Factory sensors with failure labels
A year of hourly sensor readings from six machines, with the degradation stage, remaining useful life, and the failures and work orders they lead to.
Six machines monitored hourly for a year: vibration, bearing temperature, motor current, pressure and speed, with the machine's degradation stage, its remaining useful life, and a label for failure within 24 hours. Failures and the work orders that repair them are linked back to the readings.
52,669 rows across 5 tables, 894 KB zipped. Public domain (CC0), no signup, no attribution required.
What is in it
site_id, site_name, site_kind, country, city
asset_id, site_id, asset_tag, asset_type, manufacturer, model_code, criticality, rated_power_kw, commissioned_at
reading_id, asset_id, recorded_at, operating_mode, vibration_mm_s, bearing_temp_c, motor_current_a, discharge_pressure_bar, rotor_speed_rpm, degradation_stage, rul_hours, failure_next_24h, next_failure_mode
failure_id, asset_id, failed_at, failure_mode, downtime_hours, restored_at, hours_since_last_repair
work_order_id, asset_id, order_type, opened_at, closed_at, labor_hours, parts_cost, priority
What holds, and how it was checked
Each line was measured against these exact files rather than asserted. The same checks ship inside the zip as INTEGRITY.txt, so you can re-run them yourself.
- 4 foreign-key relationships checked, 0 orphaned rows
- No row is dated before the row it belongs to
- 52,560 hourly readings from 6 machines; 1.7% are labelled as failing within 24 hours
- 39 failures; in the 72 hours before 39 of them the machine had already left the healthy state
- Remaining useful life counts down by one hour per reading in 100% of consecutive readings (it resets at a repair)
- 63 work orders, 63 of them closed on or after they opened
Questions it can answer
- How early can a model flag a failure using vibration and temperature alone?
- Does remaining useful life fall faster for some failure modes?
- How much downtime does each failure mode cost?
- Are preventive work orders placed before or after degradation begins?
Generate a custom version
Make your own version in StudioThis dataset was built by Misata Studio's engine and is fixed. RECIPE.json in the zip records the archetype, the sizes and the seed. In Studio you can start from the same kind of data, change the sizes, the rates or the period, and get a new dataset with its own certificate.
Other datasets
- Retail star schema
A dimensional model you can actually practise joins on: one fact table, four dimensions, 63,170 rows, and every join resolving.
- Machine degradation
100 machines monitored from commissioning to failure, with an exact remaining-useful-life label on every one of 23,118 readings.
- Ecommerce storefront
A year of orders across five joined tables, with a real Q4 peak and totals that reconcile to the cent.
- B2B SaaS subscription analytics
Accounts, seats, MRR, churn and support load, where company size actually drives the plan.
- Credit risk portfolio
3,000 borrowers and 4,200 commercial loans, where a credit rating actually predicts whether the loan defaults, at the rate S&P's own data says it should.
- Network intrusion / netflow
500 hosts and 20,000 labeled flows, where a port scan, a DDoS flood, and a brute-force attempt each carry the real statistical signature their MITRE ATT&CK technique actually leaves in traffic.
- Contact center queueing (Erlang C)
4 queues, 2,400 half-hour intervals over a full business month, where agents_staffed is what Erlang C (1917) says is actually required to clear each queue's own SLA target, not a plausible-looking number.
- Manufacturing SPC (Cpk / Xbar-R)
5 processes, 450 subgroups, 2,250 measurements, where process capability and out-of-control detection come from a real Xbar-R control chart -- including one process with an engineered tool-wear drift that actually trips Western Electric rules where it happens.
- Anti-money-laundering transactions with ground truth
A bank's customers, accounts and transactions, with the laundering typologies labelled, the rule-based alerts raised, and the cases and SARs that followed.
- Clinical trial: sites, patients, visits and adverse events
Two trials across nine sites: enrolment, scheduled visits, dosing, lab biomarkers and graded adverse events, all in the right order.
- Hospital encounters, diagnoses and claims
Patients, providers, encounters, ICD-10 diagnoses, prescriptions, labs and insurance claims that reconcile from billed to paid.