Nonlinear Regression Based Predictive Maintenance Framework to Reduce Unplanned Downtime in a Fishmeal Plant

Autores/as

DOI:

https://doi.org/10.26439/ciii2025.8643

Palabras clave:

Fishmeal industry, predictive maintenance, reliability modeling, scheduling threshold

Resumen

The fishing industry operates under demanding conditions in which limited and inconsistent machinery records often result in reactive maintenance strategies and unplanned downtime. This study proposes a predictive maintenance (PdM) framework for a fishmeal plant in Callao, Peru, integrating Lean principles with reliability modeling based on nonlinear regression to generate actionable maintenance planning inputs. The framework was embedded in discrete-event simulations using Arena, through which a 50% reduction in unplanned downtime and a 20% increase in equipment uptime were estimated compared with the baseline scenario. These results highlight the operational benefits of a reliability-driven planning approach and demonstrate that structured and validated maintenance records can significantly improve equipment availability and operational efficiency in fishmeal processing plants.

Descargas

Los datos de descarga aún no están disponibles.

Biografía del autor/a

  • Diego A. La Torre Villegas, Carrera de Ingeniería Industrial, Universidad de Lima, Perú

    Diego Alexander La Torre Villegas holds a Bachelor’s degree in Industrial Engineering from Universidad de Lima. He has professional experience in corporate general services, process automation, and data analysis in the energy sector at Repsol. His research focuses on manufacturing process optimization through the integration of Lean Manufacturing methodologies and machine learning techniques. His areas of interest include process automation, business intelligence, and project management.

  • Gabriel E. Nores Quispe, Carrera de Ingeniería Industrial, Universidad de Lima, Perú

    Gabriel Enrique Nores Quispe holds a Bachelor’s degree in Industrial Engineering from Universidad de Lima, Peru. He currently works as a Logistics Operations Assistant at Esmeralda Corp, where he primarily supports the technology area and participates in the implementation and management of databases oriented toward the optimization of the organization’s operational and logistics processes. His areas of interest include process optimization and database management and analysis.

  • Silvia P. Ponce Álvarez, Carrera de Ingeniería Industrial, Universidad de Lima, Perú

    Silvia Ponce Álvarez holds a PhD in Applied Physical Chemistry from Universidad Autónoma de Madrid and a Bachelor’s degree in Chemistry from Universidad Nacional Mayor de San Marcos. She completed her doctoral thesis at Instituto de Catálisis y Petroleoquímica (CSIC, Spain). She has carried out postdoctoral research at Institut für Angewandte Chemie (ACA-Berlin, Germany), Universidad de Buenos Aires (Argentina), Universidad Autónoma de Madrid (Spain), and Auburn University (United States), and was a fellow of AECI-ICI (Spain) and DAAD. She leads the research groups on Applied Nanomaterials and Circular Economy. She has participated as principal investigator and co-investigator in research projects funded by ProCiencia, PNIPA, Innovate Peru, TWAS, and UNESCO–L’Oréal, among others. She serves as an external evaluator of projects funded through competitive grants from FONDECYT, UNMSM, and PUCP, and as a reviewer for journals indexed in Scopus and Web of Science. She is the recipient of the For Women in Science 2013–Peru Award, Green Patent 2022, General Prize of the Indecopi Contest 2022, Peruvian Inventor Award 2022, and the Silver Medal at KIWIE 2023. Her research interests include nanomaterials derived from agro-industrial waste, heterogeneous and environmental catalysis, photocatalysis, and the removal of aqueous contaminants using non-conventional methods.

Referencias

[1] M. Achouch et al., “On predictive maintenance in Industry 4.0: Overview, models, and challenges,” Appl. Sci., vol. 12, no. 16, p. 8081, Aug. 2022, doi: https://doi.org/10.3390/app12168081

[2] P. Nunes, J. Santos, and E. Rocha, “Challenges in predictive maintenance – A review,” CIRP J. Manuf. Sci. Technol., vol. 40, pp. 53–67, Feb. 2023, doi: https://doi.org/10.1016/j.cirpj.2022.11.004

[3] R. B. Shetty, “Predictive maintenance in the IoT era,” in Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things, Hoboken, NJ, USA: Wiley, 2018, ch. 21, pp. 589–612, doi: https://doi.org/10.1002/9781119515326.ch21

[4] A. Dogan and D. Birant, “Machine learning and data mining in manufacturing,” Expert Syst. Appl., vol. 166, p. 114060, Mar. 2021, doi: https://doi.org/10.1016/j.eswa.2020.114060

[5] S. T. March and G. D. Scudder, “Predictive maintenance: Strategic use of IT in manufacturing organizations,” Inf. Syst. Front., vol. 21, no. 2, pp. 327–341, Mar. 2017, doi: https://doi.org/10.1007/s10796-017-9749-z

[6] M. Molęda, B. Małysiak-Mrozek, W. Ding, V. Sunderam, and D. Mrozek, “From corrective to predictive maintenance—A review of maintenance approaches for the power industry,” Sensors, vol. 23, no. 13,

p. 5970, Jun. 2023, doi: https://doi.org/10.3390/s23135970

[7] A. S. Kalafatelis, N. Nomikos, A. Giannopoulos, and P. Trakadas, “A survey on predictive maintenance in the maritime industry using machine and federated learning,” 2024, TechRxiv:173473250.04784922.v1.

