired Neurodynamics

2013 ◽  
Author(s):  
Xiao-Hong Yin ◽  
Can Yang
Keyword(s):  
Model Predictive Control ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Control Method ◽  
Kinematic Model ◽  
Input Saturation ◽  
Stability Control ◽  
Control Approach ◽  
Velocity Jump ◽  
Control Principle

Considering nonholonomic constraint and input saturation of the Automatic Guided Vehicle (AGV) kinematic model, in the present work the nonlinear model predictive control was applied and a combined tracking/stability control approach was proposed. In addition, the bio-inspired neurodynamics model was applied to generate smooth forward velocities so that the sharp velocity jump can be overcome by the proposed controller. Specifically, an optimal sub-control method consisting of cost function and constraints were obtained based on the model predictive control principle, and a terminal sub-control method was designed to make the control system stable. Finally, the effectiveness of the proposed control strategy was demonstrated through comparison studies with simulations.

Sign in / Sign up

Export Citation Format

Share Document