An Improved Machine Learning Model for Pure Component Property Estimation  

一种改进的纯组分物性预测机器学习模型

作　　者：Xinyu Cao Ming Gong Anjan Tula Xi Chen Rafiqul Gani Venkat Venkatasubramanian 曹欣羽;贡铭;Anjan Tula;陈曦;Rafiqul Gani;Venkat Venkatasubramanian

机构地区：[1]State Key Laboratory of Industrial Control Technology,College of Control Science and Engineering,Zhejiang University,Hangzhou 310027,China [2]Department of Physics,Bard College at Simon’s Rock,Great Barrington,MA 01230,USA [3]PSE for SPEED Company,Charlottenlund DK-2920,Denmark [4]Sustainable Energy and Environment Thrust,The Hong Kong University of Science and Technology(Guangzhou),Guangzhou 510000,China [5]Department of Applied Sustainability,Széchenyi István University,Györ 9026,Hungary [6]Complex Resilient Intelligent Systems Laboratory,Department of Chemical Engineering,Columbia University,New York,NJ 10027,USA

出　　处：《Engineering》2024年第8期61-73,共13页工程（英文）

基　　金：support from the National Natural Science Foundation of China(22150410338 and 61973268)is gratefully acknowledged.

摘　　要：Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product design.However,the lack of extensive data and high experimental costs hinder the development of prediction techniques for these properties.Moreover,accuracy and predictive capabilities still limit the scope and applicability of most property estimation methods.This paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach.A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different compounds.Prior selection techniques,including prior elicitation and prior predictive checking,are also applied during the building procedure to provide the model with more information from previous research findings.The framework is assessed using datasets of varying sizes for 20 pure component properties.For 18 out of the 20 pure component properties,the new models are found to give improved accuracy and predictive power in comparison with other published models,with and without machine learning.

关 键 词：Group contribution Gaussian process Warping function Prior predictive checking 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] O64[自动化与计算机技术—控制科学与工程]