Claim Missing Document
Check
Articles

Found 24 Documents
Search

Penerapan Teknologi Tepat Guna Mesin Pencetak Briket Arang dari Tempurung Kelapa yang Lebih Efisien Di Desa Jeliti Pristiansyah, Pristiansyah; Firnando, Aldo; Amrullah, Muhammad Haritsah; Hasdiansah, Hasdiansah; Aswin, Fajar; Yaqin, Rizqi Ilmal
DEDIKASI PKM Vol. 5 No. 3 (2024): DEDIKASI PKM UNPAM
Publisher : Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/dkp.v5i3.43591

Abstract

Briket arang merupakan salah satu batangan arang yang terbuat dari bahan baku tempurung kelapa dan dicetak menggunakan Mesin agar menghasilkan kalor yang sangat tinggi dan bisa menyala bertahan lama. Penggunaan briket arang dari tempurung kelapa akan memberikan kontribusi pada pengurangan ketergantungan terhadap kayu bakar, gas elpiji dan minyak tanah yang ketersediaannya semakin menipis dan tidak dapat diperbaharui khususnya bagi masyarakat dibeberapa daerah sungailiat dan pada saat yang bersamaan dapat mendukung pemanfaatan sampah tempurung kelapa sebagai salah satu bahan bakar.Penelitian ini bertujuan untuk merancang dan membangun Mesin Pencetak Briket Arang Tempurung Kelapa berkapasitas 12kg/jam dan merancang sistem perawatan pada Mesin Pencetak Briket Arang Tempurung Kelapa agar Siap digunakan dan memperpanjang usia pakai. Metode perancangan yang digunakan dalam penelitian ini adalah Verein Deutsche Ingenieuer (VDI 2222). Hasil penelitian pada Mesin Pencetak Briket Arang Kelapa dengan menggunakan metode rancangan VDI 2222 yaitu mencetak Briket Arang Kelapa dengan panjang 60cm dan mempunyai kapasitas 12kg/jam. Sistem perawatan pada mesin ini menggunakan perawatan terencana dan pemeriksaan bagi operator untuk melakukan perawatan mandiri.
A Stacking Ensemble Model for Predicting Student High School Graduation Outcomes Fitriyani, Fitriyani; Alkodri, Ari Amir; Aswin, Fajar
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1067

Abstract

This study develops and evaluates machine learning models to predict high school graduation outcomes and identify at-risk students for early intervention. Using a quantitative approach, data from 1,017 students across three public high schools were analyzed, encompassing academic performance (average yearly scores), behavioral factors (attendance rates and extracurricular participation), and socio-economic background (proxied by parental occupation). A comparative modeling strategy was applied, beginning with a Decision Tree baseline and advancing to a Stacking Ensemble model that integrated three heterogeneous base learners—Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Decision Tree—combined through a Logistic Regression meta-model. Both models were optimized using GridSearchCV and adjusted for class imbalance between graduates (93.4%) and at-risk students (6.6%). The results showed that academic variables, particularly third-year average scores (mean = 82.6, SD = 6.4) and attendance rate (mean = 94.3%), were the strongest predictors of graduation, while socio-economic indicators had minimal impact. The Stacking Ensemble achieved a notable improvement over the Decision Tree, reaching an accuracy of 99.6%, precision of 0.909, recall of 1.000, F1-score of 0.952, and AUC of 1.000, compared to the baseline accuracy of 94.9% (F1-score = 0.519, AUC = 0.83). These findings indicate the superior predictive capability of the ensemble model in identifying students at risk of non-graduation. The study’s novelty lies in combining interpretable and high-performance models to construct a practical early-warning framework that can guide educators and policymakers in targeted academic interventions. However, the near-perfect metrics also suggest potential overfitting, emphasizing the need for validation using external datasets before broader application. Overall, this research contributes a robust, data-driven methodology for improving student retention through predictive analytics in educational settings.
PENGARUH VARIASI (JARAK PENEKANAN)TERHADAP KEKUATAN SAMBUNGAN LAS GESEK (FRICTION WELDING) PADA BAJA KARBON S45C Rizqi fadilah, Muhammad; Rodika, Rodika; Aswin, Fajar
Prosiding Seminar Nasional Inovasi Teknologi Terapan Vol. 2 No. 01 (2022): Prosiding Seminar Nasional Inovasi Teknologi Terapan
Publisher : Politeknik Manufaktur Negeri Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Friction welding is a welding technique that melts metal. Jointing of metals by utilizing the heat generated by friction between metal surfaces in which variations in the pressure distance are determined. The purpose of this study is to determine the strength of the welded joint after the welding process by using variations in the pressure distance of 3mm, 4mm, and 5mm. The material used in this research is carbon steel S45C shaft. Studies have shown that welding at the deepest compression distance produces a very strong welded joint, the greater the stress during the welding process, the stronger the joint in the welding. Welding with compression distances of 4mm and 5mm. and the impact price is higher compared to the 3mm pressing distance.
ANALISIS VARIASI PARAMETER PROSES PERMESINAN TERHADAP TINGKAT KEKASARAN PERMUKAAN MATERIAL SKD 11 DENGAN MENGGUNAKAN MESIN BUBUT GEMINIS Fachrezi, Rizki; KURNIAWAN, ZALDY; ASWIN, FAJAR
Prosiding Seminar Nasional Inovasi Teknologi Terapan Vol. 2 No. 01 (2022): Prosiding Seminar Nasional Inovasi Teknologi Terapan
Publisher : Politeknik Manufaktur Negeri Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The success of the world's manufacturing industry to improve production processes is strongly influenced by the production machine tools used. Shaft is a product that requires a low surface roughness value during lathe processing, especially the Tornos Geminis S.L. semi-automatic lathe. The purpose of this study was to determine the surface roughness of carbon steel. This study uses parameters that affect the shape of the surface roughness value of the SKD11 material, namely the spindle rotation rate (1000 Rpm, 760 Rpm, 610 Rpm), feed depth level (0.4 mm, 0.6 mm, 0.8 mm)) and feeding speed. (0.8mm)/put, 0.9mm/put, 0.10mm/put). The lowest value of surface roughness of the Skd 11 material was obtained with a spindle speed of 1000 Rpm, feed rate of 0.9 mm/put and depth of cut 0.4 mm, and a surface roughness value of 1.636 m.