Advanced Upstream Data Analytics for the Shipyard Schedule Optimization and Planning Project

Periodic maintenance and modernization of naval vessels are conducted in the shipyards. According to a recent article published by the U.S. Government Accountability Office (GAO), The Navys four shipyards completed 38 of 51 (75 percent) maintenance periods late during fiscal years 2015 to 2019, causing late return of the vessels to the fleet. A naval vessels late return to the fleet result s in a decrease in operational readiness due to the reduced number of operational days available for these vessels and impacts on o ther vessels assigned to support the same or a complementary mission. There exists more than one interdependent factor that contrib utes to scheduling complexities. These include: inadequate planning for resources, quantity of overtime labor, direct yard costs, and quantity of work stoppages experienced that contribute to the tardiness in availability. Clearly, an effective yard scheduling process in NAVSEA requires careful consideration of multiple objectives and many metrics provided by different entities (32 SEA 21 /CNRMC), and analysis of data that are voluminous, come at different velocity, and consist of a different variety or types. Data r equired for yard scheduling in NAVSEA comes from multiple sources and organizations a few of them are listed below: Data sources: NMD, VSB, RMC/100-800, TAAS-INFO, eDFS, CASREPS, Spreadsheets, Shortage Reports, TSRA, Briefings, Port workload forecasts Data o wners: NSWC-Corona, CNRMC 400/700, SURFMEPP, CNSP, CNSL, Amphib PAPM, FSC, etc. Moreover, the collected data is of various types such as structured data, Time series, Text (eventually may involve images). Data may be sparse and contain data of different quali ty, and the data sources are sampled at different rates (daily, weekly, monthly, quarterly, or on an ad-hoc basis). Enabling pre dictive analytics for the yard scheduling problem has to go through a full data science pipeline that contains extensive upstream t asks for data conditioning and assessment before being subjected to advanced analytics and modeling (refer to Figure 1 that shows t he full data science pipeline). The goal of this project is to enable upstream data science capabilities that aids downstream AI/ML or predictive analytics to quantitatively achieve CNO availability process milestones