Feature
Anomaly Detection
An LSTM autoencoder continuously monitors 13 sensor-derived features and raises precision alerts the moment equipment behaviour deviates from normal — typically in under 2 seconds.
87.3%
F1 Score
91.2%
Precision
83.7%
Recall
<2s
Detection latency
How it works
01
Feature engineering
13 engineered features including temp_diff, power, and thermal ratio are computed from raw 5-sensor input.
02
Z-score normalisation
Each feature is normalised using training-set statistics before inference — preventing scale bias in LSTM reconstruction.
03
LSTM reconstruction
A (None, 10, 13) autoencoder reconstructs the input window. Elevated reconstruction error signals anomalous behaviour.
04
Ensemble scoring
0.6×LSTM_norm + 0.4×RF_prob = ensemble score. Threshold >0.5 triggers an alert with severity classification.
Input features (13)
| Feature | Source | Description |
|---|---|---|
| air_temperature | Raw sensor | Ambient air temperature (K) |
| process_temperature | Raw sensor | Process temperature (K) |
| rotational_speed | Raw sensor | Spindle RPM |
| torque | Raw sensor | Torque (Nm) |
| tool_wear | Raw sensor | Cumulative tool wear (min) |
| temp_diff | Engineered | process_temp − air_temp |
| power | Engineered | torque × rotational_speed × constant |
| thermal | Engineered | temp_diff / process_temp |
| type_H | Encoded | Machine type high quality |
| type_L | Encoded | Machine type low quality |
| type_M | Encoded | Machine type medium quality |
| rpm_torque_ratio | Engineered | rotational_speed / torque |
| wear_temp_interact | Engineered | tool_wear × temp_diff |
Severity classification
Critical
Score ≥ 0.8
High
Score 0.6 – 0.8
Medium
Score 0.4 – 0.6
Normal
Score < 0.4
Next featureMulti-Agent RCA →