Use of Artificial Neural Network in Educational Laboratory Applications: Low-Velocity Impact Test
Fuente:
ERIC Institute of Education Sciences
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Recurso educativo Open Access |
| Lingua: | en |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1867181807961636864 |
|---|---|
| author | Yusuf Uzun Mehmet Kayrici |
| author_facet | Yusuf Uzun Mehmet Kayrici Yusuf Uzun Mehmet Kayrici |
| collection | Education Resources Information Center |
| contents | Use of Artificial Neural Network in Educational Laboratory Applications: Low-Velocity Impact Test Yusuf Uzun Mehmet Kayrici Artificial Intelligence Open Education Energy Models Prediction In this study, which focuses on selecting the material and predicting its mechanical behaviors in materials science, an Artificial Neural Network (ANN) was used to predict and simulate the low-speed impact effects of hybrid nano-doped aramid composites. There are not enough studies about open education practices in this field. Since error values below 1% were obtained with the proposed method, it has been shown that ANN results contribute to the prediction and derivation of force-time, force-displacement, and energy-time curves. It was concluded that the proposed ANN model could be useful in finding solutions to the impact responses of nanohybrid-doped aramid composites. ANN successfully predicted the prediction process for Part I and Part II, with accuracy rates of 99.4% and 99.3% for the displacement feature, 99.2% and 99.1% for the energy feature, and 97.1% and 98.3% for the force feature, respectively. This study is an applied training step that will simulate the impact strength of composite materials reinforced with nano additives and make serious contributions to important and easy-to-access technical training with a library feature that can be used as a basis for use as training material. |
| format | Recurso educativo Open Access |
| id | eric_EJ1470444 |
| institution | ERIC Institute of Education Sciences |
| language | en |
| publishDate | 2025 |
| record_format | eric |
| spellingShingle | Use of Artificial Neural Network in Educational Laboratory Applications: Low-Velocity Impact Test Yusuf Uzun Mehmet Kayrici Artificial Intelligence Open Education Energy Models Prediction Use of Artificial Neural Network in Educational Laboratory Applications: Low-Velocity Impact Test Yusuf Uzun Mehmet Kayrici Artificial Intelligence Open Education Energy Models Prediction In this study, which focuses on selecting the material and predicting its mechanical behaviors in materials science, an Artificial Neural Network (ANN) was used to predict and simulate the low-speed impact effects of hybrid nano-doped aramid composites. There are not enough studies about open education practices in this field. Since error values below 1% were obtained with the proposed method, it has been shown that ANN results contribute to the prediction and derivation of force-time, force-displacement, and energy-time curves. It was concluded that the proposed ANN model could be useful in finding solutions to the impact responses of nanohybrid-doped aramid composites. ANN successfully predicted the prediction process for Part I and Part II, with accuracy rates of 99.4% and 99.3% for the displacement feature, 99.2% and 99.1% for the energy feature, and 97.1% and 98.3% for the force feature, respectively. This study is an applied training step that will simulate the impact strength of composite materials reinforced with nano additives and make serious contributions to important and easy-to-access technical training with a library feature that can be used as a basis for use as training material. |
| title | Use of Artificial Neural Network in Educational Laboratory Applications: Low-Velocity Impact Test |
| topic | Artificial Intelligence Open Education Energy Models Prediction |
| url | https://eric.ed.gov/?id=EJ1470444 |