Artificial Intelligence Applications in Aeronautical and Aerospace Engineering

This book is a comprehensive guide for anyone in the aeronautical and aerospace fields who wants to understand and leverage the transformative power of artificial intelligence to enhance safety, optimize performance, and drive innovation. The field of aeronautical and aerospace engineering is on the brink of a transformative revolution driven by rapid advancements in artificial intelligence (AI). This book analyzes AI’s multifaceted impact on the industry, exploring AI’s potential to address complex challenges, optimize processes, and push technological boundaries with a focus on enhancing safety, security, innovation, and performance. By blending technical insights with practical applications, it provides readers with a roadmap for harnessing AI to solve complex challenges and improve efficiency in aeronautics. Ideal for those seeking a deeper understanding of AI’s role in aeronautical and aerospace engineering, this book offers real-world applications, case studies, and expert insights, making it a valuable resource for anyone aiming to stay at the forefront of this rapidly evolving field. Readers will find this book: Examines AI’s transformative role in aerospace and aeronautics, from enhancing safety to driving innovation and optimizing performance; Highlights real-time applications, addressing AI’s role in boosting operational efficiency and safety in the aerospace and aeronautical industries; Offers insights into emerging AI technologies shaping the future of aerospace and aeronautical systems; Features real-world case studies on AI applications in autonomous navigation, predictive maintenance of aircraft, and air traffic management. Audience Aeronautical and aerospace engineers, AI researchers, students, and industry professionals seeking to understand and apply AI solutions in areas like safety, security, and performance optimization.

Table of Contents:
Preface xvii Part 1: Safety and Security 1 1 Artificial Intelligence Based Habitual and Average DoS Attack Detection in Avionics and Necessity Estimators in Wireless Ad Hoc and Sensor Networks 3 C. R. Bharathi and D. Mahammad Rafi Nomenclature 4 1.1 Introduction 4 1.2 Literature Survey 5 1.3 MQTT’s Impact in Wired Sensor Networks (WSN) 8 1.3.1 MQTT (Message Queuing Telemetry Transport) 8 1.3.2 Mosquitto Broker 10 1.4 Implementation 10 1.4.1 Dataset Preparation 10 1.4.2 Feature Set with Attribute Value and Type 11 1.4.3 Classification 12 1.4.4 Data Security of Avionics Systems 12 1.4.5 Applications for Avionics Systems 14 1.5 End Results and Talk 14 1.6 Conclusion 15 References 15 2 Artificial Intelligence Aerospace Based Penetrating Denial of Service Attack in Wireless Sensor Network 19 C. R. Bharathi and D. Mahammad Rafi 2.1 Overview 20 2.2 Related Work 21 2.3 Applications of Artificial Intelligence Based on DoS Detection 24 2.3.1 Compiling and Modifying Data 24 2.3.2 Choosing Features 25 2.4 Attack Model 28 2.4.1 Artificial Intelligence Aerospace Sensor Network Architecture 29 2.4.2 Aerospace WSNs, Denial-of-Service Attacks 30 2.5 Conclusion 33 References 34 3 Application of Artificial Intelligence and Machine Learning in Computational Fluid Dynamics 37 G. Gowtham, S. Nithya and R. Sundharesan Introduction 38 Motivation for AI in CFD 39 Applications of AI in CFD 40 Challenges and Considerations 41 Data Collection 43 Pre-Processing 45 AI Model Selection 46 Training Data Generation 49 AI Model Training 51 Model Validation 52 CFD Prediction 54 Post-Processing 55 Future Directions 56 Conclusion 58 References 58 4 Deep Learning Based Secure Predictive Maintenance Framework for Industrial Maintenance Using Autonomous Drones 61 Sharanya S., Karthikeyan S., Prabhakar E. and Manirao Ramachandrarao 