🚧 Rewrite continous simulation.
This commit is contained in:
+252
-128
@@ -1,24 +1,32 @@
|
||||
"""PlantEnv: gymnasium-style environment over the simulated plant (spec §8, FR-8.2.14-16).
|
||||
"""PlantEnv: gymnasium-style plant environment (spec §8, FR-8.2.14-17).
|
||||
|
||||
The environment is the decision-source interface to the distributed
|
||||
I/O: per deterministic engine tick —
|
||||
Standalone-first: requires only a virtual node + datastore — no
|
||||
scenario. The environment is the interface for continuous plant
|
||||
simulation; per deterministic tick (runner-owned clock, never
|
||||
wall-clock arithmetic):
|
||||
|
||||
state = env.observe() # WAGO input image in engineering units
|
||||
decision = policy(state) # caller's plant model / agent (no policy here)
|
||||
env.apply(actions) # decided outputs -> output image via
|
||||
# the datastore's INTERNAL write paths
|
||||
engine.pump() # engine advances exactly one tick
|
||||
state = env.observe() # ALL modules: DI/DO/AI/AO channels,
|
||||
# engineering units, names, parameters
|
||||
values = env.model(state, dt) # plant physics (subclass hook)
|
||||
env.apply(values) # new FIELD state -> DI/AI inputs;
|
||||
# DO/AO via env.force() (master-side)
|
||||
|
||||
The engine always owns the tick clock (FR-4.3.9 deterministic sim
|
||||
time); the env never reads wall-clock. `apply()` writes through the
|
||||
datastore's Modbus-equivalent dispatch so mirrors, statistics, and
|
||||
watchdog behavior stay consistent (FR-9.2.6 semantics).
|
||||
`model()` is the override point for plant physics: read what the PLC
|
||||
commanded (DO/AO), compute what the field now shows (DI/AI), return
|
||||
it. `is_done(state)` gives an optional end criterion; the default is
|
||||
False — environments run until manually stopped (SIGINT/SIGTERM).
|
||||
|
||||
Attachments: degradation (§8.3), invariants (§8.4) and aliases
|
||||
(scenario-continuous mode) hook onto the same tick when the env is
|
||||
constructed on an engine.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Callable
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
from ..modules import VirtualNode
|
||||
from .engine import ScenarioError
|
||||
|
||||
|
||||
@@ -31,43 +39,60 @@ class ChannelState:
|
||||
channel: int # 0-based channel on the module
|
||||
io_code: str # e.g. "DI0.0"
|
||||
name: str | None # configured application name, if any
|
||||
value: object # bool for di/do, float for ai/ao
|
||||
value: object # bool for di/do, int/float for ai/ao
|
||||
|
||||
|
||||
@dataclass
|
||||
class PlantState:
|
||||
"""Full observation: every channel + aliases + parameters + clock."""
|
||||
"""Full observation: every channel of every module + attachments."""
|
||||
|
||||
sim_time_ms: float
|
||||
channels: list[ChannelState] = field(default_factory=list)
|
||||
aliases: dict[str, object] = field(default_factory=dict)
|
||||
parameters: dict[str, float] = field(default_factory=dict)
|
||||
|
||||
def by_code(self, io_code: str) -> object:
|
||||
"""Value of one channel by I/O code, or KeyError."""
|
||||
for ch in self.channels:
|
||||
if ch.io_code == io_code:
|
||||
return ch.value
|
||||
raise KeyError(io_code)
|
||||
|
||||
def by_kind(self, kind: str) -> dict[str, object]:
|
||||
"""{io_code: value} for all channels of one kind."""
|
||||
return {c.io_code: c.value for c in self.channels if c.kind == kind}
|
||||
|
||||
|
||||
class PlantEnv:
|
||||
"""gym-style observe/apply environment (FR-8.2.14-16).
|
||||
"""gym-style plant environment (FR-8.2.14-17).
|
||||
|
||||
Constructed by the continuous engine; the engine stays the clock
|
||||
owner — the env's `step()` convenience drives `engine.pump()` for
|
||||
exactly one tick (server mode may tick the engine externally and
|
||||
only use observe/apply).
|
||||
Constructed on a VirtualNode (standalone) or on an engine (the
|
||||
scenario-continuous layer). The runner owns the tick clock; `tick()`
|
||||
advances sim-time deterministically by TICK_MS per call so both
|
||||
paced (serve) and unpaced (sim) runners behave identically.
