Steel Mill Energy Optimization

AI systems for optimizing energy use in electric arc furnaces, blast furnaces, and rolling mills

The Problem

“Reduce steel mill energy cost and equipment waste with AI-driven furnace and turbine optimization”

Organizations face these key challenges:

1

High and volatile energy cost across electric arc furnaces, blast furnaces, and rolling mills

2

Operator-dependent process settings causing inconsistent energy performance

3

Limited visibility into which variables most affect energy intensity in real time

4

Conservative maintenance schedules for gas turbine parts leading to premature replacement

5

Difficulty combining historian, PLC, CMMS, and turbine OEM data into one decision workflow

6

Frequent process changes from scrap quality, product mix, and ambient conditions

7

Lack of trustworthy predictive models that maintenance and operations teams will use

8

Need to preserve reliability and metallurgical quality while reducing energy use

Impact When Solved

Reduce kWh per ton and fuel consumption per ton across furnaces and rolling operationsLower peak demand charges through load forecasting and dispatch optimizationExtend gas turbine hot-section part life using customer-specific remaining useful life modelsReduce unnecessary part replacement and maintenance laborImprove furnace cycle consistency, tap-to-tap time, and thermal efficiencyIncrease asset availability by identifying degradation before failureSupport decarbonization goals through measurable energy intensity reduction

The Shift

Before AI~85% Manual

Human Does

  • •Review daily and weekly energy KPIs and compare performance against production targets.
  • •Manually adjust furnace, utility, and load-shedding setpoints based on operator judgment and SOPs.
  • •Respond to peak demand events after they emerge by coordinating production and utility curtailment.
  • •Balance throughput, quality, and maintenance priorities with limited visibility into real-time energy cost.

Automation

  • •No AI-driven analysis or optimization is used in the legacy workflow.
  • •No automated prediction of near-term energy consumption or peak demand risk is available.
  • •No continuous coordination of cross-system energy dispatch is performed.
  • •No automated anomaly detection for energy-critical assets is in place.
With AI~75% Automated

Human Does

  • •Approve recommended production, furnace, and utility operating changes within safety, quality, and output constraints.
  • •Decide how to handle exceptions when AI recommendations conflict with operational priorities or plant conditions.
  • •Set policy guardrails for tariff response, emissions limits, and acceptable tradeoffs between cost and throughput.

AI Handles

  • •Forecast near-term energy consumption, marginal energy cost per ton, and peak demand risk across major mill processes.
  • •Recommend coordinated setpoints and scheduling actions for furnaces, compressors, pumps, and on-site utilities.
  • •Continuously monitor process, equipment, ambient, and price signals to detect inefficiency and emerging anomalies.
  • •Prioritize actions for peak avoidance, load shifting, and fuel-electricity dispatch under production and emissions constraints.

Operating Intelligence

How it works

AI runs the first three steps autonomously.

Humans own every decision.

The system gets smarter each cycle.

Confidence92%
ArchetypeRecommend & Decide
Shape6-step converge
Human gates1
Autonomy
67%AI controls 4 of 6 steps

Who is in control at each step

Each column marks the operating owner for that step. AI-led actions sit above the divider, human decisions and feedback loops sit below it.

Loop shapeconverge

Step 1

Assemble Context

Step 2

Analyze

Step 3

Recommend

Step 4

Human Decision

Step 5

Execute

Step 6

Feedback

AI lead

Autonomous execution

1AI
2AI
3AI
5AI
gate

Human lead

Approval, override, feedback

4Human
6↺ Loop
AI-led step
Human-controlled step
Feedback loop
TL;DR

AI handles assembly, analysis, and execution. The human gate sits at the decision point. Every cycle refines future recommendations.

The Loop

6 steps

1 operating angles mapped

Operational Depth

Technologies

Technologies commonly used in Steel Mill Energy Optimization implementations:

Historical asset operations dataOther
4 mentions
Operator interface for review and trustOther
4 mentions
Real-time operational data feedsOther
4 mentions
Gas turbine service workflow integrationOther
3 mentions
Machine learning life-extension modelsOther
3 mentions

Key Players

Companies actively working on Steel Mill Energy Optimization solutions:

Baker HughesMitsubishi PowerSiemens Energy

Real-World Use Cases

ML-based gas turbine parts life extension from customer-specific usage patterns

AI studies how each customer actually runs a gas turbine and estimates whether certain parts can safely last longer before replacement.

predictive risk scoring on asset life consumptionproposed/early deployment use case explicitly described by ge vernova as an ai application in the energy sector.
10.0

Free access to this report