No abstract

No abstract

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.

No abstract

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.