Article
Chemistry, Multidisciplinary
Maurice Preidel, Rainer Stark
Summary: Developing smart services as part of smart service systems requires adequate data, and there is a lack of systematic support for specifying data relevant to smart services. The SemDaServ approach integrates design research methodology and utilizes domain knowledge and semantic models to address data specification challenges effectively.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Physical
Shijian Wang, Sai Zhao, Xin Guo, Guoxiu Wang
Summary: 2D materials are considered promising electrode materials for rechargeable batteries due to their advantages in active sites and reaction kinetics. Challenges remain for these materials to meet all requirements for high-performance energy storage devices. Recent advances in 2D material-based heterostructures offer opportunities for enhanced performance.
ADVANCED ENERGY MATERIALS
(2022)
Article
Computer Science, Software Engineering
Silverio Martinez-Fernandez, Justus Bogner, Xavier Franch, Marc Oriol, Julien Siebert, Adam Trendowicz, Anna Maria Vollmer, Stefan Wagner
Summary: AI-based systems are increasingly prevalent in society, but there is limited knowledge on software engineering approaches for building, operating, and maintaining these systems. Through a systematic mapping study, we identified the state-of-the-art knowledge and challenges in software engineering for AI-based systems, and classified the approaches according to different areas. Our results have valuable implications for researchers, practitioners, and educators.
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Alexis Cvetkov-Iliev, Alexandre Allauzen, Gael Varoquaux
Summary: For many machine learning tasks, improving performance requires augmenting the data table with features derived from external sources. This study proposes replacing manually crafted features with vector representations of entities, such as cities, that capture relevant information. The research shows the importance of modeling entity relationships and capturing numerical attributes for creating effective feature vectors from relational data.
Article
Engineering, Marine
Chuntong Li, Pengyu Wei, Xiaomeng Luo, Ze Jiang, Deyu Wang
Summary: Computer-aided design (CAD), computer-aided engineering (CAE), and virtual reality (VR) are integrated into a unified tool for ship structure design/analysis/virtual evaluation based on Multi-Domain Feature Mapping (MDFM). This tool utilizes Extensible Markup Language (XML) to establish a multi-layer transmission and matching mechanism between data, information and knowledge, allowing CAD, CAE, and VR to be interconnected. Additionally, a visual expression strategy of CAD model and FEA data based on Unified Mesh Model (UMM) is proposed for virtual visualization and model reconstruction and evaluation. The effectiveness of this tool is demonstrated through engineering examples.
Article
Chemistry, Multidisciplinary
Andreas Rausch, Azarmidokht Motamedi Sedeh, Meng Zhang
Summary: Autonomous systems like driverless taxis play critical safety roles with the help of AI techniques, which rely heavily on the quality of training data. Novelty detection becomes a safety measure in system development and operation, ensuring accurate performance by identifying data that differ from the training set.
APPLIED SCIENCES-BASEL
(2021)
Article
Crystallography
Juan Gomez-Peralta, Nidia G. Garcia-Pena, Xim Bokhimi
Summary: The study demonstrated the excellent performance of artificial neural networks developed based on crystal-site features in classifying compounds, retrieving missing compounds, and being suitable for multitask learning paradigms.
Article
Nanoscience & Nanotechnology
Mei Xian Low, Sherif Abdulkader Tawfik, Salvy P. Russo, Sharath Sriram, Madhu Bhaskaran, Sumeet Walia
Summary: This study demonstrates the use of a simple prestretch fabrication technique to create a functional multilayer black phosphorus-based device on a stretchable elastomeric platform, and shows that mechanical strain can effectively modulate the electronic and optical properties of black phosphorus.
ACS APPLIED NANO MATERIALS
(2022)
Article
Biochemistry & Molecular Biology
Nevsun Pihtili Tas, Oguz Kaya, Gulay Macin, Burak Tasci, Sengul Dogan, Turker Tuncer
Summary: This study successfully diagnosed ankylosing spondylitis (AS) using a pre-trained hybrid model and magnetic resonance imaging (MRI). The model demonstrated excellent classification performance across three cases and showed the ability to diagnose AS using only axial images, representing significant advancements in healthcare and economics.
Review
Materials Science, Multidisciplinary
James Damewood, Jessica Karaguesian, Jaclyn R. Lunger, Aik Rui Tan, Mingrou Xie, Jiayu Peng, Rafael Gomez-Bombarelli
Summary: High-throughput data generation methods and machine learning algorithms have revolutionized computational materials science, enabling the design of materials through the understanding of their composition, structure, and properties. This review discusses strategies for representing materials data in a numerical form suitable for machine learning models, explores how modern ML techniques can learn representations from data and transfer chemical and physical information between tasks, and highlights unresolved questions that require further investigation.
