Article
Computer Science, Artificial Intelligence
Nikos Ath. Kallioras, Nikos D. Lagaros
Summary: This study proposes a novel DL-SCALE method to enhance the computational efficiency of solving structural topology optimization problems. Experimental results demonstrate the significant advantages of DL-SCALE in reducing computing time and iteration numbers.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Automation & Control Systems
Lu Zhao, Yan Wan, Chenyuan He, Frank L. Lewis
Summary: This article investigates the identifiability and estimation problems of the reduced-order stochastic network model (IM), and provides succinct conditions for both homogeneous and heterogeneous IMs. It also develops reduced-order parameter estimation algorithms for the IMs with reduced computation.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Yi Xing, Liyong Tong
Summary: In this work, a machine learning-assisted structural optimization (MLaSO) scheme is proposed to accelerate the computational speed of structural optimization. A new machine learning model is used to predict the update of the optimization quantity during the optimization process, eliminating the need for finite element analysis and sensitivity analysis. The MLaSO scheme can be easily integrated into different structural optimization methods and does not require additional training datasets.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Computer Science, Artificial Intelligence
Mateus Roder, Leandro Aparecido Passos, Gustavo H. de Rosa, Victor Hugo C. de Albuquerque, Joao Paulo Papa
Summary: The paper introduces a weighted layer-wise information reinforcement approach for Deep Belief Networks, along with metaheuristic optimization to improve the network's learning capabilities. Experiments confirm the effectiveness of the proposed method in image classification tasks.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Interdisciplinary Applications
Nolan Black, Ahmad R. Najafi
Summary: Concurrent multiscale structural optimization aims to improve macroscale structural performance by designing microscale architectures. This work uses deep learning models to increase microstructure complexity. The deep neural network is implemented as a model for both microscale structural properties and material shape derivatives. Compared to traditional methods, the deep neural network achieves sufficient accuracy and stability in structural optimization.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Article
Automation & Control Systems
Jaydeep Rade, Aditya Balu, Ethan Herron, Jay Pathak, Rishikesh Ranade, Soumik Sarkar, Adarsh Krishnamurthy
Summary: Researchers have explored machine learning-based topology optimization methods to alleviate the computational intensity issue, but current methods still face challenges in handling high-resolution and complex three-dimensional components. This paper proposes a deep-learning-based framework that trains multiple networks to learn different steps of the topology optimization method, achieving better results than current ML-based methods.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Engineering, Multidisciplinary
Chunpeng Wang, Song Yao, Zhangjun Wang, Jie Hu
Summary: A deep-learning approach is proposed to predict an optimized high-resolution structure with multi-boundary conditions, establishing a mapping relationship between low- and high-resolution structures for the topology optimization problem. The method demonstrates the ability to accurately predict high-resolution structures in a negligible computational time and has potential for practical applications in large-scale structural design in the future.
ENGINEERING OPTIMIZATION
(2021)
Article
Engineering, Multidisciplinary
Waad Almasri, Dimitri Bettebghor, Faouzi Adjed, Florence Danglade, Fakhreddine Ababsa
Summary: This study integrates layout and mechanical constraints in the mechanical design process using deep learning technology and proposes a DL-layout-driven solution trained via a generative adversarial network framework. The solution can quickly generate mechanically valid designs conforming with layout constraints and has the capability to generate multiple shapes based on different input constraints.
ENGINEERING OPTIMIZATION
(2022)
Article
Physics, Multidisciplinary
Andrea Santoro, Federico Battiston, Giovanni Petri, Enrico Amico
Summary: Time series analysis is a powerful method to understand various phenomena in biology, neuroscience, and economics. We propose a framework to characterize the temporal evolution of higher-order dependencies within multivariate time series. Through network analysis and topology, our framework effectively distinguishes different spatiotemporal states of coupled chaotic maps. We demonstrate the significance of higher-order patterns in real-world data from brain activity, financial markets, and epidemics using simulated dynamical processes as a guide.
