Class 2 wet-pipe fire sprinkler system s. Th is in vestigation evalu ated th e water qu ality in Class 1 an d Class 2 wet-pipe fire sprin kler system s to determ in e wh eth er firesprin kler system s pose a pu blic h ealth h azard an d evalu ated th e effectiven ess of retrofittin g th ese system s with backflow preven tion assem blies based on cost-ben efit an d risk con sideration s. Previous studies have answered some questionsHave fire sprinklers caused cross-connections? Alth ou gh th ere are n u m erou s, well-docu m en ted in stan ces in wh ich cross-con n ection s h ave con tam in ated drin kin g water an d produ ced illn ess, fire sprin kler system s h ave n ot been clearly im plicated. 1 Docum en ted cross-con n ection effects of fire services date back to 1903, wh en backflow occu rred in Lowell, Mass., du rin g a firefigh tin g operation ; th e crosscon n ection cau sed an ou tbreak of disease an d death s resu lted. 2 Preven tive m easu res developed to safegu ard again st fire crosscon n ection s in clu de th e u se of addition al ch eck valves on fire sprin kler lin es to preven t th e in trodu ction of con tam in an ts in to th e drin kin g water su pply. Of 398 backflow in ciden ts reported sin ce 1900, 4.3 percen t (17) are assu m ed to h ave in volved backflow of wetpipe fire sprin kler system s in to potable water lin es. 3,4 Is water in fire sprinkler systems potable? Man y stu dies of th e qu ality of fire sprin kler water h ave been perform ed by variou s m u n icipal water pu rveyors, bu t few are form ally pu blish ed or docu m en ted. As an example, in 1975 th e City of Portlan d (Ore.) Bu reau of Water Works an alyzed th e water in eigh t sprin kler system s th at h ad been in stalled between 1926 an d 1964. 5 Sam ples were collected from th e in spector's test con n ection . All samples exceeded drin kin g water stan dards for lead (Pb), iron (Fe), an d tu rbidity. Som e of th e sam ples exceeded Charlotte-Mecklenburg
The practical application of structural health monitoring (SHM) is often limited by the availability of labelled data. Transfer learning -specifically in the form of domain adaptation (DA) -gives rise to the possibility of leveraging information from a population of physical or numerical structures, by inferring a mapping that aligns the feature spaces. Typical DA methods rely on nonparametric distance metrics, which require sufficient data to perform density estimation. In addition, these methods can be prone to performance degradation under class imbalance. To address these issues, statistic alignment (SA) is discussed, with a demonstration of how these methods can be made robust to class imbalance, including a special case of class imbalance called a partial DA scenario. SA is demonstrated to facilitate damage localisation with no target labels in a numerical case study, outperforming other state-of-the-art DA methods. It is then shown to be capable of aligning the feature spaces of a real heterogeneous population, the Z24 and KW51 bridges, with only 220 samples used from the KW51 bridge. Finally, in scenarios where more complex mappings are required for knowledge transfer, SA is shown to be a vital pre-processing tool, increasing the performance of established DA methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.