Manufacturing Machine Downtime Predictor

This dataset logs detailed machine events, sensor readings, and operational statuses from manufacturing equipment, including precise downtime events with reasons and durations. Designed for predictive maintenance, root cause analysis, and production optimization, it supports advanced analytics to minimize downtime and maximize equipment reliability. The flat structure ensures compatibility with most analytics platforms and machine learning workflows.

  • opened 5 times
  • last updated 5 Feb 2026
  • by GoMask
The brief that made it

Predictive maintenance and downtime forecasting

Sample rows

preview · 8 of 120 rows · all 18 columns
event_idstringoperational_statusstringsensor_temperature_cfloatdowntime_eventbooleandowntime_reasonstringmachine_idstringmachine_typestringfactory_idstringline_idstringtimestampdatetimedowntime_duration_minutesfloatsensor_vibration_mm_sfloatsensor_pressure_barfloatsensor_humidity_percentfloatsensor_current_ampfloatoperator_idstringmaintenance_flagbooleanremarksstring
EVT00001running37.5falseblankMC-A123HydraulicPress-XFAC-01LINE-012024-02-01T08:15:23blank0.78.955.23.2OP-101falseNormal morning operation
EVT00002stopped42.1truemechanical failureMC-B224LaserCutter-500FAC-02LINE-022024-02-01T09:22:1438.71.87.464.70OP-102falseUnexpected stop due to jam
EVT00003maintenanceblanktruescheduled maintenanceMC-C332ConveyorFlex-100FAC-01LINE-032024-02-01T10:07:47120blankblankblankblankblanktrueQuarterly scheduled service
EVT00004error89.2truesensor malfunctionMC-D441PlasticMolder-XLFAC-03LINE-042024-02-01T11:35:303.57.8blankblank0OP-103falseSensor error detected, auto shutdown
EVT00005idle22.4falseblankMC-E555RoboticArm-SMFAC-01LINE-052024-02-01T12:10:00blankblank5.1blank0.2blankfalseIdle between batches
EVT00006running41.6falseblankMC-F672HydraulicPress-XFAC-02LINE-062024-02-01T13:45:12blank0.59.748.34OP-104falseRoutine production
EVT00007stopped28.9trueoperator errorMC-G781LaserCutter-500FAC-04LINE-022024-02-01T14:03:3712.61.26.372.10OP-105falseIncorrect loading detected
EVT00008running36.2falseblankMC-H892PlasticMolder-XLFAC-02LINE-042024-02-01T15:29:55blank0.910.561.33.8OP-106falseAll systems normal

What the 120 rows show

from the 120-row sample

Error (operational status) stands out: mean sensor_temperature_c is 89.9, against 36.2 for the rest.

  • 50%downtime_event = true
  • 37.8median sensor_temperature_c
  • 11factories
  • 14machine types
  • 14lines
  • 26.3median downtime_duration_minutes
Mean sensor_temperature_c by operational_status87 rows
05010034.3running44 rows44.9stopped24 rows89.9error11 rows20.5idle8 rows
sensor_temperature_c87 rows, in bands of 10
015303192919420651060100sensor_temperature_c →

Median 37.8, from 17.8 to 98.2.

downtime_reason60 rows with a value · 60 left blank
  1. scheduled maintenance12
  2. mechanical failure11
  3. operator error9
  4. sensor malfunction8
  5. overheating7
  6. yearly calibration5
  7. software glitch4
  8. material jam2
  9. power surge1
  10. quarterly service1
18 columns by typefrom the column list below
  • string 9
  • float 6
  • datetime 1
  • boolean 2

Columns

18 columns in four groups
blueprint · 18 columns
columntypedescriptionexample
Text 9 columns
event_idstringUnique identifier for each logged machine event or recorduniqueEVT00001
machine_idstringUnique identifier for the machine generating the eventMC-A123
machine_typestringType or model of the machineHydraulicPress-X
factory_idstringUnique identifier for the factory or production site11 factories · optionalFAC-01
line_idstringIdentifier for the production line where the machine is locatedoptionalLINE-01
operational_statusstringCurrent operational state of the machine (e.g., running, stopped, maintenance, error)running · stopped · maintenance · error · idlerunning
downtime_reasonstringCategorized reason for downtime (e.g., mechanical failure, scheduled maintenance, operator error)10 reasons · optionalmechanical failure
operator_idstringIdentifier for the operator on duty during the eventoptionalOP-101
remarksstringAdditional notes or comments about the eventoptionalNormal morning operation
Numbers 6 columns
downtime_duration_minutesfloatDuration of downtime in minutes (if downtime_event is true)0 or more · optional38.7
sensor_temperature_cfloatTemperature sensor reading in degrees Celsiusoptional37.5
sensor_vibration_mm_sfloatVibration sensor reading in millimeters per secondoptional0.7
sensor_pressure_barfloatPressure sensor reading in baroptional8.9
sensor_humidity_percentfloatHumidity sensor reading as a percentage0 to 100 · optional55.2
sensor_current_ampfloatCurrent sensor reading in amperesoptional3.2
Dates and times 1 column
timestampdatetimeDate and time when the sensor readings and status were recorded2024-02-01T08:15:23
True or false 2 columns
downtime_eventbooleanIndicates if this record corresponds to a downtime event (true/false)false
maintenance_flagbooleanIndicates if the machine was under maintenance during this eventoptionalfalse

Use it for

  • downtime event50%60 of 120 rowsmean sensor temperatu…34.3runn…44.9stop…89.9error20.5idle

    A manufacturing dashboard

    The downtime_event rate, sensor_temperature_c by operational_status and a breakdown of downtime_reason. Excel, Power BI or Tableau.

  • Why do the 11 error rows have a mean sensor_temperature_c of 89.9?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable events with machine_id, machine_type and factory_id to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 18 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

10,000 rows of yours: $12.99One-time. No subscription. All prices

This dataset120 rows18 columns
Yours10,000 rows18 columns

blueprint · manufacturing-machine-downtime-predictor

Behind this dataset

Same schema. As many rows as you need.

These 120 rows came out of a blueprint — 18 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • Each row represents a unique machine event with timestamp.
  • Downtime events must include root cause classification.
  • Sensor readings (temperature, vibration, power draw) logged at regular intervals.
  • Maintenance actions and response times recorded for each event.
  • Include only anonymized, non-identifiable machine information.
Rows
Open the blueprint in Data Factory

1 credit per row. New accounts start with 25 free credits.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
manufacturing-machine-downtime-predictor

More in Manufacturing

Browse all
Also in ManufacturingFactory Sensor Equipment ReadingsManufacturing Order Fulfillment RecordsProduction Line Defect TrackingAll 1,949 datasets

What should your data show?

Preview 20 rows free
No signup. No card.