Search

Automation and accurate fault detection and diagnosis of HVAC systems is one of the most important technologies for reducing time,energy,and financial costs in building performance management.In recent years,data-driven fault detection and diagnosis methods have been heavily studied for fault detection and diagnosis of HVAC systems.However,most existing works deal with single systems and are unable to perform cross-system fault diagnosis.In this paper,a federal learning-based fault detection and diagnosis method is proposed,which uses convolutional neural networks to extract information features,aggregates features using special-designed algorithms,and perform cross-level and cross-system fault detection and diagnosis via federal lear-ning.For multi-fault level fault detection and diagnosis,federal learning is performed using data from four fault levels of chillers.Experimental results show that the average F1-score of the fault detection and diagnosis effect of the four-fault levels is close to 0.97,which is within the practical range.Federal learning uses chiller and air handling unit data for cross-system fault detection and diagnosis.Experimental results show that federal learning using different system data improves the diagnosis results of particular faults,e.g.,14.4% for RefOver faults and 2%~4% for both Refleak and Exoil faults.

[Display omitted] • An innovative framework is proposed for robust multi-objective optimization for NZEBs. • Open-source technique combining coding language and dynamic energy simulation is set. • The workflow is tested on a representative office building in Mediterranean climate. • The most robust configurations of building-HVAC system are found for NZEB target. • Analysis of occurrence frequency of design variables in Pareto front is provided. Net Zero Energy Buildings (NZEBs) play a key role to save energy. However, unpredictable scenarios and uncertainties about stability of energy production from renewables frequently cause measured performance of the building-plants system that differs from predictions. So, it is crucial to individuate the best alternatives in the early-stage design of the building and related energy systems, also considering uncertain circumstances. Hence, the aim of this paper is to enhance reliability of the building design process by providing an innovative workflow based on multi-objective optimization that encompasses robustness assessment of different design alternatives against uncertain scenarios. The standard genetic algorithm optimization routine has been deeply improved to set as a key performance indicator the robustness of energy performance of several building-HVAC system configurations, also considering the financial aspects optimization. Compliance with NZEB target of the obtained optimal solutions is then automatically verified by the algorithm. The new methodology combines open-source coding language Python and the dynamic energy simulation engine EnergyPlus. The robustness of each solution is evaluated through Taguchi method. First obtained results are related to energy-efficient solutions for the building envelope. Regarding the HVAC system, ground source (instead of air source) heat pumps and variable refrigerating flow systems are preferable. Finally, medium–high size of photovoltaic panels is preferred, although with high investment costs. [ABSTRACT FROM AUTHOR]

Verifying the capacity of different types of air filters to stop the propagation of the SARS-CoV-2 virus has become a strategic element to contain viral spreading in enclosed spaces. This paper shows the results of experimental tests about the capacity of different commercial filter grades to stop SARS-CoV-2 propagation using inactivated virions. In the first test, the obtained results showed that the F8 filter blocks SARS-CoV-2 propagation if it encounters a flow devoid of liquid phase, i.e., a biphasic flow that can wet the filtering material. On the contrary, as shown in the second test, the SARS-CoV-2 virus propagates through the F8 filter if the droplet content in the air flow is enough to wet it. In these operational conditions, i.e., when the filter is wet by a flow with a high droplet content, the absolute H14 filter was also shown to fail to stop the transmission of the SARS-CoV-2 virus. Lastly, in the third test, the viral load was shown to be stopped when the pathway of the infected droplet is blocked. • Experimental validation of the capacity of air filters to block SARS-CoV-2. • Good practice to minimize the propagation of SARS-CoV-2 in air conditioning systems. • Droplet and airborne transmission mechanism of SARS-CoV-2 virus. [ABSTRACT FROM AUTHOR]