Generalized Reconstruction-Based Contributions for Output-Relevant Fault Diagnosis With Application to the Tennessee Eastman Process

Li, Gang; Alcala, Carlos F.; Qin, S. Joe; Zhou, Donghua

doi:10.1109/tcst.2010.2071415

Cited by 150 publications

(74 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If the process sample is identified as a faulty sample, i.e. ( | ) ≥ C , it can be divided into two parts [8] : = * + f , the fault free vector is * , while the fault is f = f • f .Here f is the fault magnitude and Following the concept of fault isolation through reconstruction [24][25][26] (or similarly missing variables approach [12] ), the reconstruction-based multivariate contribution (RBMVC) corresponding to a given variable…”

Section: Problem Formulationmentioning

confidence: 99%

Penalized Reconstruction-Based Multivariate Contribution Analysis for Fault Isolation

Zhang

Chen

et al. 2013

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

-Contribution analysis in multivariate statistical process monitoring (MSPM) identifies the most responsible variables to the detected process fault. In multivariate contribution analysis, the main challenge of fault isolation is to determine the appropriate variables to be analysed and this usually results in a combinatorial optimisation problem. Reconstruction-based multivariate contribution analysis (RBMCA) is a generic framework to solve this problem. This paper derives a sufficient condition for the isolatability of faulty variables when using RBMCA. In addition, a penalized RBMCA (PRBMCA) framework is developed to enhance the effectiveness and efficiency of fault isolation, especially for process faults with small magnitude. In contrast to the original RBMCA, this penalized solution includes two steps. penalized reconstruction is used in the first step to obtain a more compact set of faulty variables. Then, the original RBMCA with branch and bound algorithm is implemented to further narrow down the faulty variables. The PRBMCA framework is a generic formulation in that it is applicable to various MSPM models. The effectiveness and computational efficiency of the proposed methodology is demonstrated through a numerical example and a benchmark problem of the Tennessee Eastman process.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Penalized Reconstruction-Based Multivariate Contribution Analysis for Fault Isolation

Zhang

Chen

et al. 2013

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…B is non-condensable and must exit from the purge stream 9, increasing the purge rate x 10 . For fault 4, step change in reactor cooling water inlet temperature directly leads to abnormal variation of reactor temperature x 9 and reactor cooling water outlet temperature x 21 . It is clear that fault 6 (A feed loss) has significant influence on the flow rate of component A in stream 1 (x 1 ).…”

Section: The Tennessee Eastman Processmentioning

confidence: 99%

“…This basic contribution analysis has been improved in various studies to consider multiple process variables simultaneously [18]. Reconstruction based contribution was proposed specifically for PCA to re-calculate the variables and monitoring statistics along "faulty directions" [19,20,21]. The variables or directions are considered faulty if the reconstructed monitoring statistics are less than control limits, i.e.…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, the contribution of multiple process variables to a detected fault is evaluated by following the reconstruction and missing variable approach [14,19,20,21]. In order to find the combination of variables that are the most responsible to the fault, a combinatorial optimization problem is formulated, followed by the development of a feasible solution set and bounds to enable the application of BAB.…”

Section: Introductionmentioning

confidence: 99%

“…p( | ) h  xM , the task is to find out which variables are contributing the most to the fault. Following the concept of variable reconstruction [19,20,21] (or similarly missing variable approach [14]), the contribution of a subset of d-dimensional variables (d<n), x m , can be evaluated through the reconstructed monitoring statistic. Let the faulty data be divided as [ , ] …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reconstruction-based multivariate contribution analysis for fault isolation: A branch and bound approach

Yang

Chen

et al. 2012

Journal of Process Control

View full text Add to dashboard Cite

-Identification of faulty variables is an important component of multivariate statistical process monitoring (MSPM); it provides crucial information for further analysis of the root cause of the detected fault. The main challenge is the large number of combinations of process variables under consideration, usually resulting in a combinatorial optimization problem. This paper develops a generic reconstruction based multivariate contribution analysis (RBMCA) framework to identify the variables that are the most responsible for the fault. A branch and bound (BAB) algorithm is proposed to efficiently solve the combinatorial optimization problem. The formulation of the RBMCA does not depend on a specific model, which allows it to be applicable to any MSPM model. We demonstrate the application of the RBMCA to a specific model: the mixture of probabilistic principal component analysis (PPCA mixture) model. Finally, we illustrate the effectiveness and computational efficiency of the proposed methodology through a numerical example and the benchmark simulation of the Tennessee Eastman process.

show abstract

Adaptive control and signal processing literature survey (No. 27)

2011

Adaptive Control & Signal

View full text Add to dashboard Cite

In order to keep readers up-to-date, the journal will contain a list of recently published journal articles relevant to the fields of adaptive control and signal processing six times a year. This list is compiled from a wide range of journals. Please note that even though the list has been broadly categorized these classifications are by no means strict, and are there to assist the reader. Please also note that inclusion in the list is not an endorsement of a paper's quality. If you have any suggestions or comments, please

show abstract

Generalized Reconstruction-Based Contributions for Output-Relevant Fault Diagnosis With Application to the Tennessee Eastman Process

Cited by 150 publications

References 30 publications

Penalized Reconstruction-Based Multivariate Contribution Analysis for Fault Isolation

Penalized Reconstruction-Based Multivariate Contribution Analysis for Fault Isolation

Reconstruction-based multivariate contribution analysis for fault isolation: A branch and bound approach

Adaptive control and signal processing literature survey (No. 27)

Contact Info

Product

Resources

About