Prediction of Initial Reaction Characteristics of Materials from Molecular Conformational Changes Based on Artificial Intelligence Technology DOI
Kaining Zhang, Lang Chen, Kun Yang

et al.

The Journal of Physical Chemistry C, Journal Year: 2022, Volume and Issue: 126(50), P. 21168 - 21180

Published: Nov. 18, 2022

To determine microscopic reaction mechanisms of energetic materials, a problem exists when there are multiple calculations but limited calculation scales. Herein, we used artificial intelligence algorithms convolutional neural network and multilayer perceptron to establish prediction model. This model was based on the storage conversion shock energy molecular conformational change as well mechanism obtained using dynamics simulation. Further, changes in parameters, such bond length, angle, dihedral volume degree predicted then initial breaking product generation probabilities were according degree. Consequently, molecules loaded with energy, could realize rapid assessment processes. The accuracy universality verified by agreement between results quantification models reactive simulation materials. Our method can predict material transformation properties materials smaller computational load higher analysis efficiency than analysis.

Language: Английский

Synthesis, design and development of energetic materials: Quo Vadis? DOI
Nikita V. Muravyev, Леонид Л. Ферштат, Qinghua Zhang

et al.

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 486, P. 150410 - 150410

Published: March 14, 2024

Language: Английский

Citations

24
High-throughput design of energetic molecules DOI
Jian Liu,

Shicao Zhao,

Bowen Duan

et al.

Journal of Materials Chemistry A, Journal Year: 2023, Volume and Issue: 11(45), P. 25031 - 25044

Published: Jan. 1, 2023

High-throughput design of energetic molecules implemented by molecular docking, AI-aided design, an automated computation workflow, a structure−property database, deep learning QSPRs and easy-to-use platform.

Language: Английский

Citations

15
General Graph Neural Network-Based Model To Accurately Predict Cocrystal Density and Insight from Data Quality and Feature Representation DOI
Jiali Guo, Ming Sun, Xueyan Zhao

et al.

Journal of Chemical Information and Modeling, Journal Year: 2023, Volume and Issue: 63(4), P. 1143 - 1156

Published: Feb. 3, 2023

Cocrystal engineering as an effective way to modify solid-state properties has inspired great interest from diverse material fields while cocrystal density is important property closely correlated with the function. In order accurately predict density, we develop a graph neural network (GNN)-based deep learning framework by considering three key factors of machine (data quality, feature presentation, and model architecture). The result shows that different stoichiometric ratios molecules in cocrystals can significantly influence prediction performances, highlighting importance data quality. addition, complementary not suitable for augmenting molecular representation prediction, suggesting strategy needs consider whether extra features sufficiently supplement lacked information original representation. Based on these results, 4144 1:1 stoichiometry ratio are selected dataset, supplemented augmentation exchanging pair coformers. determined learn train GNN-based model. Global attention introduced further optimize space identify atoms realize interpretability Benefited advantages, our outperforms competitive models exhibits high accuracy unseen cocrystals, showcasing its robustness generality. Overall, work only provides general tool experimental investigations but also useful guidelines application. All source codes freely available at https://github.com/Xiao-Gua00/CCPGraph.

Language: Английский

Citations

13
Exploring an accurate machine learning model to quickly estimate stability of diverse energetic materials DOI Creative Commons

Qiaolin Gou,

Jing Liu,

Haoming Su

et al.

iScience, Journal Year: 2024, Volume and Issue: 27(4), P. 109452 - 109452

Published: March 8, 2024

High energy and low sensitivity have been the focus of developing new energetic materials (EMs). However, there has a lack quick accurate method for evaluating stability diverse EMs. Here, we develop machine learning prediction model with high accuracy bond dissociation (BDE) A reliable representative BDE dataset EMs is constructed by collecting 778 experimental compounds quantum mechanics calculation. To sufficiently characterize EMs, hybrid feature representation proposed coupling local target into global structure characteristics. alleviate limitation dataset, pairwise difference regression utilized as data augmentation advantage reducing systematic errors improving diversity. Benefiting from these improvements, XGBoost achieves best R2 0.98 MAE 8.8 kJ mol−1, significantly outperforming competitive models.

