Statistical Fault Detection of Chemical Process - Comparative Studies

Mansouri, Majdi; Zs, Mohammed; Baklouti, Raoudha; Nounou, Mohamed; Nounou, Hazem; Hamida, Ahmed Ben

doi:10.4172/2157-7048.1000282

Cited by 17 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA and PLS have been extended to handle nonlinear data by utilizing kernels to transform the data to a higher dimensional space, where linear relationships between variables can be drawn. The extensions kernel principal component analysis (KPCA) and kernel partial least squares (KPLS) have both shown improved performance over the conventional PCA and PLS techniques when handling nonlinear data [5,13]. T 2 and Q charts are commonly used as fault detection statistics.…”

Section: Fault Diagnosis and Detectionmentioning

confidence: 99%

“…In our previous works [5,13,15], we addressed the problem of fault detection using linear and nonlinear input models (PCA and kernel PCA) and input-output model (PLS and kernel PLS)-based generalized likelihood ratio test (GLRT), in which PCA, kernel PCA, PLS, and kernel PLS methods are used for modeling and the univariate GLRT chart is used for fault detection.…”

Section: Fault Diagnosis and Detectionmentioning

confidence: 99%

“…A few popular techniques are cumulative percent variance (CPV) [13], scree plot and profile likelihood [18], and cross validation [19]. CPV is commonly utilized due to its computational simplicity and because it provides a good estimate of the number of principal components that need to be retained for most practical applications.…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

“…CPV is commonly utilized due to its computational simplicity and because it provides a good estimate of the number of principal components that need to be retained for most practical applications. CPV can be computed as follows [13]:…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

“…Once the number of principal components to retain is determined, the input data matrix can then be expressed as [13]:…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

See 4 more Smart Citations

Process Monitoring Using Data-Based Fault Detection Techniques: Comparative Studies

Sheriff¹,

Botre²,

Mansouri³

et al. 2017

Fault Diagnosis and Detection

Self Cite

View full text Add to dashboard Cite

Data based monitoring methods are often utilized to carry out fault detection (FD) when process models may not necessarily be available. The partial least square (PLS) and principle component analysis (PCA) are two basic types of multivariate FD methods, however, both of them can only be used to monitor linear processes. Among these extended data based methods, the kernel PCA (KPCA) and kernel PLS (KPLS) are the most well-known and widely adopted. KPCA and KPLS models have several advantages, since, they do not require nonlinear optimization, and only the solution of an eigenvalue problem is required. Also, they provide a better understanding of what kind of nonlinear features are extracted: the number of the principal components (PCs) in a feature space is fixed a priori by selecting the appropriate kernel function. Therefore, the objective of this work is to use KPCA and KPLS techniques to monitor nonlinear data. The improved FD performance of KPCA and KPLS is illustrated through two simulated examples, one using synthetic data and the other using simulated continuously stirred tank reactor (CSTR) data. The results demonstrate that both KPCA and KPLS methods are able to provide better detection compared to the linear versions.

show abstract

Section: Fault Diagnosis and Detectionmentioning

confidence: 99%

Section: Fault Diagnosis and Detectionmentioning

confidence: 99%

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

“…Once the number of principal components to retain is determined, the input data matrix can then be expressed as [13]:…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

See 3 more Smart Citations

Process Monitoring Using Data-Based Fault Detection Techniques: Comparative Studies

Sheriff¹,

Botre²,

Mansouri³

et al. 2017

Fault Diagnosis and Detection

Self Cite

View full text Add to dashboard Cite

show abstract

Detectability‐based controller design screening for processes under multiplicative cyberattacks

2021

View full text Add to dashboard Cite

Cyberattacks on process control systems (PCSs) may target communication links, compromising the data integrity. Cyberattack detection and mitigation are essential capabilities, as the consequences of a successful cyberattack on a PCS may be severe. While detectability may be viewed as a systems‐theoretic property, cyberattack detection in practice depends on the attack detection scheme used and the PCS design. This paper presents an approach for control parameter screening based on the detectability of sensor‐controller communication link multiplicative attacks. First, a residual set‐based condition for the undetectability of an attack is developed. A controller screening methodology aimed at identifying controller parameter choices that mask the detectability of an attack is presented. The proposed methodology can be used to incorporate the detectability of an attack as a criterion into conventional control design criteria (e.g., closed‐loop stability and economic considerations). Finally, the application of the controller screening methodology is demonstrated using two illustrative examples.

show abstract

Model‐based and data‐driven with multiscale sum of squares double EWMA control chart for fault detection in biological systems

Mansouri

Harkat

Teh

et al. 2018

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

The objectives of this paper will be sought. First, an enhanced technique that can accurately model biological processes will be developed. To deal with scenarios where a process model is available, the particle filter method will be developed to better handle the nonlinear and high-dimensional state estimation problem.Second, a multiscale sum of squares double exponentially weighted moving average (MS-SS-DEWMA) chart will be applied to the monitored residuals in order to enhance the fault detection abilities. The advantage of MS-SS-DEWMA chart is twofold: (1) The SS-DEWMA chart uses the sum of squares statistics; it simultaneously monitors the process mean and variance in a single chart. It has presented better performance than the classical EWMA-based charts.(2) The multiscale data representation can be used as an effective tool for reducing noise from a signal's time series. The effectiveness of the proposed strategy is validated using a synthetic and simulated Cad system in Escherichia coli (CSEC) data.When the simulated CSEC model is used, the developed approach is applied for monitoring some of the key variables involved in the CSEC model. The proposed strategy is also applied to detect diseases using genomic copy number data through better detection of aberrations in the genetic information of patients, which can help medical doctors make more accurate diagnosis of diseases.

show abstract

Statistical Fault Detection of Chemical Process - Comparative Studies

Cited by 17 publications

References 36 publications

Process Monitoring Using Data-Based Fault Detection Techniques: Comparative Studies

Process Monitoring Using Data-Based Fault Detection Techniques: Comparative Studies

Detectability‐based controller design screening for processes under multiplicative cyberattacks

Model‐based and data‐driven with multiscale sum of squares double EWMA control chart for fault detection in biological systems

Contact Info

Product

Resources

About