Manufacturing Predictive Maintenance Records

This dataset provides granular, time-stamped logs of machine performance and maintenance events across smart factories, including sensor readings, downtime durations, and detailed maintenance actions. It is ideal for predictive maintenance modeling, failure analysis, and optimizing operational efficiency in industrial environments.

  • opened 14 times
  • last updated 20 Aug 2025
  • by GoMask
The brief that made it

Predictive maintenance modeling and failure prediction

Sample rows

preview · 8 of 200 rows · all 18 columns
record_idstringoperating_statusstringvibration_levelfloatmaintenance_eventbooleanmaintenance_typestringmachine_idstringfactory_idstringtimestampdatetimetemperature_celsiusfloatpressure_psifloatruntime_hoursfloatdowntime_minutesintegerfailure_codestringoperator_idstringscheduled_maintenance_datedatepart_replacedstringmaintenance_descriptionstringfailure_descriptionstring
REC0001running1.8falseblankMCH-101FCT-NY012023-11-15T08:23:3468.384.2793.20blankOP-10562024-04-04blankblankblank
REC0002maintenance2.4truepreventiveMCH-102FCT-TX102023-12-01T15:45:0256.714.7121.148blankOP-20012024-06-15VAL-4A2Routine preventive maintenance performed including lubrication and checks.blank
REC0003error29.5falseblankMCH-103FCT-CA232023-10-22T22:12:19132.9199.452.4987F-HIGH-TEMPOP-11592024-09-04blankblankTemperature spike detected in main chamber causing shutdown for safety.
REC0004idleblankfalseblankMCH-104FCT-IL352023-09-03T09:34:27blankblank08blankblank2024-01-12blankblankblank
REC0005running2.2falseblankMCH-101FCT-NY012023-10-11T11:10:3875.663.1502.70blankOP-21112024-06-02blankblankblank
REC0006stopped0falseblankMCH-106FCT-CN772023-08-27T06:41:15000122F-S05OP-10862024-02-28blankblankUnexpected system stop due to sensor error requiring reset.
REC0007running1.6falseblankMCH-107FCT-TX102023-11-23T14:32:4061.941.3288.20blankOP-22332024-04-10blankblankblank
REC0008maintenance2.8trueinspectionMCH-110FCT-CA232023-07-17T18:22:2044.411.6213.736blankOP-11962024-08-17SEAL-9B3Comprehensive inspection completed including seals and pressure calibration.blank

What the 200 rows show

from the 200-row sample

Error (operating status) stands out: mean vibration_level is 55.5, against 2.3 for the rest.

  • 24%maintenance_event = true
  • 2.5median vibration_level
  • 5failure codes
  • 17factories
  • 41operators
  • 42machines
Mean vibration_level by operating_status171 rows
0501002.4running87 rows0.0stopped4 rows2.1maintena…48 rows55.5error32 rows
vibration_level171 rows, in bands of 10
070140139053655332050100vibration_level →

Median 2.5, from 0.0 to 99.9.

maintenance_type48 rows with a value · 152 left blank
  1. inspection12
  2. preventive10
  3. corrective10
  4. predictive8
  5. other8
18 columns by typefrom the column list below
  • string 10
  • integer 1
  • float 4
  • date 1
  • datetime 1
  • boolean 1

