Manufacturing
18 columns
120 rows
8 formats

Manufacturing Machine Failure Prediction

This dataset provides granular, timestamped sensor readings, operational statuses, maintenance logs, and event records for manufacturing equipment, enabling predictive failure modeling and operational optimization. It supports advanced analytics for uptime, maintenance scheduling, and ESG compliance, making it invaluable for operations directors and R&D teams seeking to maximize efficiency and sustainability.

last updated 23 Nov 2025
by GoMask

The brief that made it

Predictive maintenance scheduling and failure risk modeling

Sample rows

preview · 8 of 120 rows · all 18 columns

machine_idstring	operational_statusstring	downtime_minutesinteger	failure_eventboolean	failure_typestring	machine_typestring	locationstring	sensor_timestampdatetime	temperature_celsiusfloat	vibration_mm_sfloat	pressure_barfloat	humidity_percentfloat	maintenance_performedboolean	maintenance_typestring	maintenance_technician_idstring	energy_consumption_kwhfloat	esg_compliance_flagboolean	notesstring
MX1001	running	0	false	blank	CNC_Lathe	Section_A_North	2024-06-03T07:10:33Z	43.2	2.8	7.9	44.1	false	blank	blank	9.6	true	Normal operation. All readings within expected range.
MX1002	failed	180	true	mechanical	Robot_Arm	Section_B_East	2024-06-03T09:21:12Z	65.5	18.7	13.5	60.2	true	corrective	TECH101	0	false	Unexpected mechanical failure detected. Maintenance scheduled.
MX1003	maintenance	50	false	blank	Hydraulic_Press	Section_C_South	2024-06-03T11:33:26Z	58.3	11.9	15.7	52.6	true	preventive	TECH102	3.2	true	Preventive maintenance performed. Machine offline for one hour.
MX1004	running	0	false	blank	Packing_Robot	Section_D_West	2024-06-03T14:05:41Z	33.6	3.7	8.4	38.3	false	blank	blank	7.5	true	Packing robot operating normally.
MX1005	idle	0	false	blank	Press_Brake	Section_E_Central	2024-06-03T16:18:07Z	24.2	1.1	9.2	41.9	false	blank	blank	0.6	true	Machine idle, waiting for next batch.
MX1006	running	0	false	blank	CNC_Mill	Section_A_East	2024-06-04T07:43:17Z	47.8	4.2	10.5	65.4	false	blank	blank	10.7	true	Routine mill operation. All parameters nominal.
MX1007	stopped	30	false	blank	Injection_Molder	Section_B_North	2024-06-04T10:12:56Z	37.5	2.3	5.6	blank	true	inspection	TECH103	0.2	true	Quarterly inspection completed. Humidity sensor offline.
MX1008	failed	300	true	electrical	Robot_Arm	Section_C_West	2024-06-04T12:30:39Z	150	50	22	100	false	blank	blank	0	false	High temperature and vibration. Electrical failure. Edge case values.
MX1009	running	0	false	blank	Packing_Robot	Section_D_Central	2024-06-04T15:52:21Z	26.9	1.8	7.3	49.7	false	blank	blank	6.8	true	Packing robot running smoothly.
MX1010	idle	0	false	blank	CNC_Lathe	Section_E_South	2024-06-05T08:27:03Z	20.1	0.5	6.4	33.8	false	blank	blank	0.7	true	Machine idle awaiting operator.
MX1011	maintenance	60	false	blank	Hydraulic_Press	Section_A_West	2024-06-05T11:04:48Z	71.4	14.2	17.1	56.3	true	predictive	TECH104	2.5	false	Predictive maintenance. Energy consumption above normal.
MX1012	running	0	false	blank	CNC_Mill	Section_B_Central	2024-06-05T13:35:14Z	54.6	6.3	12.9	68.7	false	blank	blank	14.2	true	Mill operating at full capacity.
MX1013	stopped	10	false	blank	Press_Brake	Section_C_North	2024-06-05T15:49:30Z	31.7	2.2	7.8	blank	false	blank	blank	0	true	Short stop for batch change. Humidity sensor offline.
MX1014	idle	0	false	blank	Hydraulic_Press	Section_D_North	2024-06-06T07:18:19Z	0	0	0	0	false	blank	blank	0	true	Machine powered down, edge case readings.
MX1015	running	0	false	blank	Packing_Robot	Section_E_West	2024-06-06T09:43:27Z	28.4	1.7	6.5	35.4	false	blank	blank	8.1	true	Packing robot in continuous operation.
MX1016	running	0	false	blank	CNC_Mill	Section_A_Central	2024-06-06T12:11:55Z	39.8	7.5	11.2	59.7	false	blank	blank	12.8	true	Normal mill operation.
MX1017	maintenance	120	true	hydraulic	Robot_Arm	Section_B_West	2024-06-06T14:36:40Z	82.1	37.8	16.2	58.5	true	corrective	TECH105	1.2	false	Hydraulic failure detected. Corrective maintenance performed.
MX1018	running	0	false	blank	Injection_Molder	Section_C_Central	2024-06-07T08:52:03Z	46.3	4.9	8.1	67.2	false	blank	blank	8.7	true	Injection molder operating within normal parameters.
MX1019	stopped	20	false	blank	Press_Brake	Section_D_South	2024-06-07T11:43:17Z	-40	0	0	100	false	blank	blank	0	true	Machine stopped, extreme temperature and humidity readings.
MX1020	running	0	false	blank	Packing_Robot	Section_E_East	2024-06-07T14:35:51Z	31.9	2.1	7	50.1	false	blank	blank	7.2	true	Packing robot running at normal speed.

