Order from Lab 6E3854

Machine failure series

Run-to-failure sensor time series from real industrial machines (pumps, compressors, gearboxes, motors, turbines), each tied to its maintenance log and to a failure cause confirmed by someone who opened the machine. Commercial training rights, with proof the plant owner agreed, and healthy machines included at their true share.

How answering works

Any number of people fill one order. The lab receives one dataset, in its own columns.

Your agent reads the order
It looks at what you hold and says which columns you can fill, and what is missing.
Mora checks what you send
Every record: no copies, no personal data, not already public, not on Mora from someone else.
The lab pays per record it accepts
The lab named the price. You fill as much of the order as you can.

The columns the lab wants

You do not need every column. Mora says which ones each dataset fills.

Column Type What it must hold

asset_id id One physical machine, stable over its whole history

asset_class / model / install_date text, date What the machine is and how old it is

ts UTC datetime Time of each sensor reading

channel / value / unit / sample_rate_hz text, number Vibration, temperature, current, pressure, speed; 1 Hz or better, raw vibration waveform at 10 kHz and up where it exists

operating_state label Running, idle, start-up, stopped, load level

event_id / event_type / event_at id, label, datetime Failure, planned stop, inspection or alarm, and when

failure_mode / failed_component label Confirmed cause, coded (ISO 14224 or the seller's list with a mapping)

confirmed_by label How the cause was established: teardown, lab analysis, technician note, or guess

work_order_text / parts_replaced / back_in_service_at text, datetime What the technician found and did, what was replaced, when the machine ran again

Column	Type	What it must hold
`asset_id`	id	One physical machine, stable over its whole history
`asset_class / model / install_date`	text, date	What the machine is and how old it is
`ts`	UTC datetime	Time of each sensor reading
`channel / value / unit / sample_rate_hz`	text, number	Vibration, temperature, current, pressure, speed; 1 Hz or better, raw vibration waveform at 10 kHz and up where it exists
`operating_state`	label	Running, idle, start-up, stopped, load level
`event_id / event_type / event_at`	id, label, datetime	Failure, planned stop, inspection or alarm, and when
`failure_mode / failed_component`	label	Confirmed cause, coded (ISO 14224 or the seller's list with a mapping)
`confirmed_by`	label	How the cause was established: teardown, lab analysis, technician note, or guess
`work_order_text / parts_replaced / back_in_service_at`	text, datetime	What the technician found and did, what was replaced, when the machine ran again

How much, in the lab's words

At least 2,000 machines with 3 years each (about 50,000 machine-years counting the wider fleet), and 1,500 confirmed failures across 20 or more failure modes. We count in machines, machine-years and confirmed failures, never in rows.

assets
sensor-series
failure-events
work-orders
operating-context
alarms