Article
Computer Science, Artificial Intelligence
Grace W. Lindsay, David Bau
Summary: Neuroscientists use analysis tools to study neural activity and understand how it drives behavior. Evaluating the effectiveness of these tools by applying them to artificial neural networks can contribute to a unified understanding of neural systems.
COGNITIVE SYSTEMS RESEARCH
(2023)
Review
Materials Science, Ceramics
Zhike Zhao
Summary: The paper discussed the potential defects in ceramic products during the production process and explored the application and development direction of non-destructive testing technology.
CERAMICS INTERNATIONAL
(2021)
Article
Construction & Building Technology
Guanglin You, Bingzhen Wang, Jinlong Li, Aonan Chen, Jianping Sun
Summary: This study aims to predict the modulus of elasticity of bamboo-wood composites using an artificial neural network model and compare it with multiple linear regression. The results show that the ANN model built using characteristic parameters has better prediction performance.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Chemistry, Analytical
Romain Cormerais, Aroune Duclos, Guillaume Wasselynck, Gerard Berthiau, Roberto Longo
Summary: This article focuses on non-destructive testing methods for aircraft parts, mainly using ultrasonic and eddy current techniques for defect detection, and combining the advantages of these two methods through machine learning. A simulated training database with US and EC signals in an aluminum block was implemented for training artificial neural networks (ANNs) to characterize flaws. Experimental results show the effectiveness of the method in defect detection, depth estimation, and radius estimation.
Article
Construction & Building Technology
Panagiotis G. Asteris, Athanasia D. Skentou, Abidhan Bardhan, Pijush Samui, Paulo B. Lourenco
Summary: This study compared conventional soft computing techniques in estimating concrete compressive strength using non-destructive tests, finding that the BPNN model provided the most accurate predictions based on ultrasonic pulse velocity and rebound number values, thus assisting engineers in improving the accuracy of predicting concrete compressive strength during the design phase of civil engineering projects.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Materials Science, Multidisciplinary
Ali H. AlAteah, Khaled A. Alawi Al-Sodani, Moruf Olalekan Yusuf, Adeshina A. Adewumi, Mohammed M. H. Al-Tholaia, Azeez Oladipupo Bakare, Ibrahim Momohjimoh, Abdullahi Kilaco Usman
Summary: The use of waste glass powder (WGP) and silica fume (SF) powder as partial replacements for ordinary Portland cement in ternary blended concrete was investigated to promote solid waste utilization in concrete production. The concrete specimens were prepared with a binder consisting of 90% cement and 10% silica fume and waste glass powder. Models were developed to analyze the wet density, strength development, compressive strength, and elastic/shear moduli of the concrete. Additionally, the impact of geometrical shape and aspect ratio on transverse response frequencies were studied.
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T
(2023)
Article
Chemistry, Physical
Damian Kozanecki, Izabela Kowalczyk, Sylwia Krason, Martyna Rabenda, Lukasz Domagalski, Artur Wirowski
Summary: This study used numerical data developed in the VIG plate modeling process using Abaqus program to train machine learning methods, and obtained the mechanical parameters of steel elements inside the vacuum glazing by subjecting the VIG plate to forced vibrations of specific frequencies and reading the dynamic response. These research methods can be used to analyze the mechanical properties of other types of composite panels in the future.
Article
Engineering, Geological
Athanasia D. Skentou, Abidhan Bardhan, Anna Mamou, Minas E. Lemonis, Gaurav Kumar, Pijush Samui, Danial J. Armaghani, Panagiotis G. Asteris
Summary: This study examined the use of three artificial neural network (ANN)-based models to predict the unconfined compressive strength (UCS) of granite using three non-destructive test indicators. The ANN-LM model, constructed using the Levenberg-Marquardt algorithm, was determined to be the most accurate. In the validation phase, the ANN-LM model achieved the best predictive performance with R = 0.9607 and RMSE = 14.8272. The developed ANN-LM model outperformed existing models and a graphical user interface (GUI) was developed for easy estimation of UCS using this model.
ROCK MECHANICS AND ROCK ENGINEERING
(2023)
Article
Engineering, Civil
Wongi S. Na
Summary: Bolt loosening can significantly reduce load bearing capacities, highlighting the importance of monitoring bolt states.
The study utilized EMI technique with PNN neural networks to identify torque loss of bolts on three specimens with over 90% accuracy.
These results bring the piezoelectric-based non-destructive testing technique closer to application in real structures.
ENGINEERING STRUCTURES
(2021)
Article
Chemistry, Multidisciplinary
Sanghyeon Choi, Gwang Su Kim, Jehyeon Yang, Haein Cho, Chong-Yun Kang, Gunuk Wang
Summary: Researchers designed and fabricated a SiOx nanorod memristive device using the GLAD technique, proposing a controllable stochastic artificial neuron that mimics the signaling and dynamics of a biological neuron. By implementing ProbAct functions and electrical programming schemes, control over the neuron is achieved, allowing for probabilistic Bayesian inferences in genetic regulatory networks.
ADVANCED MATERIALS
(2022)
Article
Engineering, Geological
Tien-Thinh Le, Athanasia D. Skentou, Anna Mamou, Panagiotis G. Asteris
Summary: In this research, a series of artificial neural networks were trained and developed to predict the unconfined compressive strength of rock. Compiling a data and site independent database from 367 datasets, the input parameters used were Schmidt hammer number R-n, compressional wave velocity V-p, and effective porosity n(e). The study found that the ANN-ICA model had the highest accuracy.
ROCK MECHANICS AND ROCK ENGINEERING
(2022)
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
Construction & Building Technology
Shuvo Dip Datta, Md. Habibur Rahman Sobuz, Abu Sayed Mohammad Akid, Shoaib Islam
Summary: This paper presents an experimental investigation of the properties of recycled aggregate concrete (RAC) prepared with varying sizes and replacement levels of coarse aggregate. The results show that RAC achieves lower performance values with the increment of recycled aggregate replacement level. Additionally, concrete with smaller aggregate size exhibits better performance. Empirical relationships between destructive and non-destructive testing techniques are also established to efficiently predict the properties of RAC.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Construction & Building Technology
S. Karlsson, M. Kozlowski, L. Grund, S. A. K. Andersson, K. C. E. Haller, K. Persson
Summary: This paper presents a method for non-destructive testing of glass strength. Samples of annealed float glass were subjected to controlled Vickers microindentation-induced cracking and compared to un-indented samples. The non-destructive testing using nonlinear acoustic waves resulted in defect values, which were found to correlate linearly to the indentation force. Ring-on-ring testing yielded realistic strength values in the range of 45 to 110 MPa. The study shows that a non-destructive testing method for glass strength is feasible.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Energy & Fuels
Jelto Lange, Martin Kaltschmitt
Summary: A method based on artificial neural networks for probabilistic forecasting of thermal storage capacities for residential power-to-heat operation is proposed to address the issue of high curtailment rates in large-scale renewable energy production. A case study in a single-family household in northern Germany demonstrates that the proposed approach outperforms benchmark forecasting models in terms of accuracy and reliability.
Article
Materials Science, Composites
Xi Liu, Wei Shen, Jincun Fu, Toshiaki Natsuki, Lvtao Zhu
Summary: The 3-D carbon fiber reinforced resin matrix composite tubes were designed and formed using a novel braiding-winding-pultrusion processing technique. The effects of temperature environments on the mechanical responses and damage behaviors of the composite tubes were investigated, and it was found that the structural design of the tubes directly affects their axial bearing capacity.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Weihao Yuan, Ziyang Zhang, Yueshan Li, Yudong Huang, Zhengxiang Zhong, Zhen Hu
Summary: In this study, the simultaneous self-healing of matrix and interface damage of fiber-reinforced composites was achieved by integrating extrinsic self-healing based on microcapsules and internal self-healing based on coordination interaction. The high exothermic action of epoxy resin and mercaptan repair agent in the self-healing process was observed using infrared thermal imaging technology for in-situ and real-time damage detection.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Israr Ud Din, Adnan Ahmed, Farah Tarek, Wesley Cantwell, Kamran A. Khan
Summary: In this study, a finite element model driven by XCT was developed to simulate the folding characteristics of origami structures, and the results showed good agreement with experimental data. The study demonstrates the potential application of XCT-driven FE modeling in simulating foldable structures.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Yishan Yang, Yukang Lai, Song Zhao, Hongguang Chen, Renshu Li, Yongjiang Wang
Summary: This study reports the synthesis of a new transparent fiber reinforced polymer material (tGFRP) with high transparency and superior mechanical properties by controlling the refractive index of epoxy resin and using a novel processing technique.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Yuhang Liu, Kai Huang, Junfeng Ding, Shangyang Yu, Zhixing Li, Li Zhang, Licheng Guo
Summary: This study proposes a method for accurately predicting the penetration failure load of composites using acoustic emission (AE) data. The method includes a cyclic loading test schedule and an extrapolation method based on uncertainty. The results show that this method can accurately predict the failure load when LR equals 1.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Jinxia Cai, Bing Xie, Yunliang Jiang, Jinshan Lu, Zeyu Li, Pu Mao, Mohsin Ali Marwat, Haibo Zhang
