How it works

What it simulates

A fleet of rotating equipment: boiler feed pumps, an induced draft fan, a cooling water pump and a cooling tower fan. Six machines, 90 tags, published as Sparkplug B over MQTT.

Condition monitoring rather than process control. Bearing damage shows up first as impulsiveness in the vibration signal, not as a rise in overall level, so kurtosis and crest factor move while RMS is still normal.

• broadband vibration, kurtosis and crest factor per machine
• bearing temperatures, speeds and motor currents
• a duty and standby pair, so a fault has a like-for-like control beside it

What it configures on Litmus Edge

On startup, and it removes exactly what it created when you are finished:

• 6 DeviceHub devices on the Sparkplug B driver, 90 tags
• 1 Digital Twin model serving all 6 machines
• 5 multi-input Analytics groups: machine health, bearing prognosis, impulse detection, fleet reliability, live values

Scenarios you can inject

• An outer race bearing defect on the duty pump appears in impulsiveness before it appears in overall level, with the standby pump beside it as the control
• Lubrication loss or cavitation on the cooling water pump separates a supply problem from a hydraulic one
• Rotor imbalance or a slipping drive belt shows how different faults occupy different parts of the same signal