Article
Computer Science, Interdisciplinary Applications
Aaditya Chandrasekhar, Krishnan Suresh
Summary: In this study, a new topology optimization method is proposed using neural networks to represent and optimize the density field, resulting in sharp and differentiable boundaries. The research demonstrates that the method is simple to implement and illustrates its application through 2D and 3D examples. Some unresolved challenges with the proposed framework are also summarized.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
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)
Review
Computer Science, Artificial Intelligence
Hamit Taner Unal, Fatih Basciftci
Summary: The review provides a comprehensive overview of the evolutionary design of neural network architectures, focusing on the adoption of evolutionary computation techniques and encoding strategies. It analyzes the historical progress, common challenges, and divides the timeframe into three periods, covering the optimization of simple ANN architectures, rise of powerful methods, and the Deep Learning Era towards configuring advanced models of deep neural networks. The study aims to guide researchers towards promising directions in the field of neural architecture search and provide insights for fully automated machine learning.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Engineering, Multidisciplinary
Yanan Xu, Yunkai Gao, Chi Wu, Jianguang Fang, Guangyong Sun, Grant P. Steven, Qing Li
Summary: This study introduces a machine learning approach for optimizing fiber orientations in variable stiffness CFRP structures, using neural networks to estimate objective functions and design variable sensitivities. By employing active learning and quasi-global search strategies, the ML-based method shows a 12.62% improvement in structural performance compared to conventional FEA-based methods, offering a new alternative for fiber-reinforced composite design.
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING
(2021)
Article
Chemistry, Multidisciplinary
Alex Halle, Lucio Flavio Campanile, Alexander Hasse
Summary: This paper introduces an AI-assisted design method for topology optimization based on an artificial neural network, which generates geometries similar to conventional topology optimizers after training the predictor, but with significantly less computational effort.
APPLIED SCIENCES-BASEL
(2021)
Article
Energy & Fuels
Changsu Kim, Jiyong Kim
Summary: In this study, a machine learning-based approach was developed to predict the performance of Pt/CexZr1-xO2 catalysts in water-gas shift reaction (WGSR). The study identified the key properties of the support material, such as reducibility and thermal stability, that determine the catalyst performance.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2022)
Review
Computer Science, Interdisciplinary Applications
Rebekka V. Woldseth, Niels Aage, J. Andreas Baerentzen, Ole Sigmund
Summary: The question of how artificial intelligence methods can improve traditional frameworks for topology optimization has gained attention in the past few years. While different model variations have been proposed with varying levels of success, few significant breakthroughs have been achieved. The literature tends to have a strong belief in the magical capabilities of artificial intelligence, leading to misunderstandings about its limitations. This article presents a critical review of the current state of research in this field and provides recommendations for future scientific progress.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Review
Computer Science, Artificial Intelligence
Elnaz Gholipour, Ali Bastas
Summary: This review paper utilizes a systematic methodology to analyze the application of neural networks in pharmaceutical manufacturing technologies. It identifies process analysis and improvement, quality control, and additive manufacturing as the three main research themes in this area. The paper proposes potential paths and research questions for future studies and emphasizes the importance of sustainability in manufacturing technology research.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Biochemistry & Molecular Biology
Alexey Strokach, Philip M. Kim
Summary: Deep learning approaches have made significant contributions in protein design and generative models can create millions of novel proteins similar to native ones. These models can learn protein representations that are more informative than hand-engineered features, and the design process can be guided by discriminative models.
CURRENT OPINION IN STRUCTURAL BIOLOGY
(2022)
Article
Chemistry, Analytical
Sergio Alvarez-Rodriguez, Francisco G. Pena-Lecona
Summary: This article presents the design and implementation of backpropagated multilayer artificial neural networks for information processing generated by an optical encoder. A machine learning technique is proposed to train the neural networks to predict the angular position of the rotating element with remarkable accuracy. The proposed neural designs show excellent performance in small angular intervals and a methodology was proposed to avoid losing this remarkable characteristic in measurements.
