Neural Networks Attitude Decoupling Controller Design of Dual-Ducted SUAV Based on ADRC System

2014 ◽  
Vol 915-916 ◽  
pp. 411-417
Author(s):  
Tong Yue Gao ◽  
Dong Dong Wang ◽  
Tao Fei ◽  
Hai Lang Ge
Keyword(s):  
Neural Network ◽  
Strong Coupling ◽  
Attitude Control ◽  
Control Algorithm ◽  
Controller Design ◽  
Learning Ability ◽  
Effective Control ◽  
Operating Characteristics ◽  
Learning Condition ◽  
Neural Network Algorithm

This dual-ducted SUAV is a nonlinear and strong coupling of multiple-input and multiple-output system, and particularly between the pitch and roll channels channel coupling is strong, in order to implement effective control, it must be decoupled. The traditional methods are difficult to achieve effective control of the strong coupling of multivariable systems. Neural network which has a strong learning ability, is able to learn from the sample and can adapt to changing learning condition. Thus, the neural network can be used to simulate the learning process of operator, and operating characteristics information of objects can be excavated from the measured data, and accordingly change the parameters of the controller and decoupling network. This paper presents a attitude control algorithm of the dual-ducted SUAV which combine ADRC algorithms with neural network decoupling control algorithm, to design a SUAV decoupling controller. The simulation results showed that the attitude control channels between the pitch and roll were independently of each other, indicating a good solution to decouple the coupling between the pitch and roll channels based on neural network algorithm.

Neural network fuzzy control for enhancing the stability performance of quad-rotor helicopter

2017 ◽  
Vol 40 (11) ◽  
pp. 3333-3344 ◽  
Author(s):  
Jialiang Wang ◽  
Jianli Ding ◽  
Weidong Cao ◽  
Quanfu Li ◽  
Hai Zhao
Keyword(s):  
Neural Network ◽  
Fuzzy Control ◽  
Control Algorithm ◽  
Learning Ability ◽  
Effective Control ◽  
Motor Speed ◽  
Stability Performance ◽  
The Neural Network ◽  
The Stability ◽  
Fuzzy Control Algorithm

Recently, the quad-rotor helicopter has gained increasing attention owing to its very good flexibility, its ability to execute various flight missions even in harsh environments. The quad-rotor helicopter can implement different fight attitudes, which is attributed to the effective control of the motor speed about four propellers. In order to make the quad-rotor helicopter can better finish flight mission, the performance of flight stability then becomes particularly important. A neural network fuzzy control algorithm is proposed in this paper so as to guarantee the stability performance of the quad-rotor helicopter. The proposed algorithm is based on the neural network, which keeps the self-organization and self-learning ability, besides this, it utilizes the strong impression ability of constitutive knowledge as to the fuzzy logic. The proposed control scheme aims to implement good abilities such as describing qualitative knowledge, strong learning mechanism and direct processing about quantitative data of the quad-rotor helicopter. In the practical flight process of the quad-rotor helicopter, while the deviation of position and attitude information become larger, fuzzy control is adopted so as to shorten the overshoot and adjustment time. On the other hand, if the deviation of position and attitude become relatively smaller, neural network PID control will be used so as to reduce the error. Experimental results show that the proposed neural network fuzzy control algorithm exhibits good performance in the flight process of the quad-rotor helicopter.

scholarly journals Online Tuning of PID Controller Using a Multilayer Fuzzy Neural Network Design for Quadcopter Attitude Tracking Control

2021 ◽  
Vol 14 ◽  
Author(s):  
Daewon Park ◽  
Tien-Loc Le ◽  
Nguyen Vu Quynh ◽  
Ngo Kim Long ◽  
Sung Kyung Hong
Keyword(s):  
Neural Network ◽  
Network Design ◽  
Attitude Control ◽  
Pid Controller ◽  
Fuzzy Neural Network ◽  
Learning Ability ◽  
System Stability ◽  
Effective Control ◽  
Fuzzy Neural ◽  
Online Tuning

This study presents an online tuning proportional-integral-derivative (PID) controller using a multilayer fuzzy neural network design for quadcopter attitude control. PID controllers are simple but effective control methods. However, finding the suitable gain of a model-based controller is relatively complicated and time-consuming because it depends on external disturbances and the dynamic modeling of plants. Therefore, the development of a method for online tuning of quadcopter PID parameters may save time and effort, and better control performance can be achieved. In our controller design, a multilayer structure was provided to improve the learning ability and flexibility of a fuzzy neural network. Adaptation laws to update network parameters online were derived using the gradient descent method. Also, a Lyapunov analysis was provided to guarantee system stability. Finally, simulations concerning quadcopter attitude control were performed using a Gazebo robotics simulator in addition to a robot operating system (ROS), and their results were demonstrated.

