scholarly journals Robust Control Design for Autonomous Vehicles Using Neural Network-Based Model-Matching Approach

Energies ◽  
2021 ◽  
Vol 14 (21) ◽  
pp. 7438
Author(s):  
Dániel Fényes ◽  
Tamás Hegedus ◽  
Balázs Németh ◽  
Péter Gáspár
Keyword(s):  
Neural Network ◽  
Robust Control ◽  
Control Method ◽  
Reference Signal ◽  
Simulation Software ◽  
Dynamics Simulation ◽  
Control Input ◽  
Model Matching ◽  
Test Scenario ◽  
Robust Control Design

In this paper, a novel neural network-based robust control method is presented for a vehicle-oriented problem, in which the main goal is to ensure stable motion of the vehicle under critical circumstances. The proposed method can be divided into two main steps. In the first step, the model matching algorithm is proposed, which can adjust the nonlinear dynamics of the controlled system to a nominal, linear model. The aim of model matching is to eliminate the effects of the nonlinearities and uncertainties of the system to increase the performances of the closed-loop system. The model matching process results in an additional control input, which is computed by a neural network during the operation of the control system. Furthermore, in the second step, a robust H∞ is designed, which has double purposes: to handle the fitting error of the neural network and ensure the accurate tracking of the reference signal. The operation and efficiency of the proposed control algorithm are investigated through a complex test scenario, which is performed in the high-fidelity vehicle dynamics simulation software, CarMaker.

scholarly journals Path Tracking Control of Field Information-Collecting Robot Based on Improved Convolutional Neural Network Algorithm

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 797 ◽  
Author(s):  
Yili Gu ◽  
Zhiqiang Li ◽  
Zhen Zhang ◽  
Jun Li ◽  
Liqing Chen
Keyword(s):  
Neural Network ◽  
Control System ◽  
Convolutional Neural Network ◽  
Sliding Mode ◽  
Soft Soil ◽  
Simulation Software ◽  
Dynamics Simulation ◽  
Information Collection ◽  
Soil Conditions ◽  
Field Information

Due to the narrow row spacing of corn, the lack of light in the field caused by the blocking of branches, leaves and weeds in the middle and late stages of corn growth, it is generally difficult for machinery to move between rows and also impossible to observe the corn growth in real time. To solve the problem, a robot for corn interlines information collection thus is designed. First, the mathematical model of the robot is established using the designed control system. Second, an improved convolutional neural network model is proposed for training and learning, and the driving path is fitted by detecting and identifying corn rhizomes. Next, a multi-body dynamics simulation software, RecurDyn/track, is used to establish a dynamic model of the robot movement in soft soil conditions, and a control system is developed in MATLAB/SIMULINK for joint simulation experiments. Simulation results show that the method for controlling a sliding-mode variable structure can achieve better control results. Finally, experiments on the ground and in a simulated field environment show that the robot for field information collection based on the method developed runs stably and shows little deviation. The robot can be well applied for field plant protection, the control of corn diseases and insect pests, and the realization of human–machine separation.

scholarly journals Adaptive robust control for free-floating space robot with unknown uncertainty based on neural network

2018 ◽  
Vol 15 (6) ◽  
pp. 172988141881151
Author(s):  
Zhang Wenhui ◽  
Li Hongsheng ◽  
Ye Xiaoping ◽  
Huang Jiacai ◽  
Huo Mingying
Keyword(s):  
Neural Network ◽  
Mathematical Model ◽  
Robust Control ◽  
Control Method ◽  
External Disturbance ◽  
Adaptive Robust Control ◽  
Lyapunov Theory ◽  
Space Robot ◽  
Neural Network Controller ◽  
The Stability

It is difficult to obtain a precise mathematical model of free-floating space robot for the uncertain factors, such as current measurement technology and external disturbance. Hence, a suitable solution would be an adaptive robust control method based on neural network is proposed for free-floating space robot. The dynamic model of free-floating space robot is established; a computed torque controller based on exact model is designed, and the controller can guarantee the stability of the system. However, in practice, the mathematical model of the system cannot be accurately obtained. Therefore, a neural network controller is proposed to approximate the unknown model in the system, so that the controller avoids dependence on mathematical models. The adaptive learning laws of weights are designed to realize online real-time adjustment. The adaptive robust controller is designed to suppress the external disturbance and compensate the approximation error and improve the robustness and control precision of the system. The stability of closed-loop system is proved based on Lyapunov theory. Simulations tests verify the effectiveness of the proposed control method and are of great significance to free-floating space robot.

