Prediction of flyrock throw distance in quarries by variable selection procedures and ANFIS modelling technique

This study suggests application of variable reduction procedures for flyrock prediction. It was aimed to create robust and non-complex predictive models. Eleven operational blast parameters and rock mass properties were measured in an aggregate quarry. Dominant parameters for flyrock occurrence were determined by multivariate statistical methods. Two parallel ANFIS models were developed for flyrock prediction. The first ANFIS model was constructed based on the results of stepwise regression. Burden-hole diameter ratio, in-situ block size and specific charge are the input parameters of ANFIS 1. The second ANFIS model was created based on the results obtained by factor analysis. Burden-hole diameter ratio, bench height- burden ratio, number of holes and charge weight are used as input parameters for ANFIS 2. The calculated mean absolute percentage errors are lower than eight percent for the ANFIS predictions. The median absolute errors are lower than 5 meters. The study also investigates alternative accuracy measures to evaluate forecasting performance. Standardized errors, normalized errors and Nash–Sutcliffe Efficiency (NSE) were found to be useful for model validation. It is concluded that more than a single model can be created for a specific site. Pre-statistical analysis for variable reduction increases performance of the predictive models. Burden appeared to be a significant parameter for flyrock throw.

PEMBUATAN APLIKASI DENGAN MENGGUNAKAN RUMUS EMPIRIS UNTUK MEMPREDIKSI LEMPARAN BATU (FLYING ROCK) DARI KEGIATAN PELEDAKAN

Salah satu dampak lingkungan yang disebabkan dari kegiatan peledakan yaitu adanya flyrock. Flyrock merupakan fragmentasi batuan (ukuran bongkahan batuan) yang terlempar akibat hasil peledakan. Fragmentasi batuan ini jika terlempar melebihi batas radius aman dapat mengakibatkan kerusakan untuk alat mekanis dan dapat mengakibatkan cidera untuk manusia. Salah satu pendekatan yang efektif untuk mengontrol dan mencegah kecelakaan akibat flyrock adalah prediksi lemparan flyrock.Metode yang digunakan dalam perhitungan prediksi lemparan flyrock pada penelitian kali ini adalah dengan menggunakan pendekatan teori empris dari Richard and moore, Lundburg, Swedish model dan American model. Untuk menunjang dalam kecepatan perhitungan prediksi lemparan flyrock, maka dibuatlah program aplikasi perhitungan prediksi flyrock yang berbasis visual basic access. Berdasarkan perbandingan hasil perhitungan aplikasi dengan hasil lemparan flyrock aktual di lapangan didapatkan persentase error sebesar 14.58% untuk face burst, 26.49% untuk cratering, 58.76% untuk lundburg, 35.05% untuk Swedish model, 26.39% untuk American model. Keunggulan dari adanya aplikasi komputasi ini yaitu kemudahan dalam pengoperasian program yang secara garis besar hanya menginput parameter geometri peledakan sesuai teori, dan melakukan eksekusi program akan menunjang efisiensi waktu dan tenaga, serta keakuratan hasil perhitungannya akan lebih tinggi dibandingkan dengan melakukan perhitungan secara manual. Namun aplikasi yang dibuat ini masih memiliki keterbatasan fitur rangkaian interface/menu aplikasi dan aplikasi belum dapat melakukan pencetakan hasil dari output program. Kata-kata kunci: Flyrock Prediction, visual basic, Persamaan empirik, komputasi

Regression and Fitting Analysis of Flyrock Prediction Formulae for Loosening Blasting

With so many complex influence factors of blasting flyrock, there is no critical formula for prediction the flying distance of blasting flyrock which was adapted by most of the scholars. Widely existing influential prediction formulas are mainly aimed at ordinary blasting technology, using the statistical law or mechanics analysis to get the prediction. The calculated data for flyrock distance are different distinctly. Predictive values are different largely between various formulas. Moreover, when loose blasting, the values predicted by those formulas will be larger than the actual data. This situation wastes lots of human and financial resources for blasting alert. In view of the present situation, the field experiment of loosening blasting was carried and the impacts of blasting parameters to the flyrock distance in loosening blasting were considered respectively. Some blasting parameters were regressed to get a prediction formula. The correlation analysis indicates that the formula for loosening blasting is good for flying distance.