Link Dataset, Model, Space, and Collection; add eval model-index

136d039 verified 6 days ago

3.46 kB

license: mit
library_name: sklearn
pipeline_tag: tabular-classification
datasets:
  - alirezaaminzadeh/refineryguard-tep-features
tags:
  - oil-gas
  - petrochemical
  - refinery
  - process-anomaly-detection
  - tennessee-eastman
  - lstm-autoencoder
  - isolation-forest
  - time-series
  - isa-18.2
  - aria-ai
model-index:
  - name: refineryguard-lstm-ae
    results:
      - task:
          type: tabular-classification
          name: TEP fault detection (held-out Braatz test, 21 faults)
        dataset:
          name: Tennessee Eastman Process (Braatz files)
          type: alirezaaminzadeh/refineryguard-tep-features
        metrics:
          - type: pca_detection_rate
            value: 1
          - type: pca_mean_ttd_hours
            value: 1.51
          - type: pca_mean_far_pre_fault
            value: 0.025
          - type: mean_alarm_reduction_rate
            value: 0.93

RefineryGuard LSTM-AE

CPU-friendly process-anomaly bundle for the Tennessee Eastman Process:

lstm_ae.onnx — LSTM autoencoder (reconstruction error = anomaly score)
isolation_forest.joblib — window mean/std baseline
pca.joblib — 90% variance reconstruction baseline (operational primary detector)
fault_classifier.joblib — 22-class TEP fault id (HistGradientBoosting)
scaler.joblib / normal_stats.joblib / thresholds.joblib
eval_results.json — held-out Braatz test protocol

Data honesty

Trained only on TEP simulation (Downs & Vogel 1993; Braatz evaluation files). Not a live refinery model. Thresholds are 99th percentiles of normal reconstruction / IF scores on IDV(0) train windows. Recalibrate on each plant before any operational use.

Operational alerts use PCA reconstruction (lowest usable false-alarm rate among LSTM / PCA / Isolation Forest). LSTM-AE is kept for scoring and per-tag attribution; it is not the primary alarm because its pre-fault FAR on this protocol is high (~0.58).

Held-out protocol (fault after 8 h)

Detector	Detection (21 faults)	Mean TTD (h)	Mean FAR (pre-fault / IDV0)
PCA reconstruction (primary)	100%	1.51	0.025
Isolation Forest	100%	1.02	0.126
LSTM-AE	100%	0.06	0.585
Univariate 3σ baseline	100%	1.07	0.072

Mean alarm reduction (PCA incidents vs raw 3σ tag alarms): 93%. IDV(3), IDV(9), IDV(15) are weakly observable in the TEP literature.

How to score a window

import joblib, numpy as np, onnxruntime as ort
scaler = joblib.load("scaler.joblib")
thr = joblib.load("thresholds.joblib")
sess = ort.InferenceSession("lstm_ae.onnx")
# x: (T, 52) raw tags in xmeas_1..xmv_11 order, T>=20
from numpy.lib.stride_tricks import sliding_window_view
scaled = scaler.transform(x)
windows = sliding_window_view(scaled, (20, 52))[:, 0]
recon = sess.run(None, {"window": windows.astype("float32")})[0]
score = ((windows - recon) ** 2).mean(axis=(1, 2))
alert = score > thr["lstm"]

Dataset: alirezaaminzadeh/refineryguard-tep-features
Space: alirezaaminzadeh/refineryguard-process-anomaly
Collection: RefineryGuard
Product: aria-ai.ir

MIT · Aria AI Engineering Team

alirezaaminzadeh
/

refineryguard-lstm-ae

RefineryGuard LSTM-AE

Data honesty

Held-out protocol (fault after 8 h)

How to score a window

Related