A new combination of artificial neural network and K-nearest neighbors models to predict blast-induced ground vibration and air-overpressure

Amiri, Maryam; Amnieh, Hassan Bakhshandeh; Hasanipanah, Mahdi; Khanli, Leyli Mohammad

doi:10.1007/s00366-016-0442-5

Cited by 147 publications

(41 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the developed predictive models, the testing datasets are used to evaluate the performance of the models via metrics in Eqs. (4)(5)(6). Accordingly, RMSE, R 2 , and MAE are calculated on both the training and testing datasets.…”

Section: Comparison and Assessment Of The Predictive Modelsmentioning

confidence: 99%

“…However, not 100% of explosives energy was used to break rock [3]. According to previous scientists, up to 80-85% of the energy of explosives was wasted and produced ill effects, such as ground vibration (PPV), air overpressure, fly rock, dust and toxic [4][5][6][7][8]. Of these side effects, ground vibration is the most dangerous effect [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…24. In another study, [6] successfully developed the blastinduced PPV predictive model based on an artificial neural [50] investigated and studied the usability of the imperialist competitive algorithm (ICA) for predicting blast-induced PPV with two forms of equations, i.e., power and quadric. Seventy-three blasting events were collected for their aim with W, D and PPV being carefully measured.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam

Nguyen

2019

SN Appl. Sci.

View full text Add to dashboard Cite

Blast-induced ground vibration (PPV) is one of the effects of the hazard in open-pit mines. It can make vibration of the structure, instability of slope and bench, impact on underground water, and the surrounding residential. Therefore, the precise prediction of blast-induced PPV is needed to minimize undesirable effects on the surrounding environment. Also, one of the most important objectives of this study is to determine the site characteristics for the application of controlled blasting techniques. In this study, the support vector regression (SVR) approach was considered and developed for predicting blast-induced PPV in an open-pit coal mine (Vietnam) as a case study. Three forms of the equation include linear (L), polynomial (P), and radius basis function (RBF) were applied to develop the SVR models. For comparison purpose, an empirical technique was also referred to as estimate blast-induced PPV in this study on the same training dataset. A database with 181 blasting events was used for this aim. Performance indicators such as root-mean-square error (RMSE) and the coefficient of determination (R 2 ) were used to compare and evaluate the performance of the predictive models. The results showed that SVR was an effective approach for predicting blast-induced PPV in this study. Among three forms of the equation, the SVR model with RBF was the most superior model for predicting blast-induced PPV in this study with an RMSE of 0.396, R 2 of 0.924, and MAE of 0.135, whereas the empirical model only obtained performance with an RMSE of 0.856, R 2 of 0.643, and MAE of 0.575. This study provided an overview of the SVR approach in predicting blast-induced PPV. A comparison of different kernel functions for the selection of the SVR model is needed to find out the best model for predicting blast-induced PPV.

show abstract

Section: Comparison and Assessment Of The Predictive Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam

Nguyen

2019

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…The second group is uncontrollable parameters, such as rock mass parameters. Based on the literature [12][13][14][15], MC and distance between blasting-point and monitoring station (DI) are the most influential parameters on ground vibration. The ground vibration can be evaluated in terms of peak particle velocity (PPV), acceleration, frequency, and displacement [16,17].…”

Section: Introductionmentioning

confidence: 99%

Application of cuckoo search algorithm to estimate peak particle velocity in mine blasting

Fouladgar

Hasanipanah

Amnieh

2016

Engineering with Computers

Self Cite

View full text Add to dashboard Cite

“…Peak particle velocity (PPV) is the most common descriptor to evaluate -induced ground vibration and widely-used by many researchers [23,24]. In the literature, many attempts have been done to develop the empirical equations for PPV prediction [25][26][27][28][29][30][31].…”

mentioning

confidence: 99%

Prediction of blast-produced ground vibration using particle swarm optimization

Hasanipanah

Naderi

Kashir

et al. 2016

Engineering with Computers

Self Cite

124

View full text Add to dashboard Cite

work, a database including 80 data sets was collected, and the values of the maximum charge weight used per delay (W), distance between blast-point and monitoring station (D) and peak particle velocity (PPV) were measured. To develop the PSO models, PPV was used as output parameter, while W and D were used as input parameters. To check the performance of the proposed PSO models, multiple linear regression (MLR) model and United States Bureau of Mines (USBM) equation were also developed. Accuracy of models established was evaluated using statistical criteria, i.e., coefficient of correlation (R 2 ) and root mean square error (RMSE), variance absolute relative error (VARE) and Nash & Sutcliffe (NS). Finally, it was found that the PSO power form provided more accurate predictions in comparison with PSO linear form, MLR and USBM models.

show abstract

A new combination of artificial neural network and K-nearest neighbors models to predict blast-induced ground vibration and air-overpressure

Cited by 147 publications

References 37 publications

Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam

Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam

Application of cuckoo search algorithm to estimate peak particle velocity in mine blasting

Prediction of blast-produced ground vibration using particle swarm optimization

Contact Info

Product

Resources

About