plasma_sim_v2.py

import numpy as np
import pandas as pd
from scipy.integrate import odeint

def lorenz_system(current_state, t, sigma=10, rho=28, beta=8/3):
    """
    The Lorenz Attractor equations. 
    x = Proxy for Plasma Radial Position
    y = Proxy for Poloidal Magnetic Field
    z = Proxy for Toroidal Magnetic Field
    """
    x, y, z = current_state
    dx_dt = sigma * (y - x)
    dy_dt = x * (rho - z) - y
    dz_dt = x * y - beta * z
    return [dx_dt, dy_dt, dz_dt]

def generate_plasma_data(n_samples=5000):
    """
    Generates synthetic fusion data based on chaotic turbulence.
    """
    print(f"Generating {n_samples} physics-informed plasma samples...")
    
    # --- 1. Generate HEALTHY Data (The Attractor) ---
    # We simulate a stable plasma orbit on the 'strange attractor'
    dt = 0.01
    t_span = np.arange(0, n_samples * dt, dt)
    initial_state = [1.0, 1.0, 1.0]
    
    # Solve the differential equations
    healthy_data = odeint(lorenz_system, initial_state, t_span)
    
    # Add 47 dummy 'noise' sensors to mimic a 50-sensor array
    # Real sensors are just correlated versions of the main physics variables
    noise_sensors = np.random.normal(0, 0.5, (n_samples, 47))
    X_healthy = np.hstack([healthy_data, noise_sensors])
    
    # --- 2. Generate ANOMALOUS Data (The Disruption) ---
    # We simulate a 'Locked Mode' by changing the physics parameter 'rho'
    # This causes the plasma to drift off the stable manifold
    t_span_anom = np.arange(0, (n_samples // 10) * dt, dt)
    
    # rho=15 changes the topology of the attractor (Disruption Precursor)
    anomalous_data = odeint(lorenz_system, initial_state, t_span_anom, args=(10, 15, 8/3))
    
    noise_sensors_anom = np.random.normal(0, 0.5, (len(anomalous_data), 47))
    X_anomalous = np.hstack([anomalous_data, noise_sensors_anom])

    # --- 3. Save to CSV ---
    df_healthy = pd.DataFrame(X_healthy, columns=[f'sensor_{i}' for i in range(50)])
    df_healthy['label'] = 0  # 0 = Healthy
    
    df_anomalous = pd.DataFrame(X_anomalous, columns=[f'sensor_{i}' for i in range(50)])
    df_anomalous['label'] = 1  # 1 = Disruption
    
    df_final = pd.concat([df_healthy, df_anomalous], ignore_index=True)
    
    output_file = "physics_informed_data.csv"
    df_final.to_csv(output_file, index=False)
    print(f"Success! Saved physics-informed data to {output_file}")
    print("Shape:", df_final.shape)

if __name__ == "__main__":
    generate_plasma_data()