Composite Materials and Structures : Artificial Intelligence-Based Structural Health Monitoring.

Format:

Book

Author/Creator:

Altabey, Wael A.

Series:

De Gruyter STEM Series

Language:

English

Subjects (All):

Structural health monitoring.

Composite materials.

Physical Description:

1 online resource (254 pages)

Edition:

1st ed.

Place of Publication:

Berlin/Boston : Walter de Gruyter GmbH, 2025.

Summary:

Structural Health Monitoring (SHM) in composite structures is crucial for safety, increased lifespan, and cost efficiency with early damage detection.The book introduces the reader to composite materials, basic concepts, terminology, design concepts for composite materials structures, composite manufacturing, fabrication and processing.

Contents:

Intro

Preface

Contents

Chapter 1 Introduction to composite materials

1.1 Introduction to materials

1.1.1 Classification of materials

1.2 Introduction to composite materials

1.2.1 What are composites?

1.2.2 History of composite materials

1.2.3 Advantages and disadvantages

1.2.3.1 Advantages of composite materials

1.2.3.2 Disadvantages of composite materials

1.2.4 Applications of composite materials

1.2.4.1 Space applications

1.2.4.2 Automotive applications

1.2.4.3 Sporting industry applications

1.2.4.4 Marine applications

1.2.4.5 What can be made using composite materials?

1.2.4.6 What is the world market for composites?

1.2.5 Classification of composite materials

1.2.5.1 Particulate composites

1.2.5.2 Flake composites

1.2.5.3 Fiber composites

1.2.5.4 Polymer matrix composites

1.2.5.5 Metal matrix composites

1.2.5.6 Ceramic matrix composites

1.2.5.7 Carbon-carbon composites

Chapter 2 Basic concepts and terminology

2.1 Fibers and matrix

2.1.1 Matrix materials

2.1.2 Functions of a matrix

2.1.3 Properties of a matrix

2.1.4 Factors considered for the selection of matrix

2.1.5 General types of matrix materials

2.1.5.1 Thermosetting matrices (resin)

2.1.5.1.1 Comparison of common thermosetting resins

2.1.5.2 Thermoplastic matrices (resin)

2.1.6 Fiber materials

2.1.7 Functions of a fibers

2.1.7.1 Glass fibers

2.1.7.2 Carbon fibers

2.1.7.3 Aramid fibers

2.1.7.4 Silicon carbide

2.1.7.5 Organic fibers

2.2 Styles of reinforcement

Chapter 3 Design concepts for composite materials/structures

3.1 Introduction

3.1.1 Design considerations

3.1.2 Designing the laminate

3.1.3 Establishing property data

3.1.4 Designing for the environment

3.1.5 Designing for joints and assemblies.

3.1.6 Designing for robustness and through-life performance

3.1.7 Designing for manufacture

3.1.8 Designing for cost

3.2 The need for design management

3.3 The design process

Chapter 4 Composite manufacturing, fabrication, and processing

4.1 Introduction

4.2 Classification of manufacturing processes

4.2.1 Open mold process

4.2.1.1 Wet layup/hand layup

4.2.1.2 Spray layup

4.2.1.3 Filament winding

4.2.1.4 Sheet molding compound

4.2.1.5 Expansion tool molding

4.2.1.6 Contact molding

4.2.2 Closed mold process

4.2.2.1 Compression molding

4.2.2.2 Vacuum bag processing

4.2.2.3 Pressure bag molding

4.2.2.4 Injection molding

4.2.2.5 Cold press molding

4.2.2.6 Resin transfer molding

4.2.2.7 Autoclave molding

4.2.3 Continuous processes

4.2.3.1 Pultrusion

4.2.3.2 Continuous laminating processes

4.2.3.3 Braiding

4.3 Defects in manufactured polymeric composites

Chapter 5 The mechanical behavior of composite materials

5.1 Introduction

5.1.1 Isotropic material

5.1.2 Orthotropic material

5.1.3 Anisotropic material

5.2 Lamina and laminates

5.3 Failure modes of composite materials

5.3.1 Microcracking of the matrix

5.3.2 Fiber pull-out and debonding (separation of fibers and matrix)

5.3.3 Delamination

5.3.4 Breaking of fibers

5.4 Failure mechanisms of composite materials

5.5 Fatigue behavior of composite materials

5.6 Factors affecting the fatigue behavior of composite materials

5.7 Failure criteria of fatigue loading

Chapter 6 Structural health monitoring of composite structures

6.1 Introduction

6.1.1 Capability of nondestructive testing techniques for structural health monitoring

6.1.2 Characteristics of piezoelectric sensors for structural health monitoring.

6.2 Lamb wave technique-based structural health monitoring of composite structures

6.2.1 History and literature behind the Lamb wave technique

6.2.2 Lamb wave modeling and simulation

6.2.3 Lamb wave application in structural health monitoring

6.2.4 Optimal number and configuration of piezoelectric transducers

6.2.5 Lamb wave-based damage identification principle

6.3 Electrical capacitance sensor technique-based structural health monitoring of composite structures

6.3.1 History and literature behind the electrical capacitance sensor technique

6.3.2 Electrical capacitance sensor modeling and simulation

6.3.3 Electrical capacitance sensor electrode excitation strategy

