Genetic programing and non-linear multiple regression techniques to predict backbreak in blasting operation. (January 2016)

• Record Type: Journal Article
• Authors: Shirani Faradonbeh, Roohollah; Monjezi, Masoud; Jahed Armaghani, Danial
• Is Part Of: Engineering with computers. Volume 32:Number 1(2016)
• Page Start: 123
• Page End: 133
• Publication Date: 2016-01
• Subjects: Blasting -- Backbreak -- Genetic programing -- Non-linear multiple regression; Engineering design -- Data processing -- Periodicals; Computer-aided design -- Periodicals; Conception technique -- Informatique -- Périodiques; Conception assistée par ordinateur -- Périodiques; Electronic journals; 620.00285
• DOI: 10.1007/s00366-015-0404-3
• Languages: English
• ISSNs: 0177-0667

Abstract

Abstract In addition to all benefits of blasting in mining and civil engineering applications, it has some undesirable environmental impacts. Backbreak is an unwanted phenomenon of blasting which can cause instability of mine walls, decreasing efficiency of drilling, falling down of machinery, etc. Recently, the use of new approaches such as artificial intelligence (AI) is greatly recommended by many researchers. In this paper, a new AI technique namely genetic programing (GP) was developed to predict BB. To prepare a sufficient database, 175 blasting works were investigated in Sungun copper mine, Iran. In these operations, the most influential parameters on BB including burden, spacing, stemming length, powder factor and stiffness ratio were measured and used to develop BB predictive models. To demonstrate capability of GP technique, a non-linear multiple regression (NLMR) model was also employed for prediction of BB. Value account for (VAF), root mean square error (RMSE) and coefficient of determination (R 2 ) were used to control the capacity performance of the predictive models. The performance indices obtained by GP approach indicate the higher reliability of GP compared to NLMR model. RMSE and VAF values of 0.327 and 97.655, respectively, for testing datasets of GP approach reveal the superiority of this model in predicting BB, while these values were obtained as 0.865 and 81.816, respectively, for NLMR model.