Environmental Issues of Blasting: Applications of Artificial Intelligence Techniques (SpringerBriefs in Applied Sciences and Technology)

✍ Scribed by Ramesh M. Bhatawdekar, Danial Jahed Armaghani, Aydin Azizi

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 83
• Category: Library

✦ Synopsis

This book gives a rigorous and up-to-date study of the various AI and machine learning algorithms for resolving environmental challenges associated with blasting. Blasting is a critical activity in any mining or civil engineering project for breaking down hard rock masses. A small amount of explosive energy is only used during blasting to fracture rock in order to achieve the appropriate fragmentation, throw, and development of muck pile. The surplus energy is transformed into unfavourable environmental effects such as back-break, flyrock, air overpressure, and ground vibration. The advancement of artificial intelligence and machine learning techniques has increased the accuracy of predicting these environmental impacts of blasting. This book discusses the effective application of these strategies in forecasting, mitigating, and regulating the aforementioned blasting environmental hazards.

✦ Table of Contents

About This Book
Contents
About the Authors
1 An Overview of Blasting Operations and Possible Techniques to Solve Environmental Issues of Blasting
1.1 Introduction
1.2 Blast Design
1.3 Environmental Effect Due to the Blasting
1.3.1 AOp or Air Blast
1.3.2 Ground Vibration
1.3.3 Flyrock
1.4 Blasting Effect Prediction
1.4.1 Prediction of AOp
1.4.2 Prediction of Ground Vibration
1.4.3 Prediction of Flyrock Distance
1.5 Prediction Methods by Computational Techniques
1.6 Blasting Solutions Enabled by the Blastiq™ Platform
1.6.1 Blast Design
1.6.2 Blast Control
1.6.3 BlastIQ™ Advanced Technologies
1.7 Conclusion Remarks
References
2 Review of Empirical and Intelligent Techniques for Evaluating Rock Fragmentation Induced by Blasting
2.1 Introduction
2.2 Rock Fragmentation
2.3 Blastability
2.4 Fragmentation Measurement
2.5 Background of ML Models
2.5.1 Artificial Neural Network
2.5.2 Adaptive Neuro-Fuzzy Inference System (ANFIS)
2.5.3 Support Vector Machine (SVM)
2.5.4 Genetic Algorithm (GA)
2.6 Review of ML Models for Prediction of Rock Fragmentation
2.7 Discussion
2.8 Conclusion and Future Perspective
References
3 Applications of AI and ML Techniques to Predict Backbreak and Flyrock Distance Resulting from Blasting
3.1 Introduction
3.2 Measurement of Flyrock
3.2.1 Flyrock
3.2.2 Backbreak
3.3 Concepts of Some AI Models
3.3.1 Artificial Neural Network (ANN)
3.3.2 ANFIS
3.3.3 Support Vector Machine (SVM)
3.3.4 ELM
3.3.5 PSO-ELM
3.4 Backbreak Prediction Using AI Techniques
3.5 Flyrock Prediction Using AI Techniques
3.6 Discussion
3.7 Conclusion
References
4 Blast-Induced Air and Ground Vibrations: A Review of Soft Computing Techniques
4.1 Introduction
4.2 Ground Vibration
4.3 AOp
4.4 Background of Common AI Models
4.4.1 Artificial Neural Network (ANN)
4.4.2 Support Vector Machine (SVM)
4.4.3 Fuzzy Interface System (FIS)
4.5 Ground Vibration Prediction Using AI Techniques
4.6 AOp Prediction Using AI Techniques
4.7 Discussion
4.8 Conclusion
References