Summary: This research aims to develop ternary nanocomposites composed of polycarbonate, Al2O3 nanoparticles, and BaTiO3 nanowires for capacitive energy-storage. By optimizing the capacitor materials, the discharge energy density and efficiency have been improved, and the superiority of the ternary polymer nanocomposites for dielectric energy-storage has been validated through finite element analysis.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Hon Lam Cheung, Mohsen Mirkhalaf
Summary: The aim of this study is to develop physics-based models and establish a structure-property relationship for short fiber composites. High-fidelity full-field simulations are computationally expensive and time-consuming, so the use of artificial neural networks and transfer learning technique is proposed to solve this issue and improve modeling accuracy and efficiency.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Yue Jiang, Juyoung Leem, Ashley M. Robinson, Shuai Wu, Andy H. Huynh, Dongwon Ka, Ruike Renee Zhao, Yan Xia, Xiaolin Zheng
Summary: The effect of interface engineering on the combustion and mechanical performance of high-loading B/HTPB composites was investigated in this study. It was found that both covalently bonded and nonpolar/nonpolar interfaces effectively reduced the aggregation of B particles, promoting combustion efficiency and burning rate, and enhancing the mechanical properties of the composites.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
R. Mohsenzadeh, B. H. Soudmand, A. H. Najafi, M. Fattahi, D. P. Uyen
Summary: This study examines the morphological features of nano-zeolite nanoparticles incorporated into ultra-high molecular weight polyethylene nanocomposites. The dispersion of nanoparticles within the polymer matrix was improved following nano-zeolite incorporation. The size and distribution of nanoparticles were determined through tailored histograms, and the effective elastic moduli of nanocomposites were calculated, considering interfacial effects.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Chunming Ji, Jiqiang Hu, Rene Alderliesten, Jinchuan Yang, Zhengong Zhou, Yuguo Sun, Bing Wang
Summary: This paper investigates the effect of impact damage on the fatigue behavior of CF/PEEK-titanium hybrid laminates. A fatigue life model is proposed to predict the S-N curves of the laminates based on energy dissipation approach. The energy dissipation behavior of the laminates under different experimental conditions is analyzed through post-impact fatigue tests, and the correlation between impact damage and fatigue dissipation energy is determined. The validity of the proposed model is verified through fatigue tests under different stress ratios and impact energy levels.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Shaokai Hu, Ping Han, Chao Meng, Ying Yu, Shaolong Han, Haoyu Wang, Gang Wei, Zheng Gu
Summary: This study decorates MXene on the surface of carbon fiber using different bonding interactions to improve the interface adhesion and mechanical properties of carbon fiber-reinforced polymers composites (CFRPs). The results demonstrate that CFRPs reinforced by CF-c-MXene show the optimal properties, with significant improvements in impact strength and interfacial shear strength compared to the unsized carbon fiber-reinforced composites.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Steven U. Mamolo, Henry A. Sodano
Summary: This study demonstrates that chlorination of ANFs and oxygen plasma treatment of carbon fibers enables the formation of a chlorinated ANF (Cl-ANF) interphase, resulting in a 79.8% increase in interfacial shear strength and a 33.7% increase in short beam strength in CFRP composites. This method provides a rapid and reliable process to improve the mechanical properties of CFRPs without degrading the tensile strength of the carbon fibers.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Yuyang Zhang, Huimin Li, Xin Liu, Yanhong Chen, Chengwei Qin, Daining Fang
Summary: Establishing a prediction model for the mechanical properties of three-dimensional tubular braided composites at different temperatures is of great significance. This study adopted a multi-scale modeling framework based on micro-computed tomography to consider the characteristics of the real yarn cross section and establish a realistic trans-scale finite element model for the composites. The predicted mechanical properties were found to be significantly affected by temperature.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Shengtao Dai, Fei Yan, Jiaming Guo, Huiru Hu, Yu Liu, Liu Liu, Yuhui Ao
Summary: This study successfully synthesized a hyperbranched waterborne polyurethane sizing agent and cellulose nanocrystal modified zinc oxide nanohybrids to improve the interface and properties of carbon fiber reinforced composites. The modified composites exhibited remarkable enhancements in mechanical properties and exceptional UV resistance.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)
Article
Materials Science, Composites
Libera Vitiello, Martina Salzano de Luna, Veronica Ambrogi, Giovanni Filippone
Summary: The identification of the percolation threshold in short fiber composites is crucial for assessing material properties and biodegradation speed. In this study, an original rheological approach was used to estimate the percolation threshold of hemp and kenaf-based composites, which showed good agreement with conventional dielectric spectroscopy analyses.
COMPOSITES SCIENCE AND TECHNOLOGY
(2024)