Article
Engineering, Multidisciplinary
Minsik Seo, Seungjae Min
Summary: DL-MSTO+ is a deep learning-based multi-scale topology optimization framework that improves the efficiency of multi-scale topology optimization by reducing the dimensionality of design variables and predicting homogenized material properties. The framework includes two distinct deep neural networks for learning the low-dimensional representation of material microstructures and predicting the homogenized elasticity matrix. The proposed method demonstrates higher efficiency than the conventional multi-scale approach in numerical experiments and provides connectable multi-scale designs.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Martin Ohrt Elingaard, Niels Aage, Jakob Andreas Baerentzen, Ole Sigmund
Summary: This paper presents a deep learning-based de-homogenization method for structural compliance minimization, showing excellent generalization properties and performance within 7-25% of homogenization-based solutions at a fraction of the computational cost, while being robust and insensitive to domain size, boundary conditions, and loading.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Shuai Zhang, Bo Yin, Weiyi Zhang, Yu Cheng
Summary: This paper proposes a two-stage topology-aware deep learning framework that leverages graphical neural network techniques to optimize wireless networks. By properly encoding the network structure, it improves the learning target and achieves better performance.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Interdisciplinary Applications
Eun-A Sim, Seunghye Lee, Jeongmin Oh, Jaehong Lee
Summary: This paper presents a novel combination of Generative Adversarial Networks (GANs) and Clustering Analysis (CA) for topology optimization, which generates new data and selects optimized data through clustering analysis. A Topology Optimization Validation Curve (TOVC) is successfully developed through the entire volume fraction of the structure, demonstrating the adaptability and efficiency of the proposed method for topology optimization.
ADVANCES IN ENGINEERING SOFTWARE
(2021)
Article
Computer Science, Interdisciplinary Applications
Ren Kai Tan, Chao Qian, Kangjie Li, Dan Xu, Wenjing Ye
Summary: Topology optimization is a systematic approach for obtaining optimal performance in structural design, but it can be computationally expensive and deep learning models lack generalizability. This work proposes an adaptive, scalable deep learning-based model-order-reduction method using MapNet to accelerate large-scale topology optimization. The method allows simulations to be performed at a coarser mesh, reducing computational time, and introduces domain fragmentation to improve the method's transferability and scalability.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Minsik Seo, Seungjae Min
Summary: In this paper, a novel deep learning-aided material representation scheme is proposed for multi-scale topology optimization. This method establishes a general-purpose mapping from a low-dimensional variable to microstructural images using a deep generative model and a regression model. The generator and predictor networks are then integrated into the optimization process to reduce design variables and eliminate homogenization computations. The proposed method enables faster convergence and automatic satisfaction of complicated geometrical constraints.
ADVANCES IN ENGINEERING SOFTWARE
(2022)
Review
Computer Science, Interdisciplinary Applications
Nikos D. Lagaros, Vagelis Plevris, Nikos Ath Kallioras
Summary: This study provides a comprehensive review of the developments and applications of metaheuristic optimization algorithms (MOAs) in structural optimization problems. It also includes a series of tests to evaluate the efficiency of these algorithms. The findings are significant for solving real-world structural design optimization problems.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2022)
Article
Chemistry, Physical
George Kazakis, Nikos D. Lagaros
Summary: This article presents a simple Matlab code for solving topology optimization in material design with three different model order reduction approaches, including proper orthogonal decomposition (POD), on-the-fly reduced order model construction, and approximate reanalysis (AR).
Editorial Material
Chemistry, Multidisciplinary
Nikos D. Lagaros, Vagelis Plevris
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Interdisciplinary Applications
Konstantinos-Iason Ypsilantis, Matthias G. R. Faes, Jan Ivens, Nikos D. Lagaros, David Moens
Summary: This work proposes a methodology for concurrent homogenization-based optimization of microstructure type and configuration in the structural domain. The methodology combines discrete multi-material optimization with homogenization-based topology optimization to determine a unique microstructure type per element in the structure.
COMPUTERS & STRUCTURES
(2022)
Article
Construction & Building Technology
Evangelia Frangedaki, Laura Sardone, Giuseppe Carlo Marano, Nikos D. Lagaros
Summary: This study explores the design optimization in architectural and structural engineering design using digital tools and services. Optimization, previously considered a complex mathematical tool, has become more user-friendly and efficient, making it attractive for early stage architectural design. Customized structural design optimization services have emerged as an alternative to all-encompassing digital tools. The paper presents strategies for parameterizing variables in architectural synthesis and provides a review of optimization processes and tools in the field. Real-world applications of parametric optimization in the built environment are also discussed.
PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-STRUCTURES AND BUILDINGS
(2023)
Article
Parasitology
Emily Kate Francis, Jan Slapeta
Summary: Sampling in New South Wales, Australia revealed that untreated feral goats harbor genetic markers associated with anthelmintic resistance, suggesting that wild ruminants could serve as reservoirs for anthelmintic resistance.
