Research on Data-Driven Performance Assessment and Fault Early Warning of Marine Diesel Engine

To enable proactive prediction of marine diesel engine failure time and root causes, thereby reserving sufficient time for maintenance, this study proposes a data-driven multi-algorithm integration framework for performance assessment and fault early warning in marine diesel engines. By integrating the SSD (steady-state detection) algorithm, a data-driven CLIQUE clustering algorithm was chosen for automatic multi-parameter high-dimensional running condition partitioning. This innovative approach overcomes the limitations of traditional single-parameter approaches or dimensionality reduction techniques, significantly enhancing state classification accuracy. The improved classification results subsequently increase the reliability of Mahalanobis distance as a performance indicator for marine diesel engine condition assessment. Finally, the cumulative anomaly method combined with the Yamamoto test was employed for anomaly detection analysis, enabling precise identification of fault occurrence time and establishing an effective early-warning mechanism. The study demonstrates that this technique effectively characterizes the overall performance of marine diesel engines and captures their performance degradation features. Implemented on a 6RT-flex82T marine diesel engine dataset, the method achieved precise prediction of fault occurrence time with early warnings, providing approximately 20 days advance notice for maintenance planning. Furthermore, comparative analyses with existing studies revealed its superior capability in pinpointing the anomaly to the jacket cooling water outlet temperature of cylinder #2. These results confirm the method's effectiveness in both performance assessment and fault early warning for marine diesel engines, offering a novel approach for intelligent maintenance of shipboard equipment.