High precision deep-learning model combined with high-throughput screening to discover fused [5,5] biheterocyclic energetic materials with excellent comprehensive properties DOI Creative Commons
Youhai Liu, Fusheng Yang, Wenquan Zhang

et al.

RSC Advances, Journal Year: 2024, Volume and Issue: 14(33), P. 23672 - 23682

Published: Jan. 1, 2024

Finding novel energetic materials with good comprehensive performance has always been challenging because of the low efficiency in conventional trial and error experimental procedure. In this paper, we established a deep learning model high prediction accuracy using embedded features Directed Message Passing Neural Networks. The combined high-throughput screening was shown to facilitate rapid discovery fused [5,5] biheterocyclic energy excellent thermal stability. Density Functional Theory (DFT) calculations proved that performances targeting molecules are consistent predicted results from model. Furthermore, 6,7-trinitro-3H-pyrrolo[1,2-b][1,2,4]triazo-5-amine both detonation properties stability screened out, whose crystal structure intermolecular interactions were also analyzed.

Language: Английский

A Comprehensive Review of Methods for Hydrological Forecasting Based on Deep Learning DOI Open Access
Xinfeng Zhao, Hongyan Wang,

Mingyu Bai

et al.

Water, Journal Year: 2024, Volume and Issue: 16(10), P. 1407 - 1407

Published: May 15, 2024

Artificial intelligence has undergone rapid development in the last thirty years and been widely used fields of materials, new energy, medicine, engineering. Similarly, a growing area research is use deep learning (DL) methods connection with hydrological time series to better comprehend expose changing rules these series. Consequently, we provide review latest advancements employing DL techniques for forecasting. First, examine application convolutional neural networks (CNNs) recurrent (RNNs) forecasting, along comparison between them. Second, made basic enhanced long short-term memory (LSTM) analyzing their improvements, prediction accuracies, computational costs. Third, performance GRUs, other models including generative adversarial (GANs), residual (ResNets), graph (GNNs), estimated Finally, this paper discusses benefits challenges associated forecasting using techniques, CNN, RNN, LSTM, GAN, ResNet, GNN models. Additionally, it outlines key issues that need be addressed future.

Language: Английский

Citations

10
AI-enabled materials discovery for advanced ceramic electrochemical cells DOI Creative Commons
Idris Temitope Bello, Ridwan Taiwo, Oladapo Christopher Esan

et al.

Energy and AI, Journal Year: 2023, Volume and Issue: 15, P. 100317 - 100317

Published: Nov. 9, 2023

Ceramic electrochemical cells (CECs) are promising devices for clean and efficient energy conversion storage due to their high efficiency, more extended system durability, less expensive materials. However, the search suitable materials with desired properties, including ionic electronic conductivity, thermal stability, chemical compatibility, presents ongoing challenges that impede widespread adoption further advancement in field. Artificial intelligence (AI) has emerged as a versatile tool capable of enhancing expediting discovery cycle CECs through data-driven modeling, simulation, optimization techniques. Herein, we comprehensively review state-of-the-art AI applications design CECs, covering various material aspects, database construction, data pre-processing, methods. We also present some representative case studies AI-predicted synthesized provide insightful highlights about approaches. emphasize main implications contributions approach advancing CEC technology, such reducing trial-and-error experiments, exploring vast space, discovering novel optimal materials, understanding materials-performance relationships. discuss approach's limitations future directions addressing model challenges, improving extending models methods, integrating other computational experimental conclude by suggesting potential collaborations CECs.

Language: Английский

Citations

12
Artificial Neural Network‐Based Model to Predict Burning Rate of Catalysed Composite Solid Propellant DOI

Bhavana Sahu,

R. Perumal, Ganguli Babu

et al.

Propellants Explosives Pyrotechnics, Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

ABSTRACT A prediction tool for the burning rate of composite solid propellants using an artificial neural network (ANN)‐based model is proposed. The methodology adopted can be divided into two parts (a) estimation interaction between process variables Spearman rank‐order correlation method and (b) building ANN‐based to predict from a trimmed dataset consisting significant variables. multilayer perceptron (MLP) was fed with as input, backpropagation algorithm used solve mathematical in Python. ANN hyperparameters tuning carried out Grid Search It found that average motor high accuracy when compared obtained ballistic evaluation test motors. This helps propellant composition mechanical physical properties without firing motors (BEM).

Language: Английский

Citations

0
Innovative Approaches to Water Purification Harnessing Bio-Chemical Adsorbents for Multistage Potable Water Filtration DOI

Manikala Vinod Kumar,

K Madhukumar,

Nivedita Kumar

et al.

Advances in chemical and materials engineering book series, Journal Year: 2024, Volume and Issue: unknown, P. 389 - 458

Published: Nov. 29, 2024

Lifestyle choices significantly shape the intricate chemical makeup of human body, impacting health and lifespan. The use bio-chemical adsorbents in multistage potable water filtration represents a major breakthrough addressing global quality challenges. fundamentals are discussed, distinguishing between bio-based materials highlighting various types such as activated carbon, biochar, graphene oxide. concept systems is introduced by advantages over single-stage key design considerations. chapter then delves into applications purification, presenting case studies comparative analyses with traditional methods to demonstrate their efficacy performance metrics. Strategies enhance adsorption efficiency through surface modifications, hybrid systems, composite explored detail targets on environmental impact, sustainability, regulatory standards, future trends adsorbents.

