Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
KaizenAI: Methodology for the Integration of Machine Learning in Manufacturing Processes Based on Kaizen Principles. Case Study: Bottling Industry. |
| Συγγραφείς: |
Soto-Chambilla, Alonso1 asotoc@ulasalle.edu.pe, Fernández-Del-Carpio, Alvaro1 alfernandez@ulasalle.edu.pe, Córdova-Silva, Heidi2 hcordovas@unsa.edu.pe, Luque-Mamani, Edson1 eluquem@ulasalle.edu.pe, Alatrista-Corrales, Arturo1 aalatrista@ulasalle.edu.pe |
| Πηγή: |
Journal of Industrial Engineering & Management. 2026, Vol. 19 Issue 2, p288-304. 17p. |
| Θεματικοί όροι: |
*Continuous improvement process, *Manufacturing processes, *Industry 4.0, *Digital transformation, *Beverage industry, Machine learning, Condition-based maintenance |
| Περίληψη: |
Purpose: Digital transformation in manufacturing has placed artificial intelligence (AI) at the center of the debate on efficiency and sustainability. However, its adoption in established plants faces barriers related to cultural resistance, data quality, and the absence of methodologies that guide its progressive implementation. In this context, the article proposes KaizenAI, a hybrid methodology that integrates the principles of continuous improvement with the predictive capabilities of AI. Methodology: This article presents KaizenAI, a hybrid methodology that integrates the principles of the PDCA cycle with user-centered design (UCD) tools, quality function deployment (QFD), Kata routines, and digital 5S principles, combining them with machine learning models to anticipate failures and optimize processes. The proposal was validated through a case study in a bottling plant, applying a predictive model based on 18 months of operational data from the overall equipment effectiveness (OEE) system. Findings: Preliminary results show that a plant with intermediate digital maturity (2.6/6) can develop effective predictive capabilities by integrating the Kaizen approach with interpretable statistical models. The SARIMA model outperformed Random Forest and XGBoost with a 98.2% reduction in MAE, demonstrating that methodological simplicity can surpass algorithmic complexity in industrial environments with high variability. Moreover, the Kaizen--AI convergence acts as a methodological bridge for introducing digital capabilities without breaking the incremental logic of continuous improvement. Originality/value: The main contribution of the study lies in integrating the Kaizen philosophy with AI within a hybrid framework that connects the human with the digital and the incremental with the predictive. This approach facilitates the gradual adoption of AI without disrupting continuous improvement and offers a practical pathway toward Industry 4.0 while minimizing organizational resistance. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Industrial Engineering & Management is the property of Omnia Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Business Source Index |