Case study · Cement, glass & building materials

Deep-learning kiln control model piloted at Argos Roberta cement plant

Rotary kilns are the dominant energy and CO2 source in cement making, and operators lack the sensing and models to run them near optimum.

Manufacturer
Argos USA
Use cases
1
Evidence
Independently assessed
Year
2023

Independently assessed  This result was assessed or published by a party other than the manufacturer or its vendor (a World Economic Forum Lighthouse assessment, a government or institute report, or a peer-reviewed paper).

The challenge

Rotary kilns are the dominant energy and CO2 source in cement making, and operators lack the sensing and models to run them near optimum.

The approach

The University of Louisville built a deep-learning process control model and a multi-physics kiln model, then deployed and tested the predictive model and MPC at the Roberta plant.

Reported improvements

Percent change as reported by the source; hover for the exact wording

Energy consumption (potential)↓ 30%

1 use case in this implementation

  1. Process & yield optimization

    Deep-learning predictive model and model predictive control for the cement rotary kiln.

    • Potential to reduce energy consumption by 30% when smart sensors and controls are implemented at the production plant.
    • A 5% reduction in energy consumption will decrease CO2 emissions by 20 kiloton annually at the production plant.

Outcomes as reported by the source. We do not adjust, combine or extrapolate reported figures.

Related case studies

Put AI to work

Find the AI opportunities hiding in your plant.

Genvo, our implementation partner, works with manufacturers to pick the right first project, connect the systems you already run and put AI agents and tools into daily use, with people approving what goes out.

Assessments and consultations are provided by Genvo. How our partnership works.