A.I.S.A

The A.I.S.A. project addresses the gap between raw robotic data collection and actionable engineering intelligence by developing a software platform that acts as an intelligent “brain”. It combines qualitative (visual) and quantitative (UTM) datasets through a Spatio-Temporal Data Fusion Engine, while filtering the AI findings through a deterministic Expert System based on maritime rules, like CSR. By adding a 5-year historical data dimension, it predicts degradation rates to automate Class-ready condition evaluation reports and repair specifications.

A.I.S.A. is a software platform designed to bridge the gap between visual inspections (surface anomalies captured via RGB cameras) and structural thickness measurements (UTM data captured via ultrasonic probes). Instead of relying purely on standard “black-box” deep learning models, which are often rejected by Classification Societies due to their lack of explainability, the solution utilizes a robust Neuro-Symbolic AI approach. This hybrid architecture combines Computer Vision with a deterministic Expert System built upon strict IACS rules and the tacit knowledge of veteran surveyors. The system spatially registers point-based UTM data directly onto 2D visual representations and/or digital meshes. Furthermore, by incorporating 5 years of historical vessel records, the system calculates the velocity of corrosion over time. 

The tangible output is an automated Condition Evaluation Report (CER) that translates risk scores into clear, practical shipyard repair instructions, automatically estimating the exact steel weight and area required for structural renewal. By automating the data interpretation and translating complex multi-modal data into ready-to-use repair instructions, A.I.S.A. ensures that the vast amounts of raw data collected by autonomous tools (drones/crawlers) are converted into immediate, actionable intelligence, closing the loop from remote data acquisition to final maintenance execution.