VidyaSagar Asalapuram KALYPSO Houston, TX USA Irfan Khan Marine Engineering Tech. Department in joint appointment with Electrical and Computer Engineering, TAMU Galveston TX USA Kotesh Rao ADAK Digital Houston, TX USA Abstract— Condition based machinery health monitoring on marine vessels involves collecting operational sensor data on the vessel using a robust data acquisition system and determining asset health using anomaly detection analytics. Automation and digitalization of marine vessels involve smart digital technologies such as the Internet of Things (IoT) to collect ships’ health data and send it over to a central processing location where this data is analyzed. However, it is difficult to apply this to the shipping industry due to offshore data transmission bandwidth challenges. Deep Learning, a technology that can be used to conduct Machinery Health Monitoring (MHM) holds the key to solve the bandwidth problems. In this paper, we investigate the use of Convolutional Neural Networks (CNN) as a practical solution for deploying Smart Health Monitoring on Marine Vessels using the example of electric induction motors. We show a mechanism to develop data-driven deep learning model that can classify if the motor is in a healthy or faulty condition, and propose an architecture to deploy this model on the Marine vessel in real time on an edge computing hardware. While in operation, sensor data from the motor will be fed into the DL Model, and the resulting predictions will be presented in the Vessel Alarm Monitoring System. Index Terms—Condition based Machinery Health Monitoring, Marine Vessels, Ships, Convolutional Neural Networks, Deep Learning, Induction Motor, Edge Computing. I. INTRODUCTION Shipping Industry has been slow in the adoption of digital technologies like the Internet of Things, Cloud and Artificial Intelligence which are becoming mature in other areas like aerospace, manufacturing, retail, and automotive. Although late to the game, the shipping industry has now started the journey of digital transformation. The year 2018 witnessed several important events that moved the shipping industry closer to digitalization. South Korea announced that it was investing around 700 Million USD into Smart Shipyards that leverage Artificial Intelligence to provide a competitive edge in the global shipbuilding market [1]. US Navy has also undertaken digitalization effort to reduce costs and improve the speed of construction of new generation carriers using technologies such as 3D modeling and Augmented Reality [2]. American Bureau of Shipping (ABS) issued new guidelines to inspect and survey marine vessels using Unmanned Aerial Vehicles. [3] Smart Digital technologies like Internet of Things involve collection of data related to the object of interest (equipment, human, ship, machine, system or combination thereof) and sent over to a central processing location for analysis and insights. Such intelligence aids in rapid decision making about the system and results in enhanced awareness and operational outcomes that are fruitful to any business. The key factors enabling such vast possibilities are the lower cost of sensors and data storage [2], availability of large computing power and near universal coverage of 4G LTE. A typical architecture of an Industrial IoT solution involves a smart sensor sending data through backhaul communication networks via Corporate LAN or 4G LTE or LoRA, securely to an Industrial Cloud (IoT Platform). Advanced algorithms and Business Intelligence dashboards process and present this data in a user-friendly manner so the consumer can take smart data-driven decisions from anywhere, anytime, and on any device. ABS has issued Guidance Notes on Smart Function Implementation (SFI) to help guide marine and offshore applications of smart technology [3]. By implementing smart monitoring, vessel and operational data can be leveraged to assist and augment day-to-day operations and be the foundation of a Condition based Maintenance (CbM) program. While this architecture works for many land-based smart solutions, it is difficult to apply this to shipping industry without considerations to data transmission bandwidth challenges. Deep Learning, a technology that can be used conduct Machinery Health Monitoring, also holds the key to solve the bandwidth A Novel Architecture for Condition Based Machinery Health Monitoring on Marine Vessels Using Deep Learning and Edge Computing C1-3-1 XPLORE Compliant Part Number CFP19MCR-ART, ISBN: 978-1-7281-4899-1