This research presents an innovative solution to optimise maintenance planning and integrity in offshore facilities, specifically regarding corrosion management. The study introduces a prototype for maintenance planning on offshore oil platforms, developed through the Design Science Research (DSR) methodology. Using a 3D CAD/CAE model, the prototype integrates machine learning models to predict corrosion progression, essential for effective maintenance strategies. Key components include damage assessment, regulatory compliance, asset criticality, and resource optimisation, collectively enabling precise and efficient anti-corrosion plans. Case studies on oil and gas platforms validate the practical application of this methodology, demonstrating reduced costs, lower risks associated with corrosion, and enhanced planning efficiency. Additionally, the research opens pathways for future advancements, such as integrating IoT technologies for real-time data collection and applying deep learning models to improve predictive accuracy. These potential extensions aim to evolve the system into a more adaptable and powerful tool for industrial maintenance, with applicability beyond offshore to other environments, including onshore facilities.

Nitrogen oxide (NOx) emissions from heavy-duty vehicles pose significant environmental and health risks, especially in urban regions with high traffic density. This study presents a comparative multi-strategy forecasting framework to forecast NOx emissions using real-world fleet data from Brazil, enriched with interpolated meteorological variables. A preprocessing pipeline integrates onboard sensor readings, trip metadata, and weather station data through temporal and spatial interpolation, including kriging. Four regression models: linear regression, random forest, XGBoost, and LSTM, were evaluated under single-step, recursive, multi-output, and direct per-horizon forecasting strategies. Results show that forecasting performance depends jointly on the forecasting strategy and vehicle category. The multi-output strategy provided the most balanced long-horizon behaviour for LSTM in the examined case, reducing relative errors compared with less stable long-horizon alternatives, although variance explanation remained strategy-dependent. In its best single-step configuration, LSTM achieved a MAPE of 10.28%. Adjusted average speed emerged as the most relevant predictor, whereas meteorological variables improved performance only in selected settings. By integrating continuous onboard fleet data from Brazil with spatio-temporal meteorological interpolation via kriging, this study provides a reproducible benchmarking framework for vehicle-level NOx forecasting under real-world multi-horizon conditions.