Estimation of air-overpressure produced by blasting operation through a neuro-genetic technique

Blasting operations usually produce significant environmental problems which may cause severe damage to the nearby areas. Air-overpressure (AOp) is one of the most important environmental impacts of blasting operations which needs to be predicted and subsequently controlled to minimize the potential risk of damage. In order to solve AOp problem in Hulu Langat granite quarry site, Malaysia, three non-linear methods namely empirical, artificial neural network (ANN) and a hybrid model of genetic algorithm (GA)–ANN were developed in this study. To do this, 76 blasting operations were investigated and relevant blasting parameters were measured in the site. The most influential parameters on AOp namely maximum charge per delay and the distance from the blast-face were considered as model inputs or predictors. Using the five randomly selected datasets and considering the modeling procedure of each method, 15 models were constructed for all predictive techniques. Several performance indices including coefficient of determination (R ²), root mean square error and variance account for were utilized to check the performance capacity of the predictive methods. Considering these performance indices and using simple ranking method, the best models for AOp prediction were selected. It was found that the GA–ANN technique can provide higher performance capacity in predicting AOp compared to other predictive methods. This is due to the fact that the GA–ANN model can optimize the weights and biases of the network connection for training by ANN. In this study, GA–ANN is introduced as superior model for solving AOp problem in Hulu Langat site.     

Evaluation of different methods of merging SPOT MLA and PLA data for urban landuse mapping

The present study evaluates four methods of merging SPOT MLA and PLA data; namely Determinant analysis, Principal Component analysis, Hue-Saturation-Intensity (HSI) analysis and Filtering analysis. The test area is 5 km × 5 km window over Jodhpur city and its environs. SPOT MLA and PLA data acquired within one week in Nov. 1990 were used in the analysis. The results were evaluated using both visual and statistical comparison amongst the outputs. Filtering analysis produced the best results both from visual and statistical point of view and determinant analysis ranked closely second. Comparatively HSI method distorted the spectral characteristics more but visually the output was better than that of PC. The results are applicable for urban landuse mapping and need to be tested for other themes as well.     

Effect of Geological Structure on Flyrock Prediction in Construction Blasting

Blasting is sometimes inevitable in civil engineering work, to fragment the massive rock to enable excavation and leveling. In Minyak Beku, Batu Pahat also, blasting is implemented to fragment the rock mass, to reduce the in situ rock level to the required platform for a building construction. However, during blasting work, some rocks get an excessive amount of explosive energy and this energy may generate flyrock. An accident occurred on 15 July 2015 due to this phenomenon, in which one of the workers was killed and two other workers were seriously injured after being hit by the flyrock. The purpose of this study is to investigate the causes of the flyrock accidents through evaluation of rock mass geological structures. The discontinuities present on the rock face were analyzed, to study how they affected the projection and direction of the flyrock. Rock faces with lower mean joint spacing and larger apertures caused excessive flyrock. Based on the steoreonet analysis, it was found that slope failures also produced a significant effect on the direction, if the rock face failure lay in the critical zone area. Empirical models are often used to predict flyrock projection. In this study five empirical models are used to compare the incidents. It was found that none of the existing formulas could accurately predict flyrock distance. Analysis shows that the gap between predicted and actual flyrock can be reduced by including blast deign and geological conditions in forecasts. Analysis revealed only 69% of accuracy could be achieved if blast design is the only parameter to be considered in flyrock projection and the rest is influenced by the geological condition. Other causes of flyrock are discussed. Comparison of flyrock prediction with face bursting, cratering and rifling is carried out with recent prediction models.     

A Combination of Expert-Based System and Advanced Decision-Tree Algorithms to Predict Air-Overpressure Resulting from Quarry Blasting

Natural Resources Research - This study combined a fuzzy Delphi method (FDM) and two advanced decision-tree algorithms to predict air-overpressure (AOp) caused by mine blasting. The FDM was used...     

Geo-limis - a decision support system for minimizing locust impact in republic of kazakhstan

Desert locusts (DL) are serious problem during April to August in the deserts and semi-deserts of Republic of Kazakhstan and causing extensive crop damage. There is no institutional and functional mechanism to forecast the habitat of locusts and most of the area remains unnoticed after laying eggs. The key to improve DL forecasting and control depends on the collection and generation of historical database on locusts, weather and habitat from affected region. Looking at the problem, a Spatial Decision Support Systems (DSS) has been developed on ARC/INFO GIS with ergonomic user interface for ingestion and subsequent analysis of locust related information vis-à-vis bio-physical and climatic data acquired from various satellite sensors and hydromet weather server respectively, to identify high frequency breeding areas well before the physiological development is completed. Weather based analytical models for physiological development of DL has been dovetailed with the SDSS for facilitating historic and present data analysis in relation to locust activity. This has augmented the surveying capability and better forecasting.     

A Novel Intelligent ELM-BBO Technique for Predicting Distance of Mine Blasting-Induced Flyrock

Natural Resources Research - Blasting is an economical technique for rock breaking in hard rock excavation. One of its complex undesired environmental effects is flyrock, which may result in human...     

Use of Intelligent Methods to Design Effective Pattern Parameters of Mine Blasting to Minimize Flyrock Distance

Flyrock is one of the most important environmental issues in mine blasting, which can affect equipment, people and could cause fatal accidents. Therefore, minimization of this environmental issue of blasting must be considered as the ultimate objective of many rock removal projects. This paper describes a new minimization procedure of flyrock using intelligent approaches, i.e., artificial neural network (ANN) and particle swarm optimization (PSO) algorithms. The most effective factors of flyrock were used as model inputs while the output of the system was set as flyrock distance. In the initial stage, an ANN model was constructed and proposed with high degree of accuracy. Then, two different strategies according to ideal and engineering condition designs were considered and implemented using PSO algorithm. The two main parameters of PSO algorithm for optimal design were obtained as 50 for number of particle and 1000 for number of iteration. Flyrock values were reduced in ideal condition to 34 m; while in engineering condition, this value was reduced to 109 m. In addition, an appropriate blasting pattern was proposed. It can be concluded that using the proposed techniques and patterns, flyrock risks in the studied mine can be significantly minimized and controlled.

     

Application of Tree-Based Predictive Models to Forecast Air Overpressure Induced by Mine Blasting

Natural Resources Research - In surface mines and underground excavations, every blasting operation can have some destructive environmental impacts, among which air overpressure (AOp) is of major...