The basic principles of the Support Vector Machine (SVM) are introduced in this paper. A specific process to establish an SVM prediction model is given. To improve the precision of coal reserve estimation, a support v...The basic principles of the Support Vector Machine (SVM) are introduced in this paper. A specific process to establish an SVM prediction model is given. To improve the precision of coal reserve estimation, a support vector machine method, based on statistical learning theory, is put forward. The SVM model was trained and tested by using the existing exploration and exploitation data of Chencun mine of Yima bureau’s as the input data. Then coal reserves within a particular region were calculated. These calculated results and the actual results of the exploration block were compared. The maximum relative error was 10.85%, within the scope of acceptable error limits. The results show that the SVM coal reserve calculation method is reliable. This method is simple, practical and valuable.展开更多
Using the classification results by the fuzzy clustering models as the basis for choosing the choosing patterns, a feed forward networks model for classification is given. Remarkable success was achieved in training t...Using the classification results by the fuzzy clustering models as the basis for choosing the choosing patterns, a feed forward networks model for classification is given. Remarkable success was achieved in training the networks to learn the patterns and in classifying the coal reserve assets. The results show that the neural network approach for classification has some advantages such as stability and reliability.展开更多
Pit optimisation is the earliest and most established application of its kind in the minerals industry, but this has been primarily driven by metal, not coal. Coal has the same financial drivers for resource optimisat...Pit optimisation is the earliest and most established application of its kind in the minerals industry, but this has been primarily driven by metal, not coal. Coal has the same financial drivers for resource optimisation as does the metalliferous industry, yet pit optimisation is not common practice. Why? The following discussion presents the basics of pit optimisation as they relate to coal and illustrates how a technology developed for massive deposits is not suitable for thin, multi-seam deposits where mine planning is often driven more by product quality than by value drivers such as Net Present Value. An alternative methodology is presented that takes advantage of the data structure of bedded deposits to optimise resource recovery in terms of a production schedule that meets constraints on coal quality.展开更多
基金Project 072400430420 supported by the Natural Science Foundation of Henan Province
文摘The basic principles of the Support Vector Machine (SVM) are introduced in this paper. A specific process to establish an SVM prediction model is given. To improve the precision of coal reserve estimation, a support vector machine method, based on statistical learning theory, is put forward. The SVM model was trained and tested by using the existing exploration and exploitation data of Chencun mine of Yima bureau’s as the input data. Then coal reserves within a particular region were calculated. These calculated results and the actual results of the exploration block were compared. The maximum relative error was 10.85%, within the scope of acceptable error limits. The results show that the SVM coal reserve calculation method is reliable. This method is simple, practical and valuable.
文摘Using the classification results by the fuzzy clustering models as the basis for choosing the choosing patterns, a feed forward networks model for classification is given. Remarkable success was achieved in training the networks to learn the patterns and in classifying the coal reserve assets. The results show that the neural network approach for classification has some advantages such as stability and reliability.
文摘Pit optimisation is the earliest and most established application of its kind in the minerals industry, but this has been primarily driven by metal, not coal. Coal has the same financial drivers for resource optimisation as does the metalliferous industry, yet pit optimisation is not common practice. Why? The following discussion presents the basics of pit optimisation as they relate to coal and illustrates how a technology developed for massive deposits is not suitable for thin, multi-seam deposits where mine planning is often driven more by product quality than by value drivers such as Net Present Value. An alternative methodology is presented that takes advantage of the data structure of bedded deposits to optimise resource recovery in terms of a production schedule that meets constraints on coal quality.