Iterative Learning Control Based on Radial Basis Function Network for Exoskeleton Arm

2011 ◽  
Vol 415-417 ◽  
pp. 116-122 ◽  
Author(s):  
Jie Liu ◽  
Yu Wang ◽  
He Ting Tong ◽  
Ray P.S. Han
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Iterative Learning Control ◽  
Rbf Neural Network ◽  
Radial Basis Function Network ◽  
Learning Control ◽  
Iterative Learning ◽  
Control Input ◽  
Radial Basis

In this paper, we propose iterative learning control (ILC) scheme for exoskeleton arm driven by pneumatic artificial muscles (PAM), with special and unknown parameters, performing repetitive tasks. This desired control input of ILC was estimated by radial basis function (RBF) neural network incorporated experience database. An ILC controller, which uses the position of the joint where an angular sensor is used as the input of the ILC controller, is developed and tested on exoskeleton arm under well controlled conditions. RBF neural network was proposed to obtain the initial value of ILC. The experiment result on the experimental platform show that the algorithm is successful also in the application of exoskeleton arm.

Tension coordination control of double-rope winding hoisting system using hybrid learning control scheme

2019 ◽  
Vol 233 (10) ◽  
pp. 1265-1281 ◽  
Author(s):  
Xiao Chen ◽  
Zhencai Zhu ◽  
Gang Shen ◽  
Wei Li
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Iterative Learning Control ◽  
Learning Control ◽  
Iterative Learning ◽  
Control Scheme ◽  
Radial Basis ◽  
The Wire ◽  
Hoisting System

Tension difference between ropes due to asynchronous hoisting, guide rail tilt, and friction jam restricts the application of double-rope winding hoisting systems that have high-security requirement. In this article, a hybrid adaptive iterative learning control scheme is presented for a double-rope winding hoisting system driven by permanent magnet synchronous motor systems. First, based on the discrete model of the wire rope, the mathematical model of the system is established. Subsequently, in order to reduce the tension difference of the wire ropes under impact, a hybrid control scheme based on iterative learning control and radial basis function neural network is proposed to improve the performance of the controller. A radial basis function neural network–based adaptive law is developed to compensate the uncertainties of the movable headgear sheave subsystem, and radial basis function neural network–based switching gains are applied to improve the disturbance compensation speed of the iterative learning controller. Stability of the overall closed-loop system under proposed controller is proved. Finally, the experimental results show that the proposed controller is effective and has better performance than traditional controllers.

The Research Based on RBF Neural Network in the Power of Prediction of Grain Depot

2012 ◽  
Vol 182-183 ◽  
pp. 1358-1361
Author(s):  
Le Xiao ◽  
Min Peng Hu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Model ◽  
Radial Basis Function ◽  
Basis Function ◽  
Rbf Neural Network ◽  
Electricity Consumption ◽  
Nonlinear Time Series ◽  
Modeling And Prediction ◽  
Radial Basis

According to the fact that the use of electricity in grain depot is nonlinear time series, the article introduces the prediction model of electricity based on Radial Basis Function Neural Network, and conducts the modeling and prediction by adopting the historical electricity consumption of a typical grain depot. As the result of simulation shows, the model obtains better forecasting results in grain depot electricity.

scholarly journals A Novel Evaluation Model for Urban Smart Growth Based on Principal Component Regression and Radial Basis Function Neural Network

2019 ◽  
Vol 11 (21) ◽  
pp. 6125
Author(s):  
Lianyan Li ◽  
Xiaobin Ren
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Rbf Neural Network ◽  
Evaluation Model ◽  
Smart Growth ◽  
Principal Component Regression ◽  
Principal Component ◽  
Self Organizing Map ◽  
Radial Basis

Smart growth is widely adopted by urban planners as an innovative approach, which can guide a city to develop into an environmentally friendly modern city. Therefore, determining the degree of smart growth is quite significant. In this paper, sustainable degree (SD) is proposed to evaluate the level of urban smart growth, which is established by principal component regression (PCR) and the radial basis function (RBF) neural network. In the case study of Yumen and Otago, the SD values of Yumen and Otago are 0.04482 and 0.04591, respectively, and both plans are moderately successful. Yumen should give more attention to environmental development while Otago should concentrate on economic development. In order to make a reliable future plan, a self-organizing map (SOM) is conducted to classify all indicators and the RBF neural network-trained indicators are separate under different classifications to output new plans. Finally, the reliability of the plan is confirmed by cellular automata (CA). Through simulation of the trend of urban development, it is found that the development speed of Yumen and Otago would increase slowly in the long term. This paper provides a powerful reference for cities pursuing smart growth.

scholarly journals Upset Prediction in Friction Welding Using Radial Basis Function Neural Network

2013 ◽  
Vol 2013 ◽  
pp. 1-9
Author(s):  
Wei Liu ◽  
Feifan Wang ◽  
Xiawei Yang ◽  
Wenya Li
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Radial Basis Function ◽  
Basis Function ◽  
Welded Joints ◽  
Friction Welding ◽  
Rbf Neural Network ◽  
Finite Element Simulations ◽  
Welding Parameters ◽  
Radial Basis

This paper addresses the upset prediction problem of friction welded joints. Based on finite element simulations of inertia friction welding (IFW), a radial basis function (RBF) neural network was developed initially to predict the final upset for a number of welding parameters. The predicted joint upset by the RBF neural network was compared to validated finite element simulations, producing an error of less than 8.16% which is reasonable. Furthermore, the effects of initial rotational speed and axial pressure on the upset were investigated in relation to energy conversion with the RBF neural network. The developed RBF neural network was also applied to linear friction welding (LFW) and continuous drive friction welding (CDFW). The correlation coefficients of RBF prediction for LFW and CDFW were 0.963 and 0.998, respectively, which further suggest that an RBF neural network is an effective method for upset prediction of friction welded joints.

Sign in / Sign up

Export Citation Format

Share Document