STEEL AND HEAVY MANUFACTURING

Asset reliability intelligence for a European specialty-steel producer

Furnaces, rolling mills and annealing lines fail expensively, and maintenance history, KPIs and site data are spread across systems. Wexa built a reliability graph across five sites with an AI analyst that answers questions and flags the next failure.

Download this case as PDF Book a demo

potential savings identified
value of one predictive catch
sites / critical assets modelled
site OEE range surfaced and compared

CLIENT: European specialty-steel producer (5 production sites)
REGION: Europe
WHEN: 2026
ENGAGEMENT: Solution build
WEXA COMPONENTS: Wexa · context graph · AI analyst agent · reliability dashboard

01Case 19

The challenge

Unplanned downtime on electric-arc furnaces and rolling mills
Maintenance events, KPIs and asset data reviewed site by site
No single view of OEE, MTBF and MTTR across the company

What Wexa built

Graph: company → production site → asset → maintenance event, with reliability KPIs per site (OEE, MTBF, MTTR, downtime, cost)
Reliability dashboard with overview, assets, sites and events
AI analyst answering questions over the graph and explaining its evidence
The same pattern was built for a precision-machining CNC fleet: health scores, alerts, failure probability and a maintenance queue for 10 machines

02Case 19

How it runs on Wexa

FigureHow this use case runs on Wexa: client systems connected, ontology discovered, context graph in the Wexa memory layer, agents and process flows, and governance. Highlighted components are central to this use case.

03Case 19

Results

Measure	Before / without Wexa	With Wexa
Cost of unplanned downtime across 5 sites	$4.8M a year	$3.6M a year
Annual cost of the process	$4.8M	$3.6M
Time to implement the AI solution	6 months	6 weeks
AI build cost (one-time)	$480K	$44K
AI operating cost per year (models, infrastructure, upkeep, platform)	$312K	$166K
Total AI cost in year 1	$792K	$210K