Abstract
A
stopping
criterion
for
iterative
solution
methods
is
presented
that
accurately
estimates
the
solution
error
using
low
computational
overhead.
The
proposed
criterion
uses
information
from
prior
solution
changes
to
estimate
the
error.
When
the
solution
changes
are
noisy
or
stagnating
it
reverts
to
a
less
accurate
but
more
robust,
low-cost
singular
value
estimate
to
approximate
the
error
given
the
residual.
This
estimator
can
also
be
applied
to
iterative
linear
matrix
solvers
such
as
Krylov
subspace
or
multigrid
methods.
Examples
of
the
stopping
criterion's
ability
to
accurately
estimate
the
non-linear
and
linear
solution
error
are
provided
for
a
number
of different test cases in incompressible
fluid dynamics.
Users
Please
log in to take part in the discussion (add own reviews or comments).