The utility of Bayesian data reconciliation for separations

Koermer, Scott; Noble, Aaron

doi:10.1016/j.mineng.2021.106837

The utility of Bayesian data reconciliation for separations

Journal Article · Mon May 31 00:00:00 EDT 2021 · Minerals Engineering

DOI:https://doi.org/10.1016/j.mineng.2021.106837· OSTI ID:1908190

Koermer, Scott ^[1]; Noble, Aaron ^[2]

Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States); Los Alamos National Lab: CCS-6
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)

Data reconciliation methods for separation processes typically rely on classical statistical approaches to generate estimates of true mass flow rates from measurements. Knowledge regarding the uncertainty of these estimates has value in decision making, but is often not acquired. Bayesian approaches intrinsically quantify uncertainty; however, literature for Bayesian data reconciliation of separation processes is scarce. This publication outlines two Bayesian data reconciliation models and provides details for how the models were implemented for the BayesMassBal (V 1.0.0) software package written in R. To demonstrate the advantages of this approach for data reconciliation, the models were first applied to simulated data and then compared to a classical model through a Monte Carlo experiment. In this example, the Bayesian models were found to provide more accurate estimates of the simulated data, while also providing quantitative information on the estimate uncertainty. To demonstrate the use of the technique in a practical problem, the models were also applied to real data collected from a pilot-scale rare earth solvent extraction process. Here, this publication provides a small window into how Bayesian methods can be used for data reconciliation, but findings suggest Bayesian data reconciliation models for separation processes have distinct advantages over classical alternatives.

View Accepted Manuscript (DOE)

Research Organization:: West Virginia Univ., Morgantown, WV (United States)

Sponsoring Organization:: USDOE Office of Fossil Energy (FE)

Contributing Organization:: Virginia Polytechnic Inst. and State Univ. (Virginia Tech)

Grant/Contract Number:: FE0026927

OSTI ID:: 1908190

Journal Information:: Minerals Engineering, Journal Name: Minerals Engineering Vol. 169; ISSN 0892-6875

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (18)

Analytical estimator of measurement error variances in data reconciliation Keller, J. Y.; Zasadzinski, M.; Darouach, M. Computers & Chemical Engineering, Vol. 16, Issue 3 https://doi.org/10.1016/0098-1354(92)85005-S	journal	March 1992
A Bayesian approach to gross error detection in chemical process data Tamhane, Ajit C.; Iordache, Corneliu; Mah, Richard S. H. Chemometrics and Intelligent Laboratory Systems, Vol. 4, Issue 1 https://doi.org/10.1016/0169-7439(88)80011-X	journal	July 1988
Recursive bilmat algorithm: An on-line extension of data reconciliation techniques for steady-state bilinear material balance Makni, S.; Hodouin, D. Minerals Engineering, Vol. 7, Issue 9 https://doi.org/10.1016/0892-6875(94)90005-1	journal	September 1994
Making best use of model evaluations to compute sensitivity indices Saltelli, Andrea Computer Physics Communications, Vol. 145, Issue 2 https://doi.org/10.1016/S0010-4655(02)00280-1	journal	May 2002
Robust estimation of measurement error variance/covariance from process sampling data Chen, J.; Bandoni, A.; Romagnoli, J. A. Computers & Chemical Engineering, Vol. 21, Issue 6 https://doi.org/10.1016/S0098-1354(96)00295-5	journal	February 1997
Flowsheet simulation of solids processes Reimers, Claus; Werther, Joachim; Gruhn, Guenter Chemical Engineering and Processing: Process Intensification, Vol. 47, Issue 1 https://doi.org/10.1016/j.cep.2007.07.015	journal	January 2008
A general framework for data reconciliation—Part I: Linear constraints Cencic, Oliver; Frühwirth, Rudolf Computers & Chemical Engineering, Vol. 75 https://doi.org/10.1016/j.compchemeng.2014.12.004	journal	April 2015
Dynamic data reconciliation: Alternative to Kalman filter Bai, Shuanghua; Thibault, Jules; McLean, David D. Journal of Process Control, Vol. 16, Issue 5 https://doi.org/10.1016/j.jprocont.2005.08.002	journal	June 2006
Selecting proper uncertainty model for steady-state data reconciliation – Application to mineral and metal processing industries Vasebi, Amir; Poulin, Éric; Hodouin, Daniel Minerals Engineering, Vol. 65 https://doi.org/10.1016/j.mineng.2014.06.001	journal	October 2014
The Monte Carlo Method Metropolis, Nicholas; Ulam, S. Journal of the American Statistical Association, Vol. 44, Issue 247 https://doi.org/10.1080/01621459.1949.10483310	journal	September 1949
Science and Statistics Box, George E. P. Journal of the American Statistical Association, Vol. 71, Issue 356 https://doi.org/10.1080/01621459.1976.10480949	journal	December 1976
Approximate Bayesian Inference in Conditionally Independent Hierarchical Models (Parametric Empirical Bayes Models) Kass, Robert E.; Steffey, Duane Journal of the American Statistical Association, Vol. 84, Issue 407 https://doi.org/10.1080/01621459.1989.10478825	journal	September 1989
Illustration of Bayesian Inference in Normal Data Models Using Gibbs Sampling Gelfand, Alan E.; Hills, Susan E.; Racine-Poon, Amy Journal of the American Statistical Association, Vol. 85, Issue 412 https://doi.org/10.1080/01621459.1990.10474968	journal	December 1990
Blind Deconvolution via Sequential Imputations Liu, Jun S.; Chen, Rong Journal of the American Statistical Association, Vol. 90, Issue 430 https://doi.org/10.1080/01621459.1995.10476549	journal	June 1995
Bayes Factors Kass, Robert E.; Raftery, Adrian E. Journal of the American Statistical Association, Vol. 90, Issue 430 https://doi.org/10.1080/01621459.1995.10476572	journal	June 1995
Marginal Likelihood from the Gibbs Output Chib, Siddhartha Journal of the American Statistical Association, Vol. 90, Issue 432 https://doi.org/10.1080/01621459.1995.10476635	journal	December 1995
The Selection of Prior Distributions by Formal Rules Kass, Robert E.; Wasserman, Larry Journal of the American Statistical Association, Vol. 91, Issue 435 https://doi.org/10.1080/01621459.1996.10477003	journal	September 1996
Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper) Gelman, Andrew Bayesian Analysis, Vol. 1, Issue 3 https://doi.org/10.1214/06-BA117A	journal	September 2006

Similar Records

Uncertainty estimation for Bayesian reconstructions from low-count spect data

Conference · Mon Dec 30 23:00:00 EST 1996 · OSTI ID:459811

An analysis of Bayesian estimates for missing higher orders in perturbative calculations

Journal Article · Sun Sep 19 20:00:00 EDT 2021 · Journal of High Energy Physics (Online) · OSTI ID:1825077

Assessing system reliability and allocating resources: a bayesian approach that integrates multi-level data

Journal Article · Mon Dec 31 23:00:00 EST 2007 · Journal of Quality Technology · OSTI ID:960611

Related Subjects

01 COAL, LIGNITE, AND PEAT
Bayesian inference
Chemical engineering
Data reconciliation
Machine learning
Mass balance
Separation circuit

The utility of Bayesian data reconciliation for separations

Citation Formats

References (18)

Similar Records

Related Subjects