A new intelligent diagnostic method for machine maintenance

Authors:
Qianjin Guo;Haibin Yu;Aidong Xu
Affiliations:
Shenyang Inst. of Automation, Chinese Academy of Sciences, Shenyang, Liaoning, China;Shenyang Inst. of Automation, Chinese Academy of Sciences, Shenyang, Liaoning, China;Shenyang Inst. of Automation, Chinese Academy of Sciences, Shenyang, Liaoning, China
Venue:
ICMLC'05 Proceedings of the 4th international conference on Advances in Machine Learning and Cybernetics
Year:
2005

Citing 5
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence

Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
NN-driven fuzzy reasoning

International Journal of Approximate Reasoning
Universal approximations of continuous fuzzy-valued functions by multi-layer fuzzy neural networks

Fuzzy Sets and Systems
Fuzzy wavelet networks for function learning

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fuzzy neural networks display good capacity for self-adaptation and self-learning, and wavelet transformation or analysis reveals time frequency location characteristics and a multi-scale ability. Inspired by these advantages, a new intelligent diagnostic method for machine maintenance, wavelet fuzzy neural network (WFNN), is proposed in this paper. This new intelligent diagnostic method uses wavelet basis function as a membership function whose shape can be adjusted on line so that the networks have better learning and adaptive ability. An on-line learning algorithm is applied to automatically construct the wavelet fuzzy neural network. There are no rules initially in the wavelet fuzzy neural network, they are created and adapted as on-line learning proceeds via simultaneous structure and parameter learning. The advantages of this learning algorithm are that it converges quickly and the obtained fuzzy rules are more precise. The results of simulation show that this new intelligent diagnostic method has the advantages of a faster learning rate and higher diagnostic precision.