Application Research on Fault Diagnosis Based on Improved Wavelet Neural Network

Jie Jia Li; Jie Li; Rui Qu; Ying Li

doi:10.4028/www.scientific.net/AMR.499.268

Paper Titles

Design of Double-Light Shadowless Lifting Retractor
p.248

Investigation on Moiré in Multicolor Overprinting
p.253

Theoretical Research of Residual Stress on H-Beam Roller Straightening
p.258

Impact of Step Height on Deformation of Foundation for Wind Power Generator System
p.263

Application Research on Fault Diagnosis Based on Improved Wavelet Neural Network
p.268

Adaptive Synchronization for a Class of Switched Chaotic Systems with Uncertainty
p.273

High Temperature Tribological Behavior of Ball Milled Expanded Graphite/Iron Powders
p.278

Earthquake Response of Asymmetric Structure Considering Soil-Structure Interaction in Time Domain
p.282

Simulation of Cavitation Erosion in Different Throttling Pipelines
p.288

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 499Application Research on Fault Diagnosis Based on...

Application Research on Fault Diagnosis Based on Improved Wavelet Neural Network

Abstract:

Aluminum electrolysis is a nonlinear, multi-couplings, time-variable and large time-delay industrial process system. The paper puts forward the fault diagnoisis method of improved wavelet Elman neural network, which firstly simplifies the input of network with the method of principal component analysis, secondly, the weights, as well as scale factor and shift factor of the wavelet function are optimized by use of the wavelet Elman network which is optimized by improved particle swarm algorithm. Then it is verified by the simulation. The simulation results show that the method can precisely forecast the aluminium electrolysis equipment faults and improve the production and quality of aluminum.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 499)

Pages:

268-272

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.499.268

Citation:

Cite this paper

Online since:

April 2012

Authors:

Jie Jia Li, Jie Li, Rui Qu, Ying Li

Keywords:

Aluminum Electrolysis Faults, Improved Particle Swarm Algorithm, Optimization, Principal Component Analysis (PCA), Wavelet Elman Neural Network

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Guihua Di , Jian Ren. Status of Domestic and International Aluminum Consumption.

Google Scholar

[2] Jeon J Y, Okuma M. Acostic Radiation Optimization Using the Particle Swarm Optimization Algorithm[J]. International J of Series C - Mechanical System Machine Elements and Manufacturing, 2004, 47: 560-567.

DOI: 10.1299/jsmec.47.560

Google Scholar

[3] Ghicassi M, Saidane H, Zimbra DK. A dynamic artificial neural network model for forecasting time series events [J]. International Journal of Forecasting, 2005，21(2): 341～362.

DOI: 10.1016/j.ijforecast.2004.10.008

Google Scholar

[4] Marc Dupuis, Valdis Bojarevics. Weakly Coupled Thermo-electric and MHD Mathematical Models of an Aluminum Electrolysis Cell[J]. Light Metals, 2005, (1): 449~454.

Google Scholar

[5] Jagannathan S , Lewis FL. Identification of nonlinear dynamic systems using multilayered neural networks[J]. Automatica , 2006 , 32(12): 1707-1712.

DOI: 10.1016/s0005-1098(96)80007-0

Google Scholar