Application of BP neural network in the control of hydraulic die forging hammer

Li Yan*, Li Jianwei, Liu Jun

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

It is an essential problem in the control of hydraulic die forging hammer that the mathematical model between deformation and forging energy, and it is nonlinear in nature. For its pretty nonlinear function approximation ability, BP neural network is suitable for resolving the problem. The architecture and the arithmetic of BP neural network were introduced. Furthermore, the BP neural network model was established. At the same time, the process and principle of the modeling also were expounded. Then, it was explained that how to use the BP neural network model in the control process. The result of experiment showed that the method takes effect very well. Other applications of BP neural network in the control of hydraulic die forging hammer was also introduced. At last, the disadvantage of the method was discussed briefly.

Original languageEnglish
Title of host publication2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009
Pages39-41
Number of pages3
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009 - Changsha, Hunan, China
Duration: 10 Oct 200911 Oct 2009

Publication series

Name2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009
Volume1

Conference

Conference2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009
Country/TerritoryChina
CityChangsha, Hunan
Period10/10/0911/10/09

Keywords

  • BP neural network
  • Forging energy
  • Hydraulic die forging hammer

Fingerprint

Dive into the research topics of 'Application of BP neural network in the control of hydraulic die forging hammer'. Together they form a unique fingerprint.

Cite this