Dark Mode
Zalingo Synthetic Manufacturing — Premium Evaluation Kit - 1M Rows
Synthetic Tabular Data
Tags and Keywords
Trusted By
"No reviews yet"
£1,999
About
Zalingo Synthetic Manufacturing — Premium Evaluation Kit (PdM • Downtime • OEE • Quality • Energy) — 1M Rows + Notebooks
A premium, end-to-end evaluation kit for factory analytics: predictive maintenance (PdM), downtime root-cause, OEE, quality, throughput, and energy. You get ~1,000,000 privacy-safe synthetic events blending machine telemetry with labelled production/maintenance events, plus Jupyter notebooks and data dictionaries—so teams can benchmark pipelines and models quickly without exposing proprietary plant data.
Need a production-scale feed? After purchase, message us about enterprise bundles (tens of millions of rows) and weekly/daily refresh subscriptions via S3/API.
What’s Inside
- Data (Parquet, Snappy): ~1,000,000 rows, multi-part, partitioned by date/site/line/machine; includes labels and precomputed features.
- Notebooks: EDA & quality, PdM/OEE feature engineering (rolling/spectral/lagged), baseline models for failure/RUL and OEE/quality forecasting with ROC/PR, calibration, and cost curves.
- Docs & Schema: Data dictionary, label policy, quick-start, JSON schema samples.
Key Fields (representative)
- Context:
site,line_id,machine_id,asset_class(robot|press|cnc|conveyor|oven|compressor). - Timing:
ts_utc(ISO-8601). - Telemetry:
sensor_type(temperature|vibration|pressure|rpm|current|power|flow),reading_value,reading_unit. - Events:
event_type(sensor_reading|cycle_complete|changeover|downtime|maintenance|quality_event). - Failure/PdM:
failure_label (0/1),failure_mode(bearing|overheating|misalignment|lubrication|electrical|other),time_to_failure_hours. - Downtime:
downtime_start_utc,downtime_end_utc,downtime_minutes,downtime_cause(mechanical|electrical|material|planned|changeover). - Maintenance:
maintenance_type(preventive|corrective|condition_based),work_order_id,mtbf_hours,mttr_hours. - OEE & Production:
oee_availability,oee_performance,oee_quality,oee_overall,throughput_units,cycle_time_ms. - Quality:
scrap_count,scrap_reason,quality_event_class. - Energy & Environment:
energy_kwh, (optional)ambient_temp_c,humidity_pct. - Derived Features:
rolling_mean_vibration,rolling_std_temp,delta_current,anomaly_score_0_1, (optional)vibration_band_power_*. - Geo:
country(ISO-2),city. (Columns may vary slightly; see the included dictionary + preview for exact schema.)
Distribution
- Format: ZIP with /data (Parquet), /notebooks, /docs, /schema.
- Volume: ~1,000,000 rows, 25–50 columns, multi-part Parquet.
- Approx Size: 60–150 MB zipped (category-dependent).
- Partitioning: by
event_date/site/line_id/machine_idfor efficient reads.
Usage
- Failure prediction & RUL/survival — thresholds, windowing, early-warning policy.
- Anomaly detection — streaming/rolling features for alerts.
- Downtime RCA — Pareto by cause/mode, intervention simulations.
- OEE improvement — availability/performance/quality trade-offs, bottlenecks.
- Quality forecasting — scrap drivers, SPC-style monitoring.
- Energy optimisation — kWh per unit, idle losses, shift effects.
- MLOps QA — schema contracts, drift monitors, dashboard demos.
Coverage
- Geographic: Multi-country synthetic coverage (ISO codes).
- Time Range: Recent multi-year synthetic window with shift & seasonal patterns.
- PII/Proprietary: None — fully synthetic; not derived from any specific plant.
Who Can Use It
- Reliability/Quality/Process Engineers, Data Scientists/ML, Ops Excellence & OT, Integrators/Vendors for demos and validation.
Notes / Disclaimers
- Not real plant data. Not for safety-critical decision-making.
- Rates, labels, and KPIs are synthetic calibrated distributions and do not represent any specific manufacturer.
Evaluation License (Non-Production, Internal Use Only — 90 Days)
Buyer is granted a non-exclusive, non-transferable license to use the data and included assets solely for internal evaluation, prototyping, and testing for 90 days from purchase. No production use, external distribution, resale, sublicensing, or sharing beyond Buyer’s employees and on-site contractors under NDA. Derived models/features may be retained for internal research; production deployment requires a separate enterprise license. All materials are provided “as is” without warranties; liability limited to the amount paid.
QUALITY