Acoustic Fault Identification of Underwater Vehicles Based on NSOM-PNN

Author

Luan, Ruipeng ; Ben, Kerong ; Cui, Lilin

Author_Institution

Dept. of Comput. Eng., Naval Univ. of Eng., Wuhan, China

Volume

2

fYear

2009

fDate

7-8 Nov. 2009

Firstpage

384

Lastpage

388

Abstract

Aiming at the requirement of class incremental learning in acoustic fault identification research, a network model using a novel Self-organizing map--negative self-organizing map (NSOM) and probabilistic neural network (PNN) is proposed. The experiment of acoustic fault identification of underwater vehicle shows that the proposed network has better capability of class incremental learning than traditional PNN, and can improve the structure of network and accuracy of identification.

Keywords

acoustic signal processing; fault diagnosis; learning (artificial intelligence); probability; self-organising feature maps; underwater sound; underwater vehicles; NSOM-PNN; acoustic fault identification; incremental learning; negative self-organizing map; probabilistic neural network; underwater vehicles; Acoustic noise; Acoustical engineering; Automotive engineering; Bayesian methods; Fault diagnosis; Neural networks; Neurons; Probability density function; Underwater acoustics; Underwater vehicles; NSOM; acoustic fault identification; pnn;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-3835-8

Electronic_ISBN

978-0-7695-3816-7

Type

conf

DOI

10.1109/AICI.2009.224

Filename

5375811