Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal

K. H.S.M. Sampath, M. S. A. Perera, P. G. Ranjith, S. K. Matthai, X. Tao, B. Wu

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

CO2 sequestration and enhanced coal bed methane (ECBM) extraction necessitate CO2 injection into coal reservoirs that affect the coal strength properties and long-term integrity of the seam. Evaluation of CO2-induced coal strength alterations is essential to minimize the reservoir damage. Advanced soft computing models have become prevalent in rock mechanics field, as they are capable of learning trends from complex data sets, preserving the experience and using it for predictions. We present two models viz. artificial neural network (ANN) and adoptive neuro-fuzzy inference system (ANFIS) to predict the strength alterations of coal, under various CO2 saturation conditions. Model performances are compared with linear and non-linear multivariate regression analyses (L-MRA and NL-MRA). We consider three effective input parameters (i.e. coal type, CO2 saturation pressure and CO2 interaction time) and one output parameter (i.e. unconfined compressive strength (UCS)) in the models. ANN consists of a three-layer feed-forward back-propagation network with a 3-5-1 architecture and ANFIS consists of [4 4 4] Gaussian type membership functions. Model results confirm that ANFIS has the highest prediction capacity followed by ANN, with R2 equal to 0.9954 and 0.9933, respectively. Both L-MRA and NL-MRA prediction performances are not satisfactory, as R2 values are only 0.7854 and 0.7821 for two models, respectively. Thus, general statistical models like MRA fail to precisely predict the complex strength alterations. From the verified models, we show that well-trained ANN and ANFIS models can successfully fit and forecast the experimental data, and are able to predict the long-term CO2 saturation effect on coal strength.

Original languageEnglish
Pages (from-to)47-60
Number of pages14
JournalMeasurement
Volume135
DOIs
Publication statusPublished - 1 Mar 2019

Keywords

  • Adaptive neuro-fuzzy inference system (ANFIS)
  • Artificial neural network (ANN)
  • CO interaction time
  • CO saturation pressure
  • Coal rank
  • Unconfined compressive strength (UCS)

Cite this

Sampath, K. H.S.M. ; Perera, M. S. A. ; Ranjith, P. G. ; Matthai, S. K. ; Tao, X. ; Wu, B. / Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal. In: Measurement. 2019 ; Vol. 135. pp. 47-60.
@article{b626becb3dfd4feca844a4dc35b80cf3,
title = "Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal",
abstract = "CO2 sequestration and enhanced coal bed methane (ECBM) extraction necessitate CO2 injection into coal reservoirs that affect the coal strength properties and long-term integrity of the seam. Evaluation of CO2-induced coal strength alterations is essential to minimize the reservoir damage. Advanced soft computing models have become prevalent in rock mechanics field, as they are capable of learning trends from complex data sets, preserving the experience and using it for predictions. We present two models viz. artificial neural network (ANN) and adoptive neuro-fuzzy inference system (ANFIS) to predict the strength alterations of coal, under various CO2 saturation conditions. Model performances are compared with linear and non-linear multivariate regression analyses (L-MRA and NL-MRA). We consider three effective input parameters (i.e. coal type, CO2 saturation pressure and CO2 interaction time) and one output parameter (i.e. unconfined compressive strength (UCS)) in the models. ANN consists of a three-layer feed-forward back-propagation network with a 3-5-1 architecture and ANFIS consists of [4 4 4] Gaussian type membership functions. Model results confirm that ANFIS has the highest prediction capacity followed by ANN, with R2 equal to 0.9954 and 0.9933, respectively. Both L-MRA and NL-MRA prediction performances are not satisfactory, as R2 values are only 0.7854 and 0.7821 for two models, respectively. Thus, general statistical models like MRA fail to precisely predict the complex strength alterations. From the verified models, we show that well-trained ANN and ANFIS models can successfully fit and forecast the experimental data, and are able to predict the long-term CO2 saturation effect on coal strength.",
keywords = "Adaptive neuro-fuzzy inference system (ANFIS), Artificial neural network (ANN), CO interaction time, CO saturation pressure, Coal rank, Unconfined compressive strength (UCS)",
author = "Sampath, {K. H.S.M.} and Perera, {M. S. A.} and Ranjith, {P. G.} and Matthai, {S. K.} and X. Tao and B. Wu",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.measurement.2018.11.031",
language = "English",
volume = "135",
pages = "47--60",
journal = "Measurement",
issn = "0263-2241",
publisher = "Elsevier",

}

Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal. / Sampath, K. H.S.M.; Perera, M. S. A.; Ranjith, P. G.; Matthai, S. K.; Tao, X.; Wu, B.

