基于分子表面电荷密度分布与机器学习的混合物设计方法研究  

Mixture product design based on molecular surface charge density distribution and machine learning

作　　者：毛海涛[1] 王璐[1] 许志颖 解万翠 都健[1] 张磊[1] MAO Haitao;WANG Lu;XU Zhiying;XIE Wancui;DU Jian;ZHANG Lei(Institute of Chemical Process Systems Engineering,School of Chemical Engineering,Dalian University of Technology,Dalian 116024,Liaoning,China;College of Marine Science and Biological Engineering,Qingdao University of Science&Technology,Qingdao 266042,Shandong,China)

机构地区：[1]大连理工大学化工学院化工系统工程研究所,辽宁大连116024 [2]青岛科技大学海洋科学与生物工程学院,山东青岛266042

出　　处：《化工学报》2020年第S01期282-292,共11页CIESC Journal

基　　金：国家自然科学基金项目(21808025)。

摘　　要：由于混合物性能的可调控性,当前市场对其关注与日俱增。对于这类产品,基于模型的设计方法由于具有高效性以及普适性,相较于其他产品设计方法得到了更快的发展。但是对于很多性质,如气味、颜色等,准确且普适的模型尚不可得。因此,本文提出了一种基于分子表面电荷密度分布描述符(S描述符)和机器学习模型的混合物设计方法,采用描述符表征产品、再通过机器学习模型将其与性质关联,直接用于混合物产品设计。具体地,根据给定的产品性质需求,机器学习模型直接预测/设计混合物产品的S描述符;然后以欧几里德距离为指标,在给定的数据库中筛选出S描述符满足要求的候选混合物组成。最后,对候选混合物及其组分性质进行实验验证,完成设计。本文以香精的混合替代物设计作为算例,设计得到丙酸叶醇酯的两种混合香精替代物,通过实验对混合物进行了验证。结果表明,混合替代物的气味及其组分的各理化性质均与丙酸叶醇酯相近,证实本文所提出方法的有效性。Modern business pays increasing attentions to mixture products due to its adjustable characteristics.For the design methods towards such kinds of products,the development of model-based design methods is faster than others,because of its efficiency and wide application.However,the models for some properties,like odor and color,with acceptable accuracy or general application range are still not available.Therefore,an application methodology of machine learning(ML)with molecular surface charge density distribution(S descriptors)for mixture product design is proposed in this study,where descriptors are employed to represent the product and ML is responsible for correlating them to the target properties,for the purpose of designing product directly.Specifically,machine learning model is expected to predict S descriptors of candidate products according to the assigned property value,and ingredients are screened out using Euclidean-based method according to the predicted descriptors.Finally,the properties of the candidate mixtures and its ingredients are verified by experiments.This methodology is introduced using a case study of mixture substitution fragrance design for cis-3-hexenyl propionate and two mixture fragrances are obtained ultimately.The odor properties of mixtures and physicochemical properties of their components are similar to the target,which highlights the effective of the proposed method.

关 键 词：系统工程 产品设计 神经网络 分子表面电荷密度分布 混合物设计 香精 

分 类 号：TQ021.8[化学工程]