Article
Automation & Control Systems
Reza Karimzadeh, Mohsen Hamedi
Summary: This paper proposes a topology optimization algorithm based on the SIMP method, which combines data clustering and neural networks to enhance sensitivity analysis, capable of generating a support-free part design with desirable compliance. The experimental results demonstrate promising savings in material usage and manufacturing time.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Weisheng Zhang, Yue Wang, Sung-Kie Youn, Xu Guo
Summary: This study proposes a sketch-guided topology optimization approach based on machine learning, which incorporates computer sketches as constraint functions to improve the efficiency of computer-aided structural design models and meet the design intention and requirements of designers.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Computer Science, Artificial Intelligence
Zhenyang Gao, Guoying Dong, Yunlong Tang, Yaoyao Fiona Zhao
Summary: This article proposes a machine learning aided design method to generate conformal cooling systems that match the thickness distribution of the part, solving the temperature variance issue. By optimizing the design parameters, the proposed method achieves better temperature control and lower coolant pressure drop compared to conventional designs.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Review
Biochemistry & Molecular Biology
Varnavas D. Mouchlis, Antreas Afantitis, Angela Serra, Michele Fratello, Anastasios G. Papadiamantis, Vassilis Aidinis, Iseult Lynch, Dario Greco, Georgia Melagraki
Summary: De novo drug design is a process of generating novel molecular structures using computational methods, with traditional approaches including structure-based and ligand-based design. Artificial intelligence and machine learning have a positive impact in this field.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Mathematics
Amichai Mitelman, Alon Urlainis
Summary: The potential of machine learning for enhancing geotechnical analysis is recognized, but obtaining a large enough digital dataset is a challenge. This paper investigates the use of transfer learning in overcoming dataset size limitations in tunnel support analysis. The study demonstrates the effectiveness of transfer learning and suggests its potential as a valuable tool for ML-related geotechnical applications with further development and refinement.
Article
Engineering, Industrial
Huy T. Tran, Michael Balchanos, Jean Charles Domercant, Dimitri N. Mavris
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2017)
Article
Computer Science, Information Systems
Huy T. Tran, Jean Charles Domercant, Dimitri N. Mavris
IEEE SYSTEMS JOURNAL
(2019)
Article
Engineering, Civil
Karl H. Thompson, Huy T. Tran
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2020)
Article
Computer Science, Information Systems
Aleksandra Markina-Khusid, Ryan B. Jacobs, Laura Antul, Lance Cho, Huy T. Tran
Summary: This article introduces a framework for rapid and quantitative evaluation of robustness in SoS architectures, leveraging complex network methods and design of experiments techniques. Two case studies demonstrate that most network metrics capture expected robustness trends, although they may be impacted by the specific scenario.
IEEE SYSTEMS JOURNAL
(2022)
Article
Robotics
Mateus Gasparino, Arun N. Sivakumar, Yixiao Liu, Andres E. B. Velasquez, Vitor A. H. Higuti, John Rogers, Huy Tran, Girish Chowdhary
Summary: We propose a self-supervised learning approach for wheeled mobile robots to predict traversable paths. Our method autonomously generates paths using RGB and depth data, along with navigation experience, and trains a neural network using online traction estimates, avoiding the need for heuristics used by previous methods.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Walker L. Dimon, Nicholas B. Chase, Neale Van Stralen, Rupal Nigam, Michael F. Lembeck, Huy T. Tran
Summary: We propose a novel GAN-based method, D-AnoGAN, for unsupervised anomaly detection in multi-class, disconnected data manifolds. The method takes into account potential discontinuities between different manifolds through clustering and uses a multi-generator network and a bandit algorithm to cover all data manifolds. Experimental results demonstrate the effectiveness of the proposed method on multiple datasets, and a software package is introduced to generate parameterized disconnected manifold datasets for real-world applications.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Article
Engineering, Civil
Jacob Heglund, Kenneth M. Hopkinson, Huy T. Tran
Summary: This paper examines the value of using social media data to improve the resilience of critical infrastructure. The authors found statistically significant correlations between Twitter and power system data and developed models for forecasting future behaviors in the power system.
SUSTAINABLE AND RESILIENT INFRASTRUCTURE
(2021)
Article
Economics
Allen Wong, Sijian Tan, Keshav Ram Chandramouleeswaran, Huy T. Tran
TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW
(2020)
Proceedings Paper
Engineering, Aerospace
Laura Antul, Sean Ricks, Lance (Mann Kyo) Cho, Matt Cotter, Ryan B. Jacobs, Aleksandra Markina-Khusid, Janna Kamenetsky, Judith Dahmann, Huy T. Tran
2018 IEEE AEROSPACE CONFERENCE
(2018)
Proceedings Paper
Computer Science, Information Systems
Huy T. Tran, Jean Charles Domercant, Dimitri N. Mavris
2017 11TH ANNUAL IEEE INTERNATIONAL SYSTEMS CONFERENCE (SYSCON)
(2017)
Proceedings Paper
Computer Science, Hardware & Architecture
Huy T. Tran, Jean Charles Domercant, Dimitri N. Mavris
COMPLEX ADAPTIVE SYSTEMS
(2016)
Article
Engineering, Multidisciplinary
Huy T. Tran, Jean Charles Domercant, Dimitri N. Mavris
JOURNAL OF DEFENSE MODELING AND SIMULATION-APPLICATIONS METHODOLOGY TECHNOLOGY-JDMS
(2015)
Proceedings Paper
Automation & Control Systems
Michael G. Balchanos, Jean Charles Domercant, Huy T. Tran, Dimitri N. Mavris
2014 7TH INTERNATIONAL SYMPOSIUM ON RESILIENT CONTROL SYSTEMS (ISRCS)
(2014)