Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints
The aim of this study was to optimize the ultrasonic consolidation (USC) parameters for ‘PEI adherend/Prepreg (CF-PEI fabric)/PEI adherend’ lap joints. For this purpose, artificial neural network (ANN) simulation was carried out. Two ANNs were trained using an ultra-small data sample, which did not...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Polymers |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4360/16/4/451 |
_version_ | 1797297113900515328 |
---|---|
author | Dmitry Y. Stepanov Defang Tian Vladislav O. Alexenko Sergey V. Panin Dmitry G. Buslovich |
author_facet | Dmitry Y. Stepanov Defang Tian Vladislav O. Alexenko Sergey V. Panin Dmitry G. Buslovich |
author_sort | Dmitry Y. Stepanov |
collection | DOAJ |
description | The aim of this study was to optimize the ultrasonic consolidation (USC) parameters for ‘PEI adherend/Prepreg (CF-PEI fabric)/PEI adherend’ lap joints. For this purpose, artificial neural network (ANN) simulation was carried out. Two ANNs were trained using an ultra-small data sample, which did not provide acceptable predictive accuracy for the applied simulation methods. To solve this issue, it was proposed to artificially increase the learning sample by including additional data synthesized according to the knowledge and experience of experts. As a result, a relationship between the USC parameters and the functional characteristics of the lap joints was determined. The results of ANN simulation were successfully verified; the developed USC procedures were able to form a laminate with an even regular structure characterized by a minimum number of discontinuities and minimal damage to the consolidated components. |
first_indexed | 2024-03-07T22:16:32Z |
format | Article |
id | doaj.art-0b3986e6022b43de9f8e4509ae36b6c6 |
institution | Directory Open Access Journal |
issn | 2073-4360 |
language | English |
last_indexed | 2024-03-07T22:16:32Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Polymers |
spelling | doaj.art-0b3986e6022b43de9f8e4509ae36b6c62024-02-23T15:32:08ZengMDPI AGPolymers2073-43602024-02-0116445110.3390/polym16040451Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap JointsDmitry Y. Stepanov0Defang Tian1Vladislav O. Alexenko2Sergey V. Panin3Dmitry G. Buslovich4Laboratory of Mechanics of Polymer Composite Materials, Institute of Strength Physics and Materials Science of Siberian Branch of Russian Academy of Sciences, 634055 Tomsk, RussiaDepartment of Materials Science, Engineering School of Advanced Manufacturing Technologies, National Research Tomsk Polytechnic University, 634050 Tomsk, RussiaLaboratory of Mechanics of Polymer Composite Materials, Institute of Strength Physics and Materials Science of Siberian Branch of Russian Academy of Sciences, 634055 Tomsk, RussiaLaboratory of Mechanics of Polymer Composite Materials, Institute of Strength Physics and Materials Science of Siberian Branch of Russian Academy of Sciences, 634055 Tomsk, RussiaLaboratory of Nanobioengineering, Institute of Strength Physics and Materials Science of Siberian Branch of 9 Russian Academy of Sciences, 634055 Tomsk, RussiaThe aim of this study was to optimize the ultrasonic consolidation (USC) parameters for ‘PEI adherend/Prepreg (CF-PEI fabric)/PEI adherend’ lap joints. For this purpose, artificial neural network (ANN) simulation was carried out. Two ANNs were trained using an ultra-small data sample, which did not provide acceptable predictive accuracy for the applied simulation methods. To solve this issue, it was proposed to artificially increase the learning sample by including additional data synthesized according to the knowledge and experience of experts. As a result, a relationship between the USC parameters and the functional characteristics of the lap joints was determined. The results of ANN simulation were successfully verified; the developed USC procedures were able to form a laminate with an even regular structure characterized by a minimum number of discontinuities and minimal damage to the consolidated components.https://www.mdpi.com/2073-4360/16/4/451machine learningneural network simulationcarbon fiber fabricultrasonic consolidationlap jointPEI |
spellingShingle | Dmitry Y. Stepanov Defang Tian Vladislav O. Alexenko Sergey V. Panin Dmitry G. Buslovich Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints Polymers machine learning neural network simulation carbon fiber fabric ultrasonic consolidation lap joint PEI |
title | Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints |
title_full | Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints |
title_fullStr | Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints |
title_full_unstemmed | Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints |
title_short | Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints |
title_sort | application of neural network models with ultra small samples to optimize the ultrasonic consolidation parameters for pei adherend prepreg cf pei fabric pei adherend lap joints |
topic | machine learning neural network simulation carbon fiber fabric ultrasonic consolidation lap joint PEI |
url | https://www.mdpi.com/2073-4360/16/4/451 |
work_keys_str_mv | AT dmitryystepanov applicationofneuralnetworkmodelswithultrasmallsamplestooptimizetheultrasonicconsolidationparametersforpeiadherendprepregcfpeifabricpeiadherendlapjoints AT defangtian applicationofneuralnetworkmodelswithultrasmallsamplestooptimizetheultrasonicconsolidationparametersforpeiadherendprepregcfpeifabricpeiadherendlapjoints AT vladislavoalexenko applicationofneuralnetworkmodelswithultrasmallsamplestooptimizetheultrasonicconsolidationparametersforpeiadherendprepregcfpeifabricpeiadherendlapjoints AT sergeyvpanin applicationofneuralnetworkmodelswithultrasmallsamplestooptimizetheultrasonicconsolidationparametersforpeiadherendprepregcfpeifabricpeiadherendlapjoints AT dmitrygbuslovich applicationofneuralnetworkmodelswithultrasmallsamplestooptimizetheultrasonicconsolidationparametersforpeiadherendprepregcfpeifabricpeiadherendlapjoints |