Condition-Based Monitoring for Marine Engine Maintenance by Analyzing Drain Cylinder Oil Sample

Abstract

Improvement of condition-based monitoring for large bore 2-stroke marine engine cylinder liners and piston rings require close monitoring of anomaly wear elements in drain cylinder oil. This paper presents monitoring of seagoing ship engines because the environment of sailing affects the internal combustion conditions leading to mechanical failure of the cylinder liners. We presented condition-based monitoring of cylinder liners using X-ray to analyze drain cylinder oil samples. The approach for condition-based monitoring uses X-ray results to estimate wear amount and machine learning algorithm on elements in the drain cylinder oil samples. The wear amount is quantified for the purpose to estimate the degradation of cylinder liner materials through the drain cylinder oil samples, machine learning algorithm to evaluate the correlation of detected elements in drain oil samples. Finally, wear rate estimation to know the remaining useful life of the cylinder liner. Our results contributed to the improvement of condition-based monitoring of cylinder liners wear elements by quantification and machine learning to correlate elements in oil samples. Correlating wear elements facilitate quick decision-making on maintenance policies for slow-speed large bore 2-stroke engines.

Keywords

• condition-based monitoring
• machine learning algorithm
• environmental effects
• wear rate