Lead-Time Prediction in Wind Tower Manufacturing: A Machine Learning-Based Approach

Kenny-Jesús Flores-Huamán, Alejandro Escudero-Santana (), María-Luisa Muñoz-Díaz and Pablo Cortés
Additional contact information
Kenny-Jesús Flores-Huamán: Departamento de Organización Industrial y Gestión de Empresas II, Escuela Técnica Superior de Ingeniería, Universidad de Sevilla, Cm. de los Descubrimientos, s/n, 41092 Seville, Spain
Alejandro Escudero-Santana: Departamento de Organización Industrial y Gestión de Empresas II, Escuela Técnica Superior de Ingeniería, Universidad de Sevilla, Cm. de los Descubrimientos, s/n, 41092 Seville, Spain
María-Luisa Muñoz-Díaz: Departamento de Organización Industrial y Gestión de Empresas II, Escuela Técnica Superior de Ingeniería, Universidad de Sevilla, Cm. de los Descubrimientos, s/n, 41092 Seville, Spain
Pablo Cortés: Departamento de Organización Industrial y Gestión de Empresas II, Escuela Técnica Superior de Ingeniería, Universidad de Sevilla, Cm. de los Descubrimientos, s/n, 41092 Seville, Spain

Mathematics, 2024, vol. 12, issue 15, 1-34

Abstract: This study focuses on estimating the lead times of various processes in wind tower factories. Accurate estimation of these times allows for more efficient sequencing of activities, proper allocation of resources, and setting of realistic delivery dates, thus avoiding delays and bottlenecks in the production flow and improving process quality and efficiency. In addition, accurate estimation of these times contributes to a proper assessment of costs, overcoming the limitations of traditional techniques; this allows for the establishment of tighter quotations. The data used in this study were collected at wind tower manufacturing facilities in Spain and Brazil. Data preprocessing was conducted rigorously, encompassing cleaning, transformation, and feature selection processes. Following preprocessing, machine learning regression analysis was performed to estimate lead times. Nine algorithms were employed: decision trees, random forest, Ridge regression, Lasso regression, Elastic Net, support vector regression, gradient boosting, XGBoost, LightGBM, and multilayer perceptron. Additionally, the performance of two deep learning models, TabNet and NODE, designed specifically for tabular data, was evaluated. The results showed that gradient boosting-based algorithms were the most effective in predicting processing times and optimizing resource allocation. The system is designed to retrain models as new information becomes available.

Keywords: industrial machine learning; deep learning; regression; process time; prediction (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/15/2347/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/15/2347/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:15:p:2347-:d:1444072

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().