Sukumar Bandopadhyay

Reliability estimation using a genetic algorithm-based artificial neural network: An application to a load-haul-dump machine

In this study, a neural network-based model for forecasting reliability was developed. A genetic algorithm was applied for selecting neural network parameters like learning rate (@h) and momentum (@m). The input variables of the neural network model were selected by maximizing the mean entropy value. The developed model was validated by applying two benchmark data sets. A comparative study reveals that the proposed method performs better than existing methods on benchmark data sets. A case study was conducted on a load-haul-dump (LHD) machine operated at a coal mine in Alaska, USA. Past time-to-failure data for the LHD machine were collected, and cumulative time-to-failure was calculated for reliability modeling. The results demonstrate that the developed model performs well with high accuracy (R^2=0.94) in the failure prediction of a LHD machine.

Data Segmentation and Genetic Algorithms for Sparse Data Division in Nome Placer Gold Grade Estimation Using Neural Network and Geostatistics

Ore reserve estimation, based on sparse drill hole data, was conducted for a placer gold property in Nome, Alaska. A problem with sparse data is that random subdivision of the data into modelling and evaluation subsets (as is commonly done) becomes a problem, as random selection may result in biased/skewed subsets. Therefore, a technique that combined data segmentation with genetic algorithms (GA) was applied to divide the samples into three equivalent subsets: training, validation and testing. Data segmentation was done on the basis of the distribution of gold values. Neural network and a variety of kriging techniques were used to estimate gold grades. A multi-layer feed forward neural network along with “early/quick stop” training was used for neural network modelling. A comparative evaluation of kriging and neural network methods was then performed. The results revealed that neural network was generally superior to the kriging techniques for gold grade estimation in the Nome deposit.

Expert systems as decision aid in surface mine equipment selection

ABSTRACT Mining integrates the skill of many engineering disciplines. Within these disciplines lies experience and expertise found in not other industry. To capture and widely apply this expertise is the challenge to developing the knowledge base expert systems The characteristics of plausible reasoning shared by medical diagnosis and mineral exploration are common, to some degree to many other evaluation tasks as well. Hence, the purpose of this paper is to illustrate, by a cast study of mining equipment selection, the general process of capturing and encoding human expertise into a mechanical realization.

Construction of a radial basis function network using an evolutionary algorithm for grade estimation in a placer gold deposit

This paper presents a study highlighting the predictive performance of a radial basis function (RBF) network in estimating the grade of an offshore placer gold deposit. In applying the radial basis function network to grade estimation of the deposit, several pertinent issues regarding RBF model construction are addressed in this study. One of the issues is the selection of the RBF network along with its center and width parameters. Selection was done by an evolutionary algorithm that utilizes the concept of cooperative coevolutions of the RBFs and the associated network. Furthermore, the problem of data division, which arose during the creation of the training, calibration and validation of data sets for the RBF model development, was resolved with the help of an integrated approach of data segmentation and genetic algorithms (GA). A simulation study conducted showed that nearly 27% of the time, a bad data division would result if random data divisions were adopted in this study. In addition, the efficacy of the RBF network was tested against a feed-forward network and geostatistical techniques. The outcome of this comparative study indicated that the RBF model performed decisively better than the feed-forward network and the ordinary kriging (OK).

Partial ranking of primary stripping equipment in surface mine planning

Abstract Many mine planning problems involve complex socio-economic environment, variables that are not completely defined, personal bias and subjectiveness. These characteristic of complexity make attractive the use of the theory of fuzzy sets. This paper demonstrates an application of fuzzy set theory to the partial ranking of stripping equipment in the presence of ill-defined variables and imprecise data.

A hybrid ensemble model of kriging and neural network for ore grade estimation

This paper presents a new hybrid methodology involving kriging and artificial neural network for ore grade estimation of two variables namely, Al2O3% and SiO2%, in a bauxite deposit. The dataset was divided into three statistically similar subsets: training, calibration and validation sets using a genetic algorithm. The proposed hybrid ensemble model was formed using a kriging model and several neural network models. The outputs of these component models were combined using two methods to produce a unified prediction. The results indicated that the hybrid model was not a better estimator than the kriging model for the variable Al2O3%. However, it provides slightly better performance in comparison to any of the other component models in the ensemble for the variable SiO2%.

Comparing the predictive performance of neural networks with ordinary kriging in a bauxite deposit

Abstract This paper investigates the performance of neural network and ordinary kriging techniques in estimating five variables: accumulated Al2O3, accumulated SiO2, percentage Al2O3, percentage SiO2, and thickness of a bauxite deposit in India. The assay values obtained from exploratory boreholes were compiled according to the geological composition of the deposit. Genetic algorithms were used to divide the dataset into model development and evaluation subsets, ensuring that the modelling subset and evaluation subset were similar and that performance evaluation was valid. The results indicate that neural networks and ordinary kriging performed equally well in this deposit, except for the variable accumulated Al2O3. However, the coefficients of determination (R2) of predictions were not very good.

Ensemble Support Vector Machine Algorithm for Reliability Estimation of a Mining Machine

In this study, a support vector machine (SVM)-based ensemble model was developed for reliability forecasting. The hyperparameters of the SVM were selected by applying a genetic algorithm. Input variables of the SVM model were selected by maximizing the mean entropy value. The diverse members of the ensemble model were obtained by a k-means clustering algorithm, and one ensemble member was selected from each cluster by choosing the closest from the cluster center. The optimum cluster number was selected using the Davies–Bouldin index. The developed model was validated by a benchmark turbocharger data set. A comparative study reveals that the proposed method performs better than existing methods on benchmark data sets. A case study was conducted investigating a dumper operated at a coal mine in India. Time-to-failure historical data for the dumper were collected, and cumulative time to failure was calculated for reliability forecasting. Study results demonstrate that the developed model performs well with high accuracy (R2 = 0.97) in the prediction of dumper failure, and a comparison with other methods demonstrates the superiority of the proposed ensemble SVM model. Copyright

Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data

Traditional geostatistical estimation techniques have been used predominantly by the mining industry for ore reserve estimation. Determination of mineral reserve has posed considerable challenge to mining engineers due to the geological complexities of ore body formation. Extensive research over the years has resulted in the development of several state-of-the-art methods for predictive spatial mapping, which could be used for ore reserve estimation; and recent advances in the use of machine learning algorithms (MLA) have provided a new approach for solving the prob-lem of ore reserve estimation. The focus of the present study was on the use of two MLA for estimating ore reserve: namely, neural networks (NN) and support vector machines (SVM). Application of MLA and the various issues involved with using them for reserve estimation have been elaborated with the help of a complex drill-hole dataset that exhibits the typical properties of sparseness and impreciseness that might be associated with a mining dataset. To investigate the accuracy and applicability of MLA for ore reserve estimation, the generalization ability of NN and SVM was compared with the geostatistical ordinary kriging (OK) method.

Expert System for Equipment Selection

An expert system was developed for equipment selection for various unit operations in open pit mining. For each unit operation, it considers a wide variety of equipment and ranks them based on their suitability. A major difference between this system and other published expert systems in the considered domain is that it incorporates the uncertainty that is an inherent characteristic of the factors affecting equipment selection. It also allows users to specify the site-specific relative importance of each of the governing factors. This makes the system relatively flexible and allows its adaptation to different mining conditions. The programming features of the expert system include uncertainty databases and object oriented programming. The expert system is validated with a case study (Malanjkhand Copper Mine, India).