基于人工神经网络的工质基础物性预测
PREDICTION OF PHYSICAL PROPERTIES OF WORKING FLUID BASED ON ARTIFICIAL NEURAL NETWORK
林美金 1董轩 1洪小东 2廖祖维 1孙婧元 1杨遥 1王靖岱 1阳永荣1
作者信息
- 1. 浙江大学化学工程与生物工程学院,杭州 310030
- 2. 浙江大学化学工程与生物工程学院,杭州 310030;浙江大学杭州国际科创中心
- 折叠
摘要
烃类及卤代烃是制冷及余热发电等热力学循环系统潜在的理想工质,但其数量繁多且多数物性参数未知,建立准确的物性预测模型对新型工质的开发至关重要.从多个公开数据库中收集了 2 500多种烃类及卤代烃分子(含C,H,F,C1)的基础物性参数,包括正常沸点(Tb)、临界温度(Tc)、临界压力(pc)、偏心因子(ω),构建了一个工质物性数据库;进一步,通过改进基团贡献-人工神经网络(GC-ANN)的方法,模型的输入参数除基团频率外,还加入相对分子质量、Th、约化维纳指数,建立了预测烃类及卤代烃分子Tb,Tc,pc,ω的神经网络模型,所开发模型的预测误差小于传统的GC-ANN的误差.
Abstract
Traditional working fluids in thermodynamic cycles,such as refrigeration and waste heat power generation,have been associated with issues such as ozone layer depletion and global warming.The development of efficient and environmentally friendly novel working fluids has become a research focus.Hydrocarbons and halogenated hydrocarbons are ideal candidates,but their large number and many unknown thermophysical properties make it crucial to establish accurate models for predicting these properties in order to screen new working fluids effectively.In this study,the basic thermophysical parameters of more than 2 500 hydrocarbons and halogenated hydrocarbons containing C,H,F,and Cl atoms were collected from various public databases,including normal boiling point(Tb),critical temperature(Tc),critical pressure(pc)and acentric factor(ω),and furtherly,by improving the method of group contribution-artificial neural network(GC-ANN),a neural network model for predicting Tb,Tc,pc and ω of hydrocarbons and halogenated hydrocarbons containing C,H,F,and Cl atoms was established by adding relative molecular mass,Tb and approximate wiener index to the input parameters of the model.The prediction errors of the models developed in this study were smaller than those of the traditional GC-ANN.
关键词
新型工质/物性预测/基团贡献法BP神经网络Key words
new working fluid/property prediction/group contribution method/BP neural network引用本文复制引用
基金项目
国家自然科学基金(U22A20415)
浙江省尖兵领雁计划(2022C01SA442617)
出版年
2024
NETL
NSTL
维普
万方数据