论文信息 - Monitoring approach using Nonlinear Principal Component Analysis

Monitoring approach using Nonlinear Principal Component Analysis

This paper presents fault detection and diagnosis based on Neural Non Linear Principal Component Analysis (NNLPCA) and a Partial Least Square (PLS). A new process monitoring method is proposed and is applied to fault detection of a manufacturing process. The performance of the proposed approach is then illustrated and compared to those of classic LPCA.

[1] Q. Peter He,et al. A New Fault Diagnosis Method Using Fault Directions in Fisher Discriminant Analysis , 2005 .

[2] Mehmet Imregun,et al. STRUCTURAL DAMAGE DETECTION USING ARTIFICIAL NEURAL NETWORKS AND MEASURED FRF DATA REDUCED VIA PRINCIPAL COMPONENT PROJECTION , 2001 .

[3] Jie Zhang,et al. Process monitoring using non-linear statistical techniques , 1997 .

[4] Richard D. Braatz,et al. Fault Detection and Diagnosis in Industrial Systems , 2001 .

[5] Haslinda Zabiri,et al. A Principal Component Approach in Diagnosing poor Control loop performance , .

[6] Zheng Zhang,et al. 3D Representative Face and Clustering Based Illumination Estimation for Face Recognition and Expression Recognition , 2009, ISNN.

[7] M. Kramer. Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[8] O Khaled,et al. Fault detection and localization with Neural Principal Component Analysis , 2010, 18th Mediterranean Conference on Control and Automation, MED'10.

[9] Weikuan Jia,et al. PCA-Based Elman Neural Network Algorithm , 2008, ISICA.

[10] Hedi Dhouibi. UTILISATION DES RESEAUX DE PETRI A INTERVALLES POUR LA REGULATION D'UNE QUALITE : APPLICATION A UNE MANUFACTURE DE TABAC , 2005 .

[11] Ronald Eugene Shaffer,et al. Multi‐ and Megavariate Data Analysis. Principles and Applications, I. Eriksson, E. Johansson, N. Kettaneh‐Wold and S. Wold, Umetrics Academy, Umeå, 2001, ISBN 91‐973730‐1‐X, 533pp. , 2002 .