Pressure filtration: Bench-scale evaluation and modeling using multivariable regression and Artificial Neural Network

Gireesh S.S. Raman, Mark Stephen Klima, Jenna M. Bishop

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Pressure filtration offers the opportunity to produce solids (filter cake) that can be stacked or mixed with the coarse refuse, and water (filtrate) that can be recirculated in the plant. In this study, the bench-scale pressure filtration testing was performed to dewater coal refuse slurry, which was obtained from the thickener underflow stream of a coal preparation plant, and was being discharged into a slurry impoundment. A flexible fractional factorial design was developed to determine the effects of pressure, pH, and solids concentration on the performance of filtration, which was measured in terms of filtrate flux. The results indicated that the pH had a maximum effect on the filtrate flux followed by the pressure and solids concentration. Additionally, a linear regression model and an Artificial Neural Network (ANN) model were developed to predict the filtrate flux based on the test variables. Both models were able to fit the data well, with R2 values of 0.986 and 0.991 for the linear regression model and the ANN model respectively. It was also found that the test dataset had a mean squared error of 0.2 for the ANN model, while it was 3.99 for the regression model.

Original languageEnglish (US)
Pages (from-to)76-84
Number of pages9
JournalInternational Journal of Mineral Processing
Volume158
DOIs
StatePublished - Jan 10 2017

Fingerprint

artificial neural network
Neural networks
modeling
refuse
Fluxes
Linear regression
slurry
coal
Plant Preparations
Coal preparation
Coal
impoundment
evaluation
Water
Testing

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology
  • Geochemistry and Petrology

Cite this

@article{2a88e4fbde664d709db8a7bc9ea7bf18,
title = "Pressure filtration: Bench-scale evaluation and modeling using multivariable regression and Artificial Neural Network",
abstract = "Pressure filtration offers the opportunity to produce solids (filter cake) that can be stacked or mixed with the coarse refuse, and water (filtrate) that can be recirculated in the plant. In this study, the bench-scale pressure filtration testing was performed to dewater coal refuse slurry, which was obtained from the thickener underflow stream of a coal preparation plant, and was being discharged into a slurry impoundment. A flexible fractional factorial design was developed to determine the effects of pressure, pH, and solids concentration on the performance of filtration, which was measured in terms of filtrate flux. The results indicated that the pH had a maximum effect on the filtrate flux followed by the pressure and solids concentration. Additionally, a linear regression model and an Artificial Neural Network (ANN) model were developed to predict the filtrate flux based on the test variables. Both models were able to fit the data well, with R2 values of 0.986 and 0.991 for the linear regression model and the ANN model respectively. It was also found that the test dataset had a mean squared error of 0.2 for the ANN model, while it was 3.99 for the regression model.",
author = "Raman, {Gireesh S.S.} and Klima, {Mark Stephen} and Bishop, {Jenna M.}",
year = "2017",
month = "1",
day = "10",
doi = "10.1016/j.minpro.2016.11.020",
language = "English (US)",
volume = "158",
pages = "76--84",
journal = "International Journal of Mineral Processing",
issn = "0301-7516",
publisher = "Elsevier",

}

Pressure filtration : Bench-scale evaluation and modeling using multivariable regression and Artificial Neural Network. / Raman, Gireesh S.S.; Klima, Mark Stephen; Bishop, Jenna M.

In: International Journal of Mineral Processing, Vol. 158, 10.01.2017, p. 76-84.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pressure filtration

T2 - Bench-scale evaluation and modeling using multivariable regression and Artificial Neural Network

AU - Raman, Gireesh S.S.

AU - Klima, Mark Stephen

AU - Bishop, Jenna M.

PY - 2017/1/10

Y1 - 2017/1/10

N2 - Pressure filtration offers the opportunity to produce solids (filter cake) that can be stacked or mixed with the coarse refuse, and water (filtrate) that can be recirculated in the plant. In this study, the bench-scale pressure filtration testing was performed to dewater coal refuse slurry, which was obtained from the thickener underflow stream of a coal preparation plant, and was being discharged into a slurry impoundment. A flexible fractional factorial design was developed to determine the effects of pressure, pH, and solids concentration on the performance of filtration, which was measured in terms of filtrate flux. The results indicated that the pH had a maximum effect on the filtrate flux followed by the pressure and solids concentration. Additionally, a linear regression model and an Artificial Neural Network (ANN) model were developed to predict the filtrate flux based on the test variables. Both models were able to fit the data well, with R2 values of 0.986 and 0.991 for the linear regression model and the ANN model respectively. It was also found that the test dataset had a mean squared error of 0.2 for the ANN model, while it was 3.99 for the regression model.

AB - Pressure filtration offers the opportunity to produce solids (filter cake) that can be stacked or mixed with the coarse refuse, and water (filtrate) that can be recirculated in the plant. In this study, the bench-scale pressure filtration testing was performed to dewater coal refuse slurry, which was obtained from the thickener underflow stream of a coal preparation plant, and was being discharged into a slurry impoundment. A flexible fractional factorial design was developed to determine the effects of pressure, pH, and solids concentration on the performance of filtration, which was measured in terms of filtrate flux. The results indicated that the pH had a maximum effect on the filtrate flux followed by the pressure and solids concentration. Additionally, a linear regression model and an Artificial Neural Network (ANN) model were developed to predict the filtrate flux based on the test variables. Both models were able to fit the data well, with R2 values of 0.986 and 0.991 for the linear regression model and the ANN model respectively. It was also found that the test dataset had a mean squared error of 0.2 for the ANN model, while it was 3.99 for the regression model.

UR - http://www.scopus.com/inward/record.url?scp=85000461231&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000461231&partnerID=8YFLogxK

U2 - 10.1016/j.minpro.2016.11.020

DO - 10.1016/j.minpro.2016.11.020

M3 - Article

AN - SCOPUS:85000461231

VL - 158

SP - 76

EP - 84

JO - International Journal of Mineral Processing

JF - International Journal of Mineral Processing

SN - 0301-7516

ER -