Advances in Data-Driven Monitoring Methods for Complex Process

Chen, Ru Qing

doi:10.4028/www.scientific.net/amm.423-426.2448

Cited by 2 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, multivariate monitoring techniques such as the Principal Component Analysis (PCA) (Isermann, 2006) or the Partial Least Squares (PLS) can take into account the correlation between the different variables measured in the process, and they show advantages against the traditional univariate methods (Odiowei & Cao, 2009). However, there is a need for more effective techniques that can deal with problems like changing operational conditions or nonlinear systems (Odiowei & Cao, 2009;Yang, Chen, Chen & Liu, 2012;Chen, 2013). Ku, Storer, and Georgakis (1995) proposed the use of lagged variables to take into account time correlation to extend PCA to dynamic system monitoring (DPCA).…”

Section: Introductionmentioning

confidence: 99%

Statistical process monitoring of a multiphase flow facility

Ruiz-Cárcel

Cao

Lao

et al. 2015

Control Engineering Practice

217

View full text Add to dashboard Cite

a b s t r a c tIndustrial needs are evolving fast towards more flexible manufacture schemes. As a consequence, it is often required to adapt the plant production to the demand, which can be volatile depending on the application. This is why it is important to develop tools that can monitor the condition of the process working under varying operational conditions. Canonical Variate Analysis (CVA) is a multivariate data driven methodology which has been demonstrated to be superior to other methods, particularly under dynamically changing operational conditions. These comparative studies normally use computer simulated data in benchmark case studies such as the Tennessee Eastman Process Plant (Ricker, N.L. Tennessee Eastman Challenge Archive, Available at 〈http://depts.washington.edu/control/LARRY/TE/down load.html〉 Accessed 21.03.2014).The aim of this work is to provide a benchmark case to demonstrate the ability of different monitoring techniques to detect and diagnose artificially seeded faults in an industrial scale multiphase flow experimental rig. The changing operational conditions, the size and complexity of the test rig make this case study an ideal candidate for a benchmark case that provides a test bed for the evaluation of novel multivariate process monitoring techniques performance using real experimental data. In this paper, the capabilities of CVA to detect and diagnose faults in a real system working under changing operating conditions are assessed and compared with other methodologies. The results obtained demonstrate that CVA can be effectively applied for the detection and diagnosis of faults in real complex systems, and reinforce the idea that the performance of CVA is superior to other algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Statistical process monitoring of a multiphase flow facility

Ruiz-Cárcel

Cao

Lao

et al. 2015

Control Engineering Practice

217

View full text Add to dashboard Cite

show abstract

Canonical variate analysis for performance degradation under faulty conditions

Ruiz-Cárcel

Lao

Cao

et al. 2016

Control Engineering Practice

View full text Add to dashboard Cite

Condition monitoring of industrial processes can minimize maintenance and operating costs while increasing the process safety and enhancing the quality of the product. In order to achieve these goals it is necessary not only to detect and diagnose process faults, but also to react to them by scheduling the maintenance and production according to the condition of the process.The objective of this investigation is to test the capabilities of canonical variate analysis (CVA) to estimate performance degradation and predict the behaviour of a system affected by faults. Process data was acquired from a large-scale experimental multiphase flow facility operated under changing operational conditions where process faults were seeded. The results suggest that CVA can be used effectively to evaluate how faults affect the process variables in comparison to normal operation. The method also predicted future process behaviour after the appearance of faults, modelling the system using data collected during the early stages of degradation.

show abstract

Advances in Data-Driven Monitoring Methods for Complex Process

Cited by 2 publications

References 17 publications

Statistical process monitoring of a multiphase flow facility

Statistical process monitoring of a multiphase flow facility

Canonical variate analysis for performance degradation under faulty conditions

Contact Info

Product

Resources

About