Setup a CSTR environment with a setpoint change
import pcgym
# Simulation variables
nsteps = 100
T = 25
# Setpoint
SP = {'Ca': [0.85 for i in range(int(nsteps/2))] + [0.9 for i in range(int(nsteps/2))]}
# Action and observation Space
action_space = {'low': np.array([295]), 'high': np.array([302])}
observation_space = {'low': np.array([0.7,300,0.8]),'high': np.array([1,350,0.9])}
# Construct the environment parameter dictionary
env_params = {
'N': nsteps, # Number of time steps
'tsim':T, # Simulation Time
'SP' :SP,
'o_space' : observation_space,
'a_space' : action_space,
'x0': np.array([0.8, 330, 0.8]), # Initial conditions [Ca, T, Ca_SP]
'model': 'cstr_ode', # Select the model
}
# Create environment
env = pcgym.make_env(env_params)
# Reset the environment
obs, state = env.reset()
# Sample a random action
action = env.action_space.sample()
# Perform a step in the environment
obs, rew, done, term, info = env.step(action)You can read the full documentation here!
The latest pc-gym version can be installed from PyPI:
pip install pcgymExample notebooks with training walkthroughs, implementing constraints, disturbances and the policy evaluation tool can be found here.
| Environment | Reference | Source | Documentation |
|---|---|---|---|
| CSTR | Hedengren, 2022 | Source | |
| First Order Sytem | N/A | Source | |
| Multistage Extraction Column | Ingham et al, 2007 (pg 471) | Source | |
| Nonsmooth Control | Lim,1969 | Source |
The associated pre-print paper can be found here. If you use our software in your work please cite the following:
@article{bloor2024pcgymbenchmarkenvironmentsprocess,
title={PC-Gym: Benchmark Environments For Process Control Problems},
author={Maximilian Bloor and José Torraca and Ilya Orson Sandoval and Akhil Ahmed and Martha White and Mehmet Mercangöz and Calvin Tsay and Ehecatl Antonio Del Rio Chanona and Max Mowbray},
year={2024},
eprint={2410.22093},
archivePrefix={arXiv},
primaryClass={eess.SY},
url={https://arxiv.org/abs/2410.22093},
}