Maintaining the condition of a vessel and its equipment guarantees the scheduled completion of voyages and the safety of the crew.
This paper presents condition monitoring techniques for early detection of faults related to piston rings in remote cylinders of two-stroke marine diesel engines. Operational sensor data from the main engine of a container ship are provided by a shipping company.
A graphical approach complimented by correlation heatmaps and feature importance from gradient boosting trees are used for feature selection. Support Vector Machine, Random Forest and Extreme Gradient Boosting Trees are tested for residual generation from the nominal behavior.
The residual time series gives a good indication of the degradation of the system and can be used for alarm raising under strict rules. It is proven that the proposed method could alert the engine crew of a change in the condition of the piston rings much earlier than existing methods.
Taking offspring in a problem of ship emission reduction by exhaust gas recirculation control for large diesel engines, an underlying generic estimation challenge is formulated as a problem of joint state and parameter estimation for a class of multiple-input single-output Hammerstein systems with first-order dynamics, sensor delay, and a bounded time-varying parameter in the nonlinear part. This brief suggests a novel scheme for this estimation problem that guarantees exponential convergence to an interval that depends on the sensitivity of the system. The system is allowed to be nonlinear, parameterized, and time dependent, which are characteristics of the industrial problem we study. The approach requires the input nonlinearity to be a sector nonlinearity in the time-varying parameter. Salient features of the approach include simplicity of design and implementation. The efficacy of the adaptive observer is shown on simulated cases, on tests with a large diesel engine on test bed, and on tests with a container vessel.