scholarly journals Design of Satellite Attitude Control Algorithm Based on the SDRE Method Using Gas Jets and Reaction Wheels

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Luiz C. G. de Souza ◽  
Victor M. R. Arena
Keyword(s):  
Attitude Control ◽  
Control Algorithm ◽  
Controller Design ◽  
Algorithm Design ◽  
Large Angle ◽  
Space Mission ◽  
Control Technique ◽  
Gas Jets ◽  
State Dependent ◽  
Highly Nonlinear

An experimental attitude control algorithm design using prototypes can minimize space mission costs by reducing the number of errors transmitted to the next phase of the project. The Space Mechanics and Control Division (DMC) of INPE is constructing a 3D simulator to supply the conditions for implementing and testing satellite control hardware and software. Satellite large angle maneuver makes the plant highly nonlinear and if the parameters of the system are not well determined, the plant can also present some level of uncertainty. As a result, controller designed by a linear control technique can have its performance and robustness degraded. In this paper the standard LQR linear controller and the SDRE controller associated with an SDRE filter are applied to design a controller for a nonlinear plant. The plant is similar to the DMC 3D satellite simulator where the unstructured uncertainties of the system are represented by process and measurements noise. In the sequel the State-Dependent Riccati Equation (SDRE) method is used to design and test an attitude control algorithm based on gas jets and reaction wheel torques to perform large angle maneuver in three axes. The SDRE controller design takes into account the effects of the plant nonlinearities and system noise which represents uncertainty. The SDRE controller performance and robustness are tested during the transition phase from angular velocity reductions to normal mode of operation with stringent pointing accuracy using a switching control algorithm based on minimum system energy. This work serves to validate the numerical simulator model and to verify the functionality of the control algorithm designed by the SDRE method.

Attitude Decoupling Controller Design of Dual-Ducted SUAV Based on ADRC System

2014 ◽  
Vol 536-537 ◽  
pp. 1143-1148
Author(s):  
Tong Yue Gao ◽  
Dong Dong Wang ◽  
Tao Fei ◽  
Hai Lang Ge
Keyword(s):  
Strong Coupling ◽  
Controller Design ◽  
Effective Control ◽  
Multivariable Systems ◽  
Channel Coupling ◽  
Multiple Input ◽  
Strong Robustness ◽  
Output System ◽  
Coupling Characteristics ◽  
Attitude Model

This dual-ducted SUAV is a nonlinear and strong coupling of multiple-input and multiple-output system, and particularly between the pitch and roll channels channel coupling is strong, in order to implement effective control, it must be decoupled. The traditional methods are difficult to achieve effective control of the strong coupling of multivariable systems. For the SUAV model of nonlinear coupling characteristics, based on the establishment of the UAV attitude model, this paper designed an attitude ADRC decoupling controller. The simulation showed this ADRC decoupling controller had strong robustness and immunity, and solved the channels coupling between the pitch and roll.

PBP: A Type of BP Neural Network Algorithm Based on Priori Triggering

2011 ◽  
Vol 271-273 ◽  
pp. 441-447
Author(s):  
Xiao Mei Chen ◽  
Dang Gang ◽  
Tian Yang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Large Scale ◽  
Learning Ability ◽  
Traffic Flows ◽  
It Use ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Large Scale Networks ◽  
High Level

The algorithm of anomaly detection for large scale networks is a key way to promptly detect the abnormal traffic flows. In this paper, priori triggered BP neural network algorithm(PBP) is analyzed for the purpose of dealing with the problems caused by typical algorithms that are not able to adapt and learn; detect with high precision; provide high level of correctness. PBP uses K-Means and PCA to trigger self-adapting and learning ability, and also, it uses historical neuron parameter to initialize the neural network, so that it use the trained network to detect the abnormal traffic flows. According to experiments, PBP can obtain a higher level of correctness of detection than priori algorithm, and it can adapt itself according to different network environments.

scholarly journals Application of Neural Network Algorithm in Propylene Distillation

2021 ◽  
pp. 53-63
Author(s):  
Jinwei Lu ◽  
Ningrui Zhao
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Functional Relationship ◽  
Learning Ability ◽  
Neural Network Modeling ◽  
Distillation Tower ◽  
Neural Network Algorithm ◽  
Artificial Neural ◽  
Two Phases ◽  
Propylene Yield

Artificial neural network modeling does not need to consider the mechanism. It can map the implicit relationship between input and output and predict the performance of the system well. At the same time, it has the advantages of self-learning ability and high fault tolerance. The gas-liquid two phases in the rectification tower conduct interphase heat and mass transfer through countercurrent contact. The functional relationship between the product concentration at the top and bottom of the tower and the process parameters is extremely complex. The functional relationship can be accurately controlled by artificial neural network algorithms. The key components of the propylene distillation tower are the propane concentration at the top of the tower and the propylene concentration at the bottom of the tower. Accurate measurement of them plays a key role in increasing propylene yield in ethylene production enterprises. This article mainly introduces the development process of neural network model and its application progress in propylene distillation tower.

