Incremental bearing fault diagnosis method under imbalanced sample conditions
Computers & Industrial Engineering,
Год журнала:
2024,
Номер
192, С. 110203 - 110203
Опубликована: Май 14, 2024
Язык: Английский
A hybrid load forecasting system based on data augmentation and ensemble learning under limited feature availability
Expert Systems with Applications,
Год журнала:
2024,
Номер
unknown, С. 125567 - 125567
Опубликована: Окт. 1, 2024
Язык: Английский
Big data for furniture intelligent manufacturing: conceptual framework, technologies, applications, and challenges
The International Journal of Advanced Manufacturing Technology,
Год журнала:
2024,
Номер
132(11-12), С. 5231 - 5247
Опубликована: Май 8, 2024
Язык: Английский
A back propagation neural network based low frequency clustering man-hour prediction method for digital manufacturing
International Journal of Computer Integrated Manufacturing,
Год журнала:
2025,
Номер
unknown, С. 1 - 19
Опубликована: Апрель 26, 2025
Язык: Английский
An explainable multi-layer graph attention network for product completion time prediction in aircraft final assembly lines
Journal of Manufacturing Systems,
Год журнала:
2025,
Номер
80, С. 1053 - 1071
Опубликована: Май 13, 2025
Язык: Английский
Deep reinforcement learning for solving car resequencing with selectivity banks in automotive assembly shops
International Journal of Production Research,
Год журнала:
2024,
Номер
unknown, С. 1 - 22
Опубликована: Сен. 24, 2024
Язык: Английский
L2-SSA-LSTM Prediction Model of Steering Drilling Wellbore Trajectory
IEEE Access,
Год журнала:
2023,
Номер
12, С. 450 - 461
Опубликована: Дек. 27, 2023
The
high-speed
vibration
rotation
of
the
drill
bit
during
drilling
causes
logging
tool
to
be
damaged
or
distorted,
resulting
in
inaccurate
lost
data
collection.
Traditional
prediction
methods
such
as
dynamic
modeling
and
geological
have
problems
incomplete
difficult
modeling,
which
cannot
meet
accuracy
stability
requirements
wellbore
trajectory
prediction.
long
short-term
memory
neural
network
(LSTM)
for
predicting
time
series
can
achieve
accurate
prediction,
but
there
are
difficulty
adjusting
hyperparameters
LSTM
model,
slow
convergence
speed,
easy
overfitting.
This
paper
absorbs
advantages
algorithm,
ridge
regression
(L2
regularization),
sparrow
optimization
algorithm
(SSA)
machine
learning
proposes
a
well
model
steerable
based
on
L2
regularization
SSA
optimized
(L2-SSA-LSTM).
takes
hyperparameter
parameter
goal
adds
prevent
overfitting
complete
experiment
was
conducted
using
measured
sets
from
directional
two
different
oilfields.
results
show
that
compared
with
back
propagation
(BP),
consolidated
gated
recurrent
unit
(CMGRU),
dual-thread
(DTGRU),
Attention-based
Spatiotemporal
Graph
Recurrent
Neural
Network
(ASTG-RNN),
LSTM,
L2-SSA-LSTM
has
significantly
higher
trajectories
than
other
models
better
predictive
ability.
Язык: Английский
Advanced data augmentation techniques coupled with enhanced particle swarm optimization for predicting total phosphorus concentrations in limited transmission spectra samples: A case study on the Yangtze River
Journal of Water Process Engineering,
Год журнала:
2024,
Номер
68, С. 106547 - 106547
Опубликована: Ноя. 15, 2024
Язык: Английский