4.1 Evolution of Industrial Maintenance 62 4.1.1 Condition Monitoring in Industries 62 4.1.2 Classification of Condition Monitoring 63 4.2 Use Cases of Drone Technology in Industrial Activities 65 4.3 Security Dimension of Drone Technology 67 4.3.1 Cyberattacks on Drones 68 4.3.2 Counter-Drone Measures 69 4.4 Cybersecurity Framework for Deploying Drones in Predictive Maintenance 70 4.5 Conclusion 76 References 76 5 Role of Artificial Intelligence in the Life Cycle of Aircraft 79 Karthikeyan S., Sharanya S., Manirao Ramachandrarao and N. Dilip Raja 5.1 Introduction 80 5.1.1 Why Aircraft Manufacturing is Very Expensive? 81 5.2 AI for Aircraft Design 83 5.3 AI in Determining Aircraft Shape 85 5.4 AI in Aircraft Production 87 5.5 AI in Aircraft Assembly Line 89 5.6 AI in Aircraft Performance Improvement 90 5.7 Predictive Maintenance in Aircrafts 93 5.8 Conclusions 95 References 96 6 Artificial Intelligence for Aeronautical and Aerospace Applications Using Fuzzy Logic Controller 99 Anumula Swarnalatha and R. Asad Ahmed 6.1 Introduction 99 6.2 Fuzzy Logic Controllers Used in Aircraft 100 6.3 Advantages of Fuzzy Logic Controllers in Aerospace 102 6.4 Applications 103 6.4.1 Fuzzy Logic Controller Design for an Aircraft 103 6.5 Conclusion 106 References 106 7 Revolutionizing Aerospace Quality Control: Harnessing AI for Defect Detection 109 Naveen R., Rakesh Kumar C., Kowsalya, Fadhilah Mohd Sakri and Prasad G. 7.1 Introduction 110 7.1.1 Aerospace Quality Control Background 110 7.1.2 The Imperative for Quality Control Transformation 110 7.1.3 The Role of AI in the Aerospace Sector 110 7.2 Traditional Quality Control Methods 111 7.2.1 Limitations and Challenges 111 7.2.1.1 Manual Inspection Processes 112 7.2.1.2 Time-Consuming Procedures 112 7.2.2 Case Studies on Conventional Approaches 113 7.2.2.1 Case Study 1: Manual Inspection Failures 113 7.2.2.2 Case Study 2: Time-Related Complications 114 7.3 AI in Aerospace: A Paradigm Shift 115 7.3.1 Overview of AI Technologies 115 7.3.1.1 Machine Learning Algorithms 115 7.3.1.2 Computer Vision 116 7.3.2 Integration of AI in Aerospace Manufacturing 116 7.3.2.1 Design Optimization 116 7.3.2.2 Real-Time Monitoring 117 7.3.3 Advantages of AI for Quality Control 117 7.3.3.1 Real-Time Monitoring 117 7.4 Defect Detection with AI 118 7.4.1 Understanding Defects in Aerospace Components 118 7.4.1.1 Types of Defects 118 7.4.2 AI Algorithms for Defect Detection 119 7.4.2.1 Convolutional Neural Networks (CNNs) for Image Analysis 119 7.4.2.2 Anomaly Detection Algorithms 119 7.5 Implementation Strategies 120 7.5.1 Challenges in Implementing AI for Quality Control 120 7.5.1.1 Technical Challenges 120 7.5.1.2 Organizational Challenges 120 7.5.2 Best Practices and Lessons Learned 120 7.5.2.1 Collaborative Cross-Functional Teams 121 7.5.2.2 Incremental Implementation 121 7.5.3 Regulatory and Ethical Considerations 121 7.5.3.1 Compliance with Standards 121 7.5.3.2 Ethical AI Practices 121 7.6 Future Trends and Innovations 121 7.6.1 Evolving Landscape of Aerospace Quality Control 121 7.6.1.1 Integration of Advanced Sensors 122 7.6.2 Potential Advances in AI for Defect Detection 122 7.6.2.1 Explainable AI 122 7.6.3 Implications for the Future of Aerospace Manufacturing 123 7.6.3.1 Shift in Workforce Skills 123 7.7 Impact of AI Techniques on Defect Detection 123 7.7.1 Improvement in Defect Detection with AI Techniques 124 7.7.2 Specific Outcomes Influenced by AI 124 7.7.3 Enhancing Defect Detection with AI: A Comparative Analysis 125 7.7.3.1 Traditional Defect Detection Methods 125 7.7.3.2 Advantages of AI in Defect Detection 125 7.7.4 Case Studies Highlighting AI Improvements 126 7.8 Conclusion and Recommendations 129 7.8.1 Recap of Key Findings 129 7.8.1.1 Evolution of Quality Control 129 7.8.1.2 Impact of AI 129 7.8.1.3 