Extracting nonstationary features for process data analytics and application in fouling detection

Kwak, Seraphina; Ma, Yanjun; Huang, Biao

doi:10.1016/j.compchemeng.2020.106762

Cited by 12 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The more advanced methods use a model to predict clean conditions or subtract variations caused by changes in operation, i. e. variations not caused by fouling. These models can either be physical, based on knowledge of the system (white box), or data-driven (black box) (Kwak et al 2020). The latter have gained especial attention in the past years due to the large interest in machine learning (e. g. neural network models), but also thanks to progress in the field of statistics (e. g. canonical correlation analysis and co-integration analysis), often in combination with methods from control systems engineering (e. g. Kalman filtering and fuzzy logic) (Chen et al 2016, Garcia 2012, Kwak et al 2020, Lalot and Lecoeuche 2003.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of sodium salt scaling in black liquor evaporators using existing process data

Karlsson

2020

Nordic Pulp &Amp; Paper Research Journal

View full text Add to dashboard Cite

Scaling caused by sodium carbonate and sodium sulphate salts is a common problem during black liquor evaporation and mills currently have no proper tools to monitor or follow it up. The method proposed enables automatic evaluation of scaling rates and behaviours, together with washing performance, by using measurements that are already available at most mills, such as the boiling point elevation and the overall heat transfer coefficient. The method identified the scaling correctly in most cases, normally >90 %, although fast and sudden scaling proved to be challenging; its performance was also dependent on the quality of the data used. Historical data from three mills was evaluated and it was found that the scaling rate generally increased at higher concentrations of black liquor: one of the mills had almost no scaling below 70 % dry solids content. Another mill, however, deviated from this trend and had significant problems with fast and sudden scaling in one effect at around 60 % dry solids content. The correlation of process parameters revealed that this scaling was triggered, to a large extent, by the absence of tall oil brine, which is a side stream from the production of tall oil that is normally fed to the evaporators.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation of sodium salt scaling in black liquor evaporators using existing process data

Karlsson

2020

Nordic Pulp &Amp; Paper Research Journal

View full text Add to dashboard Cite

show abstract

“…In SPA, statistical measures of process variables (mean, variance, autocorrelation, cross-correlation, among others) are selected as input variables for the modeling techniques (typically, PCA), which in many cases improves detection and diagnosis performance. Recent research on variable selection includes: the application of a criteria based on mutual information for variable selection [575]; an efficient technique based on sequential analysis of fault contributions [576]; a technique to extract non-stationary variables and its application to fouling detection [577]; the integration of variable selection methods with moving window techniques for multimodal monitoring, achieving good results on a particularly challenging fault in the TEP benchmark [578]; a comparison of shallow and deep learning methods for selecting variables in an industrial test platform focused on big data and Internet of Things concepts [579]; and the application of causality-based methods for feature selection in the TEP benchmark and in an oil platform fiscal metering plant [580]. Peres and Fogliatto [4] published a review on this subject, highlighting that the most used methods are LASSO regression, the genetic algorithm and regression by direct selection (forward selection).…”

Section: Exploration Characterization and Treatment Of Process Datamentioning

confidence: 99%

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

Melo,

Câmara,

Pinto

2024

Processes

View full text Add to dashboard Cite

This paper presents a comprehensive review of the historical development, the current state of the art, and prospects of data-driven approaches for industrial process monitoring. The subject covers a vast and diverse range of works, which are compiled and critically evaluated based on the different perspectives they provide. Data-driven modeling techniques are surveyed and categorized into two main groups: multivariate statistics and machine learning. Representative models, namely principal component analysis, partial least squares and artificial neural networks, are detailed in a didactic manner. Topics not typically covered by other reviews, such as process data exploration and treatment, software and benchmarks availability, and real-world industrial implementations, are thoroughly analyzed. Finally, future research perspectives are discussed, covering aspects related to system performance, the significance and usefulness of the approaches, and the development environment. This work aims to be a reference for practitioners and researchers navigating the extensive literature on data-driven industrial process monitoring.

show abstract

“…In addition to dynamic characteristics, certain process variables display nonstationary trends due to various other factors, such as equipment aging, catalyst consumption, and different operating modes [121]. The means and variances of process measurements are time-varying, which challenges the assumption that the measured processes of traditional multivariate statistical methods are stationary [122].…”

Section: Nonstationary Process Monitoringmentioning

confidence: 99%

A Review on Data-Driven Process Monitoring Methods: Characterization and Mining of Industrial Data

Sun

2022

Processes

View full text Add to dashboard Cite

Safe and stable operation plays an important role in the chemical industry. Fault detection and diagnosis (FDD) make it possible to identify abnormal process deviations early and assist operators in taking proper action against fault propagation. After decades of development, data-driven process monitoring technologies have gradually attracted attention from process industries. Although many promising FDD methods have been proposed from both academia and industry, challenges remain due to the complex characteristics of industrial data. In this work, classical and recent research on data-driven process monitoring methods is reviewed from the perspective of characterizing and mining industrial data. The implementation framework of data-driven process monitoring methods is first introduced. State of art of process monitoring methods corresponding to common industrial data characteristics are then reviewed. Finally, the challenges and possible solutions for actual industrial applications are discussed.

show abstract

Extracting nonstationary features for process data analytics and application in fouling detection

Cited by 12 publications

References 26 publications

Evaluation of sodium salt scaling in black liquor evaporators using existing process data

Evaluation of sodium salt scaling in black liquor evaporators using existing process data

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

A Review on Data-Driven Process Monitoring Methods: Characterization and Mining of Industrial Data

Contact Info

Product

Resources

About