|
||||
"""
|
||||
|
||||
def __init__(self, engine) -> None:
|
||||
TICK_MS = 10.0
|
||||
|
||||
def __init__(self, node: VirtualNode | None = None, *,
|
||||
engine=None) -> None:
|
||||
self.engine = engine
|
||||
self._actions: dict[str, object] = {}
|
||||
self.node: VirtualNode = node if node is not None else engine.node
|
||||
self.datastore = self.node.datastore
|
||||
self.sim_time_ms = 0.0
|
||||
# attachments (optional; the scenario layer wires these)
|
||||
self.degradation = getattr(engine, "degradation", None)
|
||||
self.invariants = getattr(engine, "invariants", None)
|
||||
self._aliases = getattr(engine, "_aliases", None) if engine else None
|
||||
self._alias_value: Callable[[str], object] | None = (
|
||||
engine.alias_value if engine is not None else None)
|
||||
|
||||
# -- observation (FR-8.2.14) -----------------------------------------------
|
||||
|
||||
def observe(self) -> PlantState:
|
||||
"""Snapshot of the generic inputs (WAGO input image + aliases).
|
||||
|
||||
DI/AI channels hold the simulated field state; DO/AO hold the
|
||||
PLC-written outputs as currently in the images — all values in
|
||||
engineering units (alias scale/offset applied where defined).
|
||||
"""
|
||||
node = self.engine.node
|
||||
ds = self.engine.datastore
|
||||
"""Snapshot ALL modules (DI/DO/AI/AO) in engineering units."""
|
||||
node = self.node
|
||||
ds = self.datastore
|
||||
channels: list[ChannelState] = []
|
||||
for kind, pool in (("di", node.di), ("do", node.do),
|
||||
("ai", node.ai), ("ao", node.ao)):
|
||||
@@ -80,7 +105,8 @@ class PlantEnv:
|
||||
value = ds.get_input_word(loc.word)
|
||||
else:
|
||||
value = ds.get_output_word(loc.word)
|
||||
code = node.io_code_at_slot(kind, loc.module_index, loc.channel - 1)
|
||||
code = node.io_code_at_slot(
|
||||
kind, loc.module_index, loc.channel - 1)
|
||||
channels.append(ChannelState(
|
||||
kind=kind,
|
||||
module=node.kind_index(loc.module_index)[kind],
|
||||
@@ -89,128 +115,226 @@ class PlantEnv:
|
||||
name=node.channel_names.get(code),
|
||||
value=value,
|
||||
))
|
||||
aliases = {name: self.engine.alias_value(name)
|
||||
for name in self.engine._aliases}
|
||||
aliases = ({name: self._alias_value(name)
|
||||
for name in (self._aliases or {})}
|
||||
if self._alias_value else {})
|
||||
parameters: dict[str, float] = {}
|
||||
degradation = getattr(self.engine, "degradation", None)
|
||||
if degradation is not None:
|
||||
parameters = {n: m.value for n, m in degradation.models.items()}
|
||||
if self.degradation is not None:
|
||||
parameters = {n: m.value
|
||||
for n, m in self.degradation.models.items()}
|
||||
return PlantState(
|
||||
sim_time_ms=self.engine.sim_time_ms,
|
||||
sim_time_ms=self.sim_time_ms,
|
||||
channels=channels,
|
||||
aliases=aliases,
|
||||
parameters=parameters,
|
||||
)
|
||||
|
||||
# -- actions (FR-8.2.14) -----------------------------------------------------
|
||||
# -- plant model hook (FR-8.2.16) -------------------------------------------
|
||||
|
||||
def apply(self, actions: dict[str, object]) -> None:
|
||||
"""Queue decided outputs; they land when the engine ticks.
|
||||
def model(self, state: PlantState, dt_s: float) -> dict[str, object]:
|
||||
"""Plant physics: react to PLC commands, compute the new field.
|
||||
|
||||
Keys: I/O code ("DO0.0") or alias name ("pump_relay"). Writing
|
||||
a DI/AI through the env is an error — inputs are the field side
|
||||
(datasets/scenario steps simulate them). Keys are validated
|
||||
EAGERLY so a bad decision surfaces immediately, not at flush.
|
||||
Override in a subclass (FR-8.2.17). Receives the full observed
|
||||
state and the tick delta in seconds; returns {I/O code or alias:
|
||||
new value} for the channels it drives — DI/AI normally (the
|
||||
simulated sensors); DO/AO entries are treated as forcing and go
|
||||
through the master-side write paths. Returning {} (the default)
|
||||
makes this a pure observation environment.
