FeOs-torch - Automatic differentiation of phase equilibria.
Project description
FeOs-torch - Automatic differentiation of phase equilibria
FeOs-torch
combines the FeOs
thermodynamics engine with the machine learning/automatic differentiation framework PyTorch.
import torch
from feos_torch import PcSaftPure
# define PC-SAFT parameters
# m, sigma, epsilon_k, mu, kappa_ab, epsilon_k_ab, na, nb
params = torch.tensor([1.5, 3.5, 250.0, 0, 0.03, 1500.0, 1, 1], dtype=torch.float64, requires_grad=True)
pcsaft = PcSaftPure(params.repeat(5, 1))
# evaluate vapor pressures (in Pa)
temperature = torch.tensor([250., 300., 350., 400., 450.], dtype=torch.float64)
_, vp = pcsaft.vapor_pressure(temperature)
print(vp)
# determine the derivatives of the first vapor pressure w.r.t. PC-SAFT parameters
vp[0].backward()
print(params.grad)
tensor([ 20693.5960, 216164.6184, 1049770.6187, 3281855.9640, 7875531.7021],
dtype=torch.float64, grad_fn=<MulBackward0>)
tensor([-6.7923e+04, -1.7737e+04, -7.0413e+02, 0.0000e+00, -5.7458e+05,
-6.9122e+01, -3.6892e+04, -3.6892e+04], dtype=torch.float64)
Models
The following models and properties are currently implemented in FeOs-torch
model | vapor pressure | liquid density | equilibrium liquid density | bubble point pressure | dew point pressure |
---|---|---|---|---|---|
PC-SAFT | ✓ | ✓ | ✓ | ✓ | ✓ |
gc-PC-SAFT | ✓ | ✓ |
Cite us
If you find FeOs-torch
useful for your own research, consider citing our publication from which this library resulted.
@article{rehner2023mixtures,
author = {Rehner, Philipp and Bardow, André and Gross, Joachim},
title = {Modeling Mixtures with PCP-SAFT: Insights from Large-Scale Parametrization and Group-Contribution Method for Binary Interaction Parameters}
journal = {International Journal of Thermophysics},
volume = {44},
number = {12},
pages = {179},
year = {2023}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distributions
Close
Hashes for feos_torch-0.1.0-cp37-abi3-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f04d7725f4033913f08cc6b1d96eba231631f088debaceb6a569f544a121a3bf |
|
MD5 | 32a4854d79d52c94260b71f912b4a6bf |
|
BLAKE2b-256 | 1cf9e67af96f9ae1066bf53b3ec17bcd8510c21e713b8f6d1b727c92599eedc4 |
Close
Hashes for feos_torch-0.1.0-cp37-abi3-win32.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8cf01617c8230c17cd97cef701d84a249872c07c538cfe8fc2c35e9e3ad207f9 |
|
MD5 | 7e8ac9886646cd0bd2ef40f4e0a6297f |
|
BLAKE2b-256 | 3352f2e7f1792033ee4b898c6ab71bf301831c34ebac2c29fdd1d3099083e340 |
Close
Hashes for feos_torch-0.1.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dddbc099de1ffd532aef9982f20924c38439de806310a6bff71b61c61ce93876 |
|
MD5 | be11d1d3b6a72f9872373a16c77e1bb8 |
|
BLAKE2b-256 | aa1687210b5771b7bf6bfd7cfa09e96e5ff8009e3bd813fb12f3a539edc08b91 |
Close
Hashes for feos_torch-0.1.0-cp37-abi3-macosx_10_12_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 90f06432e711401b51d3554c041300a372c3d00fde4daadba36b7f31b2baf22f |
|
MD5 | 0c02956b8a036264f4dae2aa328c9308 |
|
BLAKE2b-256 | 72e3a8571a8dbe59ad8e5a6591c30ebeaf091566bc32b57040271b7f6d593b62 |
Close
Hashes for feos_torch-0.1.0-cp37-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5de2511c2a282762e94b2797054ee097524b16949c2cb3d369bc3d640abd69c7 |
|
MD5 | c15b3e9647d879709a4ed1d85ee7edaa |
|
BLAKE2b-256 | 3a3783ad2be69f352d85bcb242f792ed76cefe5cd3886544db3127c3f2820a77 |