Hugging Face's logo

alirezaaminzadeh
/
refineryguard-lstm-ae

Tabular Classification
Scikit-learn
Joblib
ONNX
oil-gas
petrochemical
refinery
process-anomaly-detection
tennessee-eastman
lstm-autoencoder
isolation-forest
time-series
isa-18.2
aria-ai
Eval Results (legacy)
Model card Files
xet
 Community
How to use from the
Use from the
Scikit-learn library
from huggingface_hub import hf_hub_download
import joblib
model = joblib.load(
	hf_hub_download("alirezaaminzadeh/refineryguard-lstm-ae", "sklearn_model.joblib")
)
# only load pickle files from sources you trust
# read more about it here https://skops.readthedocs.io/en/stable/persistence.html

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"]

Related

MIT · Aria AI Engineering Team

Downloads last month
-
Inference Providers NEW
Tabular Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train alirezaaminzadeh/refineryguard-lstm-ae

Space using alirezaaminzadeh/refineryguard-lstm-ae 1

Collection including alirezaaminzadeh/refineryguard-lstm-ae

Evaluation results

  • pca_detection_rate on Tennessee Eastman Process (Braatz files)
    self-reported
    1.000
  • pca_mean_ttd_hours on Tennessee Eastman Process (Braatz files)
    self-reported
    1.510
  • pca_mean_far_pre_fault on Tennessee Eastman Process (Braatz files)
    self-reported
    0.025
  • mean_alarm_reduction_rate on Tennessee Eastman Process (Braatz files)
    self-reported
    0.930