|
||||
"""
|
||||
if not isinstance(actions, dict):
|
||||
raise ScenarioError("apply() actions must be a mapping")
|
||||
validated: dict[str, object] = {}
|
||||
for key, value in actions.items():
|
||||
alias = self.engine._aliases.get(key) or self._alias_by_code(key)
|
||||
if alias is None:
|
||||
raise ScenarioError(f"apply(): unknown channel {key!r}")
|
||||
if alias.kind not in ("do", "ao"):
|
||||
raise ScenarioError(
|
||||
f"apply(): {key!r} is an input alias ({alias.kind}); "
|
||||
"only outputs (do/ao) are decided")
|
||||
validated[str(key)] = value
|
||||
self._actions.update(validated)
|
||||
return {}
|
||||
|
||||
def flush(self) -> None:
|
||||
"""Write queued actions into the output image (engine-tick step).
|
||||
def is_done(self, state: PlantState) -> bool:
|
||||
"""Optional end criterion; default runs until manually stopped."""
|
||||
return False
|
||||
|
||||
Called by the engine after the observe/decide window and before
|
||||
the pipeline advances — so the next observe() sees them
|
||||
(FR-8.2.12 atomic-env-tick paragraph).
|
||||
# -- actions (FR-8.2.15) ------------------------------------------------------
|
||||
|
||||
def apply(self, values: dict[str, object], *, force: bool = False) -> None:
|
||||
"""Write new channel values into the process images.
|
||||
|
||||
DI/AI keys (the field) write directly — this is the primary
|
||||
direction. DO/AO keys (PLC outputs) require force=True and go
|
||||
through the datastore's internal Modbus dispatch so mirrors,
|
||||
statistics, and watchdog stay consistent (FR-9.2.6) — for
|
||||
headless runs and fault setup only.
|
||||
Keys: I/O code ("AI0.0") or alias name. Unknown keys raise
|
||||
immediately (FR-8.2.16).
|
||||
"""
|
||||
for key, value in self._actions.items():
|
||||
self._write_one(key, value)
|
||||
self._actions = {}
|
||||
if not isinstance(values, dict):
|
||||
raise ScenarioError("apply() values must be a mapping")
|
||||
for key, value in values.items():
|
||||
self._write_one(key, value, force=force)
|
||||
|
||||
def _write_one(self, key: str, value: object) -> None:
|
||||
# resolve by alias name first, then by I/O code
|
||||
alias = self.engine._aliases.get(key)
|
||||
if alias is None:
|
||||
alias = self._alias_by_code(key)
|
||||
if alias is None:
|
||||
raise ScenarioError(f"apply(): unknown channel {key!r}")
|
||||
if alias.kind not in ("do", "ao"):
|
||||
def force(self, values: dict[str, object]) -> None:
|
||||
"""Master-side forcing of DO/AO (FR-8.2.15 explicit form)."""
|
||||
self.apply(values, force=True)
|
||||
|
||||
def _resolve(self, key: str):
|
||||
"""-> (kind, ChannelLocation, alias_or_None) for a code or alias."""
|
||||
# alias name first (scenario layer)
|
||||
if self._aliases and key in self._aliases and self.engine is not None:
|
||||
alias = self._aliases[key]
|
||||
return alias.kind, self.engine._alias_location(alias), alias
|
||||
# any channel by I/O code (per-type codes, FR-4.3.11 v1.5)
|
||||
code_up = str(key).strip().upper()
|
||||
node = self.node
|
||||
for kind, pool in (("di", node.di), ("do", node.do),
|
||||
("ai", node.ai), ("ao", node.ao)):
|
||||
for loc in pool:
|
||||
if node.io_code_at_slot(
|
||||
kind, loc.module_index, loc.channel - 1) == code_up:
|
||||
return kind, loc, None
|
||||
raise ScenarioError(f"apply(): unknown channel {key!r}")
|
||||
|
||||
def _write_one(self, key: str, value: object, *, force: bool) -> None:
|
||||
kind, loc, alias = self._resolve(key)
|
||||
ds = self.datastore
|
||||
if kind in ("do", "ao") and not force:
|
||||
raise ScenarioError(
|
||||
f"apply(): {key!r} is an input alias ({alias.kind}); "
|
||||
"only outputs (do/ao) are decided")
|
||||
loc = self.engine._alias_location(alias)
|
||||
ds = self.engine.datastore
|
||||
if alias.kind == "do":
|
||||
f"apply(): {key!r} is an output ({kind.upper()}); use "
|
||||
"force=True / env.force() for master-side forcing")
|
||||
scale = getattr(alias, "scale", 1.0) or 1.0
|
||||
offset = getattr(alias, "offset", 0.0) or 0.0
|
||||
if kind == "di":
|
||||
ds.set_digital_input_channel(loc.bit + 1, bool(value))
|
||||
elif kind == "ai":
|
||||
raw = int(float(value) * scale + offset) & 0xFFFF
|
||||
ds.set_input_word(loc.word, raw)
|
||||
elif kind == "do":
|
||||
result = ds.write_bits(loc.bit, [bool(value)])
|
||||
else:
|
||||
numeric = float(value) # type: ignore[arg-type]
|
||||
raw = int(numeric * alias.scale + alias.offset) & 0xFFFF
|
||||
if isinstance(result, Exception):
|
||||
raise ScenarioError(f"force() write to {key!r}: {result}")
|
||||
else: # ao
|
||||
raw = int(float(value) * scale + offset) & 0xFFFF
|
||||
result = ds.write_words(loc.word, [raw])
|
||||
if isinstance(result, Exception):
|
||||
raise ScenarioError(f"apply() write to {key!r} rejected: {result}")
|
||||
if isinstance(result, Exception):
|
||||
raise ScenarioError(f"force() write to {key!r}: {result}")
|
||||
|
||||
def _alias_by_code(self, code: str):
|
||||
"""Find an alias whose I/O code matches (per-type codes)."""
|
||||
code_up = str(code).strip().upper()
|
||||
node = self.engine.node
|
||||
for name, alias in self.engine._aliases.items():
|
||||
if alias.kind not in ("do", "ao"):
|
||||
continue
|
||||
try:
|
||||
loc = self.engine._alias_location(alias)
|
||||
except Exception:
|
||||
continue
|
||||
if node.io_code_at_slot(alias.kind, loc.module_index,
|
||||
loc.channel - 1) == code_up:
|
||||
return alias
|
||||
return None
|
||||
# -- one full tick (FR-8.2.14 cycle) ---------------------------------------------
|
||||
|
||||
def tick(self, dt_ms: float | None = None) -> PlantState:
|
||||
"""One environment tick: model() -> apply(field) -> advance.
|
||||
|
||||
Deterministic: sim-time advances by TICK_MS (or dt_ms) per call
|
||||
— never from wall-clock. Attachments advance with the tick:
|
||||
degradation (§8.3) then invariants (§8.4), FR-8.2.12 order.
|
||||
"""
|
||||
dt = dt_ms if dt_ms is not None else self.TICK_MS
|
||||
state = self.observe()
|
||||
if self.is_done(state):
|
||||
return state
|
||||
values = self.model(state, dt / 1000.0)
|
||||
if values:
|
||||
self.apply(values)
|
||||
self.sim_time_ms += dt
|
||||
if self.degradation is not None:
|
||||
self.degradation.tick(dt)
|
||||
if self.invariants is not None:
|
||||
self.invariants.tick()
|
||||
return self.observe()
|
||||
|
||||
# -- episode control (FR-8.2.16) ------------------------------------------------
|
||||
|
||||
def reset(self) -> PlantState:
|
||||
"""Fresh episode: zero images, reset wear + parameters + clock
|
||||
(deterministic — identical runs replay identically, NFR-8.7.3)."""
|
||||
self.datastore.reset_images()
|
||||
self.sim_time_ms = 0.0
|
||||
if self.degradation is not None:
|
||||
for model in self.degradation.models.values():
|
||||
model.reset()
|
||||
model.diagnosed = False
|
||||
self.degradation._last_truth = {}
|
||||
if self.invariants is not None:
|
||||
self.invariants.episodes = []
|
||||
for inv in self.invariants.invariants:
|
||||
inv.active = None
|
||||
for rl in self.invariants.rate_limits:
|
||||
rl.samples = []
|
||||
rl.breached = False
|
||||
rl.peak_rate = 0.0
|
||||
self.invariants.snapshots = []
|
||||
self.invariants._last_snapshot_ms = 0.0
|
||||
return self.observe()
|
||||
|
||||
# -- clock (FR-8.2.16) ---------------------------------------------------------
|
||||
|
||||
@property
|
||||
def tick_ms(self) -> float:
|
||||
return float(self.engine.TICK_MS)
|
||||
|
||||
@property
|
||||
def sim_time_ms(self) -> float:
|
||||
return self.engine.sim_time_ms
|
||||
|
||||
# -- episode control (FR-8.2.16) ------------------------------------------------
|
||||
|
||||
def reset(self, config: dict | None = None) -> PlantState:
|
||||
"""Fresh episode: zero images, reset wear + parameters + clock
|
||||
(deterministic — identical runs replay identically, NFR-8.7.3)."""
|
||||
self.engine.reset_episode()
|
||||
return self.observe()
|
||||
|
||||
def step(self, actions: dict[str, object] | None = None):
|
||||
"""One full env tick: apply -> engine pump -> observe (FR-8.2.14).
|
||||
|
||||
Convenience for headless agents; server mode ticks the engine
|
||||
on its own scheduler and uses observe/apply separately.
|
||||
"""
|
||||
if actions:
|
||||
self.apply(actions)
|
||||
self.engine.pump()
|
||||
return self.observe()
|
||||
|
||||
# -- §8.3/§8.4 machinery (FR-8.2.16) ----------------------------------------------
|
||||
return self.TICK_MS
|
||||
|
||||
@property
|
||||
def parameters(self) -> dict[str, float]:
|
||||
deg = getattr(self.engine, "degradation", None)
|
||||
return {n: m.value for n, m in deg.models.items()} if deg else {}
|
||||
if self.degradation is None:
|
||||
return {}
|
||||
return {n: m.value for n, m in self.degradation.models.items()}
|
||||
|
||||
@property
|
||||
def invariants(self):
|
||||
return getattr(self.engine, "invariants", None)
|
||||
|
||||
def load_env(ref: str, node: VirtualNode | None = None, *,
|
||||
engine=None) -> PlantEnv:
|
||||
"""Load an environment from a module reference (FR-8.2.17).
|
||||
|
||||
Accepts ``pkg.mod.ClassName``, ``pkg.mod.factory_fn`` (returns a
|
||||
PlantEnv), or a bare ``pkg.mod`` whose module defines either a
|
||||
class named ``Env`` or a function ``make_env(...)``.
|
||||
"""
|
||||
import importlib
|
||||
|
||||
parts = ref.split(":")
|
||||
attr_path = None
|
||||
mod = None
|
||||
leaf = None
|
||||
if len(parts) == 2:
|
||||
# explicit module:attr form — ref is the WHOLE module path
|
||||
attr_path = parts[1] or None
|
||||
mod_name = parts[0]
|
||||
else:
|
||||
# no colon: try the whole ref as a module first, then as
|
||||
# pkg.mod containing an attr (e.g. ...:Class omitted)
|
||||
try:
|
||||
mod = importlib.import_module(ref)
|
||||
mod_name = ref
|
||||
except ImportError:
|
||||
mod_name, _, leaf = ref.rpartition(".")
|
||||
if not mod_name or ("." not in mod_name and attr_path is None
|
||||
and leaf is None):
|
||||
raise ScenarioError(f"--env {ref!r}: reference must include a module path")
|
||||
|
||||
if mod is None:
|
||||
try:
|
||||
mod = importlib.import_module(mod_name)
|
||||
except ImportError as exc:
|
||||
raise ScenarioError(
|
||||
f"--env {ref!r}: cannot import {mod_name!r}: {exc}")
|
||||
|
||||
obj = None
|
||||
if attr_path is not None:
|
||||
# explicit module:attr — must exist; never fall back silently
|
||||
if not hasattr(mod, attr_path):
|
||||
raise ScenarioError(
|
||||
f"--env {ref!r}: no {attr_path!r} in {mod_name!r}")
|
||||
obj = getattr(mod, attr_path)
|
||||
elif leaf and hasattr(mod, leaf):
|
||||
obj = getattr(mod, leaf)
|
||||
elif hasattr(mod, "Env"):
|
||||
obj = getattr(mod, "Env")
|
||||
elif hasattr(mod, "make_env"):
|
||||
obj = getattr(mod, "make_env")
|
||||
else:
|
||||
raise ScenarioError(
|
||||
f"--env {ref!r}: no environment found in {mod_name!r} "
|
||||
"(expected a class, Env, or make_env())")
|
||||
|
||||
env: PlantEnv
|
||||
if isinstance(obj, type) and issubclass(obj, PlantEnv):
|
||||
env = obj(node=node, engine=engine)
|
||||
elif callable(obj):
|
||||
made = obj(node=node, engine=engine) if node is not None \
|
||||
else obj(engine=engine)
|
||||
if not isinstance(made, PlantEnv):
|
||||
raise ScenarioError(f"--env {ref!r}: did not return a PlantEnv")
|
||||
env = made
|
||||
else:
|
||||
raise ScenarioError(
|
||||
f"--env {ref!r}: not a PlantEnv subclass or factory")
|
||||
return env
|
||||
Reference in New Issue
Block a user