Case study · Semiconductors & electronics

Western Digital Shanghai uses ML for water, energy and yield gains

The back-end plant faced 250% annual growth, 18-month technology transitions, workforce constraints and corporate footprint targets.

Manufacturer
Western Digital
Use cases
3
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

The back-end plant faced 250% annual growth, 18-month technology transitions, workforce constraints and corporate footprint targets.

The approach

Western Digital applied AI optical inspection, yield/root-cause analytics, ML optimization of its water recycling plant and ML 'should-consume' energy prediction.

Reported improvements

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

Normalized water consumption↓ 62%
Normalized GHG - scope 2↓ 57%
Normalized energy consumption↓ 51%
Energy consumption↓ 35%
Water recycle rate↑ 30%

4 use cases in this implementation

  1. Visual quality inspection

    AI-powered optical inspection.

    • 35% Energy consumption
  2. Root-cause analysis for quality & yield

    Analytics platform for yield management and root-cause analysis.

    • 0.3pp Product yield optimization
  3. Energy & utilities optimization

    Machine learning dynamically optimizes the water recycling plant.

    • 30% Water recycle rate
    • 62% Normalized water consumption
  4. Energy & utilities optimization

    ML predicts expected ('should') energy use to flag abnormal consumption.

    • 51% Normalized energy consumption
    • 57% Normalized GHG – scope 2

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.