Intelligent Prognostics for Engineering Systems with Machine Learning Techniques

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
About the editors
List of contributors
Chapter 1: A bibliometric analysis of research on tool condition monitoring
	1.1 Introduction
	1.2 Data collection and research methodology
	1.3 Bibliometric analysis
		1.3.1 Research growth
		1.3.2 Most productive authors
			1.3.2.1 h-index of the first ten most productive authors
		1.3.3 Authors’ dominance ranking
		1.3.4 Top manuscripts per citations
		1.3.5 Country-wise analysis
			1.3.5.1 Country-wise collaboration
		1.3.6 Most relevant sources
		1.3.7 Keyword analysis
		1.3.8 Co-citation analysis
	1.4 Conclusion
	Appendix 1
	References
Chapter 2: Predicting restoration factor for different maintenance types
	2.1 Introduction
	2.2 Proposed model
		2.2.1 Steps of RF prediction
			2.2.1.1 To study the given system and tabulate the components of the system
			2.2.1.2 To tabulate replaced components for different maintenance types
			2.2.1.3 To apply AHP for calculating weightage of each component
			2.2.1.4 To calculate RF for different PM and CM
			2.2.1.5 To calculate failure distribution parameters
	2.3 Case study
		2.3.1 System description
		2.3.2 Parameter estimation using MLE
		2.3.3 Parameter estimation using proposed approach
			2.3.3.1 Apply AHP to calculate weightage of each component
			2.3.3.2 RF calculation for different types of PM and CM
			2.3.3.3 Calculating failure distribution parameters
			2.3.3.4 Validation
	2.4 Conclusion
	References
Chapter 3: Measurement and modeling of cutting tool temperature during dry turning operation of DSS
	3.1 Introduction
	3.2 Materials and methods
	3.3 Results and discussion
	3.4 Empirical modeling
	3.5 Conclusions
	References
Chapter 4: Leaf disease recognition: Comparative analysis of various convolutional neural network algorithms
	4.1 Introduction
	4.2 Literature review
	4.3 Dataset
	4.4 Methodology
		4.4.1 Convolutional neural network (CNN)
			4.4.1.1 VGG-19
			4.4.1.2 VGG-16
			4.4.1.3 Inception V3
			4.4.1.4 DenseNet-121(proposed approach)
	4.5 Results and discussion
	4.6 Conclusion
	References
Chapter 5: On the validity of parallel plate assumption for modelling leakage flow past hydraulic piston-cylinder configurations
	5.1 Introduction
	5.2 The leakage flow models
		5.2.1 Parallel plate model
		5.2.2 Annular flow model
	5.3 Results and discussion
		5.3.1 Comparison of leakage flow models
		5.3.2 Validation against the orifice plate model
	5.4 Concluding remarks
	Acknowledgement
	References
Chapter 6: Development of a hybrid MGWO-optimized support vector machine approach for tool wear estimation
	6.1 Introduction
	6.2 Materials and methods
		6.2.1 Experimental dataset
			6.2.1.1 Data acquisition and processing
			6.2.1.2 Tool wear
		6.2.2 Support vector regression
		6.2.3 Grey wolf optimization
		6.2.4 Modified grey wolf optimization
		6.2.5 Particle swarm optimization
	6.3 Results and discussion
	6.4 Conclusion and future work
	References
Chapter 7: The energy consumption optimization using machine learning technique in electrical arc furnaces (EAF)
	7.1 Introduction
	7.2 Literature review
	7.3 Methodology
		7.3.1 Data-driven model for power consumption in EAF
		7.3.2 Understanding key elements affecting EAF’s electricity consumption
		7.3.3 Influencing feature identification for modeling
		7.3.4 Creating the heats’ dataset
	7.4 Result and discussion
		7.4.1 Managerial implications
	7.5 Conclusion limitations and future scope
	References
Chapter 8: PID-based ANN control of dynamic systems
	8.1 Introduction
	8.2 Mathematical modeling of inverted double pendulum
	8.3 PID-based ANN control of inverted double pendulum system
	8.4 Simulation and results comparison
	8.5 Conclusion
	References
Chapter 9: Fatigue damage prognosis of offshore piping
	9.1 Introduction
	9.2 Understanding piping fatigue
	9.3 Fatigue damage prognosis
		9.3.1 General
		9.3.2 Remaining useful life prediction
	9.4 Case study
		9.4.1 Background
		9.4.2 Computational fluid dynamics analysis
		9.4.3 Deterministic RUL assessment
		9.4.4 Probabilistic RUL assessment
	9.5 Conclusion
	References
Chapter 10: Minimization of joint angle jerk for industrial manipulator based on prognostic behaviour
	10.1 Introduction
	10.2 System description
	10.3 Algorithms and objective functions
		10.3.1 Objective function
		10.3.2 Modified objective function
		10.3.3 Particle swarm optimization
	10.4 Results and discussion
		10.4.1 Performance evaluation for objective function F 1
		10.4.2 Performance evaluation for modified objective function
	10.5 Conclusion
	References
Chapter 11: Estimation of bearing remaining useful life using exponential degradation model and random forest algorithm
	11.1 Introduction
	11.2 The proposed RUL estimate approach
		11.2.1 Features extraction
		11.2.2 Root mean square
		11.2.3 Feature fitting
		11.2.4 Training of random forest
		11.2.5 RUL prediction
	11.3 Experimental result and discussion
		11.3.1 Experimental data
		11.3.2 RUL prediction using the proposed approach
			11.3.2.1 Relative accuracy
			11.3.2.2 Cumulative relative accuracy
	11.4 Conclusion
	References
Chapter 12: Machine learning-based predictive maintenance for diagnostics and prognostics of engineering systems
	12.1 Introduction and overview
	12.2 Diagnostics and prognostics based on predictive maintenance
		12.2.1 Diagnostics
		12.2.2 Prognostics
	12.3 Machine learning for predictive maintenance
		12.3.1 Machine learning-based predictive maintenance pipeline
		12.3.2 Evaluating machine learning models
	12.4 Machine learning-based predictive maintenance in engineering systems
		12.4.1 Machining systems
			12.4.1.1 Cutting tools
			12.4.1.2 Bearings
		12.4.2 Automotive systems
			12.4.2.1 Brake system
			12.4.2.2 Gear system
		12.4.3 Production systems
		12.4.4 Thermal systems
			12.4.4.1 Boilers
			12.4.4.2 Chillers
	12.5 Summary
	References
Index