ANNUAL REVIEW OF MATERIALS RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Chen Zheng, Jiajian Xing, Zhanxi Wang, Xiansheng Qin, Benoit Eynard, Jing Li, Jing Bai, Yicha Zhang
Summary: This study proposes a knowledge-based program-generation approach for robotic manufacturing systems to improve programming efficiency and enhance manufacturing stability and production quality by standardizing manufacturing program rules and knowledge.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Materials Science, Multidisciplinary
Deepesh Yadav, Tanmayee More, Balila Nagamani Jaya
Summary: This study constructs Morse-Code architectures of dot and dash features in PMMA materials using varying morphologies and arrangements of holes and splats. The crack tip driving force is determined through finite element simulations, and the fracture resistance is measured experimentally. The results show that the right combination of features can significantly enhance the fracture resistance of the material.
JOURNAL OF MATERIALS RESEARCH
(2022)
Article
Automation & Control Systems
Abdul Nasir, Muhammad Obaid Ullah, Muhammad Haroon Yousaf
Summary: Uncompromised population growth of invasive insects endangers biodiversity, agribusinesses, and ecosystems. One example is the invasion of Vespa hornets in honey harvesting areas, which devastates honeybee ecology and affects economic activities. To address this threat, a novel AI-based framework is proposed for recognizing Vespa hornets near beehives under unconstrained flying conditions using multi-modal data and multi-evidence approach.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Yipeng Chen, Baokang Dang, Jinzhou Fu, Chao Wang, Caicai Li, Qingfeng Sun, Huiqiao Li
Summary: In this study, a high-performance and inexpensive cooling structural material was developed by assembling delignified biomass cellulose fiber and inorganic microspheres. The material exhibited strong mechanical strength, excellent cooling properties, fire-retardant characteristics, and outdoor antibacterial performance, making it a promising candidate for high-performance cooling structural materials.
Article
Computer Science, Interdisciplinary Applications
Jerzy Pokojski, Karol Szustakiewicz, Lukasz Woznicki, Konrad Oleksinski, Jaroslaw Pruszynski
Summary: KBE systems have been studied for a long time, and although progress has been made, there are still challenges in implementing them in industry. Researchers have proposed guidelines to improve the quality and efficiency of KBE solutions.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2022)
Article
Materials Science, Paper & Wood
Sezen Yucel, Robert J. Moon, Linda J. Johnston, Berkay Yucel, Surya R. Kalidindi
Summary: This paper introduces a new semi-automated image analysis framework called SMART, which can reliably and quickly detect and classify CNCs from TEM and AFM images and measure their dimensions. The SMART approach shows good agreement and higher throughput in CNC identification and dimensional measurements compared to conventional manual methods.
Article
Chemistry, Multidisciplinary
Zachary S. Courtright, Nicolas P. Leclerc, Hyung Nun Kim, Surya R. Kalidindi
Summary: This paper critically compares emergent high-throughput mechanical test protocols with standardized tension tests, finding that the former can produce reliable stress-strain data using significantly smaller material volume and reduced labor. The study conducted on Inconel 718 samples demonstrates the effectiveness of high-throughput mechanical test protocols in rapidly screening mechanical properties.
APPLIED SCIENCES-BASEL
(2021)
Article
Materials Science, Multidisciplinary
Nicolas Leclerc, Ali Khosravani, Sepideh Hashemi, Daniel B. Miracle, Surya R. Kalidindi
Summary: This paper introduces new analysis protocols for extracting uniaxial stress-strain curves from Small Punch Test (SPT) measurements, establishing a correlation between SPT measurements and finite element simulations to estimate stress-strain responses, and demonstrating the ability to invert this correlation to estimate stress-strain responses for new material samples.
Article
Materials Science, Multidisciplinary
Andreas E. Robertson, Surya R. Kalidindi
Summary: Discrete dislocation structures greatly impact the mechanical properties of metal samples, but the lack of computationally efficient and statistically rigorous descriptors has hindered the development of rational protocols for their optimal design. This study introduces a framework for statistical quantification and low-dimensional representation of dislocation structures, which proves useful for comparing and observing these defects.
Article
Materials Science, Multidisciplinary
Sven P. Voigt, K. Ravikumar, Bikramjit Basu, Surya R. Kalidindi
Summary: Computerized image analysis of biological cells and tissues is essential for high-throughput microscopy, offering improved accuracy and efficiency. A novel workflow for automated analysis of fluorescence microscopy images is presented in this study, showing superior results compared to a single workflow in terms of accuracy and reliability.
Article
Materials Science, Multidisciplinary
Almambet Iskakov, Surya R. Kalidindi
Summary: This article introduces a novel multi-resolution protocol that can extract indentation stress-strain curves from tests on microscale constituents and design consistent image segmentation protocols. A case study on thermally aged steel samples demonstrates the accuracy of this approach in estimating the mechanical properties of microscale constituents and the bulk properties of the samples.
