Session: 14-01-02: Smart and Sustainable Maritime Systems

Submission Number: 152581

Predictive Thermal Digital Twin Model for a Renewably Powered Offshore AUV Servicing Platform 

Autonomous Underwater Vehicle (AUV) missions are limited in range and duration by the vehicle’s battery capacity. Meanwhile, sensor payload and ocean measurement resolution are limited by data storage capacity onboard the vehicle. These limitations necessitate that AUVs be frequently recovered to recharge and offload data. The Platform for Expanding AUV exploRation to Longer ranges (PEARL), described in this paper, aims to extend the range and endurance of AUVs while reducing data latency and operating costs. Floating on the ocean surface, PEARL is planned to be a fully autonomous servicing station that utilizes renewable energy to simultaneously provide AUV battery recharging and data uplink. This paper reports design and testing updates since the previous versions of the PEARL system. 

The autonomous requirements and operating environment place particular challenges on PEARL. The high-bandwidth communication requirements of PEARL drive us to a new-generation phased array satellite communications system. This system consumes significant amounts of power, which can result in issues such as localized heating and electromagnetic interference that may adversely affect the functionality of PEARL. To ensure the reliability of PEARL, self-monitoring, or even prognosis, of its health conditions is highly desirable. This paper focuses on the development of a thermal digital twin model to monitor thermal conditions during the field tests of PEARL on Charles River, Massachusetts. 

To build this model, we acquired temperature data from thermistors attached to various components of PEARL, which we model via corresponding nodes in our thermal network model. Components included in our model include the interior ambient air and the inner wall of a main case (called ‘brain’); the rechargeable battery and solar charge controller, both residing in the main case; the Starlink inverter and sensor payload module (called PANTHER) enclosed within their respective containers; and the solar panel. The main case is partially submerged in water, but other containers are mounted on the pontoons that separate them from the water surface. 

Temperature measurements were made during mission operations from July to November 2024 and used to calibrate the thermal digital twin. The model reproduces the thermal characteristics of PEARL with ~2% RMS error and has provided several insights on thermal cycles experienced by the PEARL system. Temperature profiles of the nodes are tightly coupled with local environments and operation modes such as data uplink and solar charging controls. The effects of design iterations (e.g., reflective surface) or natural changes (e.g., solar panel contamination) of PEARL could also be observed. 

The digital twin architecture was updated as new thermal data became available; the final version divides the main case (brain) into two zones to account for its contacts with atmosphere and water exhibiting different temperature cycles. With its predictive performance validated, the thermal digital twin can potentially be used to detect sensor anomalies by detecting outliers in the measured temperature data. Other digital twin domains, such as power management and electromagnetic interference, can be developed in the future; interferences from the Starlink antenna have been identified as a potential area of consideration when multiple autonomous surface vehicles (or AUV/UAVs) are in motion. Lastly, the results will be used to inform the design of the next-generation PEARL to be tested in an ocean setting. 

Presenting Author: Ayden Soderblom Massachusetts Institute of Technology

Presenting Author Biography: Ayden Soderblom is a Research Intern at MIT AeroAstro, where he contributes to the development of autonomous underwater vehicle (AUV) technology. His work focuses on designing docking systems and enhancing vehicle performance for the P.E.A.R.L. platform. He is an Eagle Scout and has held numerous leadership positions in his troop of 55 Scouts, from running the entire troop as the Senior Patrol Leader, to Crew Lead at Philmont, to now serving as a Junior Assistant Scoutmaster. Ayden is a high school senior at the Boston Latin School in Boston, MA. He is a native English speaker with fluency in Spanish and literacy in Latin and Hebrew. Ayden loves hiking and exploring nature and draws inspiration from the outdoors to fuel his creativity and drive.