iping suhariadi

Dr. iping suhariadi


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2022 in Journal of Cleaner Production
Verified
Journal Article
Closed access
DDDonanta Dhaneswara
Donanta Dhaneswara
HMHenny Shinta Marito
Henny Shinta Marito
JFJaka Fajar Fatriansyah
Jaka Fajar Fatriansyah
NSNofrijon Sofyan
Nofrijon Sofyan
DADamar Rastri Adhika
Damar Rastri Adhika
ISiping suhariadi
iping suhariadi

27 August 2024 in IEEE Access
Verified
Journal Article
Open access
JFJaka Fajar Fatriansyah
Jaka Fajar Fatriansyah
MAMuhamad Rafi Aqila
Muhamad Rafi Aqila
ISiping suhariadi
iping suhariadi
AFAndreas Federico
Andreas Federico
DADzaky Iman Ajiputro
Dzaky Iman Ajiputro
SHSu-Mi Hur
Su-Mi Hur
Understanding the link between material composition and mechanical properties is crucial for material design and optimization. This study utilized four machine learning models—K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN)—to predict tensile strength and examine how alloying composition affects the tensile strength of titanium (Ti) alloys. The first three models are considered simpler machine learning approaches, while the ANN is a deep learning method. The models were trained on publicly available experimental data, using fifteen alloying elements as inputs: Al, C, Cr, Cu, H, Fe, Mo, Ni, Nb, N, O, Si, Sn, V, and Zr. A new framework was proposed for evaluating the best model, which involves running several ML models, assessing metrics such as R² value, absolute percentage error distribution, and stability of R² through multiple trials, and finally comparing model accuracy using the Diebold-Mariano test. The evaluation showed that all four models achieved good accuracy, with R² values above 80%. However, the framework identified KNN as the best model due to its low error rate, the narrowest range in absolute percentage error, and more stable R² value. Additionally, the feature importance analysis highlighted how alloying elements impact tensile strength, revealing both linear and non-linear correlations. It was found that increasing Ti content and using alloying elements with an atomic radius smaller than Ti affect the tensile strength. This study illustrates the potential of machine learning in material screening and design for Ti alloys.

1 November 2013 in Japanese Journal of Applied Physics
Verified
Journal Article
Closed access
PDF file
ISiping suhariadi
iping suhariadi
KOKouichiro Oshikawa
Kouichiro Oshikawa
KKKazunari Kuwahara
Kazunari Kuwahara
KMKouichi Matsushima
Kouichi Matsushima
DYDaisuke Yamashita
Daisuke Yamashita
NINaho Itagaki
Naho Itagaki
We have studied the effects of the N2 gas flow rate on the surface morphology of ZnO films deposited by the sputtering of a ZnO target using Ar/N2. Height-height correlation function (HHCF) analysis indicates that introducing a small amount of N2 (<5 sccm) to the sputtering atmosphere enhances adatom migration, leading to a larger grain size in the ZnO films associated with an increase in the lateral correlation length. The HHCF analysis also reveals that films deposited with and without N2 exhibit a self-affine fractal surface structure. We demonstrate that utilizing such ZnO films deposited using Ar/N2 as buffer layers, the crystallinity of ZnO:Al (AZO) films on the buffer layers can be greatly improved. The electrical resistivity of 100-nm-thick AZO films decreases from 1.8×10-3 to 4.0×10-4 Ω·cm by utilizing a ZnO buffer layers prepared at N2 flow rate of 5 sccm.

12 February 2020 in ACS Applied Nano Materials
Verified
Journal Article
Closed access
ISiping suhariadi
iping suhariadi
NINaho Itagaki
Naho Itagaki
MSMasaharu Shiratani
Masaharu Shiratani

2 December 2021 in Heliyon
Verified
Journal Article
Open access
JFJaka Fajar Fatriansyah
Jaka Fajar Fatriansyah
DDDonanta Dhaneswara
Donanta Dhaneswara
ISiping suhariadi
iping suhariadi
MWMuhammad Ihsan Widyantoro
Muhammad Ihsan Widyantoro
BRBilly Adhitya Ramadhan
Billy Adhitya Ramadhan
RHRahman Hadi
Rahman Hadi
The search for the most efficient materials that can store hydrogen has been challenged by various impediments in experimental studies, such as cost and complexity. Simulation study offers an easy method to overcome this challenge, but primarily requires powerful computing resources. In this paper, a simple MD simulation using a Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) was developed to calculate the hydrogen uptake in ZSM5, Graphite Nanofiber, Graphene Oxide Framework, and reduced Graphene Oxide. The method offered a more affordable computational method and relatively straightforward approaches while maintaining a high degree of accuracy and efficiency. The comparisons between simulation and experimental results were also presented. Based on our simulation, the calculations generally agreed with the results of experiments conducted for all the materials.

1 January 2013 in Japanese Journal of Applied Physics
Verified
Journal Article
Closed access
ISiping suhariadi
iping suhariadi
KMKoichi Matsushima
Koichi Matsushima
KKKazunori Kuwahara
Kazunori Kuwahara
KOKoichi Oshikawa
Koichi Oshikawa
DYDaisuke Yamashita
Daisuke Yamashita
NINaho Itagaki
Naho Itagaki
Hydrogenated ZnO thin films have been successfully deposited on glass substrates via a nitrogen mediated crystallization (NMC) method utilizing RF sputtering. Here we aim to study the crystallinity and electrical properties of hydrogenated NMC-ZnO films in correlation with substrate temperature and H2flow rate. XRD measurements reveal that all the deposited films exhibit strongly preferred (001) orientation. The integral breadth of the (002) peak from the hydrogenated NMC-ZnO films is smaller than that of the conventional hydrogenated ZnO films fabricated without nitrogen. Furthermore, the crystallinity and surface morphology of the hydrogenated NMC-ZnO films are improved by increasing substrate temperature to 400 °C, where the smallest integral breadth of (002) 2θ–ω scans of 0.83° has been obtained. By utilizing the hydrogenated NMC-ZnO films as buffer layers, the crystallinity of ZnO:Al (AZO) films is also improved. The resistivity of AZO films on NMC-ZnO buffer layers decreases with increasing H2flow rate during the sputter deposition of buffer layers from 0 to 5 sccm. At a H2flow rate of 5 sccm, 20-nm-thick AZO films with low resistivity of 1.5×10-3Ω cm have been obtained.