A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites

作     者：C.Muir B.Swaminathan K.Fields A.S.Almansour K.Sevener C.Smith M.Presby J.D.Kiser T.M.Pollock S.Daly 

作者机构：MaterialsUniversity of California-Santa BarbaraSanta BarbaraCAUSA Mechanical EngineeringUniversity of California-Santa BarbaraSanta BarbaraCAUSA NASA Glenn Research CenterClevelandOHUSA Materials Science and EngineeringUniversity of Michigan-Ann ArborAnn ArborMIUSA 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2021年第7卷第1期

页      面：1326-1335页

核心收录：

学科分类：08[工学] 080501[工学-材料物理与化学] 0805[工学-材料科学与工程（可授工学、理学学位）] 

基　　金：C.M.and B.S.gratefully acknowledge financial support from the NASA Space Technology Research Grant Program(Grants:80NSSC19K1164 and 80NSSC17K0084) S.D.and T.M.P.gratefully acknowledge financial support from the National Science Foundation(Award:1934641) as part of the HDR IDEAS2 Institute.The authors thank Abed Musaffar for creating the CAD schematic in Fig.1a and thank Dr.Neal Brodnik for a detailed introduction to t-SNE 

主　　题：composites damage mechanism 

摘      要：In this work,we demonstrate that damage mechanism identification from acoustic emission(AE)signals generated in minicomposites with elastically similar constituents is *** waveforms were generated by SiC/SiC ceramic matrix minicomposites(CMCs)loaded under uniaxial tension and recorded by four sensors(two models with each model placed at two ends).Signals were encoded with a modified partial power scheme and subsequently partitioned through spectral *** cracking and fiber failure were identified based on the frequency information contained in the AE event they produced,despite the similar constituent elastic properties of the matrix and ***,the resultant identification of AE events closely followed CMC damage chronology,wherein early matrix cracking is later followed by fiber breaks,even though the approach is fully domain-knowledge ***,the partitions were highly precise across both the model and location of the sensors,and the partitioning was *** presented approach is promising for CMCs and other composite systems with elastically similar constituents.