Applications of Artificial Neural Networks and Machine Learning in Civil Engineering

• Autore: Kaveh Ali
• Pubblicazione: Cham : , : Springer International Publishing AG, , 2024; ©2024
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (483 pages)
• Nota di contenuto: Intro -- Preface -- Contents -- 1 Artificial Intelligence: Background, Applications and Future -- 1.1 Artificial Intelligence Background -- 1.2 Types of Artificial Intelligence -- 1.2.1 Evolutionary Computation -- 1.2.2 Swarm Intelligence -- 1.2.3 Fuzzy Systems -- 1.2.4 Expert System -- 1.2.5 Chaos Theory -- 1.2.6 Machine Learning -- 1.2.7 Neural Networks -- 1.3 General Structure of Neural Network -- 1.3.1 Feedforward -- 1.3.2 Backpropagation -- 1.3.3 Gradient Vanishing -- 1.3.4 Gradient Exploding -- 1.4 Activation Functions -- 1.4.1 Binary Step Function -- 1.4.2 Linear Activation Function -- 1.4.3 Non-linear Activation Function -- 1.5 Types of Activation Functions -- 1.5.1 Sigmoid Activation Function (Sigmoid | Logistic) -- 1.5.2 Hyperbolic Tangent Activation Function (Tanh | Hyperbolic Tangent) -- 1.5.3 Rectifier Linear Unit Activation Function (ReLU) -- 1.5.4 Leaky Rectifier Activation Function (Leaky ReLU) -- 1.5.5 Parametric Rectifier Activation Function (PReLU) -- 1.5.6 Exponential Linear Unit Activation Function (ELU) -- 1.5.7 Softmax Activation Function -- 1.5.8 Swish Activation Function -- 1.5.9 Gaussian Error Linear Unit Activation Function (GELU) -- 1.5.10 Scaled Exponential Linear Unit Activation Function (SELU) -- 1.5.11 Softplus Activation Function -- 1.5.12 Mish Activation Function -- 1.5.13 Randomized Leaky Rectified Linear Unit Activation Function (RReLU) -- 1.5.14 HardSwish Activation Function -- 1.5.15 Softsign Activation Function -- 1.5.16 HardTanh Activation Function -- 1.5.17 HardSigmoid Activation Function -- 1.5.18 Tanh Shirink Activation Function -- 1.5.19 Soft Shrink Activation Function -- 1.5.20 Hard Shrink Activation Function -- 1.6 Types of Neural Networks -- 1.6.1 Perceptron Neural Network -- 1.6.2 Feedforward Neural Network -- 1.6.3 Radial Basis Neural Network -- 1.6.4 Deep Feed Forward Neural Network. ; 1.6.5 Recurrent Neural Networks -- 1.6.6 Long Short Term Memory -- 1.6.7 Gate Return Unit -- 1.6.8 Auto Encoder Neural Network -- 1.6.9 Variational Auto Encoder Neural Network -- 1.6.10 Denozing Auto Encoder Neural Network -- 1.6.11 Sparse Auto Encoder Neural Network -- 1.6.12 Markov Chain -- 1.6.13 Hopfield Neural Network -- 1.6.14 Boltzmann Machine -- 1.6.15 Limited Boltzmann Machine -- 1.6.16 Deep Belief Network -- 1.6.17 Deep Convolution Network -- 1.6.18 Deconvolution Network -- 1.6.19 Deep Convolutional Inverse Graph Network -- 1.6.20 Generative Adversarial Networks -- 1.6.21 Liquid State Machine -- 1.6.22 Extreme Learning Machine -- 1.6.23 Echo State Network -- 1.6.24 Deep Residual Network -- 1.6.25 Kohonen Network -- 1.6.26 Support Vector Machine -- 1.6.27 Neural Turing Machine -- 1.6.28 Modular Neural Network -- References -- 2 Buckling Resistance Prediction of High-Strength Steel Columns Using Metaheuristic-Trained Artificial Neural Networks -- 2.1 Introduction -- 2.2 Numerical Modeling and Verification -- 2.3 Metaheuristics-Trained Neural Network Model -- 2.3.1 Particle Swarm Optimization -- 2.3.2 Colliding Body Optimization -- 2.3.3 Genetic Algorithm (GA) -- 2.3.4 Particle Swarm Optimization-Genetic Algorithm (PSO-GA) -- 2.3.5 Colliding Body Optimization-Genetic Algorithm (CBO-GA) -- 2.3.6 ANN Model -- 2.4 Results and Discussion -- 2.5 Concluding Remarks -- Appendix A -- Appendix B -- References -- 3 The Use of Artificial Neural Networks and Metaheuristic Algorithms to Optimize the Compressive Strength of Concrete -- 3.1 Introduction -- 3.2 A Brief Explanation of the EVPS and SA-EVPS Algorithms -- 3.3 An Overview of Artificial Neural Networks (ANNS) -- 3.4 A Brief Overview of Taguchi's Method -- 3.5 Numerical Example -- 3.6 Conclusion -- References -- 4 Design of Double Layer Grids Using Backpropagation Neural Networks -- 4.1 Introduction. ; 4.2 Structural Models and Element Grouping -- 4.3 Configuration Processing, Analysis and Design -- 4.4 Software for Training -- 4.5 Training and Testing of the Networks -- 4.5.1 Data for Design -- 4.5.2 Neural Nets for the Evaluation of Maximum Deflection of Double Layer Grids -- 4.5.3 Neural Nets for Predicting the Structural Weights -- 4.5.4 Neural Networks for Structural Design -- 4.6 Data Ordering -- 4.7 Improved Neural Net for Structural Design -- 4.8 Concluding Remarks -- References -- 5 Analysis of Double-Layer Barrel Vaults Using Different Neural Networks -- 5.1 Introduction -- 5.2 Formex Configuration Processing and Formian -- 5.3 Neural Networks -- 5.3.1 Feedforward Backpropagation -- 5.3.2 Feedforward Neural Networks -- 5.3.3 Radial Basis Function -- 5.4 Comparison Between RBF Networks and BP Networks -- 5.5 Extended Radial Basis Function -- 5.6 Nonradial Basis Functions -- 5.7 Metamodeling Using the ERBF Approach -- 5.8 Generalized Regression Neural Network -- 5.9 Generalized Regression Neural Networks Versus Backpropagation Neural Networks -- 5.10 Structural Model and Configuration Processing -- 5.11 Training and Testing the Networks -- 5.11.1 Feedforward Backpropagation Neural Network -- 5.11.2 Radial Basis Function -- 5.11.3 Extended Radial Basis Function -- 5.12 Generalized Regression Neural Networks -- 5.13 Numerical Comparison -- 5.14 Concluding Remarks -- References -- 6 BP and RBF Neural Networks for Predicting Displacements and Design of Schwedler Domes -- 6.1 Introduction -- 6.2 Structural Model -- 6.3 Analysis and Design -- 6.4 BP and RBF Neural Networks -- 6.4.1 Basic Concepts -- 6.4.2 Backpropagation Algorithm -- 6.4.3 Radial Basis Functions Networks -- 6.5 Training and Testing of the Networks -- 6.5.1 Software for Training -- 6.5.2 Neural Networks for Prediction of Deflections -- 6.5.3 Neural Networks for Design. ; 6.6 Concluding Remarks -- References -- 7 Structural Optimization by Gradient-Based Neural Networks -- 7.1 Introduction -- 7.2 The Improved Counter-Propagation -- 7.3 Gradient Computations -- 7.4 The Structure of Neuro-Optimizer -- 7.5 Numerical Results -- 7.6 Concluding Remarks -- References -- 8 Comparative Study of Backpropagation and Improved Counter-Propagation Neural Nets in Structural Analysis and Optimization -- 8.1 Introduction -- 8.2 The Improved Counter-Propagation -- 8.2.1 Network Topology -- 8.2.2 CPN as a Fast Interpolator -- 8.3 Backpropagation Neural Network -- 8.4 Numerical Implementation of the Improved CPN and BPB -- 8.4.1 Example 1 -- 8.4.2 Example 2 -- 8.5 Concluding Remarks -- References -- 9 Hybrid ECBO-ANN