Title :
Double Inverted Pendulum Control Based on Three-loop PID and Improved BP Neural Network
Author :
Sang, Yingjun ; Fan, Yuanyuan ; Liu, Bin
Author_Institution :
Fac. of Electron. & Electr. Eng., Huaiyin Inst. of Technol., Huaian, China
Abstract :
To deal with the defects of BP neural networks used in balance control of inverted pendulum, such as longer train time and converging in partial minimum, this article realizes the control of double inverted pendulum with improved BP algorithm of artificial neural networks (ANN), builds up a training model of test simulation and the BP network is 6-10-1 structure. Tansig function is used in hidden layer and Purelin function is used in output layer, LM is used in training algorithm. The training data is acquired by three-loop PID algorithm. The model is learned and trained with Matlab calculating software, and the simulink simulation experiment results prove that improved BP algorithm for inverted pendulum control has higher precision, better astringency and lower calculation. This algorithm has wide application on nonlinear control and robust control field in particular.
Keywords :
backpropagation; learning systems; multivariable control systems; neurocontrollers; nonlinear control systems; pendulums; robust control; three-term control; time-varying systems; BP algorithm; BP neural network; Matlab calculating software; Purelin function; Simulink simulation experiment; Tansig function; artificial neural network; balance control; double inverted pendulum control; model learning; multivariable system; nonlinear control; robust control; strongly coupled system; test simulation; three-loop PID algorithm; time-varying system; training algorithm; training model; Algorithm design and analysis; Artificial neural networks; Control systems; Educational institutions; Mathematical model; Software algorithms; Training; artificial neural networks; double inverted pendulum; improved back propagation algorithm; three-loop pid;
Conference_Titel :
Digital Manufacturing and Automation (ICDMA), 2011 Second International Conference on
Conference_Location :
Zhangjiajie, Hunan
Print_ISBN :
978-1-4577-0755-1
Electronic_ISBN :
978-0-7695-4455-7
DOI :
10.1109/ICDMA.2011.118