Case study · Industrial machinery

Hybrid physics-ML model optimizes gear grinding at ITAMCO

CNC grinding is the most energy-intensive step in gear manufacturing, and parameters and wheel-dressing schedules were set conservatively.

Manufacturer
ITAMCO (Indiana Technology and Manufacturing Companies)
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

CNC grinding is the most energy-intensive step in gear manufacturing, and parameters and wheel-dressing schedules were set conservatively.

The approach

WVU combined a physics model of grinding with a deep neural network to recommend wheel speed, depth of cut, infeed and dressing schedules, and implemented the app at ITAMCO.

Reported improvements

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

Processing time per part↓ 41%
Energy consumption (potential)↓ 37%

1 use case in this implementation

  1. Process & yield optimization

    Hybrid physics plus deep-neural-network model that sets grinding parameters and tool reconditioning schedules to cut energy and cycle time.

    • Decrease in processing time equal to 222 min per part with potential to save $107K per year.
    • $6.9 k potential savings with a 37% decrease in energy consumption per year.

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.