PRIN UTMOST FDD project - conference plan

Partecipation at the 9th AIGE/IIETA International Conference and the 19th AIGE 2024 Conference

The Research Unit of the University of Campania Luigi Vanvitelli (UNICAMPANIA) participated at the “9th AIGE/IIETA International Conference and the 19th AIGE 2024 Conference on "Energy Conversion, Management, Recovery, Saving, Storage and Renewable Systems”, held in Caserta, Italy, from June 3 to June 5, 2024. During the conference, the UNICAMPANIA Research Unit presented the outcomes of research activities performed within the PRIN 2022 MUR - UTMOST FDD project via a scientific paper entitled “Experimental Assessment of Environmental and Economic Impacts of Dampers’ and Filters’ Faults in a Typical Air-Handling Unit in Southern Italy”. The study focuses on the performance of Heating, Ventilation and Air-Conditioning (HVAC) systems, which account for approximately 50-60% of the total energy demand in the building sector. The scientific literature highlights that HVAC units are frequently operated under faulty conditions that can significantly affect their performance. In this paper, the performance of a typical single-duct dual-fan constant air volume Air-Handling Unit (AHU) are investigated through a number of experiments performed during Italian cooling and heating seasons under both fault free and faulty scenarios. The AHU operation is analysed while artificially introducing seven typical faults: return air damper kept always closed; fresh air damper kept always closed; fresh air damper kept always open; exhaust air damper kept always closed; supply air filter clogged at 50%; fresh air filter clogged at 50%; return air filter clogged at 50%. The faulty and fault free tests are compared to assess the environmental and economic performance impacts. The experimental data highlighted that the most adverse fault is that one corresponding to the exhaust air dumper kept always closed; in particular, it increases both the daily global equivalent CO₂ emissions and the daily operating costs up to 110% in comparison with the fault free conditions.

Partecipation at the International Conference “BSA 2024 – Building Simulation Applications”

The Research Unit of the University of Campania Luigi Vanvitelli (UNICAMPANIA) participated at the “BSA 2024 – Building Simulation Applications”, held in Bolzano, Italy, from June 26 to June 28, 2024. During this conference, the UNICAMPANIA Research Unit presented the outcomes of research activities performed within the  PRIN 2022 MUR - UTMOST FDD project  via a scientific paper entitled “TRNSYS dynamic simulation model of a typical air-handling unit: experimental calibration and validation based on field operation data in the south of Italy”. In this paper, a detailed dynamic simulation model of a typical HVAC system including a single duct dual-fan constant air volume Air-Handling Unit (AHU) has been developed via the TRaNsient SYStems software platform (TRNSYS 18). The simulation outputs have been compared with field operation data measured during 14 experiments performed with reference to a fully instrumented HVAC set-up serving the SENS i-Lab of the Department of Architecture and Industrial Design of the University of Campania Luigi Vanvitelli (Aversa, south of Italy). The comparison has been carried out to validate and assess the simulation model accuracy. The results highlighted a high capability of the developed model in simulating the experimental behaviour, with maximum percentage differences between the predicted and experimental values up to –6.0%, 18.3%, –9.1%, –10.6%, –15.3% in terms of heating coil energy, cooling coil energy, humidifier electric demand, heat pump electric consumption and refrigerating system electricity request, respectively.

Partecipation at the International Conference on Sustainability in Energy and Buildings SEB-24

The Research Unit of the Politecnico di Torino (POLITO) participated at the “International Conference on Sustainability in Energy and Buildings SEB-24”, held in Madeira, Portugal, from September 18 to September 20, 2024. During the conference, the POLITO Research Unit presented the outcomes of research activities performed within within the  PRIN 2022 MUR - UTMOST FDD project via a scientific paper entitled “Experimental performance evaluation of cost-sensitive Bayesian Networks for fault detection and diagnosis in HVAC systems”.

The study provides and validates various Bayesian-based FDD methods using experimental data from a typical air-handling unit (AHU) with artificially implemented faults. The proposed methods include a Conditional Gaussian Network (CGN) and a Tree Augmented Naïve Bayes classifier (TAN). A sensitivity analysis is performed to determine the op-timal number of input variables for the best trade-off between model complexity and fault diagnosis performance. Additionally, a cost-sensitive process is imple-mented for both BN models to reduce the False Alarm Rate (FAR). The performance and effectiveness of these models were then analyzed and compared against a baseline ML algorithm (i.e., Random Forest), demonstrating their potential to enhance FDD approaches in building energy systems.

