Machining of Hard Materials: A Comprehensive Approach to Experimentation, Modeling and Optimization (Manufacturing and Surface Engineering)

Preface
Contents
1 Introduction to Hard Materials and Machining Methods
	1.1 Introduction
	1.2 Hard Materials
	1.3 Machining Methods of Hard Materials
		1.3.1 Hard Turning
		1.3.2 Hard Broaching
		1.3.3 Hard Boring
		1.3.4 Hard Milling
	1.4 Challenges in Machining of Hard Materials
		1.4.1 Steels
		1.4.2 Titanium and Its Alloys
		1.4.3 Super-Alloys
		1.4.4 Composite Materials and Metal Matrix Composites
		1.4.5 Ceramics
	1.5 Industrial Applications of Machined Hard Materials
	1.6 Cutting Tool Materials
		1.6.1 High-Speed Steel (HSS)
		1.6.2 Cemented Carbides
		1.6.3 Ceramics
		1.6.4 Carbon Boron Nitride (CBN) Tools
		1.6.5 Polycrystalline Diamond (PCD)
	1.7 Selection of Cutting Tool Materials and Geometry
	1.8 Advantages in Machining Hard Materials with Conventional Machining
	References
2 Studies on Machining of Hard Materials
	2.1 Hard Turning Process
	2.2 Classical Engineering Experimental Approach or One Factor at a Time (OFAT)
	2.3 Numerical Modelling Approach
	2.4 Input–Output and In-Process Parameter Relationship Modelling
		2.4.1 Taguchi Method
		2.4.2 Response Surface Methodology (RSM)
		2.4.3 Desirability Function Approach (DFA)
		2.4.4 Soft Computing Optimization Tools
	2.5 Capabilities of Hard Turning Process
		2.5.1 Variables of Hard Turning Process
	2.6 Conclusion
	References
3 Experimentation, Modelling, and Analysis of Machining of Hard Material
	3.1 Selection of Experimental Design
	3.2 Workpiece and Tool Material
	3.3 Experiment Details
		3.3.1 Material Removal Rate
		3.3.2 Surface Roughness
		3.3.3 Cylindricity and Circularity Error
	3.4 Results and Discussion
		3.4.1 Response: MRR
		3.4.2 Response: SR
		3.4.3 Response: CE
		3.4.4 Response: Ce
	3.5 Regression Model Validation
	3.6 Concluding Remarks
	References
4 Intelligent Modelling of Hard Materials Machining
	4.1 Advantages of Artificial Intelligence Over Statistical Methods
	4.2 Neural Networks
	4.3 Modelling of Hard Turning Process
	4.4 Data Collection for NN Modelling
		4.4.1 Training Data
		4.4.2 Testing Data
	4.5 NN Modelling of Hard Turning Process
		4.5.1 Forward Modelling
		4.5.2 Reverse Modelling
	4.6 Back-Propagation Neural Network (BPNN)
		4.6.1 Weights
		4.6.2 Hidden Layers and Neurons
		4.6.3 Learning Rate and Momentum Constant
		4.6.4 Constants of Activation Function
		4.6.5 Bias
	4.7 Genetic Algorithm Neural Network (GA-NN)
		4.7.1 Selection
		4.7.2 Crossover
		4.7.3 Mutation
	4.8 Results of Forward Mapping
		4.8.1 BPNN
		4.8.2 GA-NN
		4.8.3 Summary Results of Forward Mapping
	4.9 Reverse Mapping
		4.9.1 Back-Propagation NN
		4.9.2 Genetic Algorithm NN
		4.9.3 Summary Results of Reverse Mapping
	4.10 Conclusions
	References
5 Optimization of Machining of Hard Material
	5.1 Genetic Algorithm
	5.2 Particle Swarm Optimization (PSO)
	5.3 Teaching–Learning-Based Algorithm (TLBO)
		5.3.1 Teacher Phase
		5.3.2 Learner Phase
	5.4 JAYA Algorithm
	5.5 Modelling and Optimization for Machining Process
	5.6 Mathematical Formulation for Multi-objective Optimization
	5.7 Results of Parameter Study of Algorithms (GA, PSO, TLBO, and JAYA)
		5.7.1 Genetic Algorithm
		5.7.2 Particle Swarm Optimization
		5.7.3 Teaching–Learning-Based Optimization and JAYA Algorithm
	5.8 Summary of Optimization Results
	5.9 Validation Experiments
	5.10 Tool Wear Studies
	5.11 Conclusions
	References
Index