Loss Term Using Bessel Functions

Physics Simulation PhysicsNeMo-ML Model Framework Technical Support (PhysicsNeMo Only)
1

I would like to use Sympy’s Bessel functions for calculating LOSS.
Here’s an example of what I’ve been trying:

import sympy as sp

# INPUT : x , t
# OUTPUT: u

x, t = Symbol("x"), Symbol("t")
geo = Line1D(0, 10)

LOSS_IC = PointwiseInteriorConstraint(
        nodes=nodes,
        geometry=geo,
        outvar={"u": sp.besselj(0, 4*pi*(x/(9.8*0.05))**0.5),"u__t": 0},
        parameterization={t: (0)},
        batch_size=cfg.batch_size.LOSS_IC,
    )
    domain.add_constraint(LOSS_IC, "LOSS_IC")

The error message I’m encountering is as follows:

Error executing job with overrides: []
An error occurred during Hydra's exception formatting:
AssertionError()
Traceback (most recent call last):
  File "/opt/conda/lib/python3.8/site-packages/hydra/_internal/utils.py", line 252, in run_and_report
    assert mdl is not None
AssertionError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "main.py", line 167, in <module>
    run()
  File "/modulus/modulus/hydra/utils.py", line 91, in func_decorated
    _run_hydra(
  File "/opt/conda/lib/python3.8/site-packages/hydra/_internal/utils.py", line 377, in _run_hydra
    run_and_report(
  File "/opt/conda/lib/python3.8/site-packages/hydra/_internal/utils.py", line 294, in run_and_report
    raise ex
  File "/opt/conda/lib/python3.8/site-packages/hydra/_internal/utils.py", line 211, in run_and_report
    return func()
  File "/opt/conda/lib/python3.8/site-packages/hydra/_internal/utils.py", line 378, in <lambda>
    lambda: hydra.run(
  File "/opt/conda/lib/python3.8/site-packages/hydra/_internal/hydra.py", line 111, in run
    _ = ret.return_value
  File "/opt/conda/lib/python3.8/site-packages/hydra/core/utils.py", line 233, in return_value
    raise self._return_value
  File "/opt/conda/lib/python3.8/site-packages/hydra/core/utils.py", line 160, in run_job
    ret.return_value = task_function(task_cfg)
  File "main", line 112, in run
    LOSS_IC = PointwiseInteriorConstraint(
  File "/modulus/modulus/domain/constraint/continuous.py", line 440, in __init__
    outvar = _compute_outvar(invar, outvar)
  File "/modulus/modulus/domain/constraint/utils.py", line 9, in _compute_outvar
    outvar[key] = np_lambdify(outvar_sympy[key], {**invar})(**invar)
  File "/modulus/modulus/utils/sympy/numpy_printer.py", line 144, in grouped_lambda
    output.append(lambdify_f_i(**invar))
  File "/modulus/modulus/utils/sympy/numpy_printer.py", line 128, in lambdify_f_i
    v = sp_lambdify_f_i(**x)
  File "<lambdifygenerated-2>", line 2, in _lambdifygenerated
NameError: name 'besselj' is not defined

Is it possible to use Bessel functions, and what changes should I make?

Thank you.