scholarly journals High-accuracy motion control of a motor servo system with dead-zone based on a single hidden layer neural network

2020 ◽  
Vol 30 (1) ◽  
pp. 27-44
Author(s):  
Jian Hu ◽  
Shupeng Cao ◽  
Chenchen Xu ◽  
Jianyong Yao ◽  
Zhiwei Xie
Keyword(s):  
Neural Network ◽  
Motion Control ◽  
Dead Zone ◽  
Servo System ◽  
High Accuracy ◽  
Hidden Layer

High-accuracy robust adaptive motion control of a torque-controlled motor servo system with friction compensation based on neural network

2018 ◽  
Vol 233 (7) ◽  
pp. 2318-2328 ◽  
Author(s):  
Jian Hu ◽  
Yuangang Wang ◽  
Lei Liu ◽  
Zhiwei Xie
Keyword(s):  
Neural Network ◽  
Motion Control ◽  
Servo System ◽  
High Accuracy ◽  
Robust Adaptive Control ◽  
Lyapunov Theory ◽  
Parametric Estimation ◽  
Friction Compensation ◽  
Nonlinear Friction ◽  
Robust Adaptive

In this paper, a high-accuracy motion control of a torque-controlled motor servo system with nonlinear friction compensation is presented. Friction always exists in the servo system and reduces its tracking accuracy. Thus, it is necessary to compensate for the friction effect. In this paper, a novel controller that combines robust adaptive control with friction compensation based on neural network observer is proposed. An improved LuGre friction model is applied into the friction compensation as it is known as a good model to express the nonlinear friction. A single hidden-layer network is utilized to observe the immeasurable friction state. Then, the robust adaptive controller is used to handle the parametric uncertainty, the parametric estimation error, friction compensation error, and other uncertainties. Lyapunov theory is utilized to analyze the stability of the closed-loop system. The experimental results demonstrate the effectiveness of the proposed algorithm.

Design of BP Neural Network Controller for Infrared Seeker Servo System Based on Stribeck Friction Model

2014 ◽  
Vol 615 ◽  
pp. 409-414
Author(s):  
Xin Ying Yan ◽  
Bo Mo ◽  
Ying He
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Dead Zone ◽  
Servo System ◽  
Friction Model ◽  
Guidance System ◽  
Low Speed ◽  
Neural Network Controller ◽  
Infrared Seeker ◽  
Stabilized Platform

The high precision of the seeker is the key to reduce the Miss-Distance and improve precision in the guidance system of missile, and the seeker stabilized platform servo system is safeguard of the overall performance of seeker. So based on the Stribeck friction model, this paper studies and compares the precision of position and velocity that controlled by PID control and BP neural network when the seeker platform working at low speed. Finally, according to the MATLAB simulation results, applying modern control theory as controller based on Stribeck friction model can improve precision and the problem of flat and dead zone at low speed.

Genetic Programming for Letters Identification Based on Neural Network

2015 ◽  
Vol 734 ◽  
pp. 642-645
Author(s):  
Yan Hui Liu ◽  
Zhi Peng Wang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Genetic Programming ◽  
Network Structure ◽  
High Accuracy ◽  
Identification System ◽  
Neural Network Structure ◽  
Hidden Layer

According to the problem that the letters identification is not high accuracy using neural networks, in this paper, an optimal neural network structure is designed based on genetic algorithm to optimize the number of hidden layer. The English letters can be identified by optimal neural network. The results obtained in the genetic programming optimizations are very satisfactory. Experiments show that the identification system has higher accuracy and achieved good ideal letters identification effect.

Modeling of Basil Leaves Drying by GA–ANN

2013 ◽  
Vol 9 (4) ◽  
pp. 393-401 ◽  
Author(s):  
Amin Taheri-Garavand ◽  
Shahin Rafiee ◽  
Alireza Keyhani ◽  
Payam Javadikia
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Relative Humidity ◽  
Moisture Content ◽  
Air Temperature ◽  
High Accuracy ◽  
Air Velocity ◽  
Feed Forward Neural Network ◽  
Air Temperatures ◽  
Hidden Layer

AbstractIn this research, the experiment is done by a dryer. It could provide any desired drying air temperature between 20 and 120°C and air relative humidity between 5 and 95% and air velocity between 0.1 and 5.0 m/s with high accuracy, and the drying experiment was conducted at five air temperatures of 40, 50, 60, 70 and 80°C and at three relative humidity 20, 40 and 60% and air velocity of 1.5, 2 and 2.5 m/s to dry Basil leaves. Then with developed Program in MATLAB software and by Genetic Algorithm could find the best Feed-Forward Neural Network (FFNN) structure to model the moisture content of dried Basil in each condition; anyway the result of best network by GA had only one hidden layer with 11 neurons. This network could predict moisture content of dried basil leaves with correlation coefficient of 0.99.

Estimating Pigment Concentrations from Spectral Images Using an Encoder‐Decoder Neural Network

2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Absorption Coefficient ◽  
Spectral Data ◽  
High Accuracy ◽  
Pigment Concentration ◽  
Scattering Coefficient ◽  
A Value ◽  
Input And Output ◽  
Pigment Concentrations

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

Squeak and rattle noise classification using radial basis function neural networks

2020 ◽  
Vol 68 (4) ◽  
pp. 283-293
Author(s):  
Oleksandr Pogorilyi ◽  
Mohammad Fard ◽  
John Davy ◽  
Mechanical and Automotive Engineering, School ◽  
Mechanical and Automotive Engineering, School ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Accuracy ◽  
Training Method ◽  
Vehicle Interior ◽  
Trained Classifier ◽  
Different Types ◽  
Noise Classification ◽  
Automatic Tool ◽  
Multi Class Classification

In this article, an artificial neural network is proposed to classify short audio sequences of squeak and rattle (S&R) noises. The aim of the classification is to see how accurately the trained classifier can recognize different types of S&R sounds. Having a high accuracy model that can recognize audible S&R noises could help to build an automatic tool able to identify unpleasant vehicle interior sounds in a matter of seconds from a short audio recording of the sounds. In this article, the training method of the classifier is proposed, and the results show that the trained model can identify various classes of S&R noises: simple (binary clas- sification) and complex ones (multi class classification).

Sign in / Sign up

Export Citation Format

Share Document