A Study on Deep Learning-Based Fault Diagnosis and Classification for Marine Engine System Auxiliary Equipment

Maritime autonomous surface ships (MASS) are proposed as a future technology of the maritime industry. One key technologies for development MASS is condition-based maintenance (CBM) based on prognostics and health management (PHM). The CBM can be used early detection abnormalities database prediction fault occurring in future. However, this has problem that requires high-quality reproduces operation state actual quantitatively systematically indicates characteristics various device. To solve problem, paper presents study method reliability. Firstly, reliability analysis target device was performed to select five types core modes. After that, simulation scenario defined test methodology drawn. A land-based testbed built test. developed with total 109 sets through Additionally, classification algorithm deep learning proposed. performance evaluated confusion matrix. will expected serve basis