scholarly journals The application of neural network algorithm and embedded system in computer distance teach system

2022 ◽  
Vol 31 (1) ◽  
pp. 148-158
Author(s):  
Qin Qiu
Keyword(s):  
Neural Network ◽  
Embedded System ◽  
Learning Ability ◽  
Distance Teaching ◽  
Teaching System ◽  
Network Computer ◽  
Neural Network Algorithm ◽  
Bus Structure ◽  
Self Learning ◽  
Distance Education System

Abstract The computer distance teaching system teaches through the network, and there is no entrance threshold. Any student who is willing to study can log in to the network computer distance teaching system for study at any free time. Neural network has a strong self-learning ability and is an important part of artificial intelligence research. Based on this study, a neural network-embedded architecture based on shared memory and bus structure is proposed. By looking for an alternative method of exp function to improve the speed of radial basis function algorithm, and then by analyzing the judgment conditions in the main loop during the algorithm process, these judgment conditions are modified conditionally to reduce the calculation scale, which can double the speed of the algorithm. Finally, this article verifies the function, performance, and interface of the computer distance education system.

Study on Multimode Intelligent Control for Ship Steering System

2011 ◽  
Vol 58-60 ◽  
pp. 2621-2633
Author(s):  
Ming Hui Wang ◽  
Yong Quan Yu ◽  
Bi Zeng
Keyword(s):  
Neural Network ◽  
Fuzzy Control ◽  
Intelligent Control ◽  
Control Method ◽  
Control Process ◽  
Steering System ◽  
Learning Ability ◽  
Effective Control ◽  
Control Effect ◽  
Ship Steering

The ship motion is characterized by nonlinearity, time varying, uncertainty and complex interference from the environment, therefore there are certain limits in conventional PID control and self-adapting control for ship steering system. This paper combines three intelligent control technologies, that is, fuzzy control, neural network and extension control, to propose a multimode intelligent control method. Fuzzy control is utilized to solve control problem of uncertainty system, and learning ability of neural network is utilized to optimize the controller parameters. A new multi-mode transition controller based on extension control is presented and well designed in this paper, which may realize smooth switching during control process. In order to satisfy the requirements of higher accuracy and faster response of complex system, every control strategy designed can realize ideal control effect within the scope of its effective control. The simulation experiment is made to test dynamic and static performances of ship steering system under model parameter perturbation and wave interference. The simulation results show that the control system achieves satisfactory performances by implementing the multimode intelligent control.

Controller Design Based on Mechatronic Model

2014 ◽  
Vol 526 ◽  
pp. 351-356
Author(s):  
Li Xi Yue ◽  
Jian Hui Zhou ◽  
Yan Nan Lu ◽  
Chong Chong Ji ◽  
Zhi Yong Yu
Keyword(s):  
Neural Network ◽  
High Speed ◽  
Controller Design ◽  
Design Method ◽  
Nonlinear Modeling ◽  
Digital Design ◽  
The Neural Network ◽  
Key Issues ◽  
Neural Network Algorithm ◽  
Computed Torque

The dissertation deals with some key issues relevant to the controller design and digital design method for a newly patented high-speed parallel manipulator. Meanwhile, a Virtual Prototyping based co-simulation platform is also established according to the ADAMS and Matlab/Simulink software. In order to promote the ability that the manipulator traces the prescribed trajectory, a model based computed torque controller is described in detail, and a neural network algorithm is also used to optimize controller parameters real-timely under the consideration of systematic nonlinear, modeling error and outer disturbance. The neural network based computed torque controller increases the robustness of system dramatically.

Research of BP Neural Network Algorithm Testing Platform Based on OPC Communication

2014 ◽  
Vol 668-669 ◽  
pp. 575-580
Author(s):  
Bing Wu Chen ◽  
Xing Chen ◽  
Hui Peng Shu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Real Time ◽  
Bp Neural Network ◽  
Data Exchange ◽  
Communication Process ◽  
Effective Control ◽  
Testing Platform ◽  
Network Algorithm ◽  
Neural Network Algorithm

Effective control algorithm can be applied to the real-time control system by the data exchange between MCGS and MATLAB with OPC technology, as a result, a testing platform for advanced control algorithms is established. The paper presents a second-order liquid level control system for research example; the BP neural network algorithm is applied to the control system. The communication process verifies that the data exchange is reliable and the simulation results show the control of the BP neural network algorithm for real-time optimized control process is effective.

Sign in / Sign up

Export Citation Format

Share Document