聚丙烯复合材料老化数据集成学习  

Ensemble learning of polypropylene-composite aging data

作　　者：武星[1,2,4] 高进 丁鹏 WU Xing;GAO Jin;DING Peng(School of Computer Science and Engineering,Shanghai University,Shanghai 200444,China;Zhejiang Laboratory,Hangzhou 311100,Zhejiang,China;Research Center of Nanoscience and Nanotechnology,College of Sciences,Shanghai University,Shanghai 200444,China;Center of Materials Informatics and Data Science,Materials Genome Institute,Shanghai University,Shanghai 200444,China)

机构地区：[1]上海大学计算机工程与科学学院,上海200444 [2]之江实验室,浙江杭州311100 [3]上海大学材料基因组工程研究院材料信息与数据科学中心,上海200444 [4]上海大学理学院,上海200444

出　　处：《上海大学学报（自然科学版）》2022年第3期440-450,共11页Journal of Shanghai University:Natural Science Edition

基　　金：国家重点研发计划资助项目(2018YFB0704400);国家自然基金资助项目(52073168);云南省重大科技专项资助项目(202102AB080019-3,202002AB080001-2);之江实验室科研攻关资助项目(2021PE0AC02);上海张江国家自主创新示范区专项发展资金重大资助项目(ZJ2021-ZD-006)。

摘　　要：聚丙烯复合材料老化实验周期长,且单次实验采集的数据样本少,使用传统机器学习方法进行预测的准确度较低.为了解决聚丙烯复合材料老化数据样本少与预测准确性低的问题,提出了一种虚拟样本生成(virtual sample generation,VSG)的集成学习预测方法.首先,对聚丙烯复合材料老化数据使用高斯混合模型(Gaussian mixed model,GMM)虚拟样本生成方法平滑生成验证有效的虚拟样本;然后,使用生成后的数据集建立集成学习预测模型,该模型包含随机森林(random forest,RF)、极端梯度提升(extreme gradient boosting,XGBoost)算法、轻量级梯度提升机(light gradient boosting machine,LightGBM)算法以及分类梯度提升(categorical boosting,CatBoost)算法.实验表明:集成学习模型的LightGBM算法与CatBoost算法性能最优,在测试数据上均方误差为0.0013与0.0001,比RF算法与XGBoost算法分别高出0.4与0.2.聚丙烯复合材料老化虚拟样本生成与集成学习方法可以有效解决实验周期长、单次实验采集的数据样本少的问题,并可取得比单一机器学习算法更优的性能.Aging experiments conducted on polypropylene composites have long durations,and a limited number of samples can be collected in a single experiment.As a result,traditional machine-learning approaches have a low prediction accuracy.To address these issues,we present an ensemble learning prediction based on virtual sample generation(VSG).To generate valid virtual samples of aging data for polypropylene composites,we first adopted the Gaussian mixed model(GMM)method and then used the generated data set to build an ensemble-learning prediction model comprising the random forest(RF),extreme gradient boosting(XGBoost),light gradient boosting machine(LightGBM),and categorical boosting(CatBoost)algorithms.The LightGBM and CatBoost algorithms in the ensemble learning model demonstrate the best performance on the test data;the mean square errors are 0.0013 and 0.0001,respectively,which are 0.4 and 0.2 higher than those of the RF algorithm and XGBoost algorithm,respectively.This study’s aging VSG and ensemble learning approach for polypropylene composites can not only successfully overcome the long experimental times and insufficient number of data samples acquired in a single experiment but outperforms a single machine-learning algorithm.

关 键 词：聚丙烯复合材料 材料老化 集成学习 高斯混合模型 

分 类 号：TB33[一般工业技术—材料科学与工程]