Plastics plant maintenance work orders and downtime logs, 11 firms
Summary
Maintenance work orders, technician closeout notes and machine downtime events from injection molding and extrusion plants. Each work order carries the asset, failure code, parts used and the technician's own words, and downtime events are joined to the work orders that cleared them. Good material for models that diagnose equipment faults, write closeout notes and predict repeat failures. Technician names and badge numbers are replaced and all costs are dropped.
Collected to order. We collect it from US companies for your order. Scope, volume and timing are confirmed in writing before you sign.
Pricing on request
Request scope and pricingAt a glance
- Planned scope. Volume, sources and timing are confirmed in writing before you sign.
- Records
- 8.5Mwork orders, downtime events, channel messages and documents
- Size
- 3.5 GB
- Tokens, estimated
- 560M
- Years
- 2018 to 2025
- Firms
- 11
- Owner profile
- 11 US plastics processors (injection molding, blown film and profile extrusion), 40 to 260 staff each, Midwest and Southeast
- Industry
- Manufacturing
- Data type
- Field operations
- Headcount
- 40 to 260 staff per firm
- Region
- United States (Midwest, Southeast)
- Languages
- English, Spanish
- Formats
- JSONL, Parquet
- Updated
Sources
| System | Kind | Records |
|---|---|---|
| CMMS work orders | Field operations | 1.24M work orders |
| MES downtime events | Databases | 6.8M downtime events |
| Microsoft Teams standard channels | Team chat | 410K messages |
| Shared drives | Shared files | 22K PM procedures and mold setup sheets |
Good for
- training models to diagnose molding and extrusion faults from symptoms and alarms
- turning short technician entries into complete closeout notes
- predicting repeat failures from work order history per asset
- evaluating agents that plan preventive maintenance around production schedules
Fields
| Field | Type | Description |
|---|---|---|
| wo_id | string | Work order number |
| firm_code | string | Pool member code |
| asset | string | Asset as named in the plant |
| asset_class | enum | injection press, extruder, chiller, dryer, robot or auxiliary |
| opened_at | timestamp | When the work order was opened |
| failure_code | string | Plant failure code |
| problem | string | Problem as reported by production |
| closeout | string | Technician closeout note |
| parts | array<string> | Parts and consumables used, without costs |
| downtime_min | int | Minutes the asset was down |
| downtime_event_ids | array<string> | Linked MES downtime events |
Example record
{
"wo_id": "WO-388104",
"firm_code": "PLS-04",
"asset": "Press 17, 500 ton",
"asset_class": "injection press",
"opened_at": "2022-01-19T23:48:00-05:00",
"failure_code": "HYD-LEAK",
"problem": "Oil on floor under clamp side, low oil alarm twice this shift. Press stopped at 23:40.",
"closeout": "Found weeping fitting on clamp cylinder return line and a cracked O-ring at the manifold. Replaced O-ring, re-torqued fitting, topped off 9 gal AW46. Ran 30 shots dry, no leaks. Mold M-2214 back in production 02:15. [PERSON_23]",
"parts": [
"O-ring kit, valve manifold, 1 ea",
"AW46 hydraulic oil, 9 gal"
],
"downtime_min": 155,
"downtime_event_ids": [
"DT-9917732"
]
}Licenses available
Exclusive
One buyer. Nobody else can license it during the exclusive term, usually 2 years.
Non-exclusive
Licensed to more than one buyer.
First look
One buyer gets 2 to 4 weeks to make an offer before anyone else sees the dataset.
What ships with it
- Datasheet: what it is, what it is good for, verified size, sources, years, format and limits.
- Provenance file: the owner shown by code, staff notice and consent status, exclusions, mapped to the EU AI Act Article 53 training-data summary and California AB 2013.
- Manifest with a hash for every file.
- QC report and de-identification report.
- Your own copy, with unique canary records.
How it is de-identified
Default exclusions removed, files flattened to text, identifiers found in three layers and replaced with consistent placeholders, and the result measured against a 99% bar for each identifier type in each source.