Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process

2015
Аутори
Patarić, Aleksandra
Gulišija, Zvonko
Jordović, Branka
Pezo, Lato

Mihailović, Marija

Stefanović, Milentije
Чланак у часопису (Објављена верзија)

Метаподаци
Приказ свих података о документуАпстракт
In this study the mechanical properties (reduction of area, S-0, tensile strength, R-m, yield strength, R-p, and elongation, A) of EN AW 7075 aluminum alloy obtained by electromagnetic casting were investigated at different operating parameters: frequency (V), field strength (T) and current intensity (I). The predictive mathematical models using Response Surface Methodology, with second order polynomial (SOP) regression models, and Artificial Neural Network model (ANN), were afterwards compared to obtained experimental results. Analysis of variance and post-hoc Tukey's HSD test at 95% confidence limit ("honestly significant differences") have been utilised to show significant differences between various samples. SOP models showed good prediction capabilities, with high coefficients of determination (r(2)), 0.531-0.977, while ANN model performed even better prediction accuracy: 0.800-0.992. The optimal samples were chosen depending on mechanical properties of the product (S-0 = 50.49mm(...2), R-m = 405.75Nmm(-2), R-p = 302.49Nmm(-2), A = 6.86%), using optimal operating parameters (V = 30 Hz, I = 250 A, T = 18 x 10(-3) At).
Кључне речи:
prediction / neural network modeling / mechanical properties / casting / aluminum alloyИзвор:
Materials Transactions, 2015, 56, 6, 835-839Издавач:
- Japan Inst Metals, Sendai
Финансирање / пројекти:
- Развој технолошких поступака ливења под утицајем електромагнетног поља и технологија пластичне прераде у топлом стању четворокомпонентних легура Al-Zn за специјалне намене (RS-34002)
- Осмотска дехидратација хране - енергетски и еколошки аспекти одрживе производње (RS-31055)
DOI: 10.2320/matertrans.M2015058
ISSN: 1345-9678
WoS: 000357692200012
Scopus: 2-s2.0-84929897648
Институција/група
Institut za tehnologiju nuklearnih i drugih mineralnih sirovinaTY - JOUR AU - Patarić, Aleksandra AU - Gulišija, Zvonko AU - Jordović, Branka AU - Pezo, Lato AU - Mihailović, Marija AU - Stefanović, Milentije PY - 2015 UR - https://ritnms.itnms.ac.rs/handle/123456789/354 AB - In this study the mechanical properties (reduction of area, S-0, tensile strength, R-m, yield strength, R-p, and elongation, A) of EN AW 7075 aluminum alloy obtained by electromagnetic casting were investigated at different operating parameters: frequency (V), field strength (T) and current intensity (I). The predictive mathematical models using Response Surface Methodology, with second order polynomial (SOP) regression models, and Artificial Neural Network model (ANN), were afterwards compared to obtained experimental results. Analysis of variance and post-hoc Tukey's HSD test at 95% confidence limit ("honestly significant differences") have been utilised to show significant differences between various samples. SOP models showed good prediction capabilities, with high coefficients of determination (r(2)), 0.531-0.977, while ANN model performed even better prediction accuracy: 0.800-0.992. The optimal samples were chosen depending on mechanical properties of the product (S-0 = 50.49mm(2), R-m = 405.75Nmm(-2), R-p = 302.49Nmm(-2), A = 6.86%), using optimal operating parameters (V = 30 Hz, I = 250 A, T = 18 x 10(-3) At). PB - Japan Inst Metals, Sendai T2 - Materials Transactions T1 - Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process EP - 839 IS - 6 SP - 835 VL - 56 DO - 10.2320/matertrans.M2015058 UR - conv_734 ER -
@article{ author = "Patarić, Aleksandra and Gulišija, Zvonko and Jordović, Branka and Pezo, Lato and Mihailović, Marija and Stefanović, Milentije", year = "2015", abstract = "In this study the mechanical properties (reduction of area, S-0, tensile strength, R-m, yield strength, R-p, and elongation, A) of EN AW 7075 aluminum alloy obtained by electromagnetic casting were investigated at different operating parameters: frequency (V), field strength (T) and current intensity (I). The predictive mathematical models using Response Surface Methodology, with second order polynomial (SOP) regression models, and Artificial Neural Network model (ANN), were afterwards compared to obtained experimental results. Analysis of variance and post-hoc Tukey's HSD test at 95% confidence limit ("honestly significant differences") have been utilised to show significant differences between various samples. SOP models showed good prediction capabilities, with high coefficients of determination (r(2)), 0.531-0.977, while ANN model performed even better prediction accuracy: 0.800-0.992. The optimal samples were chosen depending on mechanical properties of the product (S-0 = 50.49mm(2), R-m = 405.75Nmm(-2), R-p = 302.49Nmm(-2), A = 6.86%), using optimal operating parameters (V = 30 Hz, I = 250 A, T = 18 x 10(-3) At).", publisher = "Japan Inst Metals, Sendai", journal = "Materials Transactions", title = "Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process", pages = "839-835", number = "6", volume = "56", doi = "10.2320/matertrans.M2015058", url = "conv_734" }
Patarić, A., Gulišija, Z., Jordović, B., Pezo, L., Mihailović, M.,& Stefanović, M.. (2015). Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process. in Materials Transactions Japan Inst Metals, Sendai., 56(6), 835-839. https://doi.org/10.2320/matertrans.M2015058 conv_734
Patarić A, Gulišija Z, Jordović B, Pezo L, Mihailović M, Stefanović M. Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process. in Materials Transactions. 2015;56(6):835-839. doi:10.2320/matertrans.M2015058 conv_734 .
Patarić, Aleksandra, Gulišija, Zvonko, Jordović, Branka, Pezo, Lato, Mihailović, Marija, Stefanović, Milentije, "Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process" in Materials Transactions, 56, no. 6 (2015):835-839, https://doi.org/10.2320/matertrans.M2015058 ., conv_734 .