A Hybrid KPCA-PNN Approach to Condenser Fault Diagnosis with a Particle Swarm Optimizer

Xiao Xia Wang

doi:10.4028/www.scientific.net/AMR.108-111.476

Paper Titles

Road Traffic Accident Management Information System Research Based on C/S Structure
p.452

Traffic Evacuation Analysis for Explosion and Burning Radius of CNG Station
p.458

Frame Coding Complexity Prediction in H.264/AVC Rate Control
p.464

Design of a Novel High Performance Digital Fault Recorder
p.470

A Hybrid KPCA-PNN Approach to Condenser Fault Diagnosis with a Particle Swarm Optimizer
p.476

H_∞ Control of Fuzzy Neutral Systems under Sampled-Data Control
p.482

Optimization Model of Loan Portfolio Based on Mean Chance
p.488

A Study on the Flow Behavior of 42CrMo Steel under Hot Compression by Thermal Physical Simulations
p.494

Fast Computing Scheme for AGV Obstacle Distance Measure and Road Recognition
p.500

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 108-111A Hybrid KPCA-PNN Approach to Condenser Fault...

A Hybrid KPCA-PNN Approach to Condenser Fault Diagnosis with a Particle Swarm Optimizer

Abstract:

Diagnosis of condenser abnormality is very important for turbine generator reliability. This paper presents a novel approach for condenser fault diagnosis based on kernel principle component analysis (KPCA) and probabilistic neural network (PNN). KPCA is applied to PNN for feature extraction. It firstly maps data from the original input space into high dimensional feature space via nonlinear kernel function and then extract optimal feature vector as the inputs of PNN to solve condenser fault classification problems. A global optimizer, particle swarm optimizer (PSO), is employed to optimize the parameters of PNN to improve fault classification accuracy. The experimental results show that the proposed approach has a better ability in terms of diagnosis accuracy and computational efficiency compared with a number of popular fault diagnosis techniques.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 108-111)

Pages:

476-481

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.108-111.476

Citation:

Cite this paper

Online since:

May 2010

Authors:

Xiao Xia Wang

Keywords:

Condenser, Fault Diagnosis, Kernel Principle Component Analysis, Particle Swarm Optimization Algorithm (PSO), Probabilistic Neural Network (PNN)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] P.H. Wang, Y.N. Zhu, J.Y. Jia, et al: Proceedings of the CSEE, Vol. 19 (1999), pp.46-49.

Google Scholar

[2] L.Y. Ma, B.S. Wang, Z.S. Tong, et al: Proceedings of the CSEE, Vol. 21 (2001), pp.68-73.

Google Scholar

[3] J.H. Zhang, G.L. Hou, W. Zhang, et al: Proceedings of the CSEE, Vol. 24 (2004), pp.205-209.

Google Scholar

[4] G.L. Hou, X.G. Sun, J.H. Zhang, et al: Proceedings of the CSEE, Vol. 25 (2005), pp.104-108.

Google Scholar

[5] X. Zhang, W.W. Yan, X. Zhao, et al: Journal of Southeast University, Vol. 23 (2007), pp.51-56.

Google Scholar

[6] B. Scholkopf, A. Smola, K.R. Muller: Neural Computation, Vol. 10 (1998), pp.1299-1319.

Google Scholar

[7] D. F. Specht: Neural Networks, Vol. 3 (1990), pp.109-118.

Google Scholar

[8] D. F. Specht and H. Romsdahl: Proceedings of the IEEE International Conference on Neural Networks, Vol. 2 (1994), pp.1203-1208.

Google Scholar

[9] J. Kennedy and R. C. Eberhart: Proceedings of the IEEE International Conference on Neural Networks, Vol. 4 (1995), p.1942-(1948).

Google Scholar

[10] J. Kennedy and R.C. Eberhart: Swarm Intelligence (Morgan Kaufmann, USA 2001).

Google Scholar