Torque Control Permanent Magnet Synchronous Motor Environment

class gym_electric_motor.envs.ContTorqueControlPermanentMagnetSynchronousMotorEnv(supply=None, converter=None, motor=None, load=None, ode_solver=None, reward_function=None, reference_generator=None, visualization=None, state_filter=None, callbacks=(), constraints=(<gym_electric_motor.constraints.SquaredConstraint object>, ), calc_jacobian=True, tau=0.0001, physical_system_wrappers=(), **kwargs)[source]

Bases: ElectricMotorEnvironment

Description:

Environment to simulate a abc-domain continuous control set torque controlled permanent magnet synchr. motor.

Key:

'Cont-TC-PMSM-v0'

Default Components:
State Variables:

['omega' , 'torque', 'i_sd', 'i_sq', 'i_a', 'i_b', 'i_c', 'u_sd', 'u_sq', 'u_a', 'u_b', 'u_c', 'u_sup']

Reference Variables:

['torque']

Control Cycle Time:

tau = 1e-4 seconds

Observation Space:

Type: Tuple(State_Space, Reference_Space)

State Space:

Box(low=13 * [-1], high=13 * [1])

Reference Space:

Box(low=[-1, -1], high=[1, 1])

Action Space:

Box(low=[-1, -1, -1], high=[1, 1, 1])

Initial State:

Zeros on all state variables.

Example

>>> import gym_electric_motor as gem
>>> from gym_electric_motor.reference_generators import LaplaceProcessReferenceGenerator
>>>
>>> # Select a different ode_solver with default parameters by passing a keystring
>>> my_overridden_solver = 'scipy.solve_ivp'
>>>
>>> # Update the default arguments to the voltage supply by passing a parameter dict
>>> my_changed_voltage_supply_args = {'u_nominal': 400.0}
>>>
>>> # Replace the reference generator by passing a new instance
>>> my_new_ref_gen_instance = LaplaceProcessReferenceGenerator(
...     reference_state='torque',
...     sigma_range=(1e-3, 1e-2)
... )
>>> env = gem.make(
...     'Cont-TC-PMSM-v0',
...     voltage_supply=my_changed_voltage_supply_args,
...     ode_solver=my_overridden_solver,
...     reference_generator=my_new_ref_gen_instance
... )
>>> terminated = True
>>> for _ in range(1000):
>>>     if terminated:
>>>         state, reference = env.reset()
>>>     (state, reference), reward, terminated, truncated, _ = env.step(env.action_space.sample())
Parameters:

  • supply (env-arg) – Specification of the VoltageSupply for the environment

  • converter (env-arg) – Specification of the PowerElectronicConverter for the environment

  • motor (env-arg) – Specification of the ElectricMotor for the environment

  • load (env-arg) – Specification of the MechanicalLoad for the environment

  • ode_solver (env-arg) – Specification of the OdeSolver for the environment

  • reward_function (env-arg) – Specification of the RewardFunction for the environment

  • reference_generator (env-arg) – Specification of the ReferenceGenerator for the environment

  • visualization (env-arg) – Specification of the ElectricMotorVisualization for the environment

  • constraints (iterable(str/Constraint)) –

    All Constraints of the environment.

    • str: A LimitConstraints for states (episode terminates, if the quantity exceeds the limit)

    can be directly specified by passing the state name here (e.g. ‘i’, ‘omega’)

    • instance of Constraint: More complex constraints (e.g. the SquaredConstraint can be initialized and

    passed to the environment.

  • calc_jacobian (bool) – Flag, if the jacobian of the environment shall be taken into account during the simulation. This may lead to speed improvements. Default: True

  • tau (float) – Duration of one control step in seconds. Default: 1e-4.

  • state_filter (list(str)) – List of states that shall be returned to the agent. Default: None (no filter)

  • callbacks (list(Callback)) – Callbacks for user interaction. Default: ()

  • physical_system_wrappers (list(PhysicalSystemWrapper)) – List of Physical System Wrappers to modify the

  • Default (actions to and states from the physical system before they are used in the environment.) – ()

Note on the env-arg type:

All parameters of type env-arg can be selected as one of the following types:

instance: Pass an already instantiated object derived from the corresponding base class (e.g. reward_function=MyRewardFunction()). This is directly used in the environment.

dict: Pass a dict to update the default parameters of the default type. (e.g. visualization=dict(state_plots=('omega', 'u')))

str: Pass a string out of the registered classes to select a different class for the component. This class is then initialized with its default parameters. The available strings can be looked up in the documentation. (e.g. converter='Finite-2QC')

close()

Called when the environment is deleted. Closes all its modules.

get_wrapper_attr(name: str) → Any

Gets the attribute name from the environment.

has_wrapper_attr(name: str) → bool

Checks if the attribute name exists in the environment.

make(*args, **kwargs)
render(*_, **__)

Update the visualization of the motor.

reset(seed=None, options=None, *_, **__)

Reset of the environment and all its modules to an initial state.

Returns:

The initial observation consisting of the initial state and initial reference. info(dict): Auxiliary information (optional)

set_wrapper_attr(name: str, value: Any, *, force: bool = True) → bool

Sets the attribute name on the environment with value, see Wrapper.set_wrapper_attr for more info.

step(action)

Perform one simulation step of the environment with an action of the action space.

Parameters:

action – Action to play on the environment.

Returns:

Tuple of the new state and the next reference. reward(float): Amount of reward received for the last step. terminated(bool): Flag, indicating if a reset is required before new steps can be taken. info(dict): Auxiliary information (optional)

Return type:

observation(Tuple(ndarray(float),ndarray(float))

action_space: spaces.Space[ActType]
property constraint_monitor

The ConstraintMonitor of the environment.

Type:

Returns(ConstraintMonitor)

current_next_reference = None
current_reference = None
current_state = None
env_id = None
property limits

Returns a list of limits of all states in the observation (called in state_filter) in the same order

metadata: dict[str, Any] = {'render_modes': []}
property nominal_state

Returns a list of nominal values of all states in the observation (called in state_filter) in that order

property np_random: Generator

Returns the environment’s internal _np_random that if not set will initialise with a random seed.

Returns:

Instances of np.random.Generator

property np_random_seed: int

Returns the environment’s internal _np_random_seed that if not set will first initialise with a random int as seed.

If np_random_seed was set directly instead of through reset() or set_np_random_through_seed(), the seed will take the value -1.

Returns:

the seed of the current np_random or -1, if the seed of the rng is unknown

Return type:

int

observation_space: spaces.Space[ObsType]
property physical_system

Returns: PhysicalSystem: The Physical System of the Environment

property reference_generator

Returns: ReferenceGenerator: The ReferenceGenerator of the Environment

property reference_names

Returns a list of state names of all states in the observation (called in state_filter) in the same order

render_mode: str | None = None
property reward_function

Returns: RewardFunction: The RewardFunction of the environment

sim = SimulationEnvironment(tau=0.0, step=0)
spec: EnvSpec | None = None
property state_names

Returns a list of state names of all states in the observation (called in state_filter) in the same order

property unwrapped: Env[ObsType, ActType]

Returns the base non-wrapped environment.

Returns:

The base non-wrapped gymnasium.Env instance

Return type:

Env

property visualizations

Returns a list of all active motor visualizations.

workspace = Workspace()