Algorithm for Shear Strength of Partially Grouted Masonry Walls -- 9.1 Introduction -- 9.2 Overview of Artificial Neural Networks -- 9.3 Enhanced Colliding Body Optimization Algorithm (ECBO) -- 9.4 Experimental Database Gathering -- 9.5 Quality Assessment Criteria -- 9.6 Discussion -- 9.7 Proposed ECBO-ANN Approach Formulation -- 9.8 Concluding Remarks -- References -- 10 Shape Optimization of Arch Dams with Frequency Constraints by Enhanced Charged System Search Algorithm and Neural Network -- 10.1 Introduction -- 10.2 Geometrical Model of a Double-Curvature Arch Dam -- 10.2.1 Shape of the Central Vertical Section -- 10.2.2 Shape of the Horizontal Section -- 10.3 Finite Element Model of Arch Dam -- 10.3.1 Verification of the Finite Element Model -- 10.4 Arch Dam Optimization -- 10.4.1 Mathematical Model and Optimization Variables -- 10.4.2 Design Variables -- 10.4.3 Design Constraints -- 10.4.4 Objective Function -- 10.5 Enhanced Charged System Search -- 10.5.1 Review of the Charged System Search Algorithm -- 10.5.2 An Enhanced Charged System Search Algorithm -- 10.6 Neural Network -- 10.6.1 BP Neural Network. ; 10.7 Implementation of Arch Dam Optimization -- 10.8 Numerical Results -- 10.8.1 Neural Network Training and Testing -- 10.8.2 Optimization Results -- 10.9 Concluding Remarks -- References -- 11 Estimation of the Vulnerability of the Concrete Structures Using Artificial Neural Networks -- 11.1 Introduction -- 11.2 Nonlinear Dynamic Analysis and Damage Assessment -- 11.3 Artificial Neural Networks -- 11.3.1 Evaluation of Learning and Performance of the Networks -- 11.3.2 Data Classification for Training and Testing of ANNs -- 11.3.3 Training of the ANNs for Predicting the Vulnerability of the Structures -- 11.4 Concluding Remarks -- References -- 12 Efficient Training of Artificial Neural Networks Using Different Meta-Heuristic Algorithms for Predicting the FRP Strength -- 12.1 Introduction -- 12.2 Artificial Neural Network Models -- 12.3 Construction of the Database -- 12.4 Metaheuristic Optimization Technique -- 12.4.1 Genetic Algorithm -- 12.4.2 Particle Swarm Optimization -- 12.4.3 Colliding Bodies Optimization -- 12.4.4 Enhanced Colliding Bodies Optimization -- 12.5 Quality Assessment Criteria -- 12.6 Results and Discussion -- 12.7 Conclusions -- Appendix 12.1: Test Database of CFRP-Wrapped Concrete Specimen [14] -- References -- 13 A Metaheuristic-Based Artificial Neural Network for Plastic Limit Analysis of Frames -- 13.1 Introduction -- 13.2 Plastic Analysis -- 13.3 Soft Computing Methods -- 13.3.1 Metaheuristic Algorithms -- 13.3.2 Firefly Algorithm and Its Enriched Version -- 13.3.3 Artificial Neural Networks -- 13.4 Proposed Method and Numerical Validations -- 13.4.1 Example 1: Two-Bay, Three-Story Frame -- 13.4.2 Example 2: Three-Bay, Three-Story Frame -- 13.4.3 Example 4: Two-Bay Gable Frame -- 13.5 Conclusions -- References -- 14 Wavefront Reduction Using Graphs, Neural Networks and Genetic Algorithm -- 14.1 Introduction. ; 14.2 Definitions.
• Titolo autorizzato: Applications of Artificial Neural Networks and Machine Learning in Civil Engineering
• ISBN: 9783031660511; 9783031660504
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910878059703321
• Lo trovi qui: Univ. Federico II
• Serie: Studies in Computational Intelligence Series