Manufacturing / Industrial equipment
Hyster-Yale Materials Handling: Checking installed parts and missed steps during lift truck assembly
- Company
- Hyster-Yale Materials Handling
- Country
- United States
- Adoption stage
- In operation
- Source published
- Date basis
- The date the source was published. It can differ from the date adoption started.
- How the source was checked
- Read the full source text
The work problem
Hyster-Yale Materials Handling needed to confirm that all parts were installed and required assembly stages were complete while building lift trucks. NTT DATA's official release describes the aim as identifying deviations during assembly so that quality issues can be addressed before a product moves to the next stage or leaves the factory. Faster deployment and iteration than legacy methods were also objectives.
Technology and data
NTT DATA integrated vision sensors, on-site edge AI and analytics into a critical assembly workflow at the Berea, Kentucky plant. A physical AI model adapted with Archetype AI compares sensor-observed assembly activity against expected production steps. It validates installed parts and completed assembly stages and flags deviations before the product advances. Local processing helps production teams identify and address issues before products leave the factory.
Results
NTT DATA said early results reduced deployment timelines from months with legacy techniques to weeks. Hyster-Yale's manufacturing innovation director said the collaboration helps production teams maintain quality standards and product reliability. This is quality validation embedded in an actual factory assembly workflow; expansion to other factories was described as an area being explored.
Limits and open questions
Detection accuracy, the reduction in defect rates and cost savings were not disclosed. The confirmed scope is a particular assembly workflow in Berea, not a deployment across all global factories.
Sources
Compiled from public sources. These are not results from ATF Works customers.