File size: 4,739 Bytes
572c4ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
from __future__ import annotations

import json
from pathlib import Path

import numpy as np
import pandas as pd
from datasets import Dataset

PROJECT_DIR = Path(__file__).resolve().parent
DATA_DIR = PROJECT_DIR / "data"


def build_device(device_id: int, steps: int, seed: int) -> pd.DataFrame:
    rng = np.random.default_rng(seed + device_id)
    time = np.arange(steps)
    phase = device_id * 0.37
    load = 0.55 + 0.27 * np.sin(time / 93 + phase) + 0.08 * np.sin(time / 17)
    actuator = np.clip(48 + load * 42 + rng.normal(0, 1.5, steps), 0, 100)
    temperature = 34 + load * 26 + rng.normal(0, 0.7, steps) + device_id * 0.12
    pressure = 72 + load * 15 + rng.normal(0, 0.8, steps)
    vibration = 0.8 + load**2 * 2.4 + rng.normal(0, 0.08, steps)
    current = 5.2 + load * 13 + rng.normal(0, 0.25, steps)
    flow = 18 + actuator * 0.42 + rng.normal(0, 0.6, steps)
    packet_rate = 110 + load * 38 + rng.normal(0, 4, steps)
    command_rate = 4 + np.abs(np.gradient(actuator)) * 0.38 + rng.normal(0, 0.2, steps)
    labels = np.zeros(steps, dtype=np.int8)
    anomaly_type = np.full(steps, "normal", dtype=object)

    anomaly_names = [
        "sensor_drift",
        "actuator_mismatch",
        "vibration_fault",
        "pressure_spike",
        "network_flood",
    ]
    starts = rng.choice(np.arange(250, steps - 250), size=18, replace=False)
    for index, start in enumerate(starts):
        length = int(rng.integers(18, 55))
        stop = min(start + length, steps)
        kind = anomaly_names[index % len(anomaly_names)]
        labels[start:stop] = 1
        anomaly_type[start:stop] = kind
        ramp = np.linspace(0, 1, stop - start)
        if kind == "sensor_drift":
            temperature[start:stop] += 8 * ramp
        elif kind == "actuator_mismatch":
            flow[start:stop] -= 12 + actuator[start:stop] * 0.12
        elif kind == "vibration_fault":
            vibration[start:stop] += 3.5 + rng.normal(0, 0.5, stop - start)
        elif kind == "pressure_spike":
            pressure[start:stop] += 18 * np.sin(np.linspace(0, np.pi, stop - start))
        else:
            packet_rate[start:stop] += 260 + rng.normal(0, 18, stop - start)
            command_rate[start:stop] += 14

    return pd.DataFrame(
        {
            "device_id": device_id,
            "time": time,
            "temperature": temperature,
            "pressure": pressure,
            "vibration": vibration,
            "current": current,
            "flow": flow,
            "packet_rate": packet_rate,
            "command_rate": command_rate,
            "actuator_position": actuator,
            "label": labels,
            "anomaly_type": anomaly_type,
        }
    )


def add_features(frame: pd.DataFrame) -> pd.DataFrame:
    sensors = [
        "temperature",
        "pressure",
        "vibration",
        "current",
        "flow",
        "packet_rate",
        "command_rate",
        "actuator_position",
    ]
    groups = frame.groupby("device_id", sort=False)
    for column in sensors:
        frame[f"{column}_delta"] = groups[column].diff().fillna(0)
        rolling = groups[column].rolling(24, min_periods=4)
        mean = rolling.mean().reset_index(level=0, drop=True)
        std = rolling.std().reset_index(level=0, drop=True).fillna(1).clip(lower=1e-3)
        frame[f"{column}_z24"] = ((frame[column] - mean) / std).fillna(0)
    frame["flow_actuator_residual"] = frame["flow"] - (
        18 + frame["actuator_position"] * 0.42
    )
    frame["power_proxy"] = frame["current"] * frame["actuator_position"] / 100
    return frame


def main() -> None:
    DATA_DIR.mkdir(parents=True, exist_ok=True)
    frame = pd.concat(
        [build_device(device, steps=5000, seed=2026) for device in range(12)],
        ignore_index=True,
    )
    frame = add_features(frame)
    split = np.where(
        frame["device_id"] <= 7,
        "train",
        np.where(frame["device_id"] <= 9, "validation", "test"),
    )
    frame["split"] = split
    manifest = {}
    for split_name in ["train", "validation", "test"]:
        split_frame = frame[frame["split"] == split_name].reset_index(drop=True)
        path = DATA_DIR / f"{split_name}.parquet"
        Dataset.from_pandas(split_frame, preserve_index=False).to_parquet(path)
        manifest[split_name] = {
            "rows": len(split_frame),
            "devices": sorted(split_frame["device_id"].unique().tolist()),
            "anomaly_rate": float(split_frame["label"].mean()),
            "path": path.name,
        }
    (DATA_DIR / "manifest.json").write_text(
        json.dumps(manifest, indent=2),
        encoding="utf-8",
    )
    print(json.dumps(manifest, indent=2))


if __name__ == "__main__":
    main()