A novel multivariable nonlinear robust control design for turbofan engines

2021 ◽  
pp. 014233122110396
Author(s):  
Dingding Cheng ◽  
Lijun Liu ◽  
Zhen Yu
Keyword(s):  
Robust Control ◽  
Closed Loop ◽  
Control Method ◽  
Operating Conditions ◽  
Large Region ◽  
Control Performance ◽  
Nonlinear Robust Control ◽  
Turbofan Engines ◽  
Robust Control Design ◽  
Nonlinear Robust

Traditional steady-state control methods are applied to turbofan engines operating in the small region near certain operating conditions, which need to switch controllers for operating in the large region and then may lead to instability and performance degradation of the closed-loop system. In this paper, a novel multivariable nonlinear robust control method for turbofan engines is proposed to improve the control performance within the large region. To enlarge the controllable region, a polynomial state-space model describes the nonlinear characteristics of turbofan engines. Based on the analysis of the closed-loop control system, by using the Lyapunov function theorems, a polynomial robust controller is designed to ensure the stability and desired nonlinear control performance of turbofan engines. Compared with the classical PI, mixed sensitivity, and H∞ control, simulation results show that the proposed method has better transient responses, disturbance rejection, and other control performance for the turbofan engine within the large region.

Model-based robust control design and experimental validation of SCARA robot system with uncertainty

2022 ◽  
pp. 107754632110421
Author(s):  
ShengChao Zhen ◽  
MuCun Ma ◽  
XiaoLi Liu ◽  
Feng Chen ◽  
Han Zhao ◽  
...  
Keyword(s):  
Robust Control ◽  
Control Algorithm ◽  
Lyapunov Method ◽  
Control Method ◽  
External Disturbance ◽  
Scara Robot ◽  
Model Based ◽  
Robust Control Design ◽  
Robot Performance ◽  
The Stability

In this paper, we design a novel robust control method to reduce the trajectory tracking errors of the SCARA robot with uncertainties including parameters such as uncertainty of the mechanical system and external disturbance, which are time-varying and nonlinear. Then, we propose a deterministic form of the model-based robust control algorithm to deal with the uncertainties. The proposed control algorithm is composed of two parts according to the assumed upper limit of the system uncertainties: one is the traditional proportional-derivative control, and the other is the robust control based on the Lyapunov method, which has the characteristics of model-based and error-based. The stability of the proposed control algorithm is proved by the Lyapunov method theoretically, which shows the system can maintain uniformly bounded and uniformly ultimately bounded. The experimental platform includes the rapid controller prototyping cSPACE, which is designed to reduce programming time and to improve the efficiency of the practical operation. Moreover, we adopt different friction models to investigate the effect of friction on robot performance in robot joints. Finally, numerical simulation and experimental results indicate that the control algorithm proposed in this paper has desired control performance on the SCARA robot.

Rigid-Flexible Coupled Dynamics and PD-Robust Control Design for the Spacecraft with Rotating Solar Panels

2021 ◽  
Author(s):  
Yuteng Cao ◽  
Dengqing Cao ◽  
Guiqin He ◽  
Yuxin Hao ◽  
Xinsheng Ge
Keyword(s):  
Robust Control ◽  
Dynamical Equation ◽  
Vibration Suppression ◽  
Control Method ◽  
Ritz Method ◽  
Solar Panels ◽  
Central Platform ◽  
Attitude Maneuver ◽  
Control Scheme ◽  
Robust Control Design

The dynamical model for the spacecraft with multiple solar panels and the cooperative controller for such spacecraft are studied in this paper. The spacecraft consists of a rigid platform and two groups of flexible solar panels, where solar panels could be driven to rotate by the connecting shaft. The flexible solar panel involves the use of the orthogonal polynomial in two directions to describe its elastic deformation. By using the Rayleigh–Ritz method, the characteristic equation is derived to obtain natural frequencies and modal shapes of the whole spacecraft. Then the discrete rigid-flexible coupled dynamical equation of the spacecraft is obtained by using the Hamiltonian principle. The equation involves the coupling of the attitude maneuver, solar panels’ driving and vibration suppression. These dynamical behaviors are addressed by the rigid-flexible coupled mode for the first time in this paper. Based on the dynamical equation, the cooperative control scheme is designed by combing the proportional-differential and robust control method. Numerical results show the accuracy of the present modelling method and the validation of the control strategy. The modal analysis implies the complex rigid-flexible coupled characteristic between the central platform and flexible solar panels. The proposed control scheme can maintain the attitude stability while solar panels are being driven, as well as the vibration suppression of flexible solar panels.

scholarly journals Robust Control Design for Kaplan Turbine

2021 ◽  
Vol 2141 (1) ◽  
pp. 012006
Author(s):  
Hernando González Acevedo
Keyword(s):  
Robust Control ◽  
Dynamic Model ◽  
Transient Response ◽  
Reference Signal ◽  
Control Design ◽  
Parameter Uncertainties ◽  
Robust Controller ◽  
System A ◽  
Kaplan Turbine ◽  
Robust Control Design

Abstract The paper presents the dynamic model of a Kaplan turbine coupled to a DC generator, which is part of the H112D didactic system. A robust controller is designed using two different techniques: H ∞ mixed sensitivity and Quantitative feedback Theory (QFT). The robustness of the controller was analysed with three indicators: analysis of parameter uncertainties, transient response given a variable reference signal and robustness against disturbances.

