Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites
This paper presents a machine learning model to predict the effect of Al<sub>2</sub>O<sub>3</sub> nanoparticle content on the coefficient of thermal expansion in Cu-Al<sub>2</sub>O<sub>3</sub> nanocomposites prepared using an in situ chemical technique...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/7/1050 |
| _version_ | 1797438558421647360 |
|---|---|
| author | Ayman M. Sadoun Ismail R. Najjar Ghazi S. Alsoruji Ahmed Wagih Mohamed Abd Elaziz |
| author_facet | Ayman M. Sadoun Ismail R. Najjar Ghazi S. Alsoruji Ahmed Wagih Mohamed Abd Elaziz |
| author_sort | Ayman M. Sadoun |
| collection | DOAJ |
| description | This paper presents a machine learning model to predict the effect of Al<sub>2</sub>O<sub>3</sub> nanoparticle content on the coefficient of thermal expansion in Cu-Al<sub>2</sub>O<sub>3</sub> nanocomposites prepared using an in situ chemical technique. The model developed is a modification of Long Short-Term Memory (LSTM) using dwarf mongoose optimization (DMO), which mimics the behavior of DMO to find its food for predicting the behavior of the composite. The swarm of DMO consists of three groups, namely the alpha group, scouts, and babysitters. Each group has its own behavior to capture the food. The preparation of the nanocomposite was performed using aluminum nitrate that was added to a solution containing scattered copper nitrate. After that, the powders of CuO and Al<sub>2</sub>O<sub>3</sub> were obtained, and the leftover liquid was removed using thermal treatment at 850 °C for 1 h. The powders were consolidated using compaction and sintering processes. The impact of Al<sub>2</sub>O<sub>3</sub> contents on the thermal properties of the Cu-Al<sub>2</sub>O<sub>3</sub> nanocomposite was investigated. The results showed that the Thermal Expansion Coefficient (TEC) decreases with increasing Al<sub>2</sub>O<sub>3</sub> content due to the increased precipitation of Al<sub>2</sub>O<sub>3</sub> nanoparticles at the grain boundaries of the Cu matrix. Moreover, the good interfacial bonding between Al<sub>2</sub>O<sub>3</sub> and the Cu may participate in this decrease in TEC. The proposed machine learning model was able to predict the TEC of all the produced composites with different Al<sub>2</sub>O<sub>3</sub> content and was tested at different temperatures with very good accuracy, reaching 99%. |
| first_indexed | 2024-03-09T11:39:43Z |
| format | Article |
| id | doaj.art-ef61b6f604cd4dc08a64d7b42f14aa01 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T11:39:43Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-ef61b6f604cd4dc08a64d7b42f14aa012023-11-30T23:36:26ZengMDPI AGMathematics2227-73902022-03-01107105010.3390/math10071050Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> NanocompositesAyman M. Sadoun0Ismail R. Najjar1Ghazi S. Alsoruji2Ahmed Wagih3Mohamed Abd Elaziz4Mechanical Engineering Department, Faculty of Engineering, King Abdulaziz University, Jeddah 80204, Saudi ArabiaMechanical Engineering Department, Faculty of Engineering, King Abdulaziz University, Jeddah 80204, Saudi ArabiaMechanical Engineering Department, Faculty of Engineering, King Abdulaziz University, Jeddah 80204, Saudi ArabiaDepartment of Mechanical Design and Production Engineering, Faculty of Engineering, Zagazig University, Zagazig 44519, EgyptFaculty of Computer Science & Engineering, Galala University, Suze 43511, EgyptThis paper presents a machine learning model to predict the effect of Al<sub>2</sub>O<sub>3</sub> nanoparticle content on the coefficient of thermal expansion in Cu-Al<sub>2</sub>O<sub>3</sub> nanocomposites prepared using an in situ chemical technique. The model developed is a modification of Long Short-Term Memory (LSTM) using dwarf mongoose optimization (DMO), which mimics the behavior of DMO to find its food for predicting the behavior of the composite. The swarm of DMO consists of three groups, namely the alpha group, scouts, and babysitters. Each group has its own behavior to capture the food. The preparation of the nanocomposite was performed using aluminum nitrate that was added to a solution containing scattered copper nitrate. After that, the powders of CuO and Al<sub>2</sub>O<sub>3</sub> were obtained, and the leftover liquid was removed using thermal treatment at 850 °C for 1 h. The powders were consolidated using compaction and sintering processes. The impact of Al<sub>2</sub>O<sub>3</sub> contents on the thermal properties of the Cu-Al<sub>2</sub>O<sub>3</sub> nanocomposite was investigated. The results showed that the Thermal Expansion Coefficient (TEC) decreases with increasing Al<sub>2</sub>O<sub>3</sub> content due to the increased precipitation of Al<sub>2</sub>O<sub>3</sub> nanoparticles at the grain boundaries of the Cu matrix. Moreover, the good interfacial bonding between Al<sub>2</sub>O<sub>3</sub> and the Cu may participate in this decrease in TEC. The proposed machine learning model was able to predict the TEC of all the produced composites with different Al<sub>2</sub>O<sub>3</sub> content and was tested at different temperatures with very good accuracy, reaching 99%.https://www.mdpi.com/2227-7390/10/7/1050metal matrix nanocompositesthermal propertiesartificial neural networkdwarf mongoose optimization (DMO)long short-term memory (LSTM) |
| spellingShingle | Ayman M. Sadoun Ismail R. Najjar Ghazi S. Alsoruji Ahmed Wagih Mohamed Abd Elaziz Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites Mathematics metal matrix nanocomposites thermal properties artificial neural network dwarf mongoose optimization (DMO) long short-term memory (LSTM) |
| title | Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites |
| title_full | Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites |
| title_fullStr | Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites |
| title_full_unstemmed | Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites |
| title_short | Utilizing a Long Short-Term Memory Algorithm Modified by Dwarf Mongoose Optimization to Predict Thermal Expansion of Cu-Al<sub>2</sub>O<sub>3</sub> Nanocomposites |
| title_sort | utilizing a long short term memory algorithm modified by dwarf mongoose optimization to predict thermal expansion of cu al sub 2 sub o sub 3 sub nanocomposites |
| topic | metal matrix nanocomposites thermal properties artificial neural network dwarf mongoose optimization (DMO) long short-term memory (LSTM) |
| url | https://www.mdpi.com/2227-7390/10/7/1050 |
| work_keys_str_mv | AT aymanmsadoun utilizingalongshorttermmemoryalgorithmmodifiedbydwarfmongooseoptimizationtopredictthermalexpansionofcualsub2subosub3subnanocomposites AT ismailrnajjar utilizingalongshorttermmemoryalgorithmmodifiedbydwarfmongooseoptimizationtopredictthermalexpansionofcualsub2subosub3subnanocomposites AT ghazisalsoruji utilizingalongshorttermmemoryalgorithmmodifiedbydwarfmongooseoptimizationtopredictthermalexpansionofcualsub2subosub3subnanocomposites AT ahmedwagih utilizingalongshorttermmemoryalgorithmmodifiedbydwarfmongooseoptimizationtopredictthermalexpansionofcualsub2subosub3subnanocomposites AT mohamedabdelaziz utilizingalongshorttermmemoryalgorithmmodifiedbydwarfmongooseoptimizationtopredictthermalexpansionofcualsub2subosub3subnanocomposites |