Columns

18 columns in four groups
blueprint · 18 columns
columntypedescriptionexample
Text 10 columns
record_idstringUnique identifier for each maintenance or performance recorduniqueREC0001
machine_idstringUnique identifier for the machineMCH-101
factory_idstringIdentifier for the factory or plant where the machine is locatedFCT-NY01
operating_statusstringCurrent operating status of the machinerunning · idle · stopped · maintenance · errorrunning
maintenance_typestringType of maintenance performed (if maintenance_event is true)preventive · corrective · predictive · inspection · other · optionalpreventive
maintenance_descriptionstringDetailed description of maintenance performed (if applicable)optionalRoutine preventive mainte…
failure_codestringStandardized code for the type of failure or issue encountered (if any)5 codes · optionalF-HIGH-TEMP
failure_descriptionstringDetailed description of the failure or issue (if any)optionalTemperature spike detecte…
operator_idstringIdentifier for the operator or technician who logged the recordoptionalOP-1056
part_replacedstringName or code of part replaced during maintenance (if any)optionalVAL-4A2
Numbers 5 columns
temperature_celsiusfloatMeasured temperature of the machine in Celsius at the time of the record-50 to 250 · optional68.3
vibration_levelfloatMeasured vibration level of the machine (mm/s or relevant unit)0 or more · optional1.8
pressure_psifloatMeasured pressure in PSI at the time of the record0 or more · optional84.2
runtime_hoursfloatCumulative runtime of the machine in hours since last maintenance0 or more · optional793.2
downtime_minutesintegerDuration of downtime in minutes for this event, if applicable0 or more · optional0
Dates and times 2 columns
timestampdatetimeDate and time when the record was logged2023-11-15T08:23:34
scheduled_maintenance_datedateDate of next scheduled maintenance for the machineoptional2024-04-04
True or false 1 column
maintenance_eventbooleanIndicates if this record corresponds to a maintenance eventfalse

15 SQL practice questions for the Manufacturing Predictive Maintenance Records

Written for this data and checked against it: 12 SQL and 3 Power BI exercises from beginner to advanced. Try the first three free; the practice kit has all 15, a starter .sql file and an answer key with every expected result.

  1. 01BeginnerFreeSELECT · WHERE · ORDER BY

    Machines in error status

    Return record_id, machine_id and downtime_minutes for every record whose operating_status is 'error'. Sort by downtime_minutes from highest to lowest, then by record_id in ascending order.

    Tables: manufacturing_predictive_maintenance_records · your result: 3 columns, 32 rows
  2. 02BeginnerFreeDISTINCT · IS NOT NULL

    Distinct failure codes

    Return each distinct non-null failure_code as a single column named failure_code, sorted alphabetically.

    Tables: manufacturing_predictive_maintenance_records · your result: 1 columns, 5 rows
  3. 03BeginnerFreeGROUP BY · COUNT

    Records per operating status

    Count the records for each operating_status. Return operating_status and record_count, sorted by record_count from highest to lowest, then by operating_status in ascending order.

    Tables: manufacturing_predictive_maintenance_records · your result: 2 columns, 5 rows
  1. 04Average temperature by statusBeginner
  2. 05Top five factories by total downtimePower BI
  3. 06Factories with heavy downtimeIntermediate
  4. 07Temperature risk bucketsIntermediate
  5. 08Monthly record and maintenance countsIntermediate
  6. 09Machines above average vibrationIntermediate
  7. 10Average downtime by maintenance typePower BI
  8. 11Worst machine per factoryAdvanced
  9. 12Gap since previous record per machineAdvanced
  10. 13Running downtime total by monthAdvanced
  11. 14Percent of downtime by statusAdvanced
  12. 15Temperature anomalies by z-scorePower BI

Get the practice kit: the full dataset, all 15 exercises, a starter .sql and the answer key. One-time $3.99.

Get the practice kit · $3.99

Use it for

  • maintenance ev…24%48 of 200 rowsmean vibration level …2.4runn…0.0stop…2.1main…55.5error

    A manufacturing dashboard

    The maintenance_event rate, vibration_level by operating_status and a breakdown of maintenance_type. Excel, Power BI or Tableau.

  • Why do the 32 error rows have a mean vibration_level of 55.5?

    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 records with machine_id, factory_id and timestamp 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

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows18 columns
Yours1,000 rows18 columns

blueprint · manufacturing-predictive-maintenance-records

Behind this dataset

Same schema. As many rows as you need.

These 200 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
  • Machine type, serial, and location logged
  • Operational readings at hourly intervals
  • Maintenance events and failure flags recorded
  • Downtime duration and cause annotated
  • Operational shifts and usage patterns included
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
manufacturing-predictive-maintenance-records

More in Manufacturing

Browse all
Also in ManufacturingFactory IoT Sensor Fault LogsManufacturing Quality Control MetricsManufacturing Process Cycle TimesAll 1,966 datasets
In collectionsManufacturing Datasets: Analyze Production Runs, Machine Performance, and Quality Control

What should your data show?

Preview 20 rows free
No signup. No card.