Low cost · Cold start · Global Reach

Detect drivetrain faults
days before failure.

TorqueScope identifies emerging faults in wind turbines up to 59 hours before breakdown - using only the SCADA data you already collect. No new sensors. No historical failure data. No ML team required.

TORQUESCOPE DRIVETRAIN · FIG 1A DWG-001 · REV A H ROTOR ∅ GEARBOX LS MONITOR ANOMALY ↑ T − 32.3 HRS MAIN BEARING WIND 0 50 m
Method

Physics-grounded detection,
not black-box ML.

Two independent detectors, each grounded in physical principles, must agree before an alarm is raised. Neither requires fault examples. Neither requires domain expertise to deploy.

Step 01
Lomb–Scargle Periodogram

A 7-day sliding window over temperature sensors is decomposed into its frequency components. Healthy drivetrain signals show stable periodic structure - rotor harmonics, diurnal thermal cycles, mechanical resonances. Deviation from this baseline triggers the heuristic score.

score ← f(amplitude_ratio, residual_ratio, CV)
Step 02
Normal Behaviour Model

Expected temperature is modelled as a function of power output and ambient conditions across a 200-bin operational grid (20 × 10 bins). Residuals from this physics-informed lookup reveal anomalous thermal behaviour invisible in raw sensor streams.

residual ← T_actual − T_expected(P, T_amb)
Step 03
Hybrid Criticality Engine

When both detectors agree, confidence is amplified. A criticality counter accumulates evidence over time, rising on anomaly readings and decaying otherwise. Single-detector signals are suppressed by 50%, converting noise into structured forewarning.

alarm := criticality ≥ 72
Evidence

Four faults. Three farms.
All detected early.

Validated against the CARE benchmark - 95 datasets, 3 anonymised wind farms, ground-truth fault timestamps confirmed by maintenance personnel. Lead time measured from first TorqueScope alarm to documented fault onset.

# Fault Description Farm Sensors Lead Time
01 Gearbox failureDrivetrain · bearing degradation Farm A - Onshore, Portugal 86 32.3hours
02 Yaw grease pump failureYaw system · lubrication loss Farm C - Offshore, Germany 957 50.0hours
03 Gear oil pump coupling defectLubrication · coupling wear Farm C - Offshore, Germany 957 59.3hours
04 Main bearing damageBearing · rolling element fatigue Farm B - Offshore, Germany 257 29.5hours
NOTE
Lead times reference ground-truth maintenance records, not model confidence thresholds. "Fault confirmed" denotes the timestamp at which wind farm personnel documented the physical failure - not when the algorithm assigned a probability.
SEE IT WORKING

Three ways to explore TorqueScope

REAL COMMERCIAL DATA

Fleet Health

41 turbines across Kelmarsh, Penmanshiel, and Hill of Towie. Real SCADA from three UK wind farms — no synthetic data, no simulation.

Senvion MM92 & MM82 · Siemens SWT-2.3-82 Northamptonshire · Scottish Borders · Aberdeenshire CC-BY-4.0 open dataset
View fleet →
FAULT DETECTION · EARLIEST RESULT

Live Detection Demo

Watch TorqueScope detect a gearbox failure 59.3 hours before confirmation. Four real fault scenarios, streaming in real time.

CARE benchmark · 95 datasets · 3 farms Gearbox · Yaw · Main bearing 29–59 hour lead times
Run demo →
GLOBAL PORTFOLIO

Resource Intelligence

15 wind farms across 10 countries. NASA POWER climate data, Weibull analysis, generation projections, and side-by-side comparison.

7.5 GW total capacity · 15 farms Wind rose · Weibull · Monthly generation SCADA performance gap (3 farms)
Explore portfolio →
Signal

Hybrid anomaly score -
Scenario 01 (Gearbox failure)

Hybrid score across the prediction window for Farm A, Event 10. The criticality counter crosses threshold 72 a full 32.3 hours before the documented fault onset.

Hybrid anomaly score · Farm A · Asset 10 · CARE Event 10
Score
Threshold 0.475
First alert
Fault confirmed
Research

Built on Ab Astris
cross-domain signal detection.

The Lomb-Scargle periodogram at TorqueScope's core is not wind-specific. Ab Astris validates the same frequency-domain approach across six independent physical domains — proving that physics-constrained periodic signals produce stable, detectable signatures without domain-specific training.

Zenodo 2026 6 domains 3 negative controls

Ab Astris: Cross-Domain Periodic Signal Detection via Lomb-Scargle Periodograms

Validated on oceanographic tides (6 NOAA stations, 24/24 constituents detected), industrial bearings (CWRU dataset, 0.008% CV), volcanic tremor (4 volcanoes), structural resonance (CESMD buildings + Z24 bridge), and astronomical variable stars — with negative controls on cryptocurrency, heart rate variability, and sunspot data confirming the CV discriminator rejects non-physics-constrained signals.

Read the paper on Zenodo →
Advantage

Zero hardware.
Zero historical failures.
Operational from day one.

CMS installations require hardware procurement, site visits, and years of failure data to train on. TorqueScope connects to your existing historian in days.

  • No new sensors required
    CMS hardware costs €5,000–15,000 per turbine and requires a site visit for installation and calibration. TorqueScope works from any SCADA historian export.
  • Zero-shot from day one
    The Normal Behaviour Model calibrates on healthy baseline operation alone. There is no requirement to have ever observed a fault - making it viable for new farms, new markets, and operators of any size.
  • Earliness, not just detection rate
    Industry benchmarks reward detection rate. TorqueScope is designed to maximise how early. A fault caught 59 hours offshore is a planned maintenance window - not an emergency €200K repair and multi-day downtime event.
  • Interpretable physics, not opaque models
    Every alarm traces back to specific sensors and physical quantities. No fleet-wide training, no cross-operator data sharing. Interpretable outputs compatible with existing O&M workflows.
CapabilityTypical CMSTorqueScope
New sensors neededYes - €5–15K/turbineNone
Historical fault dataRequiredNot required
Deployment timelineMonthsDays
Viable on small farmsUneconomicYes
Alarm interpretabilityBlack-boxSensor-level
Max validated lead timeVaries59.3 hours
CARE
Benchmark score: 0.588 on the CARE metric across 95 datasets. Autoencoder baseline: 0.66. The 11% gap reflects missed weak-signature faults - an expected and documented limitation of a zero-training-data approach.

Connect your farm.
Get your first alert.

No contract, no hardware order, no ML team. Validated on three real wind farms across two countries. Operational within days from your existing SCADA historian.

Open Demo Investment Proposal Read the Paper