Intelligent Fault Prediction in Diesel Engines: A Comparative Study of SVM and BPNN for Condition-Based Maintenance
Abstract
This study discusses the application of Support Vector Machine (SVM) and Backpropagation Neural Network (BPNN) in predicting diesel engine health based on operational data that has been 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 a 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 the tansig activation function demonstrated superior performance, achieving an accuracy of 97.13%, MSE of 0.03, recall of 94%, precision of 100%, and an F1-score of 97%. These results confirm that BPNN outperforms SVM in capturing complex data patterns and is more accurate in detecting unhealthy engine conditions. Furthermore, dataset relabeling significantly improved prediction accuracy from 72.3% to 97.13%, emphasizing the importance of data balance in modeling. Overall, this study demonstrates that BPNN with an optimal configuration is more effective in predicting diesel engine health than SVM, making it a more reliable approach for engine condition monitoring.
Keywords: Diesel Engine; Machine Health Prediction; Support Vector Machine; Backpropagation Neural Network; Condition-Based Maintenance; Artificial Intelligence
Keywords
Full Text:
PDFReferences
A. Pratistha, M. S. ST, M. Marlita, J. Beno, and S. ST, Pengantar Transportasi. 2024.
M. A. Deni, Manajemen Risiko Pada Era Digital. 2024.
R. Ilmi, Y. Sukrawan, T. P.-M. J. of Automotive, and undefined 2024, “CONDITION BASED MONITORING IMPROVES COMPONENT DURABILITY IN HEAVY EQUIPMENT MAINTENANCE,” ejournal.upi.edu, vol. 2, no. 1, 2024, Accessed: Feb. 17, 2025. [Online]. Available: https://ejournal.upi.edu/index.php/motor/article/view/77712.
S. Belkis Alsakinah and S. K. Tinggi Maritim Yogyakarta Jl Magelang, “Pemanfaatan Teknologi Big Data pada Crane Health Management System (CHMS) dengan Pendekatan Integrative Framework,” jurnal.poltekpelni.ac.id, vol. 1, no. 1, pp. 112–120, 2025, Accessed: Feb. 17, 2025. [Online]. Available: https://jurnal.poltekpelni.ac.id/index.php/senama/article/view/41.
A. A. F. YUSRI, “OPTIMALISASI PERAWATAN PRESSURE VACUM VALVE DALAM SISTEM PERAWATAN KAPAL DI MT. ARZOYI,” 2024, Accessed: Feb. 17, 2025. [Online]. Available: http://eprints.pipmakassar.ac.id/767/.
J. Sharma, M. Mittal, G. S.-I. J. of S. Assurance, and undefined 2024, “Condition-based maintenance using machine learning and role of interpretability: a review,” Springer, vol. 15, no. 4, pp. 1345–1360, Apr. 2024, doi: 10.1007/s13198-022-01843-7.
M. O. Kuttan, J. Steinheimer, K. Zhou, A. Redelbach, and H. Stoecker, “Deep learning based impact parameter determination for the CBM experiment,” 2021, doi: 10.3390/particles4010006.
D. Hana Amalia and W. Yustanti, “Predictive Maintenance untuk Kendaraan Bermotor dengan Menggunakan Support Vector Machine (SVM),” ejournal.unesa.ac.id, vol. 03, 2021, Accessed: Feb. 17, 2025. [Online]. Available: https://ejournal.unesa.ac.id/index.php/jinacs/article/download/37718/33399.
V. Mandala, T. Senthilnathan, … S. S.-M., and undefined 2023, “An optimized Backpropagation neural network for automated evaluation of health condition using sensor data,” Elsevier, Accessed: Feb. 17, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2665917423001824.
D. Mohakul, C. Kumar, … S. S.-2023 S., and undefined 2023, “Health Monitoring of Ship’s Engine with Simulated Data by using Classifiers-Preliminary Result,” ieeexplore.ieee.org, Accessed: Feb. 17, 2025. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10157555/.
S. K. D Mohakul, CRS Kumar, Shweta Singh, “CONDITION BASED PREDICTIVE MAINTENANCE ON SHIP’S MAJOR EQUIPMENT USING AI – IJSREM,” 2023. https://ijsrem.com/download/condition-based-predictive-maintenance-on-ships-major-equipment-using-ai/ (accessed Feb. 17, 2025).
S. García et al., “Big data preprocessing: methods and prospects,” vol. 1, no. 1, Dec. 2016, Accessed: Jan. 29, 2023. [Online]. Available: https://link.springer.com/article/10.1186/s41044-016-0014-0.
S. Zhao, Y. Guo, Q. Sheng, and Y. Shyr, “Advanced Heat Map and Clustering Analysis Using Heatmap3,” Biomed Res. Int., vol. 2014, 2014, doi: 10.1155/2014/986048.
T. Wahyuni, A. A.- Prisma, P. Seminar, and undefined 2018, “Analisis Regresi Logistik terhadap Keputusan Penerimaan Beasiswa PPA di FMIPA Unnes Menggunakan Software Minitab,” journal.unnes.ac.id, Accessed: Feb. 17, 2025. [Online]. Available: https://journal.unnes.ac.id/sju/prisma/article/download/20360/9692.
E. Budiman, A. Lawi, and S. La Wungo, “Implementation of SVM Kernels for Identifying Irregularities Usage of Smart Electric Voucher,” in 5th International Conference on Computing Engineering and Design, ICCED 2019, 2019, pp. 1–5, doi: 10.1109/ICCED46541.2019.9161077.
V. A. Temeng, C. K. Arthur, and Y. Y. Ziggah, “Suitability assessment of different vector machine regression techniques for blast-induced ground vibration prediction in Ghana,” Model. Earth Syst. Environ., vol. 8, no. 1, pp. 897–909, Mar. 2022, doi: 10.1007/S40808-021-01129-0.
L. Zhao, S. Lee, S. J.- Electronics, and undefined 2021, “Decision tree application to classification problems with boosting algorithm,” mdpi.com, 2021, doi: 10.3390/electronics10161903.
DOI: http://dx.doi.org/10.12962%2Fj25807471.v9i2.22724
JMES The International Journal of Mechanical Engineering and Sciences by Lembaga Penelitian dan Pengabdian kepada Masyarakat (LPPM) ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://iptek.its.ac.id/index.php/jmes.