Artificial Intelligence-Based Design of Reinforced Concrete Structures

Artificial Neural Networks for Engineering Applications

1st Edition - April 29, 2023
Author: Won-Kee Hong
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 2 5 2 - 8
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 2 5 3 - 5

Artificial Intelligence-Based Design of Reinforced Concrete Structures: Artificial Neural Networks for Engineering Applications is an essential reference resource for readers w… Read more

Purchase options

Limited Offer

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code needed.

Institutional subscription on ScienceDirect

Request a sales quote

Artificial Intelligence-Based Design of Reinforced Concrete Structures: Artificial Neural Networks for Engineering Applications is an essential reference resource for readers who want to learn how to perform artificial intelligence-based structural design. The book describes, in detail, the main concepts of ANNs and their application and use in civil and architectural engineering. It shows how neural networks can be established and implemented depending on the nature of a broad range of diverse engineering problems. The design examples include both civil and architectural engineering solutions, for both structural engineering and concrete structures.

Those who have not had the opportunity to study or implement neural networks before will find this book very easy to follow. It covers the basic network theory and how to formulate and apply neural networks to real-world problems. Plenty of examples based on real engineering problems and solutions are included to help readers better understand important concepts.

Cover image
Title page
Table of Contents
Copyright
Preface
1. Design of reinforced concrete beams and columns based on artificial neural networks
1.1. What can be learned from this book?
1.2. An evolution of artificial neural networks in civil engineering
1.3. Common machine learning versus artificial neural networks with deep learning using deep layers
1.4. Accuracy and interpretability of common artificial intelligence models
2. Understanding artificial neural networks: analogy to the biological neuron model
2.1. A learning and memory capability similar to that of the human brain
2.2. Activation functions
3. Factors influencing network trainings
3.1. Requirement for good training accuracies
3.2. Data initialization
3.3. Data normalization
3.4. Multilayer perception
3.5. Training, validation, testing, and design
3.6. Backpropagation for adjusting weights and bias
3.7. Conclusions
4. Forward and backpropagation for artificial neural networks
4.1. Gradient descent algorithm
4.2. A simple artificial neural network with forward propagation algorithm for a reinforced concrete beam
4.3. Conclusions
5. Training methods: designs based on training entire data, parallel training method, chained training scheme, and chained training scheme with revised sequence
5.1. Past studies
5.2. Significance of the chapter
5.3. Machine learning models versus deep layers based on artificial neural networks for structural engineering applications
5.4. Artificial neural networks and big data generation
5.5. Feature selection scores
5.6. Training methods, TED, PTM, CTS, and CRS
5.7. Chained training scheme with revised sequence
5.8. Conclusions
6. Singly reinforced concrete beams based on regression models and artificial neural networks
6.1. Significance of the chapter
6.2. Generation of big data
6.3. Beam design by an ANN based on TED (training on entire inputs and outputs simultaneously); one forward problem and four reverse problems
6.4. Singly reinforced concrete beams based on shallow neural network
6.5. Design of singly reinforced concrete beams (machine learning)
6.6. Recommendations and conclusions
7. Design of doubly reinforced concrete beams based on artificial neural network (deep learning) and regression models (machine learning)
7.1. Introduction
7.2. Motivation of the artificial neural network–based design
7.3. Deep neural networks for structural engineering
7.4. Generation of large structural datasets and network training
7.5. Design of doubly reinforced concrete beams based on artificial neural network
7.6. ANN-based reverse design charts based on ACI 318-19
7.7. Reverse designs using Gaussian process regression models enhanced by sequence training/designing technique based on feature selection algorithms
7.8. Feature selections for training structural datasets
7.9. Chained training scheme with Revised Sequence
7.10. Conclusion
8. Design of reinforced columns based on artificial neural networks
8.1. Introduction
8.2. Design of concrete columns
8.3. Generation of big data
8.4. Column design by artificial neural networks based on training networks on entire data, parallel training method, and chained revised sequence: one forward design and five reverse designs
8.5. Verification of an ANN-based optimization by ANN-based Lagrange and large datasets
8.6. Recommendations and conclusions
Appendix A: Manual to use MATLAB for training artificial neural networks
Appendix B: MATLAB code for Revise Scenario 4 of Table 8.4.1
Index

Life sciences

Physical sciences & Engineering

Social sciences & Humanities

Health