scholarly journals Synthesis of a neural network control regulator of a nonlinear model of an inverted pendulum on a cart

2020 ◽  
pp. 25-36
Author(s):  
Alexsander Voevoda ◽  
◽  
Victor Shipagin ◽  
Keyword(s):  
Neural Network ◽  
Network Structure ◽  
Inverted Pendulum ◽  
Polynomial Matrix ◽  
Matrix Decomposition ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Network Controller ◽  
Nonlinear Object ◽  
Neural Network Structure

In this article, we consider a method for selecting a structure of a neural network used to regulate an "inverted pendulum on a cart" object taking into account its additional features of a mathematical description, namely, nonlinear parameters. The algorithm is illustrated by the example of control synthesis which includes two neuroregulators. One of them is responsible for bringing the cart to the specified position, and the second is responsible for holding the pendulum in a vertical position. The structure transformations will be performed for the controller responsible for bringing the cart to the specified position. The architecture of a neural network controller is based on a discrete controller synthesized using polynomial matrix decomposition. For the original controller, we define the limits of its possible control of a nonlinear system. To increase the range of control of a nonlinear object, we perform transformations of the neural network structure of the original controller. We will make some complications in the structure of the neural network of the regulator, namely, increase the number of neurons and replace some activation functions with nonlinear ones (hyperbolic tangent). Next, we suggest one of the ways to select initial values of weight coefficients. Then we train the neural network and check the performance of the resulting controller on a nonlinear object. At the next stage, we compare the obtained performance of a controller having a complicated neural network structure with the performance of a classical controller. Thus, the purpose of this study is to formalize the synthesis procedure for a neural network controller for controlling a nonlinear object using a calculated classical controller for a linearized object model. The proposed method of generating the architecture of a neural network of controllers makes it possible to increase the range of control by a nonlinear object in comparison with the controller obtained by the method of polynomial matrix decomposition for a linear object. Compared to the typical ones, the proposed neural network structure is not redundant and therefore does not require additional computing resources to configure it.

Research on Intelligent Variable Frequency of Air-Conditioner Control System Based on Fuzzy Control

2011 ◽  
Vol 110-116 ◽  
pp. 4076-4084
Author(s):  
Hai Cun Du
Keyword(s):  
Neural Network ◽  
Control System ◽  
Fuzzy Control ◽  
Fuzzy Neural Network ◽  
Air Conditioner ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Network Controller ◽  
Fuzzy Neural ◽  
Fuzzy Control Strategy

In this paper, we determine the fuzzy control strategy of inverter air conditioner, the fuzzy control model structure, the neural network and fuzzy control technology, structural design of the fuzzy neural network controller as well as the neural network predictor FNNC NNP. Simulation results show that the fuzzy neural network controller can control the accuracy greatly improved the compressor, and the control system has strong adaptability to achieve a truly intelligent; model of the controller design and implementation of technology are mainly from the practical point of view, which is practical and feasible.

Sunlight Greenhouse Temperature Prediction Model Based on Bayesian Regularization BP Neural Network

2015 ◽  
Vol 740 ◽  
pp. 871-874
Author(s):  
Hui Zhao ◽  
Li Rong Shi ◽  
Hong Jun Wang
Keyword(s):  
Neural Network ◽  
Network Structure ◽  
Bp Neural Network ◽  
Principal Component ◽  
Coupling Factor ◽  
Bayesian Regularization ◽  
The Neural Network ◽  
Neural Network Structure ◽  
Input Variables ◽  
Bp Neural Network Model

Directing against the problems of too large size of the neural network structure due to the existence of a complex relationship between the input coupling factor and too many input factors in establishing model for predicting temperature of sunlight greenhouse. This article chose the environmental factors that affect the sunlight greenhouse temperature as data sample. Through the principal component analysis of data samples, three main factors were extracted. These selected principal component values were taken as the input variables of BP neural network model. Use the Bayesian regularization algorithm to improve the BP neural network. The empirical results show that this method is utilized modify BP neural network, which can simplify network structure and smooth fitting curve, has good generalization capability.

Design and Realization of Experimental Autonomous Driving System Based on Neural Network Control

2012 ◽  
Vol 241-244 ◽  
pp. 1953-1958
Author(s):  
Qing Fu Kong ◽  
Fan Ming Zeng ◽  
Jie Chang Wu ◽  
Jia Ming Wu
Keyword(s):  
Neural Network ◽  
Autonomous Driving ◽  
Network Control ◽  
Neural Network Control ◽  
Test Results ◽  
Driving System ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Network Controller ◽  
Autonomous Driving System

Intelligent vehicle is an attractive solution to the traffic problems caused by automobiles. An experimental autonomous driving system based on a slot car set is designed and realized in the paper. With the application of a wireless camera equipped on the slot car, the track information is acquired and sent to the controlling computer. A backpropogation (BP) neural network controller is built to imitate the way of player’s thinking. After being trained, the neural network controller can give the proper voltage instructions to the direct current (DC) motor of the slot car according to different track conditions. Test results prove that the development of the autonomous driving system is successful.

