Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal INTEK: Jurnal Penelitian Jurnal Teknik Mesin Sinergi
Nurdin, Fadli
Unknown Affiliation
Computer Science & IT Energy Engineering Mechanical Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Intelligent Fault Prediction in Diesel Engines: A Comparative Study of SVM and BPNN for Condition-Based Maintenance Nurdin, Fadli; Effendi, Mohammad Khoirul
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.5362

Abstract

This study discusses the application of Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN) in predicting diesel engine health based on operational data relabeled using K-Means Clustering. Two types of SVM kernels were tested, namely Radial Basis Function (RBF) and Sigmoid, with various parameter combinations. The results indicate that SVM with Sigmoid kernel achieved an accuracy of 94.06%, but was less sensitive in detecting unhealthy engine conditions. In comparison, the BPNN method with a three-hidden-layer configuration (1-2-1 neurons) and tansig activation function showed superior performance with 97.13% accuracy, MSE of 0.03, recall of 94%, precision of 100%, and F1-score of 97%. These findings prove that BPNN outperforms SVM in capturing complex data patterns and is more accurate in detecting unhealthy engine conditions. Additionally, relabeling the dataset significantly improved predictive accuracy from 72.3% to 97.13%, highlighting the importance of balanced data in modeling. Overall, this study demonstrates that optimally configured BPNN is more effective in predicting diesel engine health than SVM, making it a more reliable approach for engine condition monitoring.  
Prediksi Kesehatan Mesin Diesel Menggunakan Metode SVM dan BPNN Dengan Reduksi Ketidakseimbangan Data Nurdin, Fadli; Mohammad Khoirul Effendi
Jurnal Teknik Mesin Sinergi Vol 23 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/sinergi.v23i1.5507

Abstract

Dalam sistem pemeliharaan prediktif, ketidakseimbangan kelas seringkali memengaruhi kinerja model pembelajaran mesin, terutama dalam mendeteksi kondisi mesin yang tidak sehat. Penelitian ini mengusulkan strategi relabeling menggunakan algoritma K-Means clustering untuk mengatasi ketidakseimbangan kelas pada prediksi kesehatan mesin diesel. Dataset yang digunakan terdiri dari enam parameter operasional (RPM mesin, tekanan oli, tekanan bahan bakar, tekanan pendingin, suhu oli, dan suhu pendingin), yang diproses melalui tahap pembersihan data, analisis korelasi, serta penyesuaian distribusi label dengan memindahkan sebagian data dari kelas mayoritas ke minoritas. Dua model prediksi dikembangkan: Support Vector Machine (SVM) dengan kernel RBF dan Sigmoid, serta Back Propagation Neural Network (BPNN) dengan arsitektur [3 3 1] dan fungsi aktivasi satlins. Hasil evaluasi menunjukkan bahwa proses relabeling meningkatkan akurasi model secara signifikan dari 72,30% menjadi 91,93%. Model BPNN memberikan kinerja terbaik dengan akurasi 94,21%, melampaui model SVM maupun studi acuan sebelumnya. Pendekatan ini menunjukkan efektivitas dalam meningkatkan keandalan prediksi melalui distribusi data yang lebih seimbang, khususnya untuk mendeteksi kerusakan mesin.
Co-Authors Mohammad Khoirul Effendi Mohammad Khoirul Effendi