DMK · Motor Monitoring System

Your motor, live on screen.

The DMK gives you a real-time window into your motor's electrical behaviour: 3-phase voltages, currents, FFT analysis rendered as an oscilloscope, live, at up to 250 kHz sampling rate. Every sine wave, every transient, every ripple. You can see it all.

Contact us for more
Your motor, live on screen.
THE CHALLENGE

Traditional motor monitoring is blind to reality.

Most motor monitoring systems give you after-the-fact data: averages, trends, and alerts that arrive too late. You miss the critical electrical events that precede failure.

Delayed Detection
By the time you notice a problem, damage has already begun
Incomplete Picture
Missing real-time electrical signatures and transient events
Data Overload
Too much noise, not enough clear data
SOLUTION
DMK SOLUTION

Real-time electrical visibility.

The DMK transforms complex motor data into clear, readable output. See what's happening inside your motor as it happens.

01REAL-TIME CAPTURE

High-speed data acquisition

Capture electrical signals at 250 kHz sampling rate with precision measurement hardware. Every voltage fluctuation, current spike, and harmonic distortion is recorded in real-time.

  • 3-phase voltage monitoring ±0.1% accuracy
  • Current measurement up to 1000A range
  • FFT analysis real-time spectrum processing
data_acquisition.py
DMKRT Motor Monitoring System: time and DQ chart view
02DATA LOGGING

DATA LOGGING

Continuous, timestamped acquisition across all channels. The DMK writes every sample directly to a structured local database: 8 channels simultaneously, at up to 250 kHz, with no gaps, no manual triggers, and no data loss. Every session is queryable, replayable, and exportable the moment recording stops.

  • 8-channel simultaneous logging: U_V, V_W, W_U, Is1-3, Angle, Udc
  • Microsecond-precision timestamps across the full session
  • Navigate any time window: load, zoom, and replay any moment
database_viewer.py
Database Viewer with Plot
03INTELLIGENT ANALYSIS

AI-powered pattern recognition

Advanced algorithms analyze electrical signatures to predict failures before they occur. Machine learning models identify subtle patterns that indicate developing issues.

  • Anomaly detection: statistical pattern analysis
  • Predictive modeling: failure probability forecasting
  • Continuous learning: improves with motor data
analysis_engine.py
04MONITORING

DATA MONITORING

Intelligent fault detection: your rules or ours. Point the Data Monitor at any logged session and run a detection pass. Choose from our built-in algorithms (Rate of Change, Absolute Threshold) or define your own logic entirely. The system scans the full dataset, indexes every event, and plots each fault with a ±10 ms context window across all three phases.

  • Pre-built algorithms: Rate of Change and Absolute Threshold, ready to deploy
  • Custom algorithm support: define your own detection conditions
  • Fault library: every event indexed, selectable, and export-ready in one click
visualizer.py
Fault Detector and Plotter
Fault 2  |  V_W at T = 0  |  Row 1 090 975  |  1.8 ms detection
Ready: 12 500 ms session loaded

Add your own algorithm or ask us to add one.