Two Grade Learning Goal Neural Network Modeling with Power Activation Function

Authors

Jiacun Liu, 1. Faculty of Electrics and Information Engineering, GuangDong Ocean University, Zhanjiang 524088,China; ;
Qixiang Mei, 2. Faculty of Mathemarics and Computer Science, GuangDong Ocean University, Zhanjiang 524088,China;
Donghong Yang, 1. Faculty of Electrics and Information Engineering, GuangDong Ocean University, Zhanjiang 524088,China; ;

Abstract

Abstract: In order to obtain the very generalized and accurater mathematic model, a regression neural network algorithm with frequency decomposition power function and two grade learning objectives was proposed. The network structure is divided into frequency decomposition, input layer, hidden layer and output layer. The input signal is decomposed into several frequency range and sent to the hidden layer. The transfer function of hidden layer is power function. The hidden layer and output layer have learning objectives respectively, and the neural network has local and globe feedback. The hidden layer adopts the local gradient algorithm based on vector angle and the output layer uses the global linear regression algorithm. The neural network model was used to adjust the PID parameters of control system; the controlled variable was achieved by modified iterative learning algorithm, then the PID parameters were turned by constrained linear least squares algorithm. Simulation shows that the neural network model is generalized and accurate; the quality of control system is excellent than traditional turned methods.

Recommended Citation

Liu, Jiacun; Mei, Qixiang; and Yang, Donghong (2020) "Two Grade Learning Goal Neural Network Modeling with Power Activation Function," Journal of System Simulation: Vol. 29: Iss. 1, Article 6.
DOI: 10.16182/j.issn1004731x.joss.201701006
Available at: https://dc-china-simulation.researchcommons.org/journal/vol29/iss1/6

First Page

34

Revised Date

2015-07-15

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201701006

Last Page

42

CLC

TP13;TP183

Recommended Citation

Liu Jiacun, Mei Qixiang, Yang Donghong. Two Grade Learning Goal Neural Network Modeling with Power Activation Function[J]. Journal of System Simulation, 2017, 29(1): 34-42.

DOI

10.16182/j.issn1004731x.joss.201701006