FICA-PNN fault diagnosis for penicillin fermentation process

Author

Yang Qing ; Yao Jingtang ; Zhang Xu ; Chao Xiaojie

Author_Institution

Sch. of Inf. Sci. & Eng., Shenyang Ligong Univ., Shenyang, China

fYear

2011

fDate

22-24 July 2011

Firstpage

4351

Lastpage

4354

Abstract

A novel ensemble approach based on fast independent component analysis and probabilistic neural network (FICA-PNN) is presented to diagnose faults in the fed-batch penicillin fermentation process. FICA is used to extract fastly the information of a non-Gaussian process. PNN is used as a classifier for diagnosing faults. The experimental results clearly demonstrate that the proposed approach is faster and more efficient and has higher accuracy rate compared to conventional fault diagnosis approaches.

Keywords

Gaussian processes; fault diagnosis; fermentation; independent component analysis; neural nets; pharmaceutical technology; FICA-PNN; fast independent component analysis; fault diagnosis; nonGaussian process; penicillin fermentation process; probabilistic neural network; Algorithm design and analysis; Classification algorithms; Fault diagnosis; Independent component analysis; Monitoring; Probabilistic logic; Substrates; Fast Independent Component Analysis; Fault Diagnosis; Fica-Pnn; Penicillin Fermentation Process; Probabilistic Neural Network;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (CCC), 2011 30th Chinese

Conference_Location

Yantai

ISSN

1934-1768

Print_ISBN

978-1-4577-0677-6

Electronic_ISBN

1934-1768

Type

conf

Filename

6001549