In: Measurement, Vol. 135, 01.03.2019, p. 47-60.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal

AU - Sampath, K. H.S.M.

AU - Perera, M. S. A.

AU - Ranjith, P. G.

AU - Matthai, S. K.

AU - Tao, X.

AU - Wu, B.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - CO2 sequestration and enhanced coal bed methane (ECBM) extraction necessitate CO2 injection into coal reservoirs that affect the coal strength properties and long-term integrity of the seam. Evaluation of CO2-induced coal strength alterations is essential to minimize the reservoir damage. Advanced soft computing models have become prevalent in rock mechanics field, as they are capable of learning trends from complex data sets, preserving the experience and using it for predictions. We present two models viz. artificial neural network (ANN) and adoptive neuro-fuzzy inference system (ANFIS) to predict the strength alterations of coal, under various CO2 saturation conditions. Model performances are compared with linear and non-linear multivariate regression analyses (L-MRA and NL-MRA). We consider three effective input parameters (i.e. coal type, CO2 saturation pressure and CO2 interaction time) and one output parameter (i.e. unconfined compressive strength (UCS)) in the models. ANN consists of a three-layer feed-forward back-propagation network with a 3-5-1 architecture and ANFIS consists of [4 4 4] Gaussian type membership functions. Model results confirm that ANFIS has the highest prediction capacity followed by ANN, with R2 equal to 0.9954 and 0.9933, respectively. Both L-MRA and NL-MRA prediction performances are not satisfactory, as R2 values are only 0.7854 and 0.7821 for two models, respectively. Thus, general statistical models like MRA fail to precisely predict the complex strength alterations. From the verified models, we show that well-trained ANN and ANFIS models can successfully fit and forecast the experimental data, and are able to predict the long-term CO2 saturation effect on coal strength.

AB - CO2 sequestration and enhanced coal bed methane (ECBM) extraction necessitate CO2 injection into coal reservoirs that affect the coal strength properties and long-term integrity of the seam. Evaluation of CO2-induced coal strength alterations is essential to minimize the reservoir damage. Advanced soft computing models have become prevalent in rock mechanics field, as they are capable of learning trends from complex data sets, preserving the experience and using it for predictions. We present two models viz. artificial neural network (ANN) and adoptive neuro-fuzzy inference system (ANFIS) to predict the strength alterations of coal, under various CO2 saturation conditions. Model performances are compared with linear and non-linear multivariate regression analyses (L-MRA and NL-MRA). We consider three effective input parameters (i.e. coal type, CO2 saturation pressure and CO2 interaction time) and one output parameter (i.e. unconfined compressive strength (UCS)) in the models. ANN consists of a three-layer feed-forward back-propagation network with a 3-5-1 architecture and ANFIS consists of [4 4 4] Gaussian type membership functions. Model results confirm that ANFIS has the highest prediction capacity followed by ANN, with R2 equal to 0.9954 and 0.9933, respectively. Both L-MRA and NL-MRA prediction performances are not satisfactory, as R2 values are only 0.7854 and 0.7821 for two models, respectively. Thus, general statistical models like MRA fail to precisely predict the complex strength alterations. From the verified models, we show that well-trained ANN and ANFIS models can successfully fit and forecast the experimental data, and are able to predict the long-term CO2 saturation effect on coal strength.

KW - Adaptive neuro-fuzzy inference system (ANFIS)

KW - Artificial neural network (ANN)

KW - CO interaction time

KW - CO saturation pressure

KW - Coal rank

KW - Unconfined compressive strength (UCS)

UR - http://www.scopus.com/inward/record.url?scp=85056737481&partnerID=8YFLogxK

U2 - 10.1016/j.measurement.2018.11.031

DO - 10.1016/j.measurement.2018.11.031

M3 - Article

VL - 135

SP - 47

EP - 60

JO - Measurement

JF - Measurement

SN - 0263-2241

ER -