Affiliation:
1. Hebei Chemical and Pharmaceutical College
2. Hebei University of Science and Technology
Abstract
To deal with the defects of the steepest descent in slowly converging and easily immerging in partialm in imum,this paper proposes a new type of PID control system based on the BP neural network, which is a combination of the neural network and the PID strategy. It has the merits of both neural network and PID controller. Moreover, Fletcher-Reeves conjugate gradient in controller can make the training of network faster and can eliminate the disadvantages of steepest descent in BP algorithm. The parameters of the neural network PID controller are modified on line by the improved conjugate gradient. The programming steps under MATLAB are finally described. Simulation result shows that the controller is effective.
Publisher
Trans Tech Publications, Ltd.
Reference8 articles.
1. C C Hang, K J A strom, W K Ho1 R efinem ents of the Ziegler-N icho ls tun ing form ula[J]1 IEE Proceeding–D, 2001, 138(2): 111-1181.
2. W K Ho, C C Hang, J H Zhou1 Perfo rm ance and Gain and Phase M argins of W ell-Known P I Tun ing Fo rm u las[J] 1 IEEE Transactions on Con tro l System s Techno logy, 2005, 3(2): 245-2481.
3. W K Ho, C C Hang, L S Cao1 Tun ing of P ID Con tro llers B ased on Gain and Phase Margin Specification s[J]1 Automatica, 2005, 31(3): 497-5021.
4. Q G W ang, C C Hang, X P Yang1 Single-loop con troller design via IMC p rincip les[J]1 Automatica, 2009, 37: 2041-20481.
5. M Zhuang, D P A therton1 A u tom atic tun ing of op tim um P ID contro llers[J] 1 IEE PROCEED INGS-D, 2003, 140(3): 216-2241.