Evolutionary Random Forest Algorithm for Predicting the Maximum Failure Depth of Open Stope Hangingwalls

Chongchong Qi, Qiusong Chen

Research output: Contribution to journalArticle

Abstract

The prediction of the failure depth of open stope hangingwalls (HWs) has become a crucial task for underground mines worldwide. In this paper, an evolutionary random forest (RF) technique that combines the RF algorithm and particle swarm optimization (PSO) was proposed to model the non-linear relationship between maximum failure depth (MI-D) of stope HWs and its influencing variables. The training and verification of RF models were conducted on a dataset collected from the literature, and a total number of 125 valid HW cases were analyzed. The 13 influencing variables were used as inputs. Hyper-parameters of RF models were tuned by PSO with fivefold cross-validation, and the performance of RF models was measured by root-mean-square error and correlation coefficient (R). Experimental results show that the RF algorithm had great potential for predicting the MFD of HWs. The R values between the predicted and actual MFD values were 0.93 and 0.84, respectively. The stope design method was found to be the most significant influencing variable with an importance score of 0.516 out of 1, followed by the RQD of rock mass (0.127), stope strike (0.078), and HW height (0.075).

Original languageEnglish
Article number8528310
Pages (from-to)72808-72813
Number of pages6
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018

Cite this

@article{939ffdf68ece40c2be69f8b7adc5680e,
title = "Evolutionary Random Forest Algorithm for Predicting the Maximum Failure Depth of Open Stope Hangingwalls",
abstract = "The prediction of the failure depth of open stope hangingwalls (HWs) has become a crucial task for underground mines worldwide. In this paper, an evolutionary random forest (RF) technique that combines the RF algorithm and particle swarm optimization (PSO) was proposed to model the non-linear relationship between maximum failure depth (MI-D) of stope HWs and its influencing variables. The training and verification of RF models were conducted on a dataset collected from the literature, and a total number of 125 valid HW cases were analyzed. The 13 influencing variables were used as inputs. Hyper-parameters of RF models were tuned by PSO with fivefold cross-validation, and the performance of RF models was measured by root-mean-square error and correlation coefficient (R). Experimental results show that the RF algorithm had great potential for predicting the MFD of HWs. The R values between the predicted and actual MFD values were 0.93 and 0.84, respectively. The stope design method was found to be the most significant influencing variable with an importance score of 0.516 out of 1, followed by the RQD of rock mass (0.127), stope strike (0.078), and HW height (0.075).",
keywords = "Failure depth prediction, five-fold cross validation, open stope hangingwall, particle swarm optimization, random forest, variable importance, CEMENTED PASTE BACKFILL, DECISION TREE, STABILITY, FRAMEWORK, MACHINE, WASTE",
author = "Chongchong Qi and Qiusong Chen",
year = "2018",
doi = "10.1109/ACCESS.2018.2880009",
language = "English",
volume = "6",
pages = "72808--72813",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

Evolutionary Random Forest Algorithm for Predicting the Maximum Failure Depth of Open Stope Hangingwalls. / Qi, Chongchong; Chen, Qiusong.

In: IEEE Access, Vol. 6, 8528310, 2018, p. 72808-72813.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evolutionary Random Forest Algorithm for Predicting the Maximum Failure Depth of Open Stope Hangingwalls

AU - Qi, Chongchong

AU - Chen, Qiusong

PY - 2018

Y1 - 2018

N2 - The prediction of the failure depth of open stope hangingwalls (HWs) has become a crucial task for underground mines worldwide. In this paper, an evolutionary random forest (RF) technique that combines the RF algorithm and particle swarm optimization (PSO) was proposed to model the non-linear relationship between maximum failure depth (MI-D) of stope HWs and its influencing variables. The training and verification of RF models were conducted on a dataset collected from the literature, and a total number of 125 valid HW cases were analyzed. The 13 influencing variables were used as inputs. Hyper-parameters of RF models were tuned by PSO with fivefold cross-validation, and the performance of RF models was measured by root-mean-square error and correlation coefficient (R). Experimental results show that the RF algorithm had great potential for predicting the MFD of HWs. The R values between the predicted and actual MFD values were 0.93 and 0.84, respectively. The stope design method was found to be the most significant influencing variable with an importance score of 0.516 out of 1, followed by the RQD of rock mass (0.127), stope strike (0.078), and HW height (0.075).

AB - The prediction of the failure depth of open stope hangingwalls (HWs) has become a crucial task for underground mines worldwide. In this paper, an evolutionary random forest (RF) technique that combines the RF algorithm and particle swarm optimization (PSO) was proposed to model the non-linear relationship between maximum failure depth (MI-D) of stope HWs and its influencing variables. The training and verification of RF models were conducted on a dataset collected from the literature, and a total number of 125 valid HW cases were analyzed. The 13 influencing variables were used as inputs. Hyper-parameters of RF models were tuned by PSO with fivefold cross-validation, and the performance of RF models was measured by root-mean-square error and correlation coefficient (R). Experimental results show that the RF algorithm had great potential for predicting the MFD of HWs. The R values between the predicted and actual MFD values were 0.93 and 0.84, respectively. The stope design method was found to be the most significant influencing variable with an importance score of 0.516 out of 1, followed by the RQD of rock mass (0.127), stope strike (0.078), and HW height (0.075).

KW - Failure depth prediction

KW - five-fold cross validation

KW - open stope hangingwall

KW - particle swarm optimization

KW - random forest

KW - variable importance

KW - CEMENTED PASTE BACKFILL

KW - DECISION TREE

KW - STABILITY

KW - FRAMEWORK

KW - MACHINE

KW - WASTE

U2 - 10.1109/ACCESS.2018.2880009

DO - 10.1109/ACCESS.2018.2880009

M3 - Article

VL - 6

SP - 72808

EP - 72813

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8528310

ER -