Predicting performance-related properties of refrigerant based on tailored small-molecule functional group contribution

2025-03-23

AI Summary

Existing group contribution (GC) methods for small molecules exhibit strong generalizability but suffer from large prediction errors for refrigerants, hindering rational design of low-global-warming-potential (GWP), high-efficiency refrigerants. Method: This work introduces, for the first time, a dedicated functional-group partitioning scheme tailored to small-molecule refrigerants (halogenated and oxygenated hydrocarbons, C₁–C₄), integrating multitask machine learning with GC modeling to predict five key thermodynamic properties: normal boiling point, critical temperature and pressure, enthalpy of vaporization, and acentric factor. Customized group decomposition, synergistic internal–external database expansion, and transfer-based validation are employed. Contribution/Results: The proposed model achieves significantly higher accuracy than generic GC approaches across all target properties—reducing mean absolute error by 35–62%. It establishes a new, interpretable, and high-precision paradigm for elucidating structure–property relationships and enabling high-throughput screening of next-generation refrigerants.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Description Logics
• Cognitive Modeling & Cognitive Systems: Applications

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

As current group contribution (GC) methods are mostly proposed for a wide size-range of molecules, applying them to property prediction of small refrigerant molecules could lead to unacceptable errors. In this sense, for the design of novel refrigerants and refrigeration systems, tailoring GC-based models specifically fitted to refrigerant molecules is of great interest. In this work, databases of potential refrigerant molecules are first collected, focusing on five key properties related to the operational efficiency of refrigeration systems, namely normal boiling point, critical temperature, critical pressure, enthalpy of vaporization, and acentric factor. Based on tailored small-molecule groups, the GC method is combined with machine learning (ML) to model these performance-related properties. Following the development of GC-ML models, their performance is analyzed to highlight the potential group-to-property contributions. Additionally, the refrigerant property databases are extended internally and externally, based on which examples are presented to highlight the significance of the developed models.

Problem

• Tailoring group contribution methods for small refrigerant molecules
• Predicting key refrigerant properties using GC-ML models
• Extending refrigerant databases to validate model significance

Innovation

• Tailored small-molecule group contribution method
• Combined GC with machine learning modeling
• Extended refrigerant property databases internally externally