Claim Missing Document
Check
Articles

Found 3 Documents
Search

Machine Learning-Based Regression Model for Predicting Global Horizontal Radiation and Global Horizontal Irradiance: A Case Study in Banda Aceh Fajar Sabri, M Salamul; Muhammad, Ikramullah; Rizqullah, Akbar; Fikri, Thaharul; Fajri, Nural; Mizanus Sabri, Faris Ahmad
Rekayasa Material, Manufaktur dan Energi Vol 8, No 2: JULI 2025
Publisher : Fakultas Teknik UMSU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/rmme.v8i2.26011

Abstract

Global Horizontal Radiation (GHR) and Global Horizontal Illumination (GHI) are critical environmental parameters that play a vital role in solar energy development, precision agriculture, and sustainable urban planning. However, their prediction remains challenging due to the high variability caused by atmospheric conditions. This study evaluates the performance of various machine learning models in predicting GHR and GHI using a comprehensive dataset comprising 29 environmental features. The models tested include Linear Regression, Random Forest Regressor, XGBoost Regressor, LightGBM Regressor, Support Vector Regressor (SVR), and Artificial Neural Network (ANN). The results consistently show that ensemble-based models, particularly LightGBM Regressor, provide the best predictive performance for both target variables, achieving very high R-squared values (approaching 0.999). XGBoost and Random Forest also demonstrate highly competitive performance. ANN performs well, while Linear Regression and SVR show lower accuracy. These findings underscore the significant potential of advanced machine learning models in predicting environmental parameters with high accuracy, which has important implications for renewable energy optimization, smart agriculture, and sustainable urban planning.
Chemical treatments' effect on the structural and mecha-nical properties of polyvinyl alcohol/spent coffee ground composite films Muhibbuddin, Muhibbuddin; Ilham, Farid; Muhammad, Ikramullah; Rizal, Samsul
Jurnal Polimesin Vol 23, No 5 (2025): October
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jpl.v23i5.7204

Abstract

Chemical treatments are a common strategy for improving the compatibility of natural fillers with polymer matrices. However, their specific impact on Spent Coffee Grounds (SCG) as reinforcement for Polyvinyl Alcohol (PVA) composites remains unclear. This study investigates the effects of alkalization, bleaching, and acid hydrolysis on the structural and mechanical properties of PVA/SCG composite films. The SCG was treated with 10% NaOH, 10% NaOCl, and 1 M H₂SO₄. FTIR analysis showed that untreated SCG exhibited characteristic C–H stretching peaks at 2922 cm⁻¹ and 2853 cm⁻¹, corresponding to methyl and methylene groups in cellulose and hemicellulose. After alkalization and bleaching, these peaks nearly disappeared, indicating excessive removal of hemicellulose and lignin and suggesting structural degradation of the filler. In contrast, acid hydrolysis largely preserved these peaks, reflecting milder structural modification. Mechanical testing confirmed this trend: the untreated composite achieved the best performance, with tensile strength of 2.30 MPa and tear resistance of 2.12 N All chemically treated samples showed reduced strength and toughness, with alkalization being the most detrimental. These findings demonstrate that the decline in mechanical properties is directly correlated with structural damage detected by FTIR, emphasizing the need to optimize treatment severity.
Modification of sugarcane bagasse as polymer composite reinforcement via alkalization and benzylation Thalib, Sulaiman; Zakaria, Sarani; Azhari, Che Husna; Muhammad, Ikramullah; Usman, Husni
Jurnal Polimesin Vol 23, No 2 (2025): April
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jpl.v23i2.6404

Abstract

This research evaluates the impact of chemical modification on the thermal, structural, chemical, and mechanical properties of sugarcane bagasse particles for their application as reinforcement in polymer composites, which was conducted through alkalization and subsequent benzylation. Sugarcane bagasse was first mechanically refined, then treated with sodium hydroxide to produce alkalized bagasse (ALC), followed by etherification with benzyl chloride to yield benzylated bagasse (BLC). The untreated and modified particles were characterized using TGA, DSC, XRD, FTIR, and tensile testing. Thermal analysis showed degradation temperaturesof 250 °C, 245 °C, and 240 °C for untreated, ALC, and BLC, respectively. XRD revealed a decrease in crystallinity after treatment, indicating increased amorphous content due to surface modification. FTIR confirmed the replacement of hydroxyl groups with benzyl groups, enhancing hydrophobicity. Mechanical testing demonstrated a significant improvement in the tensile strength and modulus of PA6 composites reinforced with BLC, with the highest values (49.5 MPa and 1224.3 MPa) achieved using 100 µm BLC particles. These results highlight the effectiveness of chemical modification in improving interfacial compatibility and mechanical performance, supporting the use of modified bagasse as a sustainable reinforcement for bio-based composites.