Future Trends and Innovations 130 7.8.2 The Path Forward: Recommendations for Industry Stakeholders 130 7.8.2.1 Embrace Continuous Learning 130 7.8.2.2 Collaborative Research and Development 130 7.8.2.3 Regulatory Engagement 130 7.8.3 Final Thoughts on the Future of Aerospace Quality Control 130 7.8.4 Scope of the Future Work 131 References 131 8 Utilizing AI Techniques for Detecting Damage in Aerospace Applications 133 Rakesh Kumar C., Naveen R., Kowsalya, Fadhilah Mohd Sakri and Prasath M.S. 8.1 Introduction 134 8.2 Detection of Damage in Composite Materials for Aircraft Components 136 8.2.1 Enhanced Defect Detection with AI: Comparative Analysis 136 8.2.2 Recent Studies on AI in Aerospace Engineering 138 8.3 AI-Based Aircraft Composite Damage Detection 139 8.3.1 Data Collection 140 8.3.2 Image Recognition and Computer Vision 141 8.3.3 Sensor Data Analysis 141 8.3.4 Feature Extraction 141 8.3.5 Machine Learning Models 142 8.3.6 Anomaly Detection 143 8.3.7 Integration of Multiple Data Sources 143 8.3.8 Real-Time Monitoring 143 8.3.9 Human-in-the-Loop Validation 144 8.3.10 Continuous Learning and Improvement 144 8.3.11 Regulatory Compliance 145 8.3.12 Discussion on the Application and Effectiveness of AI in Detecting Damage 145 8.3.13 Improved Detection Accuracy 145 8.3.14 Reduced False Positives and False Negatives 145 8.3.15 Enhanced Predictive Capabilities 146 8.3.16 Comparison with Traditional Methods 146 8.3.17 Limitations and Challenges 146 8.4 AI Methodologies for Defect Detection in Aerospace Manufacturing 147 8.4.1 AI Algorithms 147 8.4.2 Metrics and Evaluation Criteria 147 8.5 Conclusion 148 References 149 9 Sense and Avoid System for Navigation of Micro Aerial Vehicle in Cluttered Environments 151 Anbarasu B., Anitha G., Balaji G., Shabahat Hasnain Qamar, Sathish Kumar K., Naren Shankar R. and Santhosh Kumar G. 9.1 Introduction 152 9.2 Related Works 153 9.3 Proposed Methodology 154 9.4 Sense and Avoid Algorithm 155 9.4.1 Raw Disparity to Depth Conversion 155 9.4.2 Obstacle Detection 156 9.4.3 Collision Avoidance 157 9.5 Experimental Results and Discussions 157 9.6 Conclusions 165 References 165 Part 2: Technological Advancements and Innovations 169 10 A Review on Mixed Reality and Artificial Intelligence for Smart Aviation Sector: Current Trends, Opportunities, and Challenges 171 G. Jegadeeswari, B. Kirubadurai, Jaganraj R. and Vinoth Thangarasu 10.1 Introduction 172 10.2 A Mixed Reality for Smart Aerospace Engineering 174 10.3 Integrated Reality to Enhance the Passenger Experience 177 10.4 Opportunities and Challenges During and Post COVID-19 179 10.5 Conclusion 181 Acknowledgments 182 References 182 11 A Comprehensive Assessment of Unmanned Aerial Vehicles’ Fuel Cell Electric Propulsion Systems 189 Kirubadurai B., Jaganraj R., Jegadeeswari G. and Vinoth Thangarasu 11.1 Introduction 190 11.2 Fuel Cell Types 191 11.3 Machine Learning Technique 192 11.4 Problems with UAVs Powered by FC 192 11.4.1 Issues of On-Board Hydrogen Storage 192 11.4.2 Problem with Limited Power Output 193 11.4.3 Slow-Response Issue 194 11.4.4 Efficiency Issue of FC Propulsion Systems 195 11.4.5 Reinforcement Learning 196 11.5 UAV Hardware Design and Integration 200 11.5.1 Electrical System Diagram Excluding Super Capacitor and Fuel Cell Stack 201 11.6 UAV in the Machine Learning Environment 202 11.6.1 Wireless Network/Computer 202 11.6.2 Smart Cities and Military 202 11.6.3 Agriculture 203 11.7 Conclusion 204 References 204 12 AI-Powered Prediction of Centerline Total Pressure Variations in Coaxial Nozzles by Varying the Lip Thickness 211 R. Naren Shankar, Irish Angelin S., Bakiya Ambikapathy, K. Sathish Kumar and Parvathy Rajendran 12.1 Introduction 212 12.2 Methodology 213 12.3 Results and Discussions 218 12.4 Conclusion 223 References 223 