This book examines the abilities of new machine learning models for predicting ore grade in mining engineering. A variety of case studies are examined in this book. A motivation for preparing this book was the absence of robust models for estimating ore grade. Models of current books can also be used for the different sciences because they have high capabilities for estimating different variables. Mining engineers can use the book to determine the ore grade accurately. This book helps identify mineral-rich regions for exploration and exploitation. Exploration costs can be decreased by using the models in the current book. In this book, the author discusses the new concepts in mining engineering, such as uncertainty in ore grade modeling. Ensemble models are presented in this book to estimate ore grade. In the book, readers learn how to construct advanced machine learning models for estimating ore grade. The authors of this book present advanced and hybrid models used to estimate ore grade instead of the classic methods such as kriging. The current book can be used as a comprehensive handbook for estimating ore grades. Industrial managers and modelers can use the models of the current books. Each level of ore grade modeling is explained in the book. In this book, advanced optimizers are presented to train machine learning models. Therefore, the book can also be used by modelers in other fields. The main motivation of this book is to address previous shortcomings in the modeling process of ore grades. The scope of this book includes mining engineering, soft computing models, and artificial intelligence.
Author(s): Mohammad Ehteram, Zohreh Sheikh Khozani, Saeed Soltani-Mohammadi, Maliheh Abbaszadeh
Publisher: Springer
Year: 2022
Language: English
Pages: 108
City: Singapore
Preface
Contents
List of Figures
List of Tables
1 The Necessity of Grade Estimation
1.1 Introduction
1.1.1 The Importance of Ore Grade Estimation
1.2 Conventional Ore Grade Estimation Models
1.3 New Models for Estimating Ore Grade
1.4 General Remarks
References
2 A Review of Modeling Approaches
2.1 Introduction
2.1.1 A Review of Studies of Applying MLMs for Estimating Ore Grade
2.2 Advantages and Disadvantages of Ore Grade Estimation Models
2.3 Shortcomings of Previous Studies
2.4 General Remarks
References
3 Structure of Different Kinds of ANN Models
3.1 Introduction
3.1.1 A Review of Studies of Applying MLP, RBFNN, GMDH, and ELM for Estimating Different Variables in Geosciences and Mining Engineering, and Other Fields
3.2 Structure of Multi-Layer Perceptron Models
3.3 Structure of RBFNN Models
3.4 Structure of Extreme Learning Machine (ELM) Models
3.5 Structure of Group Method of Data Handling Neural Networks
3.6 General Remarks
References
4 Optimization Algorithms and Classical Training Algorithms
4.1 Introduction
4.1.1 Backpropagation Algorithm
4.2 Levenberg–Marquardt Algorithm (LM)
4.3 Scaled Conjugate Gradient Algorithm
4.4 Variable Learning Rate Algorithm
4.5 Optimization Algorithm
4.5.1 Salp Swarm Algorithm (SSA)
4.5.2 Sine Cosine Algorithm (SCA)
4.5.3 Structure of Shark Swarm Optimization
4.5.4 Structure of Naked Mole-Rat (NMR) Algorithm
4.5.5 Structure of Particle Swarm Optimization
4.5.6 Structure of Genetic Algorithm for Solving Optimization Problems
4.6 Evolutionary Multi-Layer Perceptron (MLP) and Radial Basis Function Neural Network Models (RBFNN)
4.7 Evolutionary Extreme Learning Machine (ELM)
4.8 Evolutionary Group Method of Data Handling Neural Networks (GMDH)
4.9 General Remarks
References
5 Predicting Aluminum Oxide Grade
5.1 Introduction
5.1.1 Structure of Bayesian Model Averaging
5.2 Case Study
5.3 Results
5.3.1 Determination of Values of Random Parameters
5.3.2 Investigation of the Accuracy of Models for Predicting Ore Grade
5.3.3 Discussion
5.4 Conclusion
References
6 Predicting Silicon Dioxide Grade
6.1 Introduction
6.1.1 Case Study
6.2 Results
6.2.1 Sensitivity Analysis for Choice of Algorithm Parameters
6.2.2 Investigation of the Accuracy of Models
6.3 Discussion
6.4 General Remarks
References
7 Predicting Copper Ore Grade
7.1 Introduction
7.1.1 Kriging Method
7.2 Hybrid ELM and Kriging Method
7.3 Case Study
7.4 Part A
7.4.1 Results of Part A
7.5 Part B
7.5.1 Results for Part B
7.6 General Remarks
References
8 Estimating Iron Ore Grade
8.1 Introduction
8.2 Part A
8.2.1 Case Study
8.2.2 Results
8.3 Part B
8.3.1 Generalized Likelihood Uncertainty Estimation
8.4 Analysis of Uncertainty Results
8.5 Discussion on the GMDH Models
8.6 General Remarks
References
9 Conclusion and General Remarks for Estimating Ore Grade
9.1 Introduction
9.1.1 Final Results
9.1.2 Suggestions for the Future Studies
References