scholarly journals Stability Control and Turning Algorithm of an Alpine Skiing Robot

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3664 ◽  
Author(s):  
Si-Hyun Kim ◽  
Bumjoo Lee ◽  
Young-Dae Hong
Keyword(s):  
Humanoid Robot ◽  
Control Method ◽  
Stability Control ◽  
Simulation Software ◽  
Dynamics Simulation ◽  
Alpine Skiing ◽  
Turning Radius ◽  
Pass Through ◽  
The Many ◽  
Robot Platform

This paper proposes a general stability control method that uses the concept of zero-moment-point (ZMP) and a turning algorithm with a light detection and ranging (LiDAR) sensor for a bipedal alpine skiing robot. There is no elaborate simulator for skiing robots since the snow has complicated characteristics, such as compression and melting. However, real experiments are laborious because of the many varied skiing conditions. The proposed skiing simulator could be used, so that a humanoid robot can track its desired turning radius by modeled forces that are similar to real ones in the snow. Subsequently, the robot will be able to pass through gates with LiDAR sensors. By using ZMP control, the robot can avoid falling down while tracking its desired path. The performance of the proposed stabilization method and autonomous turning algorithm are verified by a dynamics simulation software, Webots, and the simulation results are obtained while using the small humanoid robot platform DARwIn-OP.

Neural Network-Based Tracking Control of Underactuated Autonomous Underwater Vehicles With Model Uncertainties

2014 ◽  
Vol 137 (2) ◽  
Author(s):  
Bong Seok Park
Keyword(s):  
Neural Network ◽  
Tracking Control ◽  
Control Method ◽  
Autonomous Underwater Vehicles ◽  
Underwater Vehicles ◽  
Reference Trajectory ◽  
Control Input ◽  
Model Uncertainties ◽  
Dynamic Surface ◽  
Hydrodynamic Damping

In this paper, we propose a neural network (NN)-based tracking control method for underactuated autonomous underwater vehicles (AUVs) with model uncertainties. In order to solve the difficulties in designing the controller for underactuated AUVs, the additional virtual control input is developed, and the approach angle, which generates the desired yaw angle to track any reference trajectory, is introduced. Moreover, the NNs are used to deal with model uncertainties in the hydrodynamic damping terms of AUVs. Finally, the proposed controller is designed based on the dynamic surface control (DSC) method, and the boundedness of all tracking errors is proved by using the Lyapunov stability theory. Some simulation results demonstrate the performance of the proposed control method.

Integrated Control of Suspension and Steering Systems Based on Vehicle Handling and Performance

2012 ◽  
Vol 457-458 ◽  
pp. 953-960
Author(s):  
Wei Liu ◽  
Wen Ku Shi ◽  
De Guang Fang ◽  
Fu Xiang Guo
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Ride Comfort ◽  
Integrated Control ◽  
Electrical Power ◽  
Simulation Software ◽  
Dynamics Simulation ◽  
Power Steering ◽  
Neural Network Controller ◽  
And Performance

In this paper, the features of electrical power steering (EPS) and semi-active suspension (SAS) systems have been carefully researched, and an integrated control strategy based on neural network theory was proposed to achieve the integrated control of EPS and SAS systems. In order to achieve the simulation of the integrated control strategy, a neural network controller of EPS and SAS systems was designed under MATLAB environment, and a passenger car virtual prototyping model including the EPS and SAS systems was established in vehicle dynamics simulation software SIMPACK. By ride comfort and handing stability simulation, the integrated control strategy was proved to be effective. The primary goal of this paper is to propose an effective and reliable integrated control strategy of EPS and SAS systems, and improve the ride comfort as well as handing stability of automobile.

A High Precision Positioning Control Method Based on Learning Algorithm with Reference Model

2011 ◽  
Vol 211-212 ◽  
pp. 671-675
Author(s):  
Kenji Nakajima ◽  
Hiroyuki Saitou ◽  
Seiji Hashimoto
Keyword(s):  
Neural Network ◽  
High Precision ◽  
Control Method ◽  
Reference Model ◽  
Learning Algorithm ◽  
Input Saturation ◽  
Control Input ◽  
Precision Positioning ◽  
Positioning Control ◽  
The Neural Network

In this paper, a high precision positioning control method based on the learning algorithm with the reference model is proposed. The reference model is composed of a plant model and a feedback controller. In the proposed control method, disturbance, modeling error and nonlinear characteristic can be effectively compensated by the neural network-based controller, which learns the reference model. Moreover, the control-input saturation problem due to the over-learning for the neural network can be avoided. The effectiveness of the proposed control method is experimentally verified using the precision positioning equipment with nonlinear friction characteristics.

Sign in / Sign up

Export Citation Format

Share Document