AI Energy Optimization in the Steel Industry | متادیپ

AI Energy Optimization in the Steel Industry

−18% energy use & +9% productivity on a continuous steel casting line with MetaDeep's custom predictive models.

Executive summary

Energy was over 35% of product cost at a billet & long-steel producer. MetaDeep's custom ML models, trained on the plant's own historical sensor data, cut energy use 18% and peak-hour energy cost 22%, boosted line productivity 9%, and paid back in under 8 months.

Challenge (Situation & Task)

A continuous-casting line ran on heavy energy costs (induction furnace electricity + preheating gas), yet energy decisions were made manually by operators — with no visibility into load changes, peak-hour price fluctuation, or input material quality.

Goals: cut specific energy consumption, forecast 24h usage, lower peak-hour cost, and provide a decision dashboard.

MetaDeep solution (Action)

Architecture: IoT sensors / MES data → ingestion → time-series store → prediction models → optimizer → dashboard / signals to controllers.

Three custom models (trained on 2 years of that plant's sensor data):

Energy forecasting — LSTM/Prophet time series for power & gas.
Energy saving — XGBoost to find the optimal furnace power mix.
Production-load forecast — hierarchical demand model to align output with low-cost grid windows.

The optimizer balances load vs energy subject to quality constraints (temperature, melt chemistry, solidification rate).

Measurable results

Metric	Before	After	Change
Specific energy (kWh/t)	640	525	−18%
Line productivity	baseline	up	+9%
Peak-hour energy cost	high	reduced	−22%
24h forecast accuracy	—	94%	new
ROI	—	8 months	—

Key takeaway

Success came from customizing models on the plant's own data — real equipment behavior rather than industry averages.