13 Enhancing Jet Noise Reduction: AI-Powered Predictions of Core Length and Total Pressure Variations in Coaxial Nozzles 225 R. Naren Shankar, Irish Angelin S., Bakiya Ambikapathy, K. Sathish Kumar and Parvathy Rajendran 13.1 Introduction 226 13.2 Methodology 227 13.3 Results and Discussions 233 13.4 Conclusion 238 References 238 14 Application of Artificial Intelligence and Machine Learning in Composite Material Design 241 G. Gowtham, S. Nithya and J. V. Saiprasanna Kumar Introduction 242 Overview 243 AI Uses in Different Sectors 246 Challenges and Considerations 249 AI Use in Aircraft Materials 250 Material Discovery and Design 251 Material Optimization 252 Quality Control 254 Predictive Maintenance 255 Composite Material Design 256 Material Recycling 257 Data Analytics for Performance Monitoring 259 Supply Chain Management 259 Energy Efficiency and Sustainability 261 Conclusion 263 References 263 15 Design Optimization Study of UAV Propeller Using Aeroacoustics 265 Prem Kumar P.S., Kirthika S., Kishore Kumar S. and Hariharasubramaniyan A. Nomenclature 266 Introduction 266 Methodology 268 Computational Implementation 268 Domain Generation 269 Meshing 270 Solver Setup and Boundary Conditions 271 Results and Discussion 272 Base Propeller 272 Serration Design 1 272 Serration Design 2 272 Serration Design 3 274 Conclusion and Future Work 275 References 275 16 Autonomous Mapping and AI-Based Navigation Using Deep Learning, SLAM, and Optical Flow for Micro Aerial Vehicle 277 B. Anbarasu, S. Seralathan and A. Muthuram 16.1 Introduction 278 16.2 Related Work 281 16.2.1 AI-Based MAV Navigation 281 16.3 Methodology 282 16.3.1 SLAM System for UAV Navigation 283 16.3.2 US City Block Dataset for MAV Navigation 284 16.3.3 Data Collection for MAV Navigation 286 16.3.4 CNN Model and Preprocessing for MAV Navigation 289 16.3.4.1 CNN Model Training 290 16.3.5 Gunnar-Farnebäck Algorithm 291 16.4 Results and Discussions 292 16.5 Conclusion 298 References 300 Part 3: Performance And Efficiency Optimization 303 17 The Essential Phases in Aircraft Component Manufacturing Using Artificial Intelligence 305 Boopathy G., Rajamurugu N., Siva Prakasam P. and Sai Prasanna Kumar J.V. Abbreviations 306 17.1 Introduction 306 17.2 Precision in Engineering and Design for the Fabrication of Aircraft Components 308 17.2.1 Role of Aerospace Engineers in Production of Aircraft Parts 310 17.2.2 Design Software Utilized in Fabrication of Aircraft Parts 310 17.2.3 Standards for Precision in Performance and Safety of Aircraft Parts 311 17.2.4 Potential of Digital Twins in the Manufacturing of Aircraft Components 312 17.3 Material Selection and Characteristics of Aircraft Parts 313 17.3.1 Significance of Lightweight and Resilient Materials 315 17.3.2 Environmentally Harsh Resistance of Materials 316 17.3.3 Common Materials Used in Aircraft Component Manufacturing 317 17.3.4 Predictive Procurement: Utilizing AI for Strategic Supply Chain Optimization 320 17.4 Manufacturing Techniques and Quality Control Measures 320 17.4.1 Statistical Process Control Using AI for Real-Time Quality Assurance 322 17.5 Assembly Processes and Integration of Aircraft 323 17.6 Routine Maintenance and Inspection of Aircraft Parts 325 17.7 Conclusion 327 References 328 18 Artificial Intelligence in Failure Prediction of Aircraft Components and Inventory Leveraging 333 Vinu Ramadhas, Krishnadhas Subash and K. Vijayaraja 18.1 Introduction 334 18.2 Inspection and Defects 334 18.2.1 Routine Inspections 334 18.2.2 Aircraft Defects 335 18.3 Platform-Centric Data 336 18.3.1 Routine Inspection Database 336 18.3.2 Repair and Component Replacement Database 336 18.3.3 Operational Database 338 18.3.4 Spare FOL Consumption 338 18.3.5 Incident/Accident Details 338 18.3.6 HUMS Database 339 18.4 Asset-Centric Data 