Hybrid-Intelligence Lean Six Sigma for Error-Proof Part Supply: Graph Neural Networks and Multiobjective Optimization
Year: 2026
Type: preprint
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.
Source: Research Square
Authors: Minh Ly, Do Ngoc Hien
Institution: Van Lang University
Language: English
Subfield: Management Information Systems
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7234215894