The Application of Double Closed-Loop Unit Gain Negative Feedback and BP Neural Network Controller in Single Inverted Pendulum

2012 ◽  
Vol 490-495 ◽  
pp. 1723-1727
Author(s):  
Jun Ting Wang ◽  
Guo Ping Liu ◽  
Wei Jin ◽  
Gen Fu Xiao
Keyword(s):  
Neural Network ◽  
Mathematical Model ◽  
Negative Feedback ◽  
Bp Neural Network ◽  
Closed Loop ◽  
Inverted Pendulum ◽  
Root Locus ◽  
Neural Network Controller ◽  
Network Controller ◽  
The Mathematical Model

In the paper the mathematical model of the single inverted pendulum is established, on the base of the root locus and the control tasks the control system is made up of double closed-loop unit gain negative feedback and BP neural network controller. The results show that the inverted pendulum is efficiently controlled.

Application of BP Neural Network Controller on Inverted Pendulum

2013 ◽  
Vol 328 ◽  
pp. 72-76
Author(s):  
Huan Xin Cheng ◽  
Dao Sheng Zhang ◽  
Li Cheng
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Inverted Pendulum ◽  
Network Control ◽  
Coupled Systems ◽  
Control Effect ◽  
Strongly Coupled ◽  
Neural Network Controller ◽  
Network Controller ◽  
The Mathematical Model

The traditional PID control, which is based on linearization, is often hard to obtain the optimal control effect on such nonlinear, multiple-output, strongly coupled systems like inverted pendulum. To solve the problem above, the BP neural network controller was developed for inverted pendulum. On the basis of establishing and analyzing the mathematical model of single inverted-pendulum, this paper established the state space expression, and then designed a neural network control system based on BP algorithm. The simulation was researched by Matlab and the running results show that this control has good robustness and can achieve satisfactory control effect.

scholarly journals Application of Firefly Algorithm based Neural Network Controller

2019 ◽  
Vol 8 (11) ◽  
pp. 2659-2662
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Firefly Algorithm ◽  
Frequency Control ◽  
Optimization Technique ◽  
Load Frequency Control ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Network Controller ◽  
Hidden Layer

The Firefly Algorithm is comparison of new optimize procedure based on PSO as tautness. The paper presents the competence and forcefulness of the Firefly algorithm as the optimize concept for a proportional–integral–derivative organizer under various loading conditions. The proposed PID controller is attempt to designed and implemented to frequency-control of a two area interconnected systems. The hidden layer formation is not personalized, as the interest lies only on the reckoning of the weights of the system. In sequence to obtain a practicable report, the weights of the neural network are computational or optimized by minimizing function cost or error. A Firefly Algorithm is an efficient but uncomplicated meta-heuristic optimization technique inspired by expected motion of fireflies towards more light, is used for the preparation of neural network. The simulation report view that the calculation competence of training progression using Firefly Optimization performance with Load frequency control. A study of the output report of the system PID controller and FA based neural network controllers are made for 1% change in load in area 1 and it is found that the proposed controllers ensures a better steady state response of the systems

scholarly journals CHOOSING A NEURAL NETWORK STRUCTURE FOR SIGNAL PROCESSING AS AN EXPERIMENT PLANNING

2021 ◽  
pp. 123-132
Author(s):  
Leonid A. Slavutskii ◽  
Elena V. Slavutskaya
Keyword(s):  
Neural Network ◽  
Signal Processing ◽  
Network Structure ◽  
Electric Power Industry ◽  
Planning Theory ◽  
Experiment Planning ◽  
Harmonic Amplitude ◽  
The Neural Network ◽  
Nonlinear Distortions ◽  
Neural Network Structure

The paper is devoted to the use of artificial neural networks for signal processing in electrical engineering and electric power industry. Direct propagation neural network (perceptron) is considered as an object in the theory of experiment planning. The variants of the neural network structure empirical choice, the quality criteria of its training and testing are analyzed. It is shown that the perceptron structure choice, the training sample, and the training algorithms require planning. Variables and parameters of neuro algorithm that can act as factors, state parameters, and disturbing influences in the framework of the experimental planning theory are discussed. The proposed approach is demonstrated by the example of neural network analysis of the industrial frequency signal of 50 Hz nonlinear distortions. The possibility of using an elementary perceptron with one hidden layer and a minimum number of neurons to correct the transformer saturation current is analyzed. The conditions under which the neuro algorithm allows one to restore the values of the main harmonic amplitude, frequency and phase with an error of no more than one percent are revealed. The signal processing in a «sliding window» with a duration of a fraction of the fundamental frequency period is proposed, and the neuro algorithm accuracy characteristics are estimated. The possibility to automate the neural network structure choosing for signal processing is discussed.

A Neural Network Structure Decomposition Based on Pruning and its Visualization Method

2013 ◽  
Vol 17 (3) ◽  
pp. 443-449
Author(s):  
Atsushi Shibata ◽  
◽  
Jiajun Lu ◽  
Fangyan Dong ◽  
Kaoru Hirota
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Network Structure ◽  
Robot Motion ◽  
Network Structures ◽  
Visualization Method ◽  
Pruning Method ◽  
The Neural Network ◽  
Structure Decomposition ◽  
Neural Network Structure

To decompose neural network structures for composite tasks, a pruning method and its visualization method are proposed. Visualization by placing the neurons on a 2D plane clarifies the structure related to each composited task. Experiments on a composite task using two tasks from a UCI dataset show that the neural network of the composite task contains more than 80% of neurons. The proposed methods target the transfer learning of robot motion, and results of an adaptation experiments are also referred.

Sign in / Sign up

Export Citation Format

Share Document