Compares each sensor's latest reading against fixed IEC limits — no
learning, instantly explainable, highest trust. At/above the warning limit is flagged; at/above
critical it's urgent.
Parameter
Latest
Warn
Critical
Status
MOISTURE-H2O PHASE C (PPM)
2.0 ppm
10.0
30.0
OK
MOISTURE-H2O PHASE B (PPM)
2.0 ppm
10.0
30.0
OK
HYDROGEN-H2 PHASE B (PPM)
2.0 ppm
100.0
700.0
OK
HYDROGEN-H2 PHASE C (PPM)
2.0 ppm
100.0
700.0
OK
MOISTURE-H2O PHASE A (PPM)
3.0 ppm
10.0
30.0
OK
HYDROGEN-H2 PHASE A (PPM)
2.0 ppm
100.0
700.0
OK
COMMON WINDING TEMP PHASE C
50.0 °C
98.0
120.0
OK
SERIES WINDING TEMP PHASE A
51.0 °C
98.0
120.0
OK
BOTTOM OIL TEMPERATURE PHASE C
33.0 °C
75.0
95.0
OK
COMMON WINDING TEMP PHASE A
52.0 °C
98.0
120.0
OK
TERTIARY WINDING TEMP PHASE C
50.0 °C
98.0
120.0
OK
BOTTOM OIL TEMPERATURE PHASE B
34.0 °C
75.0
95.0
OK
SERIES WINDING TEMP PHASE B
52.0 °C
98.0
120.0
OK
BOTTOM OIL TEMPERATURE PHASE A
34.0 °C
75.0
95.0
OK
TERTIARY WINDING TEMP PHASE B
52.0 °C
98.0
120.0
OK
COMMON WINDING TEMP PHASE B
53.0 °C
98.0
120.0
OK
AMBIENT TEMP
32.0 °C
40.0
50.0
OK
SERIES WINDING TEMP PHASE C
50.0 °C
98.0
120.0
OK
TERTIARY WINDING TEMP PHASE A
51.0 °C
98.0
120.0
OK
② Statistical · Z-Score Consensus
Learns each sensor's own normal range, then flags points by a
2-of-3 consensus of global Z-score, rolling Z-score, and IQR — catching drift and spikes even while
still under the IEC limit.
Sensor
Anomalous pts
of total
Rate
MOISTURE-H2O PHASE C (PPM)
4
84
4.8%
③ Isolation Forest · Multivariate ML
An unsupervised model that learns the joint normal pattern
across all sensors at once — so it can flag a combination that's abnormal even when every sensor
alone looks fine (e.g. winding hot while load is light).
MULTIVARIATE CONTEXT · 24/100
Singled out the 4 most-unusual of
84 multivariate snapshots — it always isolates the oddest sensor
combinations by design, so this is a context signal, not a standalone verdict
(the overall priority above fuses all four methods). The flagged snapshots deviate most on:
(multivariate = all sensors viewed together, not one at a time.)
MOISTURE-H2O PHASE C (PPM)+4.5σ
HYDROGEN-H2 PHASE A (PPM)+0.0σ
MOISTURE-H2O PHASE A (PPM)+0.0σ
Likely drivers (approximate) — Isolation Forest gives no exact per-sensor
attribution; ranked by mean deviation of the flagged snapshots vs the window normal.
④ DGA · Duval Triangle + IEC Ratios
Identifies the type of fault from dissolved gases — corona,
sparking, arcing, or overheating — using the Duval Triangle and IEC 60599 gas ratios.
CO
0
ppm
H2
2
ppm
CH4
0
ppm
CO2
0
ppm
C2H2
0
ppm
C2H4
0
ppm
C2H6
0
ppm
The three combustible gases are reduced to their
relative % of CH₄ / C₂H₄ / C₂H₂ (they sum to 100). That single point is plotted on the
Duval Triangle — the zone it lands in names the fault:
No hydrocarbon gases (CH₄/C₂H₄/C₂H₂)
present — nothing to plot on the Duval Triangle.
PDPartial discharge (corona)
D1Discharge of low energy (sparking)
D2Discharge of high energy (arcing)
T1Thermal fault below 300 C
T2Thermal fault 300-700 C
T3Thermal fault above 700 C
DTMixed thermal and electrical fault
IEC 60599 ratio cross-check
R1 = C₂H₂ / C₂H₄0.0
R2 = CH₄ / H₂0.0
R5 = C₂H₄ / C₂H₆0.0
Duval Triangle
ND
No fault detected / not determinable
IEC 60599 ratios
ND
No fault detected / not determinable
Two independent methods, shown side by side; the DGA score uses the
more severe of the two. ND = no fault determinable.