Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data
In this work, the ultimate strength of aluminum/silicon carbide (Al/SiC) composites was predicted by using acoustic emission (AE) parameters through artificial neural network (ANN) analysis. With this aim, a series of fourteen Al/SiC tensile samples were loaded up to the failure to investigate the a...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
University of Belgrade - Faculty of Mechanical Engineering, Belgrade
2018-01-01
|
Series: | FME Transactions |
Subjects: | |
Online Access: | https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2018/1451-20921802253C.pdf |
id |
doaj-6a3307973bee46ef8cf6d935851ab54f |
---|---|
record_format |
Article |
spelling |
doaj-6a3307973bee46ef8cf6d935851ab54f2020-11-25T03:53:30ZengUniversity of Belgrade - Faculty of Mechanical Engineering, BelgradeFME Transactions1451-20922406-128X2018-01-014622532581451-20921802253CNeural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle dataChristopher Loo Mahil C.0Sasikumar T.1Santulli C.2Fragassa C.3Sathyabama University, Department of Mechanical Engineering, IndiaLord Jegannath College of Engineering & Technology, Department of Mechanical Engineering, IndiaUniversità degli Studi di Camerino, School of Architecture and Design, ItalyAlma Mater Studiorum University of Bologna, Department of Industrial Engineering, ItalyIn this work, the ultimate strength of aluminum/silicon carbide (Al/SiC) composites was predicted by using acoustic emission (AE) parameters through artificial neural network (ANN) analysis. With this aim, a series of fourteen Al/SiC tensile samples were loaded up to the failure to investigate the amplitude distribution of AE events detected during loading. A back propagation ANN was prepared to correlate the amplitude values generated during loading up to 60% of known ultimate strength with ultimate failure strength of the samples. Three individual neural networks generated with parameters like hits, the Felicity ratio and rise angle were trained towards anticipating the ultimate strength value, which was predicted within the worst case error of -3.51 %, -4.73 %, and -2.73 %, respectively. The failure prediction accuracy by using rise angle as input was found to be slightly better, although the three neural networks all proved effective.https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2018/1451-20921802253C.pdffailure predictionacoustic emissionfelicity ratioriseanglefeed forward neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Christopher Loo Mahil C. Sasikumar T. Santulli C. Fragassa C. |
spellingShingle |
Christopher Loo Mahil C. Sasikumar T. Santulli C. Fragassa C. Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data FME Transactions failure prediction acoustic emission felicity ratio riseangle feed forward neural network |
author_facet |
Christopher Loo Mahil C. Sasikumar T. Santulli C. Fragassa C. |
author_sort |
Christopher Loo Mahil C. |
title |
Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data |
title_short |
Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data |
title_full |
Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data |
title_fullStr |
Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data |
title_full_unstemmed |
Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data |
title_sort |
neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data |
publisher |
University of Belgrade - Faculty of Mechanical Engineering, Belgrade |
series |
FME Transactions |
issn |
1451-2092 2406-128X |
publishDate |
2018-01-01 |
description |
In this work, the ultimate strength of aluminum/silicon carbide (Al/SiC) composites was predicted by using acoustic emission (AE) parameters through artificial neural network (ANN) analysis. With this aim, a series of fourteen Al/SiC tensile samples were loaded up to the failure to investigate the amplitude distribution of AE events detected during loading. A back propagation ANN was prepared to correlate the amplitude values generated during loading up to 60% of known ultimate strength with ultimate failure strength of the samples. Three individual neural networks generated with parameters like hits, the Felicity ratio and rise angle were trained towards anticipating the ultimate strength value, which was predicted within the worst case error of -3.51 %, -4.73 %, and -2.73 %, respectively. The failure prediction accuracy by using rise angle as input was found to be slightly better, although the three neural networks all proved effective. |
topic |
failure prediction acoustic emission felicity ratio riseangle feed forward neural network |
url |
https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2018/1451-20921802253C.pdf |
work_keys_str_mv |
AT christopherloomahilc neuralnetworkpredictionofaluminumsiliconcarbidetensilestrengthfromacousticemissionriseangledata AT sasikumart neuralnetworkpredictionofaluminumsiliconcarbidetensilestrengthfromacousticemissionriseangledata AT santullic neuralnetworkpredictionofaluminumsiliconcarbidetensilestrengthfromacousticemissionriseangledata AT fragassac neuralnetworkpredictionofaluminumsiliconcarbidetensilestrengthfromacousticemissionriseangledata |
_version_ |
1724477642847027200 |