A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill

Chongchong Qi, Andy Fourie, Qiusong Chen, Qinli Zhang

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

The recycling of waste tailings as cemented paste backfill (CPB) has attracted worldwide attention because of the increasing environmental awareness during mineral resources excavation. However, lots of mechanical tests are required to understand the strength development of CPB and its prediction under the combined effect of influencing variables is almost an unexplored field. This study proposes a strength prediction model integrating boosted regression trees (BRT) and particle swarm optimization (PSO), where the BRT algorithm was used for modelling the non-linear relationship between inputs and outputs and PSO was used for the BRT hyper-parameters tuning. An extensive mechanical experiment was performed to provide the dataset for the PSO-BRT model. This dataset contained unconfined compressive strength (UCS) results of 585 CPB specimens produced with a different combination of influencing variables, including the physical and chemical characteristics of tailings, the cement-tailings ratio, the solids content, and the curing time. 10-fold cross validation was used as the validation method, and performance measures were chosen as the mean squared error and the correlation coefficient. The results show that PSO was efficient in the hyper-parameters tuning of the BRT. The optimum BRT model was very accurate at predicting CPB strength. The relative importance of influencing variables was investigated, in which the cement-tailings ratio was found to be the most significant variable for CPB strength. This research indicates that more efficient reuse of waste tailings as CPB can be achieved by reducing the required number of mechanical experiments during engineering applications.

Original languageEnglish
Pages (from-to)566-578
Number of pages13
JournalJournal of Cleaner Production
Volume183
DOIs
Publication statusPublished - 10 May 2018

Fingerprint

artificial intelligence
Tailings
backfill
tailings
Artificial intelligence
Recycling
Particle swarm optimization (PSO)
prediction
Trees (mathematics)
Cements
Tuning
cement
Mineral resources
Excavation
Compressive strength
Curing
mineral resource
compressive strength
Experiments
waste recycling

Cite this

@article{a906e7a5c4234ee497357f50db650159,
title = "A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill",
abstract = "The recycling of waste tailings as cemented paste backfill (CPB) has attracted worldwide attention because of the increasing environmental awareness during mineral resources excavation. However, lots of mechanical tests are required to understand the strength development of CPB and its prediction under the combined effect of influencing variables is almost an unexplored field. This study proposes a strength prediction model integrating boosted regression trees (BRT) and particle swarm optimization (PSO), where the BRT algorithm was used for modelling the non-linear relationship between inputs and outputs and PSO was used for the BRT hyper-parameters tuning. An extensive mechanical experiment was performed to provide the dataset for the PSO-BRT model. This dataset contained unconfined compressive strength (UCS) results of 585 CPB specimens produced with a different combination of influencing variables, including the physical and chemical characteristics of tailings, the cement-tailings ratio, the solids content, and the curing time. 10-fold cross validation was used as the validation method, and performance measures were chosen as the mean squared error and the correlation coefficient. The results show that PSO was efficient in the hyper-parameters tuning of the BRT. The optimum BRT model was very accurate at predicting CPB strength. The relative importance of influencing variables was investigated, in which the cement-tailings ratio was found to be the most significant variable for CPB strength. This research indicates that more efficient reuse of waste tailings as CPB can be achieved by reducing the required number of mechanical experiments during engineering applications.",
keywords = "Boosted regression trees, Cemented paste backfill, Particle swarm optimization, Recycling, Strength prediction, Waste tailings",
author = "Chongchong Qi and Andy Fourie and Qiusong Chen and Qinli Zhang",
year = "2018",
month = "5",
day = "10",
doi = "10.1016/j.jclepro.2018.02.154",
language = "English",
volume = "183",
pages = "566--578",
journal = "Journal of Cleaner Production",
issn = "0959-6526",
publisher = "Elsevier",

}

A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill. / Qi, Chongchong; Fourie, Andy; Chen, Qiusong; Zhang, Qinli.

In: Journal of Cleaner Production, Vol. 183, 10.05.2018, p. 566-578.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill

AU - Qi, Chongchong

AU - Fourie, Andy

AU - Chen, Qiusong

AU - Zhang, Qinli

PY - 2018/5/10

Y1 - 2018/5/10

N2 - The recycling of waste tailings as cemented paste backfill (CPB) has attracted worldwide attention because of the increasing environmental awareness during mineral resources excavation. However, lots of mechanical tests are required to understand the strength development of CPB and its prediction under the combined effect of influencing variables is almost an unexplored field. This study proposes a strength prediction model integrating boosted regression trees (BRT) and particle swarm optimization (PSO), where the BRT algorithm was used for modelling the non-linear relationship between inputs and outputs and PSO was used for the BRT hyper-parameters tuning. An extensive mechanical experiment was performed to provide the dataset for the PSO-BRT model. This dataset contained unconfined compressive strength (UCS) results of 585 CPB specimens produced with a different combination of influencing variables, including the physical and chemical characteristics of tailings, the cement-tailings ratio, the solids content, and the curing time. 10-fold cross validation was used as the validation method, and performance measures were chosen as the mean squared error and the correlation coefficient. The results show that PSO was efficient in the hyper-parameters tuning of the BRT. The optimum BRT model was very accurate at predicting CPB strength. The relative importance of influencing variables was investigated, in which the cement-tailings ratio was found to be the most significant variable for CPB strength. This research indicates that more efficient reuse of waste tailings as CPB can be achieved by reducing the required number of mechanical experiments during engineering applications.

AB - The recycling of waste tailings as cemented paste backfill (CPB) has attracted worldwide attention because of the increasing environmental awareness during mineral resources excavation. However, lots of mechanical tests are required to understand the strength development of CPB and its prediction under the combined effect of influencing variables is almost an unexplored field. This study proposes a strength prediction model integrating boosted regression trees (BRT) and particle swarm optimization (PSO), where the BRT algorithm was used for modelling the non-linear relationship between inputs and outputs and PSO was used for the BRT hyper-parameters tuning. An extensive mechanical experiment was performed to provide the dataset for the PSO-BRT model. This dataset contained unconfined compressive strength (UCS) results of 585 CPB specimens produced with a different combination of influencing variables, including the physical and chemical characteristics of tailings, the cement-tailings ratio, the solids content, and the curing time. 10-fold cross validation was used as the validation method, and performance measures were chosen as the mean squared error and the correlation coefficient. The results show that PSO was efficient in the hyper-parameters tuning of the BRT. The optimum BRT model was very accurate at predicting CPB strength. The relative importance of influencing variables was investigated, in which the cement-tailings ratio was found to be the most significant variable for CPB strength. This research indicates that more efficient reuse of waste tailings as CPB can be achieved by reducing the required number of mechanical experiments during engineering applications.

KW - Boosted regression trees

KW - Cemented paste backfill

KW - Particle swarm optimization

KW - Recycling

KW - Strength prediction

KW - Waste tailings

UR - http://www.scopus.com/inward/record.url?scp=85042729158&partnerID=8YFLogxK

U2 - 10.1016/j.jclepro.2018.02.154

DO - 10.1016/j.jclepro.2018.02.154

M3 - Article

VL - 183

SP - 566

EP - 578

JO - Journal of Cleaner Production

JF - Journal of Cleaner Production

SN - 0959-6526

ER -