Language: Английский

Citations

4
Prediction and Construction of Energetic Materials Based on Machine Learning Methods DOI Creative Commons
Xiaowei Zang, Xiang Zhou, Haitao Bian

et al.

Molecules, Journal Year: 2022, Volume and Issue: 28(1), P. 322 - 322

Published: Dec. 31, 2022

Energetic materials (EMs) are the core of weapons and equipment. Achieving precise molecular design efficient green synthesis EMs has long been one primary concerns researchers around world. Traditionally, advanced were discovered through a trial-and-error processes, which required research development (R&D) cycles high costs. In recent years, machine learning (ML) method matured into tool that compliments aids experimental studies for predicting designing EMs. This paper reviews critical process ML methods to discover predict EMs, including data preparation, feature extraction, model construction, performance evaluation. The main ideas basic steps applying analyzed outlined. state-of-the-art about applications in property prediction inverse material is further summarized. Finally, existing challenges strategies coping with proposed.

Language: Английский

Citations

19
Simple rule for linking atoms to construct high energy isomers DOI
Rong Wang, Chaoyang Zhang

Physical Chemistry Chemical Physics, Journal Year: 2023, Volume and Issue: 25(15), P. 10384 - 10391

Published: Jan. 1, 2023

The present work concerns a basic issue in molecular science, i.e., constructing high energy isomer with given composition. Three compositions of CH3NO2, CH4N2O2, and CH3NO3 are adopted to construct various isomers the internal calculated compared ascertain its dependence on linking order atoms. Thereby, simple rule for CHNO is summarized. separation reducing C/H atoms oxidizing O by N as well direct linkage C-C, C-H, O-O, benefits energy; other hand, O-O leads low stability, thus double atom necessary build stable energetic molecule. C-O O-H significantly weakens or diminishes activity related atoms, can be called died This expected promote screening molecules fields fuels materials.

Language: Английский

Citations

7
Molecular descriptor-enhanced graph neural network for energetic molecular property prediction DOI Open Access
Tianyu Gao, Yujin Ji, Cheng Liu

et al.

Science China Materials, Journal Year: 2024, Volume and Issue: 67(4), P. 1243 - 1252

Published: March 14, 2024

Language: Английский

Citations

2
Recent advances in studying the nonnegligible role of noncovalent interactions in various types of energetic molecular crystals DOI
Xiao Zhao, Weihua Zhu

CrystEngComm, Journal Year: 2022, Volume and Issue: 24(35), P. 6119 - 6136

Published: Jan. 1, 2022

This highlight summarizes the research progress on considerable effects of noncovalent interactions diverse types energetic materials and enlighten us to explore new factors that affect key performance explosives.

Language: Английский

Citations

10
Searching for the analogues of 1,1-dinitro-2,2-diamino ethylene (FOX-7) by high-throughput computation and machine learning DOI Creative Commons
Wen Qian, Jing Huang, Shitai Guo

et al.

FirePhysChem, Journal Year: 2023, Volume and Issue: 3(4), P. 339 - 349

Published: April 6, 2023

1,1-dinitro-2,2-diamino ethylene (FOX-7) is typically representative of low sensitivity and high energy compound. In this work, analogues FOX-7 are screened using a combined method high-throughput computation (HTC) machine learning (ML). The molecules generated with typical unsaturated hydrocarbons backbones random combination substituents -H, -NH2 -NO2, then HTC performed based on 200 sample molecules. ML models established the results, detonation parameters predicted most accurate model extreme gradient boosting (XGB). Finally, stability filtered confirmed by quantum chemistry calculations, besides FOX-7, 8 more energetic as well (detonation velocity ≥ 8841.1 m/s, pressure 34.6 GPa parameter bond dissociation 201.7 kJ/mol) achieved. This work has shown efficiency methods in searching new target

Language: Английский

Citations

4
Understanding of the difference in packing density of some energetic isomers DOI
Rong Wang, Yaoyao Linghu, Kai Zhong

et al.

CrystEngComm, Journal Year: 2023, Volume and Issue: 25(42), P. 5951 - 5965

Published: Jan. 1, 2023

This work describes the underlying mechanism for packing density differences in energetic isomers and presents a strategy constructing high compounds.

Language: Английский

Citations

4