BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//EURODYN//Schedule//DE
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:88@eurodyn2026.org
DTSTAMP:20261026T144037Z
DTSTART;TZID=Europe/Berlin:20260928T150000
DTEND;TZID=Europe/Berlin:20260928T152000
SUMMARY:Feature Reconstruction and Monitoring of Load Test Data under Var
 ying Environmental Conditions
LOCATION:Room F128
DESCRIPTION:MS 22\n\nPresenter: Neumann\, Lizzie\n\nAuthors: Neumann\, Li
 zzie\; Wittenberg\, Philipp\; Mendler\, Alexander\; Gertheiss\, Jan\n\nC
 hair: Høgsberg\, Jan\n\nAbstract: System outputs in Structural Health Mo
 nitoring (SHM)\, such as sensor measurements or extracted features like 
 eigenfrequencies\, are influenced not only by (potential) damage but als
 o by environmental and operational parameters (EOP). Identifying these f
 actors and removing their effects from the data is essential before proc
 eeding with further analysis. Most existing methods for this task focus 
 on the expected values of system outputs\, e.g.\, using different types 
 of response surface modeling.  However\, it has been shown that confound
 ing variables can also affect the (co-)variance of and between system ou
 tputs. This is particularly important because the covariance matrix is a
 n essential building block in many damage detection methods in SHM. Beyo
 nd standard response surface modeling\, a nonparametric kernel approach 
 can be used to estimate a conditional covariance matrix that can change 
 depending on the identified confounding factor. This improves our unders
 tanding of how\, e.g.\, temperature affects the system outputs.  In this
  work\, we present a new confounder-adjusted version of feature reconstr
 uction. It uses the conditional covariance matrix as the basis for (cond
 itional) principal component analysis. The resulting (conditional) princ
 ipal component scores are then used to reconstruct system outputs with t
 he confounding influences removed.  In particular\, the new approach eli
 minates the confounder’s effect on both the mean and the covariance. As 
 will be shown on load test data from the Vahrendorfer Stadtweg bridge in
  Hamburg\, Germany\, the reconstructed features can then be employed for
  monitoring\, e.g.\, using an appropriate control chart\, resulting in f
 ewer false alarms and a higher probability of detecting damage.
URL:https://eurodyn2026.org/submission/88
END:VEVENT
END:VCALENDAR