Healthy and Faulty Experimental Performance of a Typical HVAC System under Italian Climatic Conditions: Artificial Neural Network-Based Model and Fault Impact Assessment

The heating, ventilation, and air conditioning (HVAC) system serving the test room of SENS i-Lab Department Architecture Industrial Design University Campania Luigi Vanvitelli (Aversa, south Italy) has been experimentally investigated through a series tests performed during both summer winter under normal faulty scenarios. In particular, five distinct typical faults have artificially implemented in HVAC analyzed transient steady-state operation. An optimal artificial neural network-based model created MATLAB platform verified by contrasting experimental data with predictions twenty-two different network architectures. selected architecture coupled dynamic simulation developed using TRaNsient SYStems (TRNSYS) software main aims (i) making available an dataset characterized labeled covering wide range operating climatic conditions; (ii) providing accurate tool able to generate operation for assisting further research fault detection diagnosis units; (iii) evaluating impact on occupant indoor thermo-hygrometric comfort, temporal trends key parameters, electric energy consumptions.