The increasing complexity of platforms on modern warships necessitates the implementation of advanced control and monitoring systems to ensure operational efficiency, safety, and availability. In this context, the present research endeavor focuses on identifying the critical components and causes of failures through a detailed analysis of the reliability of the system and the diagnosis. In the domain of ship machinery control and monitoring systems, the integration of machine learning – encompassing functions ranging from anomaly detection to decision assistance – signifies a disruptive innovation with the capacity to transform decision-making processes within the complex and challenging environment of a warship. The present document delineates a functional architecture for the implementation of supervised machine learning (ML) algorithms, encompassing data preprocessing, feature extraction, model training, and evaluation. The integration of classification and regression techniques in the context of supervised machine learning for the purpose of anomaly detection and decision support within control and supervision systems of ship machinery is hereby proposed. This integration of techniques represents a disruptive innovation in the operational management of warships. Furthermore, it delves into the integration of machine learning (ML) into the ship's engineering console, with the objective of processing data from sensors that monitor critical parameters. These parameters include, but are not limited to, temperature, pressure, vibration, revolutions per minute (RPM), frequency, and voltage. These sensors are utilized in various components of the ship, such as engines, generators, and other equipment. The implementation of the ML allows for the planning of preventive and corrective maintenance, thereby extending the useful life of the machinery and subsystems. This, in turn, ensures stability, efficiency, and control of the Navy's resources. The anticipated outcomes of this initiative include a substantial enhancement in technical availability, a notable decrease in unplanned failures, and an augmentation in the autonomy of complex systems supervision.