izpis_h1_title_alt

Signali akustične emisije med obremenjevanjem polimernih kompozitov
Misson, Martin (Author), Kek, Tomaž (Mentor) More about this mentor... This link opens in a new window, Potočnik, Primož (Co-mentor)

.pdfPDF - Presentation file, Download (3,13 MB)
MD5: 5D4C604F5CA97A1EECF7D7C7987C2F49

Abstract
Analizirani so bili karakteristični signali akustične emisije, ki nastanejo kot posledica različnih mehanizmov lomov v materialu. Signali so bili pridobljeni z upogibnega obremenjevanja polimernih kompozitov s steklenimi in karbidnimi vlakni. Popis značilnosti signalov v časovni ali frekvenčni domeni ni zadostoval za nastanek razločljivih gruč v prostoru vektorjev značilk. Iz tega razloga so bile uporabljene nove značilke, izpeljane z globokim učenjem konvolucijskega avtoenkoderja, ki so vsebovale informacijo o vsebini zvezne valčne transformacije. Po odstranjevanju točk osamelcev z metodo DBSCAN je bilo z vektorji značilk doseženo tvorjenje bolj razločljivih gruč kot s prvotnimi vektorji značilk. Nenadzorovano razvrščanje vektorjev značilk karakterističnih signalov vsakega kompozita posebej je bilo izvedeno z metodo K-means. Primerjava izpeljanih vektorjev značilk visokofrekvenčnih karakterističnih signalov kompozitov z različnimi vlakni je razkrila raznolike gruče, ki so bile uspešno razvrščene z metodo spektralnega razvrščanja.

Language:Slovenian
Keywords:akustična emisija, polimerni kompoziti, konvolucijski avtoenkoder, zvezna valčna transformacija, izpeljava značilk, gručenje
Work type:Master's thesis/paper (mb22)
Tipology:2.09 - Master's Thesis
Organization:FS - Faculty of Mechanical Engineering
Year:2021
Publisher:[M. Misson]
Number of pages:XXII, 57 str.
UDC:620.179.16:678.7(043.2)
COBISS.SI-ID:78444547 This link opens in a new window
Views:84
Downloads:22
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Acoustic emission signals at loading of polymer composites
Abstract:
The characteristic acoustic emission (AE) signals generated as a result of different damage mechanisms in the material were analyzed. The signals were obtained from bending of glass (GFE) and carbon fibre epoxy (CFE) composites. Characterization of signals in the time or frequency domain was not sufficient for the formation of distinct clusters in the space of feature vectors. For this reason, new features with time-frequency domain content were extracted from deep convolutional autoencoder. After removing the isolated points by the DBSCAN method, the formation of more distinct clusters was achieved with respect to the original feature vectors. The unsupervised classification of the feature vectors was performed separately for each composite using the K-means method. Comparison of the extracted feature vectors of high-frequency characteristic signals of GFE and CFE composites revealed diverse clusters that were adequately sorted using the spectral clustering method.

Keywords:acoustic emission, polymer composites, convolutional autoencoder, continuous wavelet transform, feature extraction, clustering

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back