CIESC Journal ›› 2022, Vol. 73 ›› Issue (4): 1493-1500.DOI: 10.11949/0438-1157.20211377

• Thermodynamics • Previous Articles     Next Articles

Critical temperature prediction of working fluids using molecular fingerprints and topological indices

Jiahui REN1(),Yu LIU1(),Chao LIU1,Lang LIU2,Ying LI3   

  1. 1.Key Laboratory of Low-grade Energy Utilization Technologies and Systems, Ministry of Education, School of Energy and Power Engineering, Chongqing University, Chongqing 400030, China
    2.State Key Laboratory of Pollution Control and Resource Reuse, Nanjing 210023, Jiangsu, China
    3.CNNC Key Laboratory on Nuclear Reactor ThermoHydraulics Technology, Nuclear Power Institute of China, Chengdu 610213, Sichuan, China
  • Received:2021-09-27 Revised:2022-01-06 Online:2022-04-25 Published:2022-04-05
  • Contact: Yu LIU

基于分子指纹和拓扑指数的工质临界温度理论预测

任嘉辉1(),刘豫1(),刘朝1,刘浪2,李莹3   

  1. 1.重庆大学低品位能源利用技术及系统教育部重点实验室,能源与动力工程学院,重庆 400030
    2.污染控制与资源化研究国家重点实验室,江苏 南京 210023
    3.中国核动力研究设计院中核核反应堆热工水力技术重点实验室,四川 成都 610213
  • 通讯作者: 刘豫
  • 作者简介:任嘉辉(1997—),男,硕士研究生,jiahuiren@cqu.edu.cn
  • 基金资助:
    国家自然科学基金项目(51876015);污染控制与资源化研究国家重点实验室开放基金(PCRRF19038)

Abstract:

The critical temperature is a very critical thermophysical property, and its theoretical prediction has always been a hot topic in thermophysical property research. However, the previously reported models cannot effectively distinguish the isomers in working fluids. To solve this problem, the new structure description ‘molecular fingerprints + topological index’ was considered in the predicted model, the average absolute deviation between the predicted and experimental values is 3.99%, which proves the reasonable prediction performance of the proposed model. Then the estimation accuracy of the model was compared with previous models, the results indicated that the proposed model can not only effectively distinguish the isomers of working fluids, but also surpass other existing models with respect to accuracy.

Key words: working fluids, thermodynamic properties, critical temperature, topological index, machine learning, neural networks, prediction

摘要:

临界温度是一种非常关键的热物理性质,对其进行理论预测一直是热物性研究的热点。然而,早期预测模型往往不能有效区分工质同分异构体。本文借助机器学习算法,采用“分子指纹+拓扑指数”的新型分子结构描述方法表达工质的分子结构并建立临界温度模型,在测试集预测中的绝对平均偏差为3.99%,表明本文模型具有良好的预测能力。本文模型与文献对比的结果表明,新模型不仅可以有效区分工质同分异构体,在计算精度方面也超越了现有其他模型。

关键词: 工质, 热力学性质, 临界温度, 拓扑指数, 机器学习, 神经网络, 预测

CLC Number: