Although hydraulic accumulators play a vital role in the hydraulic system, they face the challenges of being broken by continuous abnormal pulsating pressure which occurs due to the malfunction of hydraulic systems. Hence, this study develops anomaly detection algorithms to detect abnormalities of pulsating pressure for hydraulic accumulators. A digital pressure sensor was installed in a hydraulic accumulator to acquire the pulsating pressure data. Six anomaly detection algorithms were developed based on the acquired data. A threshold averaging algorithm over a period based on the averaged maximum/minimum thresholds detected anomalies 2.5 h before the hydraulic accumulator failure. In the support vector machine (SVM) and XGBoost model that distinguish normal and abnormal pulsating pressure data, the SVM model had an accuracy of 0.8571 on the test set and the XGBoost model had an accuracy of 0.8857. In a convolutional neural network (CNN) and CNN autoencoder model trained with normal and abnormal pulsating pressure images, the CNN model had an accuracy of 0.9714, and the CNN autoencoder model correctly detected the 8 abnormal images out of 11 abnormal images. The long short-term memory (LSTM) autoencoder model detected 36 abnormal data points in the test set.

Modern merchant ships use marine propulsion systems equipped with an ultra-long-stroke diesel engine that directly drives a large slow-turning propeller. Such systems use fewer cylinders and generate greater power at slower shaft speeds, which affords improved propulsion performance as well as low repair and maintenance costs. However, this also results in higher torsional vibrations, which can lead to the fatigue of the shafting system. Tests performed on various marine propulsion systems with 5- to 7-cylinder engines have shown that engines with fewer cylinders exhibit a correspondingly wider barred speed range (BSR) and higher torsional vibration stresses. Thus, it is necessary to investigate the optimal engine operation patterns required to quickly pass the BSR with smaller torsional vibration. In this study, we carried out a series of BSR passage experiments during actual sea trials to evaluate the intermediate shaft performance under different engine operation patterns. The fractional damage accumulations due to transient torsional vibration stresses were calculated to estimate the fatigue lifetime of the shafting system. Our analysis results show that the torsional fatigue damage during BSR decelerations are small and negligible; however, the fractional damage during accelerations is a matter of concern. Our study determines the optimal main engine operation pattern for quick passage through the BSR with the smallest torsional vibration amplitudes and the least fractional damage accumulation, which can therefore extend the fatigue lifetime of the entire propulsion shafting system. Based on this analysis, we also suggest the optimum engine pattern for safe BSR passage.

It is known that a ship’s shafting system can be adversely affected by hull deformation, variations in the engine power, the propeller load, and eccentric propeller thrusts, thereby increasingly affecting the behavior of the shaft’s movement. A deformed shafting system may also lead to a potential risk of bearing damage by causing a change in the local load of the rear part of the after-stern tube bearing of the propeller shaft. With this concern, a series of previous studies were focused on optimizing the effects of hull deformation by securing a proper level of propulsion shaft stability and optimizing the relative inclination angle and oil film retention based on a quasi-static state, that is, Rules for the Classification of Steel Ships and experiences of shipyards. However, despite our efforts to resolve this issue, marine accidents involving stern tube bearing damage have continued to occur under relatively unattended ship motions in a transient state, that is, a quasi-static state that can possibly cause sudden stern flow field changes. Therefore, to improve the stability of the propulsion shaft, it is necessary to understand ship motions and the conditions of shafting systems in a dynamic state and a transient state when the system is designed. From this point of view, this study investigated the effect of changes in eccentric propeller forces on the motion of the propeller shaft in a representative transient state of a 50,000 deadweight tonnage tanker by means of the strain gauge method and a displacement sensor. The research findings demonstrate that propeller thrust fluctuations have a direct effect on the shaft stability by significant changes in the shaft motion that can lead to unbalanced supporting loads on the stern tube bearing. These results clearly reproduce the cause of damage to the ship in which the accident occurred at a reliable level and will be a reference for establishing pragmatic guidelines for preventing damage to similar ships in the future.

The injection timing of fuel in a diesel engine affects the combustion condition. Advanced fuel injection prolongs the ignition delay, positively impacting the increase in maximum combustion pressure and improving output. However, excessively advanced fuel injection can cause knocking. Moreover, premature ignition results in increased compression work when the maximum combustion pressure occurs before top dead center (TDC). This study aimed to diagnose and rectify starting failures, noise, and vibrations in a commercially operated ship engine by measuring the combustion pressure during low load operation. The target engine was a 4-stroke diesel, and the fuel injection system was mechanically controlled by a camshaft. The measured engine exhibited a 4.5 °CA error between the TDC, determined by the flywheel mark and the actual TDC. This discrepancy was influenced by excessively advanced fuel injection timing. It was confirmed that fuel injection and ignition were excessively advanced in all cylinders. After readjusting the engine by delaying the fuel injection timing by approximately 10 °CA, the combustion pressure was remeasured. The ignition was delayed by approximately 6.5 °CA at the same load, and the ignition intervals were uniformly adjusted. As the ignition timing was retarded, the compression work decreased and the expansion work increased in each cylinder, resulting in improved output across all cylinders. The amplitude of crankshaft angular velocity variation significantly decreased, improving uneven rotational force.

The measurement of shaft bending (whirling) moment can be performed via a telemetry system including strain gauges which can obtain the bending stress. By using a single bridge of strain gauge, it was possible to obtain only the nominal bending moment. However, in case of the propeller shaft vibration measurement, the true dynamic bending moment is needed to evaluate the effect of propeller forces on the stability of the bearings. To deal with this, typically two bridges of strain gauge at 90 degrees are needed. This research presents a novel reliability assessment method in establishing the true dynamic bending moment using only one bridge of strain gauge. This is achieved by using the actual bending stress measured by strain gauge combined with its own phase lag stress at an angle of 90 degrees. To validate this technique, the experiments were performed under the rapid turning transient states during a sea trial of a 50,000 DWT oil/chemical tanker. As a result, great fluctuations in propeller force were detected, resulting in a non-uniform oil film in the bearings. The displacement sensor was also installed and confirmed the established true dynamic bending moment.