Hybrid-Intelligence Lean Six Sigma for Error-Proof Part Supply: Graph Neural Networks and Multiobjective Optimization

Abstract Purpose This study aims to eliminate part-supply errors, reduce non-value-added labour, and improve ergonomic conditions in high-mix single-axis linear actuator assembly using the DMAIC methodology. Methods A DMAIC-based case study was conducted in a Vietnamese precision-component manufacturing plant. Pareto analysis, process observation, 4M Ishikawa diagrams, on-site verification, and cause-prioritization matrices identified three root causes from seven candidates. Five improvement solutions were implemented, including single-order kitting, a two-level tray conveyor, centralized automatic ball feeding, point-of-use parts storage, and barcode-based poka-yoke verification. Results Missing and incorrect parts accounted for 76% of assembly part defects, with an initial supply-error rate of 0.31%. Supply errors decreased from 6.33 per month to zero during the post-improvement verification month (p ≈ 0.0018). Ball insertion time decreased by 1.13 minutes per cycle, while non-value-added labour was reduced by 3,203 hours annually. The improvements generated annual savings of US$7,110 from a US$5,200 investment, achieving an 8.8-month payback period and a first-year return on investment of approximately 37%. Value : This study demonstrates a cost-effective, human-centred DMAIC approach integrating error-proofing, material-flow redesign, and ergonomic improvements to enhance assembly quality, operational efficiency, and sustainable manufacturing practices.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-11410941/v1
Primary Topic
Quality and Supply Management
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Hybrid-Intelligence Lean Six Sigma for Error-Proof Part Supply: Graph Neural Networks and Multiobjective Optimization

Minh Ly Duc, Do Ngoc Hien
1 links
Research Square
Quality and Supply Management
preprint

Hybrid-Intelligence Lean Six Sigma for Error-Proof Part Supply: Graph Neural Networks and Multiobjective Optimization

Minh Ly Duc, Do Ngoc Hien
preprint en

Abstract

Abstract Purpose This study aims to eliminate part-supply errors, reduce non-value-added labour, and improve ergonomic conditions in high-mix single-axis linear actuator assembly using the DMAIC methodology. Methods A DMAIC-based case study was conducted in a Vietnamese precision-component manufacturing plant. Pareto analysis, process observation, 4M Ishikawa diagrams, on-site verification, and cause-prioritization matrices identified three root causes from seven candidates. Five improvement solutions were implemented, including single-order kitting, a two-level tray conveyor, centralized automatic ball feeding, point-of-use parts storage, and barcode-based poka-yoke verification. Results Missing and incorrect parts accounted for 76% of assembly part defects, with an initial supply-error rate of 0.31%. Supply errors decreased from 6.33 per month to zero during the post-improvement verification month (p ≈ 0.0018). Ball insertion time decreased by 1.13 minutes per cycle, while non-value-added labour was reduced by 3,203 hours annually. The improvements generated annual savings of US$7,110 from a US$5,200 investment, achieving an 8.8-month payback period and a first-year return on investment of approximately 37%. Value : This study demonstrates a cost-effective, human-centred DMAIC approach integrating error-proofing, material-flow redesign, and ergonomic improvements to enhance assembly quality, operational efficiency, and sustainable manufacturing practices.

Research Square
Van Lang University (VN)
Ho Chi Minh City University of Technology and Education
Industry, innovation and infrastructure
Quality and Supply Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon