248 lines
10 KiB
Python
248 lines
10 KiB
Python
import gymnasium as gym
|
|
import numpy as np
|
|
from gymnasium import spaces
|
|
import ctypes
|
|
from collections import deque
|
|
from typing import Tuple
|
|
import sys
|
|
import os
|
|
import matplotlib.pyplot as plt
|
|
import queue
|
|
|
|
os.environ["OMP_NUM_THREADS"] = "1"
|
|
os.environ["MKL_NUM_THREADS"] = "1"
|
|
|
|
current_dir = os.path.dirname(os.path.abspath("__file__"))
|
|
parent_dir = os.path.abspath(os.path.join(current_dir, os.pardir))
|
|
sys.path.append(parent_dir)
|
|
from CelerisLab import FlowField
|
|
from CelerisLab import utils
|
|
|
|
config_cuda = utils.load_cuda_config(
|
|
os.path.join(parent_dir, "configs", "config_cuda.json")
|
|
)
|
|
config_field = utils.load_flow_field_config(
|
|
os.path.join(parent_dir, "configs", "config_flowfield.json")
|
|
)
|
|
|
|
S_DIM, A_DIM = 12, 3
|
|
U0 = config_field.velocity
|
|
T0 = 1000
|
|
SAMPLE_INTERVAL = 800
|
|
FIFO_LEN = 120
|
|
CONV_LEN = 60
|
|
MAX_STEPS = 720
|
|
if config_field.data_type == "FP32":
|
|
DATA_TYPE = np.float32
|
|
else:
|
|
raise ValueError(f"Unsupported data type {config_field.data_type}.")
|
|
|
|
|
|
class CustomEnv(gym.Env):
|
|
"""Custom Environment that follows gym interface."""
|
|
|
|
metadata = {"render_modes": ["human"], "render_fps": T0 / SAMPLE_INTERVAL}
|
|
|
|
def __init__(self, device_id=0):
|
|
super().__init__()
|
|
self.action_space = spaces.Box(low=-1, high=1, shape=(A_DIM,), dtype=DATA_TYPE)
|
|
self.observation_space = spaces.Box(
|
|
low=-1, high=1, shape=(S_DIM,), dtype=DATA_TYPE
|
|
)
|
|
self.fifo_states = deque(maxlen=FIFO_LEN)
|
|
self.fifo_target = deque(maxlen=FIFO_LEN)
|
|
self.fifo_forces = deque(maxlen=FIFO_LEN)
|
|
self.force_norm_fact = 1.0
|
|
self.sens_norm_fact = np.ones(6, dtype=DATA_TYPE)
|
|
self.sens_deviation = np.zeros(6, dtype=DATA_TYPE)
|
|
self.reward_sim_now = 0.0
|
|
self.reward_yaw = 0.0
|
|
self.reward_sim = 0.0
|
|
self.current_step = 0
|
|
|
|
self.flow_field = FlowField(config_field, config_cuda, device_id)
|
|
L0 = 20
|
|
U0 = config_field.velocity
|
|
NX = self.flow_field.FIELD_SHAPE[0]
|
|
NY = self.flow_field.FIELD_SHAPE[1]
|
|
center: Tuple[float, float, float] = (10 * L0, (NY - 1) / 2, 0)
|
|
self.flow_field.add_cylinder(center, L0)
|
|
center: Tuple[float, float, float] = (25 * L0, (NY - 1) / 2 + 2 * L0, 0)
|
|
self.flow_field.add_sensor(center, L0 / 4)
|
|
center: Tuple[float, float, float] = (25 * L0, (NY - 1) / 2, 0)
|
|
self.flow_field.add_sensor(center, L0 / 4)
|
|
center: Tuple[float, float, float] = (25 * L0, (NY - 1) / 2 - 2 * L0, 0)
|
|
self.flow_field.add_sensor(center, L0 / 4)
|
|
center: Tuple[float, float, float] = (40 * L0, (NY - 1) / 2 + 2 * L0, 0)
|
|
self.flow_field.add_sensor(center, L0 / 4)
|
|
center: Tuple[float, float, float] = (40 * L0, (NY - 1) / 2, 0)
|
|
self.flow_field.add_sensor(center, L0 / 4)
|
|
center: Tuple[float, float, float] = (40 * L0, (NY - 1) / 2 - 2 * L0, 0)
|
|
self.flow_field.add_sensor(center, L0 / 4)
|
|
self.flow_field.run(int(4*NX/U0), np.zeros(7, dtype=DATA_TYPE))
|
|
|
|
for i in range(FIFO_LEN):
|
|
self.flow_field.run(SAMPLE_INTERVAL, np.zeros(7, dtype=DATA_TYPE))
|
|
self.fifo_target.append(self.flow_field.obs.copy()[2:8])
|
|
self.fifo_states.append(self.flow_field.obs.copy()[8:14])
|
|
|
|
# target = np.array(self.fifo_target)[:, 0]
|
|
# state = np.array(self.fifo_states)[:, 0]
|
|
# target_mean = np.mean(target)
|
|
# state_mean = np.mean(state)
|
|
# correlation = np.correlate(target - target_mean, state - state_mean, "full")
|
|
# lags = np.arange(-len(target) + 1, len(target))
|
|
# self.LAG = lags[np.argmax(correlation)]
|
|
self.LAG = -9
|
|
|
|
self.flow_field.apply_ddf()
|
|
center: Tuple[float, float, float] = (30 * L0, (NY - 1) / 2, 0)
|
|
self.flow_field.add_cylinder(center, L0 / 2)
|
|
center: Tuple[float, float, float] = (31.3 * L0, (NY - 1) / 2 + 0.75 * L0, 0)
|
|
self.flow_field.add_cylinder(center, L0 / 2)
|
|
center: Tuple[float, float, float] = (31.3 * L0, (NY - 1) / 2 - 0.75 * L0, 0)
|
|
self.flow_field.add_cylinder(center, L0 / 2)
|
|
self.flow_field.run(int(4*NX/U0), np.zeros(10, dtype=DATA_TYPE))
|
|
self.flow_field.get_ddf()
|
|
|
|
for i in range(FIFO_LEN):
|
|
self.flow_field.run(SAMPLE_INTERVAL, np.zeros(10, dtype=DATA_TYPE))
|
|
self.fifo_target.append(self.flow_field.obs.copy()[2:8])
|
|
self.fifo_states.append(self.flow_field.obs.copy()[8:14])
|
|
self.fifo_forces.append(self.flow_field.obs.copy()[14:20])
|
|
|
|
self.save_target = self.fifo_target.copy()
|
|
self.save_states = self.fifo_states.copy()
|
|
self.save_forces = self.fifo_forces.copy()
|
|
self.flow_field.get_ddf()
|
|
|
|
temp_states = np.array(self.fifo_states)
|
|
self.force_norm_fact = 6 * np.max(np.abs(np.array(self.fifo_forces)))
|
|
for i in range(6):
|
|
self.sens_deviation[i] = np.mean(temp_states[:, i])
|
|
self.sens_norm_fact[i] = 5 * np.max(np.abs(temp_states[:, i] - self.sens_deviation[i]))
|
|
|
|
|
|
def step(self, action):
|
|
assert self.action_space.contains(action), "%r (%s) invalid" % (
|
|
action,
|
|
type(action),
|
|
)
|
|
|
|
# barrier = threading.Barrier(2)
|
|
result_queue = queue.Queue()
|
|
|
|
def run_flow_field(action):
|
|
self.flow_field.context.push()
|
|
U0 = config_field.velocity
|
|
try:
|
|
temp = np.zeros(10, dtype=DATA_TYPE)
|
|
temp[7:10] = np.array((action*8+[0,-4,4])*U0, dtype=DATA_TYPE)
|
|
self.flow_field.run(SAMPLE_INTERVAL, temp)
|
|
finally:
|
|
self.flow_field.context.pop()
|
|
# barrier.wait()
|
|
self.fifo_target.append(self.flow_field.obs.copy()[2:8])
|
|
self.fifo_states.append(self.flow_field.obs.copy()[8:14])
|
|
self.fifo_forces.append(self.flow_field.obs.copy()[14:20])
|
|
|
|
def proc_data():
|
|
target = np.array(self.fifo_target)
|
|
states = np.array(self.fifo_states)
|
|
forces = np.array(self.fifo_forces)[-1, :] / self.force_norm_fact
|
|
cd = (forces[0] + forces[2] + forces[4]) / 3
|
|
cl = (forces[1] + forces[3] + forces[5]) / 3
|
|
ave_v = np.mean(states[:, 1] + states[:, 3] + states[:, 5]) / 3
|
|
targ = (target[-1, :] - self.sens_deviation) / self.sens_norm_fact
|
|
sens = (states[-1, :] - self.sens_deviation) / self.sens_norm_fact
|
|
|
|
similarities = 0.0
|
|
sim_now = 0.0
|
|
|
|
def calc_sim(target, state, lag):
|
|
target_mean = np.mean(target)
|
|
state_mean = np.mean(state)
|
|
target_std = np.std(target)
|
|
|
|
aligned_state = np.roll(state, lag)
|
|
|
|
if lag >= 0:
|
|
seq_target = target[-CONV_LEN:]-target_mean
|
|
seq_state = aligned_state[-CONV_LEN:]-state_mean
|
|
else:
|
|
seq_target = target[:CONV_LEN]-target_mean
|
|
seq_state = aligned_state[:CONV_LEN]-state_mean
|
|
|
|
seq_diff = seq_target - seq_state
|
|
sim_cor = 10*(np.corrcoef(seq_target, seq_state)[0, 1] - 1)
|
|
sim_div = -np.abs((target_mean - state_mean) / target_std * 0.75)
|
|
sim_amp = -np.abs(np.std(seq_diff) / target_std * 2)
|
|
|
|
return np.exp((sim_cor + sim_div + sim_amp) / 3)
|
|
|
|
for i in range(0, 6):
|
|
target_seq = (target[:, i] - self.sens_deviation[i]) / self.sens_norm_fact[i]
|
|
state_seq = (states[:, i] - self.sens_deviation[i]) / self.sens_norm_fact[i]
|
|
similarities += calc_sim(target_seq, state_seq, -self.LAG) / 6
|
|
sim_now += np.abs(target_seq[self.LAG-1] - state_seq[-1]) / 6
|
|
|
|
self.reward_sim_now = np.exp(-sim_now*10)
|
|
self.reward_yaw = 1 - np.exp(-np.abs(ave_v * 10))
|
|
self.reward_sim = similarities
|
|
reward = np.clip(0.5 * self.reward_sim_now - 0.3 * self.reward_yaw + 0.8 * self.reward_sim, 0, 1)
|
|
# barrier.wait()
|
|
result_queue.put((np.hstack([targ, sens]), reward))
|
|
|
|
run_flow_field(action)
|
|
proc_data()
|
|
observation, reward = result_queue.get()
|
|
|
|
truncated = bool(np.any(observation > 1) or np.any(observation < -1))
|
|
observation = np.clip(observation, -1, 1)
|
|
self.current_step += 1
|
|
done = self.current_step >= MAX_STEPS
|
|
return observation, float(reward), done, truncated, {}
|
|
|
|
def reset(self, seed=None):
|
|
self.flow_field.apply_ddf()
|
|
self.fifo_target = self.save_target.copy()
|
|
self.fifo_states = self.save_states.copy()
|
|
self.fifo_forces = self.save_forces.copy()
|
|
self.current_step = 0
|
|
return np.zeros(S_DIM, dtype=np.float32), {}
|
|
|
|
def render(self, mode="human"):
|
|
NX = self.flow_field.FIELD_SHAPE[0]
|
|
NY = self.flow_field.FIELD_SHAPE[1]
|
|
self.flow_field.get_ddf()
|
|
ddf_plot = self.flow_field.ddf.copy().reshape((9, NY, NX)).transpose(2, 1, 0)
|
|
ux = (ddf_plot[:, :, 1] + ddf_plot[:, :, 5] + ddf_plot[:, :, 8] - ddf_plot[:, :, 3] - ddf_plot[:, :, 6] - ddf_plot[:, :, 7]) / U0
|
|
uy = (ddf_plot[:, :, 2] + ddf_plot[:, :, 5] + ddf_plot[:, :, 6] - ddf_plot[:, :, 4] - ddf_plot[:, :, 7] - ddf_plot[:, :, 8]) / U0
|
|
speed = np.sqrt(ux**2 + uy**2)
|
|
plt.figure(figsize=(10, 5))
|
|
plt.imshow(speed.T, origin='lower', cmap='viridis', extent=[0, NX, 0, NY])
|
|
plt.colorbar(label='Speed')
|
|
plt.title('Scalar Velocity Field')
|
|
plt.xlabel('X')
|
|
plt.ylabel('Y')
|
|
plt.tight_layout()
|
|
plt.show()
|
|
|
|
def save_field(self, filename):
|
|
NX = self.flow_field.FIELD_SHAPE[0]
|
|
NY = self.flow_field.FIELD_SHAPE[1]
|
|
self.flow_field.get_ddf()
|
|
ddf_plot = self.flow_field.ddf.copy().reshape((9, NY, NX)).transpose(2, 1, 0)
|
|
flag_plot = self.flow_field.flag.copy().reshape((NY, NX)).transpose(1, 0)
|
|
ux = (ddf_plot[:, :, 1] + ddf_plot[:, :, 5] + ddf_plot[:, :, 8] - ddf_plot[:, :, 3] - ddf_plot[:, :, 6] - ddf_plot[:, :, 7]) / U0
|
|
uy = (ddf_plot[:, :, 2] + ddf_plot[:, :, 5] + ddf_plot[:, :, 6] - ddf_plot[:, :, 4] - ddf_plot[:, :, 7] - ddf_plot[:, :, 8]) / U0
|
|
with open(os.path.join(parent_dir, "output", filename), "w") as f:
|
|
f.write("Title= \"LBM 2D\"\r\n")
|
|
f.write("VARIABLES= \"X\",\"Y\",\"flag\",\"U\",\"V\",\r\n")
|
|
f.write(f"ZONE T= \"BOX\",I= {NX},J= {NY},F=POINT\r\n")
|
|
for j in range(NY):
|
|
for i in range(NX):
|
|
f.write(f"{i},{j},{flag_plot[i, j]},{ux[i, j]},{uy[i, j]}\r\n")
|
|
|
|
def close(self):
|
|
self.flow_field.__del__() |