[8] A. Sahli, R. Evans, and A. Manohar, “Predictive maintenance in Industry 4.0: Current themes,” Procedia CIRP, vol. 104, pp. 1948–1953, Nov. 2021, doi: https://doi.org/10.1016/j.procir.2021.11.329

[9] A. Ucar, M. Karakose, and N. Kırımça, “Artificial intelligence for predictive maintenance applications: Key components, trustworthiness, and future trends,” Appl. Sci., vol. 14, no. 2, Art. no. 898, Jan. 2024, doi: https://doi.org/10.3390/app14020898

[10] R. R. Neeraj et al., “Modelling and simulation of discrete manufacturing industry,” Mater. Today: Proc., vol. 5, no. 11, pp. 24971–24983, Jan. 2018, doi: https://doi.org/10.1016/j.matpr.2018.10.298

[11] S. Kumar, K. K. Raj, M. Cirrincione, G. Cirrincione, V. Franzitta, and R. R. Kumar, “A comprehensive review of remaining useful life estimation approaches for rotating machinery,” Energies, vol. 17, no. 22, Art. no. 5538, Nov. 2024, doi: https://doi.org/10.3390/en17225538

[12] Deloitte Analytics Institute, “Predictive maintenance position paper,” Deloitte, London, U.K., 2017. Accessed: Aug. 15, 2025. [Online]. Available: https://www2.deloitte.com/content/dam/Deloitte/de/Documents/deloitte-analytics/Deloitte_Predictive-Maintenance_PositionPaper.pdf

[13] S. Vilarinho, I. Lopes, and J. A. Oliveira, “Preventive maintenance decisions through maintenance optimization models: A case study,” Procedia Manuf.,

vol. 11, pp. 1170–1177, Jan. 2017, doi: https://doi.org/10.1016/j.promfg.2017.07.241

[14] Y. Pang, Y. Wang, X. Lai, S. Zhang, P. Liang, and X. Song, “Enhanced Kriging leave-one-out cross-validation in improving model estimation and optimization,” Comput. Methods Appl. Mech. Eng., vol. 414, Art. no. 116194, Sep. 2023, doi: https://doi.org/10.1016/j.cma.2023.116194

[15] T. Zhou and Y. Peng, “An active-learning reliability method based on support vector regression and cross-validation,” Comput. Struct., vol. 276, Art. no. 106943, Feb. 2023, doi: https://doi.org/10.1016/j.compstruc.2022.106943

[16] S. Ayvaz and K. Alpay, “Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time,” Expert Syst. Appl., vol. 173, Art. no. 114598, Jul. 2021, doi: https://doi.org/10.1016/j.eswa.2021.114598

[17] J. C. Oliveira Ojeda et al., “Application of a predictive model to reduce unplanned downtime in automotive industry production processes: A sustainability perspective,” Sustainability, vol. 17, no. 9, Art. no. 3926, Apr. 2025, doi: https://doi.org/10.3390/su17093926

[18] T. Abbasi, K. H. Lim, N. S. Rosli, I. Ismail, and R. Ibrahim, “Development of predictive maintenance interface using multiple linear regression,” in Proc. 2018 Int. Conf. Intell. Adv. Syst. (ICIAS), Kuala Lumpur, Malaysia, Aug. 2018, doi: https://doi.org/10.1109/ICIAS.2018.8540602

[19] K. C. Siju and M. Kumar, “Bayesian estimation of reliability using time-to-failure distribution of parametric degradation models,” J. Stat. Comput. Simul., vol. 88, no. 9, pp. 1717–1748, Mar. 2018, doi: https://doi.org/10.1080/00949655.2018.1445743

[20] S.-T. Tseng and I.-C. Lee, “Optimum allocation rule for accelerated degradation tests with a class of exponential-dispersion degradation models,” Technometrics, vol. 58, no. 2, pp. 244–254, Apr. 2016, doi: https://doi.org/10.1080/00401706.2015.1033109

[21] H. Mahfoud, O. Moutaoukil, M. T. Benchekroun, and A. Latif, “Real-time predictive maintenance-based process parameters: Towards an industrial sustainability improvement,” in Proc. Int. Conf. Adv. Intell. Syst. Sustain. Dev. (AI2SD’2023), pp. 18–34, Mar. 2024, doi: https://doi.org/10.1007/978-3-031-54288-6_3

[22] C. Resende et al., “TIP4.0: Industrial Internet of Things platform for predictive maintenance,” Sensors, vol. 21, no. 14, p. 4676, Jul. 2021, doi: https://doi.org/10.3390/s21144676

Descargas

Publicado

2026-06-08

Número

Núm. 004 (2025): IV Congreso Internacional de Ingeniería Industrial

Sección

Ponencias

Licencia

Derechos de autor 2026 Congreso Internacional de Ingeniería Industrial de la Universidad de Lima

Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.