What the 120 rows show

from the 120-row sample

Failed (operational status) stands out: mean downtime_minutes is 212.2, against 17.4 for the rest.

22%failure_event = true
0median downtime_minutes
4maintenance types
7machine types
25locations
42.1median temperature_celsius

Mean downtime_minutes by operational_status120 rows

downtime_minutes120 rows, in bands of 50

Median 0, from 0 to 300.

failure_type26 rows with a value · 94 left blank

mechanical10
electrical6
hydraulic5
software3
other2

18 columns by typefrom the column list below

string 8
integer 1
float 5
datetime 1
boolean 3

Columns

18 columns in four groups

blueprint · 18 columns
column	type	description	example
Text 8 columns
`machine_id`	string	Unique identifier for each machine in the factoryunique	MX1001
`machine_type`	string	Type or model of the machine7 types	CNC_Lathe
`location`	string	Physical location or section of the factory where the machine is installed	Section_A_North
`operational_status`	string	Current operational status of the machinerunning · idle · maintenance · stopped · failed	running
`failure_type`	string	Type of failure that occurred (if any)mechanical · electrical · hydraulic · software · other · optional	mechanical
`maintenance_type`	string	Type of maintenance performed (if any)preventive · corrective · predictive · inspection · other · optional	corrective
`maintenance_technician_id`	string	Identifier for the technician who performed maintenanceoptional	TECH101
`notes`	string	Additional notes or comments related to the event or readingoptional	Normal mill operation.
Numbers 6 columns
`temperature_celsius`	float	Temperature reading from the machine's sensor in degrees Celsius-40 to 150	43.2
`vibration_mm_s`	float	Vibration level measured in millimeters per second0 or more	2.8
`pressure_bar`	float	Pressure reading from the machine's sensor in bar0 or more	7.9
`humidity_percent`	float	Humidity level as a percentage0 to 100 · optional	44.1
`downtime_minutes`	integer	Total downtime in minutes associated with this event0 or more · optional	0
`energy_consumption_kwh`	float	Energy consumed by the machine during this period in kilowatt-hours0 or more · optional	9.6
Dates and times 1 column
`sensor_timestamp`	datetime	Timestamp of the sensor reading	2024-06-03T07:10:33Z
True or false 3 columns
`failure_event`	boolean	Indicates whether a failure event occurred at this timestamp	false
`maintenance_performed`	boolean	Indicates if maintenance was performed at this timestamp	false
`esg_compliance_flag`	boolean	Indicates whether machine operation met ESG compliance at this timestampoptional	true

Use it for

A manufacturing dashboard
The failure_event rate, downtime_minutes by operational_status and a breakdown of failure_type. Excel, Power BI or Tableau.
Why do the 21 failed rows have a mean downtime_minutes of 212.2?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Machines120
MX10010running
MX1002180failed
MX1008300failed
A software demo
Believable machines with machine_type, location and sensor_timestamp to fill a screen in front of a buyer.

This dataset120 rows18 columns

Yours1,000 rows18 columnslocation: UK only

blueprint · manufacturing-machine-failure-prediction

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 machine must have at least one maintenance event within dataset period.
Sensor readings include temperature, vibration, and pressure with realistic drift and outliers.
Failure events cannot occur simultaneously for multiple machines.
Downtime durations are proportional to failure type and recent maintenance history.
Include at least two predictive features not directly observable (e.g., calculated risk score or estimated remaining useful life).
Machines with recurring issues must show reduced operational efficiency.

Rows1,000 rows10,000 rows100,000 rows1,000,000 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-machine-failure-prediction

What should your data show?

No signup. No card.

Sample rows

What the 120 rows show

Columns

Use it for

A manufacturing dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Manufacturing

What should your data show?