Language: Английский

Citations

1
Progress of Artificial Intelligence in Drug Synthesis and Prospect of Its Application in Nitrification of Energetic Materials DOI Creative Commons
Bojun Tan, Jing Zhang, Chuan Xiao

et al.

Molecules, Journal Year: 2023, Volume and Issue: 28(4), P. 1900 - 1900

Published: Feb. 16, 2023

Artificial intelligence technology shows the advantages of improving efficiency, reducing costs, shortening time, number staff on site and achieving precise operations, making impressive research progress in fields drug discovery development, but there are few reports application energetic materials. This paper addresses high safety risks current nitrification process materials, comprehensively analyses summarizes main their control elements process, proposes possibilities suggestions for using artificial to enhance “essential safety” reviews field synthesis, looks forward prospects materials provides support guidance safe processing propellants explosives industry.

Language: Английский

Citations

2
Physically evocative meso-informed sub-grid source term for energy localization in shocked heterogeneous energetic materials DOI Open Access
Yen T. Nguyen, Pradeep Kumar Seshadri, H. S. Udaykumar

et al.

Journal of Applied Physics, Journal Year: 2023, Volume and Issue: 134(16)

Published: Oct. 23, 2023

Reactive burn models for heterogeneous energetic materials (EMs) must account chemistry as well microstructure to predict shock-to-detonation transition (SDT). Upon shock loading, the collapse of individual voids leads ignition hotspots, which then grow and interact consume surrounding material. The sub-grid dynamics shock-void interactions hotspot development are transmitted macro-scale SDT calculations in form a global reactive “burn model.” This paper presents physically evocative model, called meso-informed source terms energy localization (MISSEL), close governing equations calculating SDT. model parameters explicitly related four measurable physical quantities: two depending on (the porosity ϕ average pore size D¯void), one shock–microstructure interaction fraction critical ξcr), other front velocity Vhs). These quantities individually quantifiable using small number rather inexpensive meso-scale simulations. As constructed, overcomes following problems that hinder models: (1) opacity more sophisticated surrogate/machine-learning approaches bridging meso- macro-scales, (2) large high-resolution mesoscale simulations necessary train machine-learning algorithms, (3) need calibration many free appear phenomenological models. is tested against experimental data James curves specific class pressed 1,3,5,7-tetranitro-1,3,5,7-tetrazoctane materials. simple, evocative, fast-to-construct MISSEL suggests route develop frameworks physics-informed, simulation-derived

Language: Английский

Citations

2
Ti/CuO and Ti/CuO/Cellulose Nitrate Nanothermites: An Early Insight into Their Combustion Mechanism DOI Creative Commons
Mateusz Polis, Agnieszka Stolarczyk, Konrad Szydło

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(17), P. 4333 - 4333

Published: Aug. 29, 2024

Most nanothermite compositions utilise Al as a fuel, due to its low cost, high reactivity and availability. Nevertheless, aluminothermites exhibit ignition temperature active metal content. In this paper, the combustion behaviour of Ti/CuO Ti/CuO/NC systems is discussed. The were prepared with wet-mixing/sonication process followed by an electrospray technique examined in terms their mechanical radiation sensitivity, energetic parameters morphology. results exhibited strong correlation between equivalence ratio parameters. performed tests showed crucial impact addiction chosen binder on morphology performance compositions. our experiments indicate occurrence different mechanism than one observed for Al-based nanothermites. case, involves limitation diffusion oxidising agent decomposition products into reactive fuel core.

Language: Английский

Citations

0
Artificial Intelligence, Transformation and Expectations in Graphic Design Processes DOI
Mehmet Akif Özdal

İnsan ve Sosyal Bilimler Dergisi, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 28, 2024

Artificial intelligence (AI), as the pioneer of today's technological advances, brings innovation to many sectors and graphic design is among these sectors. Within rapidly developing technology our age, integration AI technologies into field provides a significant acceleration in processes. In this context, it predicted that use contributes accelerate processes, increase efficiency improve user experience interactive design. Additionally, research examines current potential status. The study adopts qualitative methods comparative analysis logical reasoning limited reviewed literature studies reviewed.The findings show AI-assisted tools enable more creative solutions. results AI-supported

Language: Английский

Citations

0
Multi‐Task Multi‐Fidelity Learning of Properties for Energetic Materials DOI Creative Commons
Robert J. Appleton, Daniel Klinger, Brian H. Lee

et al.

Propellants Explosives Pyrotechnics, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 23, 2024

Abstract Data science and artificial intelligence are playing an increasingly important role in the physical sciences. Unfortunately, field of energetic materials data scarcity limits accuracy even applicability ML tools. To address limitations, we compiled multi‐modal data: both experimental computational results for several properties. We find that multi‐task neural networks can learn from outperform single‐task models trained specific As expected, improvement is more significant data‐scarce These using descriptors built simple molecular information be readily applied large‐scale screening to explore multiple properties simultaneously. This approach widely applicable fields outside materials.

Language: Английский

Citations

0
An ensemble learning model to predict enhanced COrner turning (ECOT) for PBX 9502 DOI
D.G. Walters, Levi Lystrom, W. Lee Perry

et al.

AIP conference proceedings, Journal Year: 2024, Volume and Issue: 3066, P. 470007 - 470007

Published: Jan. 1, 2024

Language: Английский

Citations

0