This book focuses on the application of soft computing in materials and manufacturing sectors with the objective to offer an intelligent approach to improve the manufacturing process, material selection and characterization techniques for developing advanced new materials. It unveils different models and soft computing techniques applicable in the field of advanced materials and solves the problems to help the industry and scientists to develop sustainable materials for all purposes. The book focuses on the overall well-being of the environment for better sustenance and livelihood. Firstly, the authors discuss the implementation of soft computing in the various areas of engineering materials. They also review the latest intelligent technologies and algorithms related to the state-of-the-art methodologies of monitoring and effective implementation of sustainable engineering practices. Finally the authors examine the future generation of sustainable and intelligent monitoring techniques beneficial for manufacturing, and cover novel soft computing techniques for the purpose of effective manufacturing processes at par with the standards laid down by the International Standards of Organization (ISO). This book is intended for academics and researchers from all the fields of engineering interested in joining interdisciplinary initiatives on soft computing techniques for advanced materials and manufacturing.
Author(s): Amar Patnaik, Vikas Kukshal, Pankaj Agarwal, Ankush Sharma, Mahavir Choudhary
Series: Edge AI in Future Computing
Publisher: CRC Press
Year: 2022
Language: English
Pages: 247
City: Boca Raton
Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgements
Editors
List of Contributors
Chapter 1 Predictive Maintenance of Industrial Rotating Equipment Using Supervised Machine Learning
1.1 Introduction: Need for Condition Monitoring
1.2 Methodology: Approaches Followed for Predictive Maintenance
1.2.1 Steps for Predictive Maintenance
1.2.2 A Brief Introduction to Fitting Model
1.2.3 Estimation of Remaining Useful Life
1.2.4 Case Study: Induced Draft (ID) Fan-Motor System
1.3 Computational Procedure
1.3.1 Data Pre-processing
1.3.2 Feature Selection for Predictive Maintenance
1.3.3 Variation of Vibration with Other Selected Variables
1.3.4 Fitted Model
1.3.5 Model Validation
1.3.6 Detecting Outliers
1.3.7 Remaining Useful Life Estimation using PCA
1.4 Results and Discussion
1.4.1 Predicted Solution to Decrease Vibration
1.4.2 Benefits of Using the Supervised Machine Learning Technique
1.5 Conclusion and Future Scope
References
Chapter 2 Predictive Approach to Creep Life of Ni-based Single Crystal Superalloy Using Optimized Machine Learning Regression Algorithms
2.1 Introduction
2.2 Creep Mechanisms in Ni-based Superalloys
2.3 Creep Life of Ni-based Superalloys
2.4 Lattice Misfit in Ni-Based Superalloys
2.5 Machine Learning Algorithms for Creep Life
2.6 Materials and Methodology
2.7 Results and Discussion
2.7.1 Importance of Features
2.8 Conclusions
2.9 Future Scope
2.9.1 Dataset and Code Availability
Abbreviations
References
Chapter 3 Artificial Neural Networks Based Real-time Modelling While Milling Aluminium 6061 Alloy
3.1 Introduction
3.2 Literature Review
3.3 Exploratory Data Analysis
3.4 Artificial Neural Networks
3.5 Our Model
3.6 Results
3.7 Conclusion
References
Chapter 4 Smart Techniques of Microscopic Image Analysis and Real-Time Temperature Dispersal Measurement for Quality Weld Joints
4.1 Introduction
4.2 Allied Investigation
4.3 Experimental Investigation of Weld Bead Geometry
4.4 Weld Bead Geometry Processing and Texture Features Extraction
