Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive maintenance up to more effective condition-based maintenance approaches. The central idea in condition-based maintenance is to monitor the propulsion equipment by exploiting heterogeneous sensors, enabling diagnosis and, most of all, prognosis of the propulsion system's components and of their potential future failures. The success of condition-based maintenance clearly hinges on the capability of developing effective predictive models; for this purpose, effective use of machine learning methods is proposed in this article. In particular, authors take into consideration an application of condition-based maintenance to gas turbines used for vessel propulsion, where the performance and advantages of exploiting machine learning methods in modeling the degradation of the propulsion plant over time are tested. Experiments, conducted on data generated from a sophisticated simulator of a gas turbine, mounted on a Frigate characterized by a COmbined Diesel eLectric And Gas propulsion plant type, will allow to show the effectiveness of the proposed machine learning approaches and to benchmark them in a realistic maritime application.

Economic sustainability of running Naval Propulsion Plants is a key element to cope with, and maintenance costs represent a large slice of total operational expenses: last decades' approaches, based on a repairing-replacing methodology, are being trespassed by more effective approaches, relying on effective continuous monitoring of assets wear. In this framework, Condition-Based Maintenance (CBM) is becoming key thanks to the enhancing capabilities of monitoring the propulsion equipment by exploiting heterogeneous sensors: this enables diagnosis and prognosis of the propulsion system's components and of their potential future failures. The success of CBM is based on the capability of developing effective predictive models, for which purpose state-of-the-art Machine Learning (ML) methods must be developed. Nevertheless, testing the performance of ML models for CBM purposes is not straightforward, mostly due to the lack of publicly available datasets for benchmarking purposes: thus, we present in this work a new dataset, that will be freely distributed to the community working on ML models for CBM, generated from an accurate simulator of a naval vessel Gas Turbine propulsion plant. The latter is then used for benchmarking the effectiveness of two state-of-the-art ML techniques in the considered maritime domain.