6.3.4 3D electrical capacitance sensor governing equation

6.3.5 Factors affecting the electrical capacitance sensor technique

6.3.6 Effect of the number of electrodes on the performance of electrical capacitance sensors

6.3.7 The life of electrical capacitance sensor

6.4 Fiber-optic sensor technique-based structural health monitoring of composite structures

6.4.1 History and literature behind the fiber-optic technique

6.4.2 Common types of fiber-optic sensors

6.4.3 Description of fiber Bragg grating sensors

6.4.4 Working principle of fiber Bragg grating sensors

6.4.5 Improve the design of the fiber Bragg grating for large-strain sensor

6.5 Artificial intelligence

6.5.1 Machine learning

6.5.2 Deep learning

6.5.3 Artificial neural networks

6.5.4 Damage identification with artificial neural networks in composite structures

6.5.4.1 Gray-box model

Chapter 7 Case studies on structural health monitoring of composite structures

7.1 Structural health monitoring of composite pipelines.

7.1.1 Case study (1): predicting water absorption in composite pipes using electrical capacitance sensors integrated with deep learning approach

7.1.2 Methodology

7.1.2.1 The geometric model

7.1.2.2 Numerical work

7.1.2.2.1 System assumptions

7.1.2.3 The structural-thermal-electrostatic (multi-physics) coupled field modeling

7.1.2.3.1 The static model analysis

7.1.2.3.2 Electrostatic field results

7.1.2.4 The mass of water absorption (M%) monitoring

7.1.2.5 Deep neural networks

7.1.2.5.1 Architecture of the developed deep neural network

7.1.2.5.2 Deep neural network training and test sets

7.1.2.5.3 The training and testing algorithm

7.1.2.5.4 The developed deep neural network predicted data of M%

7.1.2.6 Validity of the proposed technique

7.1.2.6.1 Theoretical validation

7.1.2.6.2 Experimental validation

7.1.2.6.3 Evaluation of present algorithm accuracy and reliability

7.1.2.7 Summary

7.1.3 Case study (2): predicting long-term creep thermomechanical fatigue behavior monitoring in composite pipelines using electrical capacitance sensors integrated with deep learning approach

7.1.3.1 Methodology

7.1.3.2 The geometric model

7.1.3.3 Numerical work

7.1.3.3.1 The structural-thermal-electrostatic modeling analysis

7.1.3.3.2 S-N curve of fatigue behavior for basalt fiber-reinforced polymer composite pipeline

7.1.3.3.3 D-N curve of fatigue damage model for basalt fiber-reinforced polymer composite pipeline

7.1.3.4 Deep neural networks

7.1.3.4.1 Deep neural network configuration for LTCTMF behavior in basalt fiber-reinforced polymer composite pipeline

7.1.3.4.2 Deep neural network training and testing

7.1.3.4.3 The training and testing algorithms

7.1.3.5 Electrical capacitance sensor results for LTCTMF behavior in basalt fiber-reinforced polymer composite pipelines.

7.1.3.6 Validity of the proposed technique

7.1.3.6.1 Theoretical validation

7.1.3.6.2 Experimental validation

7.1.3.7 The deep neural network predicted data of Sf(t)

7.1.3.8 Utilizing the trained deep neural network for predicting nonfinite element model data

7.1.3.9 Summary

7.1.4 Case study (3): structural health monitoring of composite pipelines utilizing fiber optic sensors and machine learning approach

7.1.4.1 Methodology

7.1.4.2 The geometric model

7.1.4.2.1 Damaged pipeline system modeling

7.1.4.2.2 Modal analysis of the pipeline

7.1.4.2.3 Stress-strain analysis in a stressed thick-walled pipe

7.1.4.3 Pipeline monitoring-based fiber Bragg grating sensor technology

7.1.4.4 Design theory of fiber Bragg grating strain sensor array

7.1.4.5 The basalt fiber-reinforced polymer pipeline damage identification model

7.1.4.5.1 A k-nearest neighbor algorithm

7.1.4.5.2 The convolutional neural network modeling

7.1.4.6 The displacement response identification

7.1.4.7 Experimental validation of the proposed method

7.1.4.8 Hybrid convolutional neural network + k-nearest neighbor (ECNN) architecture as a surrogate model

7.1.4.9 The displacement response prediction based on ECNN

7.1.4.10 Summary

7.2 Structural health monitoring of composite ducts

7.2.1 Case Study (4): structural health monitoring of composite dual-chamber muffler using deep learning algorithm for predicting acoustic behavior

7.2.1.1 Methodology

7.2.1.2 Materials and methods

7.2.1.2.1 The geometric model

7.2.1.2.2 Basic acoustic equations of the dual-chamber muffler

7.2.1.2.3 Acoustic properties of composite laminated muffler

7.2.1.2.4 Acoustic transmission loss

7.2.1.3 Artificial neural networks

7.2.1.3.1 Convolutional neural network.

7.2.1.3.2 Recurrent neural network with long short-term memory (RNN-LSTM) blocks.

Notes:

Description based on publisher supplied metadata and other sources.

Part of the metadata in this record was created by AI, based on the text of the resource.

ISBN:

3-11-221309-2

OCLC:

1538444649