Fault detection and isolation in nonlinear systems with partial Reduced Kernel Principal Component Analysis method

In this article, we suggest an extension of our proposed method in fault detection called Reduced Kernel Principal Component Analysis (RKPCA) (Taouali et al., 2015) to fault isolation. To this end, a set of structured residues is generated by using a partial RKPCA model. Furthermore, each partial RKPCA model was performed on a subset of variables to generate structured residues according to a properly designed incidence matrix. The relevance of the proposed algorithm is revealed on Continuous Stirred Tank Reactor.

Download Full-text

Fault Detection and Identification in NPP Instruments Using Kernel Principal Component Analysis

18th International Conference on Nuclear Engineering: Volume 1 ◽

10.1115/icone18-29777 ◽

2010 ◽

Cited By ~ 2

Author(s):

Jianping Ma ◽

Jin Jiang

Keyword(s):

Principal Component Analysis ◽

Fault Detection ◽

Power Plants ◽

Principal Component ◽

Component Analysis ◽

Fault Isolation ◽

Kernel Principal Component Analysis ◽

Isolation And Identification ◽

Detection And Identification ◽

Fault Detection And Identification

In this paper, kernel principal component analysis (KPCA) is studied for fault detection and identification in the instruments of nuclear power plants. We propose to use mean values of the sensor reconstruction errors of a KPCA model for fault isolation and identification. They provide useful information about the directions and magnitudes of detected faults, which are usually not available from other fault isolation techniques. The performance of the method is demonstrated by applications to real NPP measurements.

Download Full-text

On the application of recursive principal component analysis method to fault detection and isolation

2015 4th International Conference on Systems and Control (ICSC) ◽

10.1109/icosc.2015.7153296 ◽

2015 ◽

Author(s):

I. Jaffel ◽

O. Taouali ◽

I. Elaissi ◽

H. Massaoud

Keyword(s):

Principal Component Analysis ◽

Fault Detection ◽

Principal Component ◽

Component Analysis ◽

Fault Detection And Isolation ◽

Analysis Method ◽

Principal Component Analysis Method

Download Full-text

Monitoring a Reverse Osmosis Process with Kernel Principal Component Analysis: A Preliminary Approach

Applied Sciences ◽

10.3390/app11146370 ◽

2021 ◽

Vol 11 (14) ◽

pp. 6370

Author(s):

Elena Quatrini ◽

Francesco Costantino ◽

David Mba ◽

Xiaochuan Li ◽

Tat-Hean Gan

Keyword(s):

Principal Component Analysis ◽

Fault Detection ◽

Water Purification ◽

Principal Component ◽

Temporal Correlation ◽

Component Analysis ◽

Kernel Principal Component Analysis ◽

Original Dataset ◽

Monitoring Process ◽

Machine Health

The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the one hand, the monitoring process reveals various discontinuities due to different characteristics of the input water. On the other hand, the monitoring process is discontinuous and random itself, thus not guaranteeing continuity of the parameters and hindering a straightforward analysis. Consequently, further research on water purification processes is paramount to identify the most suitable techniques able to guarantee good performance. Against this background, this paper proposes an application of kernel principal component analysis for fault detection in a process with the above-mentioned characteristics. Based on the temporal variability of the process, the paper suggests the use of past and future matrices as input for fault detection as an alternative to the original dataset. In this manner, the temporal correlation between process parameters and machine health is accounted for. The proposed approach confirms the possibility of obtaining very good monitoring results in the analyzed context.

Download Full-text