Exploiting data analytics-based processes for detecting and diagnosing the occurrence of faults in HVAC systems
Reference persons ALFONSO CAPOZZOLI
Description Recent years have seen an increasing interest of the scientific community in exploring solutions to improve energy efficiency in buildings by implementing advanced data-analytics based energy management strategies. According to the literature, around 20% of energy consumption in buildings is attributable to incorrect system configurations and inappropriate operating procedures that can be effectively detected through automatic analytics processes. Due to lack of proper maintenance, failure of components or incorrect installation, building systems are frequently run in faulty conditions where a fault is intended as an unpermitted deviation of at least one characteristic property of the system from the acceptable, usual, standard condition. The objective behind Fault detection and diagnosis (FDD) is twofold. On one hand fault detection consists in the recognition of a fault occurrence, and on the other hand fault diagnosis corresponds to the identification of the causes and the location of the fault.
In this perspective the thesis project aims at contributing to the FDD research field demonstrating the high contribution that data analytics methodologies can bring.
Deadline 24/02/2022 PROPONI LA TUA CANDIDATURA