Partecipation at the 6th Central European Symposium on Building Physics – CESBP 2025

The Research Unit of the University of Campania Luigi Vanvitelli (UNICAMPANIA) participated at the “6th Central European Symposium on Building Physics – CESBP 2025”, held in Budapest, Hungary, from September 11 to September 13, 2025. During the conference, the UNICAMPANIA Research Unit presented the outcomes of research activities performed within within the  PRIN 2022 MUR - UTMOST FDD project  via a scientific paper entitled “Different Faults’ Severities of Fans in A Typical Air-Handling Unit in Southern Italy: Experimental Assessment of Indoor Conditions, Electric Demands, CO₂ Emissions and Costs”. This study presents a comprehensive dataset generated through a series of experiments conducted on a typical single-duct dual-fan constant air volume air-handling unit (AHU) serving a test room in southern Italy. The AHU performance has been analyzed under both faulty and normal scenarios during winter and summer. Eight artificially induced fan faults have been investigated: supply air fan (SAF) stuck at (i) 0%, (ii) 25%, (iii) 75% and (iv) 100% of its maximum velocity as well as return air fan (RAF) stuck at (v) 0%, (vi) 25%, (vii) 75% and (viii) 100% of its maximum velocity. The faulty AHU performance has been compared to the fault-free scenarios (with both fans operating at 50% of their maximum velocity) under identical boundary conditions to quantify deviations in terms of indoor thermo-hygrometric conditions, electric energy consumption, equivalent global CO₂ emissions, and operational costs. With respect to normal operation, fans’ faults can cause an increase of daily total electricity demand, equivalent global CO₂ emissions, and operating costs from a minimum of about 3% up to a maximum of approximately 110%. Moreover, they can reduce the time percentage during which indoor air relative humidity or temperature remains within the desired range from a mini-mum of about 0.2% up to a maximum of approximately 62.0%.

Partecipation at the International Conference on Sustainability in Energy and Buildings SEB-25

The Research Unit of Politecnico di Torino (POLITO) and of the University of Campania Luigi Vanvitelli (UNICAMPANIA) participated at the “International Conference on Sustainability in Energy and Buildings SEB-25”, held in Catania, Italy, from September 17 to September 19, 2025. During the conference, the Research Units presented the outcomes of research activities performed within the within the  PRIN 2022 MUR - UTMOST FDD project  via the scientific papers entitled “Experimental Assessment of Valves’ Fault Severities in an Air-Handling Unit: Energy, Environmental, and Economic Impacts Under Italian Conditions” and "Cost-sensitive bayesian networks for FDD in HVAC systems: a fault impact-driven approach".

The first study provides a comprehensive faulty and fault-free performance dataset derived from experimental tests carried out on a typical air-handling unit (AHU) operating in southern Italy during winter and summer. This study examined ten faulty scenarios with the valves supplying the cooling coil and the post-heating coil stuck at different opening percentages: 0%, 25%, 50%, 75%, and 100%. Faulty operation has been compared with fault-free tests carried out under comparable boundary conditions. The results revealed that stuck-valve faults can increase daily electric energy demand, global equivalent CO₂ emissions, and operating costs from a minimum of 0.6% up to a maximum of 96.1%, as well as decrease the ability to maintain indoor air temperature and relative humidity within desired thresholds up to 75.8% and 96.8%, respectively.

The second study proposes a cost-sensitive FDD framework based on Tree Augmented Naïve Bayes (TAN) BNs, aimed at improving fault prioritization in multiclass classification tasks. The framework was trained and tested on 34 operational conditions—33 faulty and one normal state simulated for a Fan coil unit—using separate models for summer and winter. Misclassification costs, derived from a fault impact analysis based on energy and comfort related KPIs, were used to guide the learning pro-cess. The cost sensitive TAN model achieved detection accuracies of 93% (winter) and 99% (summer), and diagnosis accuracies of 76% and 82%, respectively. Precision and recall analyses showed significantly better performance for the 17 most impactful faults compared to the least impactful ones, confirming the model ability to prioritize the faults that matter most while maintaining high overall accuracy.