Molecular descriptor-enhanced graph neural network for energetic molecular property prediction

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

Published: March 14, 2024

Language: Английский

---

Enhancing Hansen Solubility Predictions with Molecular and Graph-Based Approaches

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2024, Volume and Issue: 251, P. 105168 - 105168

Published: Aug. 1, 2024

Language: Английский

---

Study on the prediction and inverse prediction of detonation properties based on deep learning

Defence Technology, Journal Year: 2022, Volume and Issue: 24, P. 18 - 30

Published: Dec. 1, 2022

The accurate and efficient prediction of explosive detonation properties has important engineering significance for weapon design. Traditional methods predicting performance include empirical formulas, equations state, quantum chemical calculation methods. In recent years, with the development computer deep learning methods, researchers have begun to apply performance. method advantage simple rapid properties. However, some problems remain in study based on learning. For example, there are few studies mixed explosives, parameters equation state application predict formulation explosives. Based an artificial neural network model a one-dimensional convolutional model, three improved models were established this work aim solving these problems. training data models, called JWL (EOS) inverse was obtained through KHT thermochemical code. After training, tested overfitting using validation-set test. Through model-accuracy test, accuracy real formulations by comparing predicted value reference value. results show that errors within 10% 3% pressure velocity, respectively. refers which consist TNT, RDX HMX. correlation coefficient between curves above 0.99. error 9%. This indicates utility engineering.

Language: Английский

---

Machine-Learning-Guided Identification of Coordination Polymer Ligands for Crystallizing Separation of Cs/Sr

ACS Applied Materials & Interfaces, Journal Year: 2022, Volume and Issue: 14(29), P. 33076 - 33084

Published: July 8, 2022

Separation of Cs/Sr is one many coordination-chemistry-centered processes in the grand scheme spent nuclear fuel reprocessing, a critical link for sustainable energy industry. To deploy crystallizing separation technology, we planned to systematically screen and identify candidate ligands that can efficiently selectively bind Sr2+ form coordination polymers. Therefore, mined Cambridge Structural Database characteristic structural information developed machine-learning-guided methodology ligand evaluation. The optimized machine-learning model, correlating molecular structures with predicted coordinative properties, generated ranking list potential compounds selective crystallization. sequestration capability selectivity over Cs+ promising identified (squaric acid chloranilic acid) were subsequently confirmed experimentally, commendable performances, corroborating artificial-intelligence-guided strategy.

Language: Английский

---

Extended atom-based and bond-based group contribution descriptor and its application to melting point prediction of energetic compounds

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2023, Volume and Issue: 243, P. 105021 - 105021

Published: Nov. 1, 2023

Language: Английский

---