Publications

@inproceedings{10.1007/978-3-031-82334-3_61,
  isbn = {978-3-031-82334-3},
  abstract = {This study focuses on the exploration and application of machine learning techniques to predict the process time of operations with high variability. The proposed methodology includes the identification of significant parameters, the individual prediction of every operation and the integration of individual prediction to determine the lead time of the chain. The study is conducted in wind tower manufacturing plants located in Spain and Brazil. The proposed approach overcomes the limitations of other current techniques such as direct formulation or linear programming. The results indicate that, overall, gradient boosting models, such as XGBoost or LightGBM, achieve better performance in a significant portion of the operations, although other models like NODE also demonstrate superior results in certain specific operations.},
  pages = {350--355},
  address = {Cham},
  publisher = {Springer Nature Switzerland},
  year = {2025},
  booktitle = {Organizational Engineering, Coping with Complexity},
  title = {Machine Learning Techniques to Predict Process Time in Operations with High Variability},
  editor = {Carrasco-Gallego, Ruth
and Moreno-Serna, Jaime
and Gutierrez, Miguel
and Avil{\'e}s-Palacios, Carmen},
  author = {Flores-Huam{\'a}n, Kenny-Jes{\'u}s
and Mu{\~{n}}oz-D{\'i}az, Mar{\'i}a-Luisa
and Rodr{\'i}guez-Palero, Mar{\'i}a
and Escudero-Santana, Alejandro},
}

@article{math12152347,
  doi = {10.3390/math12152347},
  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.},
  issn = {2227-7390},
  url = {https://www.mdpi.com/2227-7390/12/15/2347},
  article-number = {2347},
  number = {15},
  year = {2024},
  volume = {12},
  journal = {Mathematics},
  title = {Lead-Time Prediction in Wind Tower Manufacturing: A Machine Learning-Based Approach},
  author = {Flores-Huamán, Kenny-Jesús and Escudero-Santana, Alejandro and Muñoz-Díaz, María-Luisa and Cortés, Pablo},
}