4.5 Real-Time Temperature Data Measurement Logger
4.5.1 Microprocessor (89S52)
4.5.2 Operational Amplifier
4.5.3 Thermocouple Input and Output
4.5.4 Analog to Digital Converter Circuit (3202)
4.5.5 LCD Section
4.5.6 RS 232 Interface with 89S52
4.5.7 Twin Voltage Converter
4.5.8 Bridge Rectifier
4.6 Real-Time Temperature Distribution Measurement
4.7 Result and Discussion
4.8 Conclusion
References
Chapter 5 Industrial Informatics Cache Memory Design for Single Bit Architecture for IoT Approaches
5.1 Introduction
5.1.1 The Return of STSRAMs to Mainstream Embedded Design
5.1.2 Consumption of Power Increases
5.1.3 Wearable Electronics STSRAMCs
5.1.4 STSRAMCs and Internet of Things
5.2 Literature Survey
5.3 Motivation and Overview
5.4 Problem Statement
5.5 The Need for Low Power VLSI Design
5.6 Cache Memory Design for Single Bit STSRAM SA Architecture
5.6.1 CWD Working and Schematic
5.6.2 STSRAMC Working and Schematic
5.6.3 Sense Amplifiers
5.6.3.1 DSA
5.6.3.2 LSA
5.7 Methodology
5.7.1 Power Reduction Sleep Transistor Technique
5.7.2 Power Reduction Dual Sleep Technique
5.7.3 Power Reduction Sleepy Stack Technique
5.7.4 Power Reduction Forced Stack Technique
5.8 Result and Discussion
5.8.1 Simulation of Single Bit STSRAMC VDSA Architecture
5.8.2 Simulation of Single Bit STSRAMC CDSA Architecture
5.8.3 Simulation of Single Bit STSRAMC CTDSA Architecture
5.8.4 Simulation of Single Bit STSRAMC VLTSA Architecture
5.8.5 Simulation of Single Bit STSRAMC CLTSA Architecture
5.9 Comparison Table
5.10 Conclusion and Future Scope
5.11 Abbreviations
References
Chapter 6 The Bending Behavior of Carbon Fiber Reinforced Polymer Composite for Car Roof Panel Using ANSYS 21
6.1 Introduction
6.2 Materials
6.2.1 Materials Specicatfiions
6.2.1.1 Reinforcement
6.2.1.2 Matrices
6.3 Methodology
6.3.1 Various Steps Involved in Designing and Analysis of Carbon Fiber Reinforced Polymer Composite
6.3.2 Composite Sample
6.3.3 Meshing
6.3.4 Boundary Conditions
6.4 Results and Discussion
6.4.1 Composite Sample Having Carbon Fiber and Resin Epoxy
6.4.2 Composite Sample Having Carbon Fiber and Resin Polyester
6.4.3 Composite Sample Having Carbon Fiber and PVC Foam
6.5 Conclusions
References
Chapter 7 Sustainable Spare Parts Inventory and Cost Control Management Using AHP-Based Multi- Criterion Framework: Perspective on Petroleum & Fertilizer Industries
7.1 Introduction
7.2 Review of Relevant Literature
7.2.1 Review of Research Papers
7.2.2 Review of Petroleum Handbook and Reports
7.2.3 Industry Need for Multi-Criterion Approach; A Pilot Survey
7.3 Problem Statement and Basis of Proposed Frame Work
7.4 Methodology of Research Work and Process
7.4.1 Ranking of Selective Inventory Control Methods Using AHP Technique
7.4.1.1 Assumptions for Framework
7.4.2 AHP Process for Developing MCIC Model
7.4.2.1 Equipment Criticality and Failure Rate
7.4.2.2 Spares Replacement Frequency
7.4.2.3 Cost of Item (COI)
7.4.2.4 Replenishment Time (RT)
7.4.2.5 Companywide Interchangeability/Commonality (CWI)
7.4.3 Pairwise Comparison of Criteria
7.4.4 Pairwise Comparison of Output Alternatives Based on Criteria
7.5 Decision Tree Multi-Criterion Inventory Control (MCIC) Model
7.5.1 Description of Sustainable Stocking Category and Policy Guideline
7.6 Suitability of Stocking Category for Group Classification in the MCIC Model
7.6.1 Sample Size Determination
7.6.2 Response Summary
7.6.3 Hypotheses Design and Testing
7.6.4 Reliability and Normality Test for the Group of Hypotheses
7.6.5 Non-Parametric One-Sample Test for Hypotheses
7.7 Pilot Cases Analysis: Stocking Levels Traditional v/s Proposed, Based on Model
7.7.1 Case-I
