From the start of life, people used their brains to make something better in design in ordinary works. Due to that, metaheuristics are essential to living things, and several inspirations from life have been used in the generation of new algorithms. These algorithms have unique features, but the usage of different features of different algorithms may give more effective optimum results in means of precision in optimum results, computational effort, and convergence.
This book is a timely book to summarize the latest developments in the optimization of structural engineering systems covering all classical approaches and new trends including hybrids metaheuristic algorithms. Also, artificial intelligence and machine learning methods are included to predict optimum results by skipping long optimization processes. The main objective of this book is to introduce the fundamentals and current development of methods and their applications in structural engineering.
Author(s): Gebrail Bekda, Sinan Melih Nigdeli
Series: Studies in Systems, Decision and Control
Publisher: Springer
Year: 2023
Language: English
Pages: 306
Preface
Contents
Introduction and Overview: Hybrid Metaheuristics in Structural Engineering—Including Machine Learning Applications
1 Introduction
2 Metaheuristics
3 Artificial Intelligence and Machine Learning
4 Overview of the Book Content
References
Hybrid Metaheuristics
The Development of Hybrid Metaheuristics in Structural Engineering
1 Introduction
2 Metaheuristic Algorithms and Optimization
3 The Structural Optimization Problems
3.1 Objective Function
3.2 Design Constraints
4 Review of Structural Engineering Applications Using Hybrid Algorithms
5 Conclusion
References
Optimum Design of Reinforced Concrete Columns in Case of Fire
1 Introduction
2 Design of Reinforced Concrete Column According to Eurocode 2
3 Hybrid Metaheuristic Algorithm
4 Numerical Examples
5 Results and Conclusion
References
Hybrid Social Network Search and Material Generation Algorithm for Shape and Size Optimization of Truss Structures
1 Introduction
2 Utilized Methods
2.1 Social Network Search
2.2 Material Generation Algorithm
3 Hybrid Method
4 Problem Statement
5 Design Examples
5.1 Describing the Examples
5.2 Numerical Results
6 Conclusion
References
Development of a Hybrid Algorithm for Optimum Design of a Large-Scale Truss Structure
1 Introduction
2 Jaya Algorithm and Flower Pollination Algorithm
3 Hybridization of Metaheuristics
4 Design of Truss Structure
5 Numerical Investigations for 72-Bar Truss
6 Conclusions
References
Structural Control Systems and Tuned Mass Damper Optimization by Using Jaya and Hybrid Algorithms
1 Introduction
2 Vibration
3 Structure Control Systems
3.1 Passive Control System
3.2 Active Control System
3.3 Semi-Active Control System
3.4 Hybrid Control System
4 Metaheuristic Algorithms
4.1 Jaya Algorithm
4.2 Hybrid Algorithm
5 Numerical Example
6 Conclusion
References
Manta Ray Foraging and Jaya Hybrid Optimization of Concrete Filled Steel Tubular Stub Columns Based on CO2 Emission
1 Introduction
2 Optimization Methodology
2.1 Jaya Optimization
2.2 Manta Ray Foraging Optimization (MRFO)
3 Result Analysis
4 Conclusion
References
Optimum Design of Dam Structures Using Multi-objective Chaos Game Optimization Algorithm
1 Introduction
2 Optimization Problem Formulation
2.1 Concrete Volume
2.2 Natural Frequency
3 Developed Method
3.1 Single Objective Chaos Game Optimization
3.2 Multi-Objective Chaos Game Optimization
4 Numerical Results
4.1 Arch Dam Modeling [2]
4.2 Results and discussion
5 Conclusion
References
Machine Learning
The State of Art in Machine Learning Applications in Civil Engineering
1 Introduction
2 Historical Development of Machine Learning
3 Machine Learning Types
3.1 Supervised Learning
3.2 Unsupervised Learning
3.3 Semi-Supervised Learning
3.4 Reinforcement Learning
4 Machine Learning Algorithms
4.1 Random Forest (RF)
4.2 Decision Tree (DT)
4.3 Naive Bayes (NB)
4.4 Support Vector Machine (SVM)
4.5 K-Nearest Neighbors (KNN)
4.6 Logistic Regression (LR)
5 Evaluation of Classifier Performances
5.1 Confusion Matrix
5.2 Performance Metrics
6 Evaluation of Regressor Performances
6.1 R2 (Coefficient of Determination)
6.2 Mean Absolute Error (MAE)
6.3 Mean Squared Error (MSE)
6.4 Root Mean Squared Error (RMSE)
6.5 Mean Absolute Percentage Error (MAPE)
7 Overfitting and Underfitting
8 Machine Learning in Civil Engineering
8.1 Structural Engineering
8.2 Geotechnical Engineering
8.3 Hydraulic Engineering
8.4 Construction Management
8.5 Transportation Engineering
9 Summary and Conclusions
References
Machine Learning Application of Structural Engineering Problems
1 Introduction
2 Methodology
2.1 Optimum Design of Structural System Elements with Jaya Algorithm
2.2 Design Parameters for Tubular Column and I-Beam Optimization
2.3 Class Prediction of Column and Beam Sections with Machine Learning
3 Numerical Examples
3.1 Tubular Column
3.2 I-Section Beam
4 Discussion and Conclusions
References
Modeling Civil Engineering Problems via Hybrid Versions of Machine Learning and Metaheuristic Optimization Algorithms
1 Introduction
2 Design Problem Definition
2.1 Lake Level
2.2 Pile Group Design
3 Solution Algorithms
3.1 Machine Learning Algorithm
3.2 Metaheuristic Optimization Algorithms
4 Implementation of Hybrid Optimization Algorithms
4.1 Hybrid Optimization Algorithms
4.2 Dataset of Lake Level(LL)
4.3 Date Set of Pile Group (PG)
4.4 Design Optimization Problem
5 Hybrid Optimization Algorithms Results
5.1 Optimization Analyses
5.2 Performance of Hybrid Algorithms
6 Discussions
7 Conclusions
References
Comparison of Multilayer Perceptron and Other Methods for Prediction of Sustainable Optimum Design of Reinforced Concrete Columns
1 Introduction
2 Material and Methods
2.1 Generating a Dataset via Optimization Algorithm
2.2 Data Description
2.3 Machine Learning
2.4 K Fold Cross Validation
2.5 Performance Criterion
3 Results and Discussion
4 Conclusion
References
Artificial Intelligence and Deep Learning in Civil Engineering
1 Introduction
2 Artificial Intelligence (AI)
2.1 Deep Learning
2.2 Deep Learning in Civil Engineering
3 Summary and Conclusions
References
Deep Learning-Based Framework for Reconstruction and Optimisation of Building Information Models Containing Parametric Rules
1 Introduction
2 Methodology
2.1 Optimal Design Formulation
2.2 Building Behaviour Forecasting with Deep Neural Net
3 Results and Discussion
3.1 Performance Assessment Using Deep Learning
3.2 Evaluation of Alternative Designs
3.3 Generation and Optimisation of BIM Models
4 Conclusions
References
