Variogram-based fault diagnosis in an interconnected tank system

Kouadri, Abdelmalek; Aitouche, M. A.; Zelmat, M.

doi:10.1016/j.isatra.2012.01.003

Cited by 17 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first case involves the model of a continuous bioreactor system that has been considered in different dynamic modeling and control studies, e.g., for data-driven univariate dynamic modeling, Quasi-sliding model control, and the design of nonlinear observers . The second application considers the model of a three-tank system that has been commonly used as a benchmark in different monitoring, control, and fault detection and diagnosis studies. − The third case study involves the model for a shale-oil pyrolysis batch system that has been frequently addressed as an example of batch process dynamic optimization. , …”

Section: Applicationsmentioning

confidence: 99%

Dynamic Surrogate Modeling for Multistep-ahead Prediction of Multivariate Nonlinear Chemical Processes

Shokry

Baraldi

Zio

et al. 2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

This work proposes a methodology for multivariate dynamic modeling and multistep-ahead prediction of nonlinear systems using surrogate models for the application to nonlinear chemical processes. The methodology provides a systematic and robust procedure for the development of data-driven dynamic models capable of predicting the process outputs over long time horizons. It is based on using surrogate models to construct several Nonlinear AutoRegressive eXogenous models (NARX), each one approximating the future behavior of one process output as a function of the current and previous process inputs and outputs. The developed dynamic models are employed in a recursive schema to predict the process future outputs over several time steps (multistep-ahead prediction). The methodology is able to manage two different scenarios: 1) one in which a set of input-output signals collected from the process is only available for training, and 2) another in which a mathematical model of the process is available and can be used to generate specific datasets for training. With respect to the latter, the proposed methodology includes a specific procedure for the selection of training data in dynamic modeling based on Design Of Computer Experiment (DOCE) techniques. The proposed methodology is applied to case studies from the process industry presented in the literature. The results show very high prediction accuracies over long time horizons. Also, thanks to the flexibility, robustness and computational efficiency of surrogate modeling, the methodology allows dealing with a wide range of situations, which would be difficult to address using first principle models.

show abstract

Section: Applicationsmentioning

confidence: 99%

Dynamic Surrogate Modeling for Multistep-ahead Prediction of Multivariate Nonlinear Chemical Processes

Shokry

Baraldi

Zio

et al. 2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…The use of the variogram function was proposed to measure the variability of data in the two-dimensional space. Whereas autocorrelation of the variogram function provides a one-dimensional measure and an indication of how the distribution leaves normality (Kerry & Oliver, 2007; Kouadri et al, 2012), the variogram estimates the degree of spatial dependence and therefore provides an objective measure on the variability gradient of the two-dimensional weight mapping (Yupeng & Miguel, 2011; Ericeira et al, 2013).…”

Section: Artificial Neural Network and Spatial Analysismentioning

confidence: 99%

Feature evaluation and selection for condition monitoring using a self-organizing map and spatial statistics

Silva¹,

Wilcox

2018

AIEDAM

View full text Add to dashboard Cite

This paper presents a novel approach to sensor-based feature evaluation and selection using a self-organizing map and spatial statistics as a combined technique applied to tool condition monitoring of the turning process. This approach takes advantage of the unique features of unsupervised neural networks combined with spatial statistics to perform analyses into the contributions of the different sensor-based features, carrying large quantities of noise, to achieve a classification of tool wear and a quantitative measure of each feature's suitability. This method does not assume a prior direct correlation between features avoiding misconstructions inherent to common approaches that assume that only obviously correlated features should be considered for condition monitoring. Instead, and taking advantage of neural networks ability to perform non-linear modeling, it has allowed a prior modeling of the process and then analyzed each feature's contribution toward classification. It was found that some of the commonly used features have proven to have a significant contribution to the classification of cutting tool wear, whereas others adversely affect classification performance. Further, it is demonstrated that the proposed combined technique can be used extensively to quantitatively evaluate the contribution of different features toward system monitoring in the presence of noisy data.

show abstract

“…The idea of utilizing variogram for variable selection comes from the fact that a variogram of particular measurement holds the information about the relative error levels of the sampling and analysis of that measurement. Variogram is a fundamental tool within Theory of Sampling (Gy, 2004) and has already been considered in drift estimation (Paakkunainen et al, 2007), temporal uncertainty propagation (Jalbert et al, 2011), fault diagnosis (Kouadri et al, 2012), statistical process control (Minnit, Pitard, 2008), and as a process stability measure (Bisgaard, Kulachi, 2005).…”

Section: Variable Selection Using Variogrammentioning

confidence: 99%

A Variogram-Based Tool for Variable Selection in a Wastewater Treatment Effluent Prediction

Ohenoja

Tomperi

2018

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

In this study, a variogram method was utilized as a variable selection tool for finding the optimal subsets of variables for developing predictive models for the quality of wastewater treatment effluent. The quality of effluent was here assessed by biological and chemical oxygen demand and suspended solids in biologically treated wastewater. The dataset included, in addition to traditional process measurements, results of a novel optical monitoring device which was used for imaging an activated sludge process in-situ during a period of over one year. The study showed that the variogram based method has potential in fast and computationally easy variable selection. The developed models can be used for proactive monitoring and estimating the quality of effluent in several stages hours before in comparison to laboratory analysis taken from treated wastewater.

show abstract

Variogram-based fault diagnosis in an interconnected tank system

Cited by 17 publications

References 7 publications

Dynamic Surrogate Modeling for Multistep-ahead Prediction of Multivariate Nonlinear Chemical Processes

Dynamic Surrogate Modeling for Multistep-ahead Prediction of Multivariate Nonlinear Chemical Processes

Feature evaluation and selection for condition monitoring using a self-organizing map and spatial statistics

A Variogram-Based Tool for Variable Selection in a Wastewater Treatment Effluent Prediction

Contact Info

Product

Resources

About