Article
Chemistry, Multidisciplinary
Georgios Kazakis, Nikos D. Lagaros
Summary: This research aims to provide a simplified MATLAB code to address the challenge of multi-scale concurrent topology optimization. By utilizing the Bi-directional Evolutionary Structural Optimization (BESO) method, it optimizes both the macro-scale and micro-scale simultaneously, taking into account their interactions and interdependencies. This advancement is significant in the field of topology optimization and enhances its applications across various engineering disciplines.
APPLIED SCIENCES-BASEL
(2023)
Article
Construction & Building Technology
Mohammed A. Almomani, Nedal Al-Ababneh, Khairedin Abdalla, Nadim I. Shbeeb, John-Paris Pantouvakis, Nikos D. Lagaros
Summary: Upgrading the Syrian refugee shelter design using 3D concrete printing is a promising method to provide durable shelters. This research uses the Analytical Hierarchal Process to select the best technology for constructing these shelters, with contour crafting being identified as the most suitable technology.
Article
Engineering, Multidisciplinary
Konstantinos-Iason Ypsilantis, George Kazakis, Matthias G. R. Faes, Jan Ivens, Nikos D. Lagaros, David Moens
Summary: This work proposes a filtering technique for the optimization of composite structures, specifically focusing on topology and fiber orientation. The filter is designed to couple morphology and topology, suppress the impact of finite element morphology, and steer fiber orientation towards topologically dense areas. It is crucial for boundary optimization, where fiber orientation needs to conform to local morphology.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Construction & Building Technology
Spyros Damikoukas, Stavros Chatzieleftheriou, Nikos D. Lagaros
Summary: This study introduces a new seismic assessment protocol for buildings before and after earthquakes, emphasizing the importance of using recorded structural response data for assessment, while also pointing out that data collection nowadays does not require expensive equipment and over-qualified personnel.
Article
Humanities, Multidisciplinary
Iordanis A. Naziris, Chara Ch Mitropoulou, Nikos D. Lagaros
Summary: Fire protection for cultural heritage structures is a challenging task that can benefit from performance-based design and computational tools. This study proposes a computational selection and resource allocation model and applies it to two case studies, demonstrating its effectiveness and utility in optimizing fire protection designs.
Article
Environmental Studies
G-Fivos Sargentis, Nikos D. Lagaros, Giuseppe Leonardo Cascella, Demetris Koutsoyiannis
Summary: The formation of societies is influenced by spatial clustering, which optimizes economies of scale in the management of the water-energy-food nexus. The current conflict and economic sanctions on Russia significantly impact society, particularly in terms of energy and food supply. Cities that rely on a wider area for energy and food are highly vulnerable, and the problem is exacerbated by recent urbanization.
Article
Humanities, Multidisciplinary
Iordanis A. Naziris, Chara Ch Mitropoulou, Nikos D. Lagaros
Summary: The preservation of cultural heritage structures requires efficient fire protection design processes. Performance-Based (PB) approaches are more effective in dealing with the conflict between authenticity preservation, special fire protection measures, and the unique needs of such structures. In this study, a Multi-Criteria Decision Making (MCDM) problem is used to upgrade the fire safety level of cultural heritage structures. The proposed model incorporates the Analytic Hierarchy Process (AHP) to assess fire safety and authenticity preservation levels. Two multi-criteria optimization approaches are applied to generate optimized solutions for the fire safety upgrading scheme.
Article
Construction & Building Technology
Chara Ch. Mitropoulou, Iordanis A. Naziris, Nikos Ath. Kallioras, Nikos D. Lagaros
Summary: This study examines the minimization problem of the torsional response of an eccentric, multi-story reinforced concrete (RC) building by strengthening its vertical structural elements with RC jackets. The lateral-torsional response of such structural systems can result in higher ductility demands on the perimeter of the plan view.
FRONTIERS IN BUILT ENVIRONMENT
(2022)
Article
Construction & Building Technology
Rajai Al-Rousan, Osama Nusier, Khairedin Abdalla, Mohammad Alhassan, Nikos D. Lagaros
Summary: This research paper investigates the effects of using carbon-fiber-reinforced polymer (CFRP) laminates on the structural response and failure mode of damaged-by-sulfate concrete-filled tubular (CFT) circular steel columns under combined axial and cyclic lateral loads. The study found that the performance of CFT circular steel column models significantly improved when wrapped with 5 to 10 layers of CFRP. Using 8 to 10 layers of CFRP showed similar results. The results also showed that externally repairing the damaged-by-sulfate models with CFRP wraps enhanced their cyclic behavior, increasing load capacity, horizontal displacement, displacement ductility, energy dissipation, and having little effect on secant stiffness.