339 18.4.1 Aircraft Variant and Numbers 339 18.4.2 Operational and Maintenance Staff 340 18.4.3 Critical Component Float 341 18.4.4 Test Sets and NDT Equipment 341 18.4.5 Mandatory Spare Availability 341 18.5 Fault Tree Analysis 342 18.6 AI-Assisted Application 344 18.6.1 Inspection and Maintenance Changes 344 18.6.2 Modification and Lifing Analysis 345 18.6.3 Exploitation and Operational Limitations 345 18.7 Conclusion 346 References 346 19 Performance Analysis and Optimization of Eppler- 398 Unmanned Aerial Vehicle Using Machine Learning Techniques 349 R. Manikandan, A. Parthiban, T. Gopalakrishnan and Mandeep Singh 19.1 Introduction 350 19.1.1 Eppler Profile 353 19.1.2 Artificial Intelligence Role in Network-Based UAV 356 19.1.3 Wireless Network Issues 356 19.1.4 Design of Network Issues 357 19.1.5 Localization and Trajectory 357 19.2 Experimental Methods 358 19.2.1 Design Phase and Wind Tunnel Testing 358 19.2.2 Flow Visualization Techniques 358 19.3 Computational Model 359 19.3.1 Simulation Setup 359 19.3.2 Aerodynamic Characteristics 360 19.3.3 Airfoil Geometric Creation 361 19.3.4 Grid Generation 362 19.3.5 Applications of Machine Learning in UAV Using Artificial Neural Network (ANN) 364 19.3.6 AI Techniques are Used to Identify and Classify High-Risk Areas and Motion Characteristics of UAVs 367 19.4 Results of Smooth, Bump, and Upper Surface Bumped Eppler-398 Airfoil 368 19.4.1 Validation 375 19.4.2 Flow Visualization Techniques 376 19.5 Ann 377 19.5.1 Enhancing Security and Privacy in UAV Networks with AI 382 19.5.2 Optimizing UAV Network Performance Through Intelligent AI Networking 383 19.5.3 Predictive Maintenance in UAV Networks via AI 384 19.5.4 AI-Driven Localization and Trajectory Planning in UAV Operations 385 19.5.5 Tackling Technical Challenges in AI-UAV Network Integration 385 19.6 Summary and Future Work 386 References 388 20 Navigation of Unconventional Drones — Autonomous Ornithopter 391 Syam Narayanan S., P. Rajalaksmi, Yogesh Gangurde, Akshith Mysa and Satyajit Movidi 20.1 Ornithopters 392 20.1.1 Conventional Versus Unconventional UAVs 392 20.1.2 Brief History 395 20.2 Autonomous Navigation 396 20.2.1 Navigation and Control 396 20.3 Autonomous Navigation for Ornithopters 402 20.3.1 GPS-Based and GPS-Denied Navigation — Comparative Overview 403 20.3.2 Software Systems 404 20.3.2.1 Simultaneous Localization and Mapping (SLAM) 404 20.3.2.2 ORBSLAM3 for Ornithopters 405 20.3.2.3 ROS (Robot Operating System) 407 20.3.2.4 ROS Control and Its Use in Ornithopters 408 20.4 Artificial Intelligence for Ornithopters 410 20.4.1 AI in Navigation 410 20.4.2 AI in Control 410 20.5 Ultra-Wide Band-Based Indoor GPS System for Ornithopters (Case Study) 411 20.5.1 Ultra-Wide Band Technology for Localization 411 20.5.1.1 Advantages of UWB for Localization 412 20.5.2 Indoor GPS Setup 413 20.5.3 Methodology 413 20.5.4 Scope of Navigation Using UWB 415 Conclusion 416 References 416 Index 419

About the Author :
K. Sathish Kumar, PhD is a professor in the Department of Aeronautical Engineering at the Nehru Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India with over 15 years of research and teaching experience. He has authored numerous articles in international journals and serves as a mentor to several start-ups, fostering innovation in aerospace. His research focuses on jet mixing characteristics, nozzle design, and supersonic flow control. R. Naren Shankar, PhD is a professor in the Department of Aeronautical Engineering at Vel Tech Rangarajan Dr. Sagunthala Research and Development Institute of Science and Technology, India. He has published one book and 32 research articles, and has filed three patents. His research interests encompass high-speed jets, aerodynamics, propulsion, and unconventional energy engineering.