7.7.2 CASE-II
7.8 Conclusions and Managerial Implications
7.8.1 Managerial Implications
7.8.2 Future Perspective
7.9 Abbreviations
Acknowledgement
References
Chapter 8 Simulation of Deployment of Inflatable Structures Through Uniform Pressure Method
8.1 Introduction
8.2 Soft Computing and Scope of Artificial Intelligence in Generative Design
8.3 InflationModel
8.4 Numerical Simulation
8.4.1 Description of CAE model
8.4.2 Concerned Inflation Models
8.4.3 User Subroutine
8.5 Results and Discussion
8.5.1 Simulation Result
8.5.2 Validation Experiment
8.6 Conclusion and Future Scope
Abbreviations
References
Chapter 9 Experimental and Machine Learning Approach to Evaluate the Performance of Refrigerator and Air Conditioning Using TiO[sub(2)] Nanoparticle
9.1 Introduction
9.2 Experimental Setup
9.2.1 Set Up and Performance Test
9.2.2 Preparation of Nano Lubricant
9.3 Machine Learning Models
9.3.1 Gaussian Process Regression
9.3.2 Support Vector Regression
9.4 Results and Discussion
9.5 Conclusion
References
Chapter 10 Numerical and Experimental Investigation on Thinning in Single-Point Incremental Sheet Forming
10.1 Introduction
10.2 Materials and Methodology
10.2.1 FEA Modeling
10.2.2 Experimental Setup
10.2.3 FEA Simulation Plan
10.3 Result and Discussion
10.3.1 FEA simulation
10.3.2 Influence of Control Parameters on Minimum Thickness
10.4 Conclusion
Abbreviation
References
Chapter 11 Smart Manufacturing: Opportunities and Challenges Overcome by Industry 4.0
11.1 Introduction
11.2 Definition and Framework
11.2.1 Industry 4.0
11.2.2 Smart Manufacturing
11.3 Modern Technologies Assisting Smart Manufacturing
11.3.1 Digital Manufacturing
11.3.2 Artificial Intelligence and Machine Learning
11.3.3 Internet of Things
11.3.4 Big Data and Analytics
11.4 Challenges of Smart Manufacturing and Fourth Generation Industries
11.4.1 Security of Computer-Based Systems
11.4.2 Multilingualism and Diversity
11.5 Conclusion
Chapter 12 Multi-Response Optimization of Input Parameters in End Milling of Metal Matrix Composite Using TOPSIS Algorithm
12.1 Introduction
12.2 Materials and Method
12.2.1 Fabrication of Composite Material
12.2.2 Experimental Procedure
12.3 Methodology
12.4 Result and Discussion
12.4.1 Experimental Result
12.4.2 ANOVA Result for Response MRR
12.4.3 ANOVA for RA
12.4.4 The Effect of Machining Parameters on the Responses
12.5 Optimization of Milling Parameters
12.5.1 TOPSIS Algorithm
12.6 Conclusion
References
Chapter 13 Numerical and Experimental Investigation of Additive Manufactured Cellular Lattice Structures
13.1 Introduction
13.2 Materials and Methodology
13.2.1 Modelling of Lattice Structures and Standard Block
13.2.2 Specimen Fabrication
13.2.3 Mechanical Testing of Specimen
13.3 Results and Discussion
13.3.1 Finite Element Method of Lattice Structures
13.3.2 Comparison of Experimental and Analysis Results of FCC and Star Lattice Structures
13.4 Conclusion
Abbreviations
References
Chapter 14 Wear Measurement by Real-Time Condition Monitoring Using Ferrography
14.1 Introduction
14.2 Wear Measurement
14.3 Wear Debris Analysis
14.4 Case Study
14.5 Conclusion
Abbreviations
References
Chapter 15 Design, Modelling and Comparative Analysis of a Horizontal Axis Wind Turbine
15.1 Introduction
15.2 Analytical Design
15.2.1 Wind Observations (m/sec)
15.2.2 Design Considerations
15.2.3 Rotor Design
15.3 Software Modelling and Analysis
15.3.1 Solidworks CAD Models and Renders:
15.3.2 Material Assignment
15.3.3 Structural Analysis
15.3.4 Aerodynamic Analysis
15.3.5 Rotor Design
15.4 Qblade Aerodynamic Simulations
15.5 Results and Discussions
15.6 Conclusions
References
Index