MECHANICS OF MATERIALS
(2022)
Article
Materials Science, Multidisciplinary
Abhishek Biswas, Surya R. Kalidindi, Alexander Hartmaier
Summary: This study presents a hybrid method that combines the classical crystallographic yield locus method (CYL) with the crystal plasticity finite element method (CPFEM) to determine the anisotropic yield locus (YL) of a material. The hybrid method is shown to produce reliable results for diverse crystallographic textures, even with pronounced plastic anisotropy. The calibrated CYL method is used to construct a smooth yield function that can potentially be used in standard continuum plasticity methods for finite element analysis.
MODELLING AND SIMULATION IN MATERIALS SCIENCE AND ENGINEERING
(2022)
Article
Materials Science, Multidisciplinary
Samannoy Ghosh, Marshall Johnson, Rajan Neupane, James Hardin, John Daniel Berrigan, Surya R. Kalidindi, Yong Lin Kong
Summary: The paper presents a method that integrates a microfluidics-driven multi-scale 3D printer with a machine learning algorithm to precisely tune ink composition and classify internal features, helping to understand the complex evaporative-driven assembly process and autonomously optimize printing parameters.
FLEXIBLE AND PRINTED ELECTRONICS
(2022)
Article
Materials Science, Multidisciplinary
Andreas E. Robertson, Surya R. Kalidindi
Summary: This article presents a theoretical and computational framework for efficiently generating microstructure instances corresponding to specified 2-point statistics. The framework utilizes an N-output Gaussian Random Field model and provides algorithms for efficient sampling. The study demonstrates the relationship between 2-point statistics and spatially resolved sampled microstructures.
Article
Materials Science, Multidisciplinary
Prathik R. Kaundinya, Kamal Choudhary, Surya R. Kalidindi
Summary: Machine learning has greatly enhanced traditional materials discovery and design pipeline, particularly in predicting material properties. However, predicting complex spectral targets such as electron density of states (DOS) remains challenging. This study presents an extension of the atomistic line graph neural network to accurately predict DOS and evaluates two methods of target representation.
Article
Materials Science, Paper & Wood
Sezen Yucel, Robert J. Moon, Linda J. Johnston, Douglas M. Fox, Byong Chon Park, E. Johan Foster, Surya R. Kalidindi
Summary: The study compared the use of the SMART semi-automatic image analysis program with conventional manual methods for analyzing TEM images of CNC particles. SMART showed a lower variability between laboratories and displayed difficulties in identifying CNCs in images with poor quality, suggesting a potential for improving standardization in CNC size characterization.
Article
Materials Science, Multidisciplinary
Adam P. Generale, Richard B. Hall, Robert A. Brockman, V. Roshan Joseph, George Jefferson, Larry Zawada, Jennifer Pierce, Surya R. Kalidindi
Summary: This study demonstrates the successful application of Bayesian inference for simultaneous estimation of eleven material parameters of a viscous multimode CDM model, providing uncertainty estimates and principled decision making, applicable to mechanical models with high-dimensional parameter sets.
MECHANICS OF MATERIALS
(2022)
Article
Materials Science, Multidisciplinary
Venkata Surya Karthik Adapa, Nicolas P. Leclerc, Aditya Venkatraman, Thomas Feldhausen, Surya R. Kalidindi, Christopher J. Saldana
Summary: This study investigates the viability of small punch test (SPT) protocols for evaluating the mechanical properties of DED fabricated alloy mixtures. It is shown that these protocols can reliably track the changes in mechanical properties and that the addition of IN625 to 316L enhances the mechanical properties.
MATERIALS & DESIGN
(2023)
Article
Materials Science, Multidisciplinary
Andreas E. Robertson, Conlain Kelly, Michael Buzzy, Surya R. Kalidindi
Summary: Conditional microstructure generation tools provide an important and affordable method for creating statistically diverse datasets for Integrated Computational Materials Engineering and Materials Informatics. In this paper, a generative framework is proposed that combines statistical conditioning and visual realism by approximating a microstructure's generating process using a two-layer probabilistic graphical model. Through case studies, the framework is shown to successfully match both lower-order and higher-order statistics. The ability of these models to extrapolate outside of the training data is briefly explored, highlighting the value of systematically generating diverse microstructure datasets.
Article
Materials Science, Multidisciplinary
Adrienne Muth, Aditya Venkatraman, Reji John, Adam Pilchak, Surya R. Kalidindi, David L. McDowell
Summary: A novel surrogate modeling approach is proposed to identify grains with a higher propensity to form fatigue cracks. This approach utilizes computational methods to build robust linkages between local neighborhood statistics and the probability of fatigue crack formation.
MECHANICS OF MATERIALS
(2023)