Data Analytics Applied to the Mining Industry

Description

Data Analytics Applied to the Mining Industry describes the key challenges facing the mining sector as it transforms into a digital industry able to fully exploit process automation, remote operation centers, autonomous equipment and the opportunities offered by the industrial internet of things. It provides guidelines on how data needs to be collected, stored and managed to enable the different advanced data analytics methods to be applied effectively in practice, through use of case studies, and worked examples. Aimed at graduate students, researchers, and professionals in the industry of mining engineering, this book: Explains how to implement advanced data analytics through case studies and examples in mining engineering Provides approaches and methods to improve data-driven decision making Explains a concise overview of the state of the art for Mining Executives and Managers Highlights and describes critical opportunity areas for mining optimization Brings experience and learning in digital transformation from adjacent sectors Cover Half Title Title Page Copyright Page Table of Contents Preface About the Author 1. Digital Transformation of Mining Introduction DT in the Mining Industry Data Sources Connectivity Information of Things (IoT) Data Exchange Safety of the Cybers Remote Operations Centers (ROCs) Platforms Incorporated Wireless Communications Optimization Algorithms Decision-Making Advanced Analytics Individuals Process of Analysis Technology in Advanced Analytics DT and the Mining Potential The Role of People in Digital Mining Transformation for Future Mining The Role of Process in Mining Digital Transformation for Future Mining The Role of Technology in Mining Digital Transformation for Future Mining Academy Responsibilities in Mining DT Improvement Summary References 2. Advanced Data Analytics Introduction Big Data Analytics Deep Learning CNNs Deep Neural Network Recurrent Neural Network (RNN) ML Fuzzy Logic Classification Techniques Clustering Evolutionary Techniques Genetic Algorithms (GAs) Ant Colony Optimization (ACO) Bee Colony Optimization (BCO) Particle Swarm Optimization (PSO) Firefly Algorithm (FA) Tabu Search Algorithm (TS) BDA and IoT Summary References 3. Data Collection, Storage, and Retrieval Types of Data Sources of Data Critical Performance Parameters Data Quality Data Quality Assessment Data Quality Strategies Dealing with Missing Data Dealing with Duplicated Data Dealing with Data Heterogeneity Data Quality Programs Data Acquisition Data Storage Data Retrieval Data in the Mining Industry Geological Data Operations Data Geotechnical Data Mineral Processing Data Summary References 4. Making Sense of Data Introduction Part I: From Collection to Preparation and Main Sources of Data in the Mining Industry Part II: The Process of Making Data Prepared for Challenges Data Filtering and Selection: Can Tell What is Relevant? Data Cleaning: Bad Data to Useful Data Data Integration: Finding a Key is Key Data Generation and Feature Engineering: Room for the New Data Transformation Data Reduction: Dimensionality Reduction Part III: Further Considerations on Making Sense of Data Unfocused Analytics (A Big Data Analysis) vs. Focused Analytics (Beginning with a Hypothesis) Time and Date Data Types Treatment Dealing with Unstructured Data: Image and Text Approaches Summary References 5. Analytics Toolsets Statistical Approaches Statistical Approaches Selection Analysis of Variance Study of the Correlation Correlation Matrix Reliability and Survival (Weibull) Analysis Multivariate Analysis State-Space Approach State-Space Modeling State-Space Forecasting Predictive Models Regression Linear Regression Logistic Regression Generalized Linear Model Polynomial Regression Stepwise Regression Ridge Regression Lasso Regression Elastic Net Regression Time Series Forecasting Residual Pattern Exponential Smoothing Models ARMA models ARIMA Models Machine Learning Predictive Models Support Vector Machine and AVM for Support Vector Regression (SVR) Artificial Neural Networks Summary References 6. Process Analytics Process Analytics Process Analytics Tools and Methods Lean Six Sigma Business Process Analytics Cases & Applications Big Data Clustering for Process Control Cloud-Based Solution for Real-Time Process Analytics Advanced Analytics Approach for the Performance Gap BDA and LSS for Environmental Performance Lead Time Prediction Using Machine Learning Applications in Mining Mineral Process Analytics Drill and Blast Analytics Mine Fleet Analytics Summary References 7. Predictive Maintenance of Mining Machines Applying Advanced Data Analysis Introduction The Digital Transformation How Can Advanced Analytics Improve Maintenance? Key PdM – Advanced Analytics Methods in the Mining Industry RF Algorithm in PdM ANN in PdM Support Vector Machines in PdM K-Means in PdM DL in PdM Diagnostic Analytics and Fault Assessment Predictive Analytics for Defect Prognosis System Architecture and Maintenance in Mining Maintenance Big Data Collection Framework for PdM Implementation Requirements for PdM Cases and Applications Digital Twin for Intelligent Maintenance PdM for Mineral Processing Plants PdM for Mining Fleet References 8. Data Analytics for Energy Efficiency and Gas Emission Reduction Introduction Advanced Analytics to Improve the Mining Energy Efficiency Mining Industry Energy Consumption Data Science in Mining Industry Haul Truck FC Estimate Emissions of GHG Mine Truck FC Calculation Artificial Neural Network Modeling Built Application Established Network Applied Model (Case Studies) Product Results Established Optimization of Efficient Mine Truck FC Parameters Optimization Genetic Algorithms GA System Developed Outcomes Conclusion References 9. Making Decisions Based on Analytics Introduction Organization Design and Key Performance Indicators (KPIs) Organizational Changes in the Digital World Embedding KPIs in the Organizational Culture Decision Support Tools Phase 1 – Intelligence Phase 2 – Data Preparation Phase 3 – Design Phase 4 – Choice Phase 5 – Implementation AAs Solutions Applied for Decision-Making Intelligent Action Boards (Performance Assistants) Predictive and Prescriptive Models Optimization Tools Digital Twin Models Augmented Analytics Expert Systems ESs Components, Types, and Methodologies ESs Components ESs Types ESs Methodologies and Techniques Rule-Based Systems Knowledge-Based Systems Artificial Neural Networks Fuzzy Expert Systems Case-Based Reasoning ESs in Mining Summary References 10. Future Skills Requirements Advanced-Data Analytics Company Profile – Operating Model What is and How to Become a Data-Driven Company? Corporative Culture Talent Acquisition and Retention Technology The Profile of a Data-Driven Mining Company Jobs of the Future in Mining Future Skills Needed Challenges Need for Mining Engineering Academic Curriculum Review In-House Training and Qualification Location of Future Work Remote Operation Centers On-Demand Experts Summary References Index