A hybrid machine learning framework for wind pressure prediction on buildings with constrained sensor networks
Foad Mohajeri Nav,
No information about this author
Seyedeh Fatemeh Mirfakhar,
No information about this author
Reda Snaiki
No information about this author
et al.
Computer-Aided Civil and Infrastructure Engineering,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 18, 2025
Abstract
Accurate
and
efficient
prediction
of
wind
pressure
distributions
on
high‐rise
building
façades
is
crucial
for
mitigating
structural
risks
in
urban
environments.
Conventional
approaches
rely
extensive
sensor
networks,
often
hindered
by
cost,
accessibility,
architectural
limitations.
This
study
proposes
a
novel
hybrid
machine
learning
(ML)
framework
that
reconstructs
high‐fidelity
(HFWP)
coefficient
fields
from
limited
number
sensors
leveraging
dynamic
spatiotemporal
feature
extraction
mapping.
The
methodology
consists
four
key
stages:
(1)
low‐fidelity
field
reconstruction
data
using
constrained
QR
decomposition,
(2)
dimensionality
reduction
both
HFWP
reconstructions
to
extract
dominant
features,
(3)
mapping
the
reduced‐order
representations
long
short‐term
memory
network,
(4)
over
time.
proposed
approach,
which
predicts
time
history
coefficients
various
directions,
validated
tunnel
data,
with
case
studies
multiple
façades—including
windward,
right‐side,
leeward
surfaces—under
placement
scenarios.
also
evaluated
against
alternative
ML
models,
demonstrating
superior
accuracy
reconstructing
full
field.
results
highlight
robustness
generalization
capability
model
across
different
directions
configurations,
making
it
practical
solution
real‐time
estimation
health
monitoring
digital
twin
applications.
Language: Английский
The experimental and numerical results of a spinning/whirling composite thick-beam of glass fibers reinforced with CNR based on SSDT and neutral axis with electric field
Fatemeh Bargozini,
No information about this author
Mehdi Mohammadimehr
No information about this author
International Journal of Lightweight Materials and Manufacture,
Journal Year:
2025,
Volume and Issue:
unknown
Published: May 1, 2025
Language: Английский
Two‐stage nonparametric framework for missing data imputation, uncertainty quantification, and incorporation in system identification
Computer-Aided Civil and Infrastructure Engineering,
Journal Year:
2024,
Volume and Issue:
39(19), P. 2881 - 2902
Published: May 26, 2024
Abstract
In
many
engineering
applications,
missing
data
during
system
identification
can
hinder
the
performance
of
identified
model.
this
paper,
a
novel
two‐stage
nonparametric
framework
is
proposed
for
imputation,
uncertainty
quantification,
and
its
integration
in
with
reduced
computational
complexity.
The
does
not
require
functional
forms
both
imputation
model
mathematical
Moreover,
through
construction
single
model,
analytical
expressions
predictive
distributions
be
given
entries
across
all
missingness
patterns.
Furthermore,
expectation
variance
distribution
are
provided
to
impute
values
quantify
uncertainty,
respectively.
This
incorporated
into
by
mitigating
influence
samples
imputations
training
testing.
applied
three
including
simulated
example
two
real
applications
on
structural
health
monitoring
seismic
attenuation
modeling.
Results
reveal
minimum
reduction
21%
root
mean
squared
error
values,
compared
those
achieved
directly
removing
incomplete
samples.
Language: Английский
Modal identification of wind turbine tower based on optimal fractional order statistical moments
Computer-Aided Civil and Infrastructure Engineering,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Oct. 23, 2024
Abstract
In
vibration
testing
of
civil
engineering
structures,
the
first
two
modes
are
crucial
in
representing
global
dynamic
behavior
structure
measured.
present
study,
a
comprehensive
method
is
proposed
to
identify
wind
turbine
towers,
which
based
on
analysis
fractional
order
statistical
moments
(FSM).
This
study
offers
novel
contributions
key
aspects:
(1)
theoretical
derivations
relationship
between
FSM
and
mode;
(2)
successful
use
32/7‐order
displacement
moment
as
optimal
tower
modes,
by
combining
with
noise
resistance
analysis,
sensitivity
stability
respectively.
Using
method,
was
used
modal
towers.
By
obtaining
response
same
vertical
line,
then
calculated
estimate
corresponding
structural
vibration.
Considering
other
influencing
factors
field
test,
identification
results
this
index
under
different
excitation
forms
conditions
were
analyzed
numerical
simulation
verified
test
data.
The
evaluation
show
that
can
accurately
presents
new
robust
for
identification,
is,
simple
effective
its
implementation.
Language: Английский
Effects of Aerodynamic Damping and Gyroscopic Moment of A Semi-submersible Floating Vertical Axis Wind Turbine: An Experimental Study
Journal of Offshore Mechanics and Arctic Engineering,
Journal Year:
2024,
Volume and Issue:
147(2)
Published: Sept. 10, 2024
Abstract
Floating
vertical-axis
wind
turbines
(VAWTs)
offer
certain
advantages
over
floating
horizontal-axis
(HAWTs),
particularly
in
terms
of
the
potential
to
lower
cost
energy.
In
this
study,
a
5
MW
VAWT
concept
with
three
straight
blades
and
semi-submersible
hull
deployed
water
depth
42
m
was
presented.
addition,
experimental
setup
is
introduced,
calibration
tests
are
also
performed
validate
physical
model
system.
Subsequently,
aerodynamic
damping
gyroscopic
moment
effects
were
investigated
by
wind/wave
basin
scale
ratio
1/50.
Results
indicate
that
can
suppress
fluctuations
platform's
surge
pitch
motion
at
their
respective
resonance
frequencies
tends
increase
speed
below-rated
speed.
Additionally,
surge-induced
pitch-induced
hardly
affect
wave
frequency
response.
Meanwhile,
natural
substantially
altered
due
loads.
The
rotating
rotor
platform
together
excite
significant
moments,
leading
noticeable
oscillations
roll
motion.
there
an
increasing
trend
effect
rotational
During
normal
operation
VAWT,
influence
roll/pitch
motions.
Overall,
study
contributes
providing
valuable
insights
into
characteristics
VAWTs.
Language: Английский
Rapid simulation method for assessing seismic damage to building curtain walls on a regional scale using designed wind load capacity
Integrated Computer-Aided Engineering,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 16
Published: Sept. 19, 2024
This
study
introduces
a
rapid
simulation
method
for
assessing
seismic
damage
to
building
curtain
walls
at
regional
scale.
Although
the
results
are
approximate,
this
approach
enables
quick
evaluations,
making
it
an
important
instrument
emergency
responses
during
disaster
situations.
method’s
independence
from
numerical
models
is
noteworthy
advantage.
Unlike
conventional
approaches,
eliminates
need
structural
analysis
when
evaluating
capacities
of
regionally.
Creating
reliable
both
time-consuming
and
labor-intensive,
primarily
due
detailed
design
information
they
require.
In
contrast,
presented
leverages
wind
load
which
designed.
It
based
on
core
premise
that
most
walls,
designed
resistance,
possess
could
serve
as
substitutes
their
capacities,
even
if
not
explicitly
such
loads.
To
assess
effectiveness,
was
applied
assessments
across
regions
experiencing
varying
intensities:
weak,
moderate,
strong.
The
suggest
likelihood
sustaining
in
with
weak
be
five
times
higher
than
strong
wind.
underscores
importance
considerations
walls.
Moreover,
findings
closely
match
actual
assessment
data
region
moderate
intensity.
Language: Английский