AKTU Mine Automation & Data Analytics (BMN073) Syllabus PDF – B.Tech 4th Year

Course Outcomes

UNIT I [08 Hours]

Foundations of Mine Automation and Autonomous Systems Automation Fundamentals: essential elements of an automated system; automation in the mine production system; principles and strategies of automation; introduction to automation productivity and levels of automation.

Autonomous Mining Systems: autonomous haulage systems (AHS); automated drilling systems; tele-remote and autonomous operating modes; selection considerations for autonomous equipment.

Fleet Management & Remote Operations: Fleet Management Systems — Truck Dispatch System (TDS), Computerised Maintenance Management System (CMMS) and Enterprise Resource Planning (ERP) for the mining industry; mine remote operations and control; mining robotics and “armchair mining”; remote operating centres.

UNIT II [08 Hours]

Sensing, Communication, Tracking and Virtual-Reality Technologies Automated Communication & Tracking Technologies: proximity-detection systems; GNSS/UPS positioning; radar systems; RFID and geo-fencing; CCD cameras and machine vision; image processing;

SCADA architecture and its applications in mines.

Virtual Reality & Simulation: virtual-reality applications in mining; mining-equipment concept development; mine-safety training applications; mining-operation simulations and visualisation of the mining process for safe operations.

UNIT III [08 Hours]

Statistical Foundations and Introduction to Machine Learning Descriptive Statistics: measures of central tendency and dispersion; data summarisation and visualisation; probability and probability distributions (discrete and continuous) relevant to mining data.

Inferential Statistics: sampling and estimation; hypothesis testing; regression analysis; analysis of variance (ANOVA); interpretation of results for mining problems.

Introduction to Machine Learning: basic concepts, terminology and the learning workflow; supervised, unsupervised and reinforcement learning; the data-analytics pipeline for mining applications.

UNIT IV [08 Hours]

Supervised Learning, Neural Networks and Deep Learning Supervised Learning: classification and regression; feature engineering; training, validation and testing; the bias–variance trade-off; model-evaluation metrics.

Artificial Neural Networks: the perceptron and multilayer networks; activation functions; the back-propagation algorithm; network training and regularisation.

Deep Learning: deep network architectures (overview); representation and feature learning; representative applications of deep learning to mining and geoscience data.

UNIT V [08 Hours]

Unsupervised Learning, Big-Data Analytics and AI Applications in Mining Unsupervised Learning: clustering techniques; pattern and structure discovery in unlabelled mining data; dimensionality reduction (overview).

Big-Data Analytics: characteristics and challenges of big data; data acquisition, storage and management; analytics frameworks and pipelines for large-scale mining data.

Applications in Mining: application of big-data analytics and artificial intelligence in mining — predictive maintenance, production and energy optimisation, safety analytics and decision-support systems.

Reference Books

1. Hastie, T., Tibshirani, R. and Friedman, J., The Elements of Statistical Learning, Vol. 2, Springer, New York, 2009.
2. Montgomery, D. C. and Runger, G. C., Applied Statistics and Probability for Engineers, John Wiley & Sons, 2010.
3. Almgren, G., Kumar, U. and Vagenas, N., Mine Mechanization & Automation, 1st Edition.
4. O’Shea, J. and Polis, M., Automation in Mining, Mineral and Metal Processing, Proceedings of the 3rd IFAC Symposium, Montreal, Canada, 18–20 August 1980.
5. Moreira, J., Carvalho, A. and Horvath, T., A General Introduction to Data Analytics, Wiley, 2019.
6. Runkler, T. A., Data Analytics: Models and Algorithms for Intelligent Data Analysis, Vieweg+Teubner Verlag, 2012. LAB