Title: Data Driven Industrial Digitalization in Shipping through Reverse Engineering of Systems.
Abstract: A mathematical framework to support industrial digitization in shipping is presented in this study. The framework supports a data flow path, i.e. from industrial IoT (i.e. with Big Data) to predictive analytics, where digital models with advanced data analytics are introduced. These digital models, based on a deep learning approach of linear autoencoders facilitated by classical mechanics, are derived from ship performance and navigation data sets. A combination of such models and advanced data analytics can provide a good solution to various data handling challenges. Hence, data anomaly detection and recover procedures associated with the same framework to improve the respective data quality are also described. Since the respective data sets are used to derive these digital models with advanced data analytics, the same mathematical framework is also categorized as a reverse engineering approach.
Download the flyer (coming soon).