<![CDATA[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]]>
Copyrights © 2025
