Ricerc@Sapienza

Modeling and predicting failures in the field of predictive maintenance is a challenging task. An important issue of an intelligent predictive maintenance system, exploited also for Condition Based Maintenance applications, is the failure probability estimation that can be found uncalibrated for most standard and custom classifiers grounded on Machine learning.

n this paper we present an interesting application of the Decision Support System, known as the OCC_System, designed for faults recognition and classification within the real-world Medium Voltage power grid of Rome, Italy, managed by the Azienda Comunale Energia e Ambiente (ACEA) company. Given a historical data set consisting of fault patterns described by heterogeneous features related to endogenous and exogenous factors, the recognition system is trained to classify fault states assigning them a probability of fault.

The paper introduces an innovative Predictive Maintenance (PdM) system to assess the quality of engine oil for buses, tested in Ravenna (Italy) within the “European Bus System of the Future – EBSF_2” project, funded by the European Union. The system relies on PdM software linked to oil sensors and filters, installed on a test fleet and using a specifically designed Information Technology (IT) architecture. The system enables continuous assessment of the oil quality, which is highly predictive of engine performance.

The European Bus System of the Future (EBSF_2) is a research project funded by the European Union with the aim of developing a new generation of buses across Europe. The goals are to increase the attractiveness and efficiency of buses by testing advanced operational and technological solutions. Among these are more comfortable internal layouts, the implementation of a standard IT architecture, intelligent garage procedures, energy-efficient auxiliaries and green driving assistance systems, all of which are being tested in several demonstrators.