Skip to content
Planning & productionTextiles

Understand yarn breaks in weaving

demi links the stops of every loom to yarn lot, warp beam, room climate and setting and shows what drives the yarn breaks.

Today

A loom stops at every warp or weft break, and in a weaving mill that adds up to thousands of stops a week. Every stop costs running time, operator time and often a fault in the fabric. The looms have long recorded the stop data, but nobody links it to yarn lot, warp beam, room climate and setting. When breaks rise, people adjust the loom, although the cause often lies in the yarn or the hall.

An example

At Fibrana, 36 rapier looms weave the GW 220 g/m² fabric from PA 6.6 dtex 1100. For three weeks, warp breaks have risen from 1.8 to 3.1 per 100,000 picks, and the weavers have been adjusting the settings. The agent links 41,000 stops to warp beam, yarn lot, room climate and setting: the rise affects only warp beams from yarn lot 23-118, most of all when relative humidity in hall 2 drops below 50 % at night. Looms with beams from other lots run as before. The weaving manager has the humidification raised at night and uses the rest of the lot in the weft instead of the warp, and purchasing files a claim with the supplier, backed by the data.
Fictional company, typical workflow.

Your data, wherever it lives

Why your looms stop is spread out today: stops and pick counts in the looms and the production data system, yarn lots, warp beams and orders in the ERP, room climate in the halls' data loggers, setting sheets and shift notes in spreadsheets. demi reads, understands and links them per stop, with your rights. The AI shows in minutes whether lot, warp beam, climate or setting drives the breaks, and your weaving manager decides what changes.

Where the data lives today

  • Machines & sensors
  • MES
  • ERP
  • Office files
Data LayerOne view of everything, with your rights

How demi solves it

Three layers in this order: connect the data first, then the rights, then the AI.

  1. 1 · ConnectData Layer

    Data sources in this case: stop data and speeds from the looms, the weaving mill's production data system, yarn lots, warp beams and orders in the ERP, climate data of the halls, setting sheets and shift notes in spreadsheets. demi replaces nothing and links every stop to loom, article, warp beam, yarn lot, shift and the room climate at that moment. Every rise can then be traced back to the lot or the setting.

  2. 2 · PermitPermission Layer

    Weaving, warping, quality and plant management see stop data and results; only purchasing sees supplier ratings and yarn purchase prices. The weaving manager decides whether a lot is blocked or claimed or a setting is changed; every decision is recorded.

  3. 3 · ActIntelligence Layer

    The agent calculates warp and weft breaks per 100,000 picks for every loom, warp beam and yarn lot, exactly from the recorded stops. It compares groups that differ in only one factor, such as the same loom with a different lot, and shows which factor explains a rise and how many stops are behind it. The language model only explains the result.

How it runs

  1. 1

    demi reads the stops and running times of every loom, plus warp beam, yarn lot and room climate.

  2. 2

    The agent calculates breaks per 100,000 picks for loom, warp beam, lot and shift.

  3. 3

    When breaks rise, it compares groups that differ in only one factor.

  4. 4

    It shows whether yarn lot, warp beam, climate or setting explains the rise, with the stops as evidence.

  5. 5

    The weaving manager decides on climate, setting, blocking or a claim.

What changes

  • Fewer stops and more running time per loom

  • Claims to the yarn supplier backed by data, not impressions

  • Fewer fabric faults caused by yarn breaks

What does it bring you?

Check it with your own numbers

Every starting value is an assumption you can change. The calculation sits right below, step by step.

Assumption, editable

Your numbers

Result

+90 hfreed per year

Assumptions and calculation

demi links stops to yarn lot, beam and climate and shows what drives the breaks; you decide.

2.5 h → 1.75 h per case

How does it run today?

What is already digital saves less: the factor lowers the share demi brings.

How we calculate

10 break analyses × 2.5 h × 30% × 1.0 (manual) × 12 months = 90 h

Value per year, before demi costs

Freed per year+90 h

Assumption: labour cost of €49.50 per hour in German manufacturing in 2025 (Destatis), plus workplace, IT and overheads.

= Value per year, before demi costs

+€5,850

gained per year

90 h ÷ 1,760 h per role = 0.1 full-time roles

An estimate, not a promise. The starting values are assumptions for an industrial company with 150 to 500 people.

Combine with more cases and get the package

Questions about this use case

Where does the loom stop data come from?

Modern looms record every stop with cause, time and pick count, older ones through a production data system or counters. How the data gets to demi, as an export or through an interface, we clarify in conversation. demi does not intervene in the loom's control.

How is the yarn lot linked to a single stop?

Through the warp beam: warping and sizing record which lot went onto which beam, in the ERP, the production data system or on route cards. The agent reads this assignment, also from paper or spreadsheets, and links every stop to the beam that was in the loom at that moment. For the weft it uses the packages loaded during the shift.

Does room climate really matter?

Often, and the agent shows it with your data instead of rules of thumb. It lays temperature and relative humidity of every hall next to the breaks per hour and compares periods with the same article and lot. If the climate is behind it, you see it; if not, it says so too.

Does demi also find looms that run worse than their neighbours?

Yes. With the same article, lot and climate, a loom with clearly more stops stands out, and the agent shows which setting, speed or last maintenance sets it apart from the others. The loom fixer decides whether it gets readjusted.

See this case with your data

In the demo we show you the workflow on your own systems.

Your configurator

No use cases yet

Your configurator is still empty

Add a use case from any card or case page and see what it brings per year, with the calculation. Free, no sign-up, no commitment: try it out and change any number.

Browse use cases