DEMAND PREDICTION IN INDUSTRY 4.0 THROUGH A TRANSFORMER-BASED ARCHITECTURE (PREDICCIÓN DE LA DEMANDA EN LA INDUSTRIA 4.0 EMPLEANDO UNA ARQUITECTURA BASADA EN TRANSFORMERS)
Resumen
Given the changing circumstances faced by the industry today product demand is constantly influenced by several factors such as global economic conditions affected by wars, pandemics and recessions. For companies to cope with these challenges effectively, it is crucial to have a dependable demand prediction system that can be swiftly and efficiently communicated to their supply chain. However, this can be challenging for large consortiums with distributed supply chains spanning different countries. In this study a neural network architecture based on Transformers is proposed for demand prediction. This system could be integrated into a cloud service accessible to various locations within a company's supply chain, thus reducing information delays. By evaluating our approach with real product demand data and comparing it with other architectures the experiments prove that our model outperforms other methods.
Keywords: Demand prediction, Industry 4.0, Transformers.
Resumen
En la actualidad, la industria enfrenta desafíos debido a factores cambiantes como guerras, pandemias y recesiones que afectan la demanda de productos. Para enfrentar estos retos es crucial contar con un sistema confiable de predicción de demanda que se comunique eficientemente con la cadena de suministro. Sin embargo, esto puede ser un reto para grandes consorcios con cadenas de suministro distribuidas en diferentes países. En este estudio se propone una arquitectura de red neuronal basada en transformadores para predecir la demanda. Este sistema se integraría en un servicio en la nube accesible desde distintas ubicaciones dentro de la cadena de suministro, reduciendo los retrasos en la información. Los experimentos con datos reales demuestran que nuestro modelo supera a otras arquitecturas de predicción de demanda.
Palabras Clave: Industria 4.0, Predicción de demanda, Transformadores.
Texto completo:
579-595 PDFReferencias
Agapitos, A., Brabazon, A., & O’Neill, M. Regularised gradient boosting for financial time-series modelling. Computational Management Science. Vol. 14, p. 367-91, 2017.
Bandara, K., Shi, P., Bergmeir, C., Hewamalage, H., Tran, Q., & Seaman, B. Sales demand forecast in e-commerce using a long short-term memory neu-ral network methodology. Neural Information Processing: 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12–15, 2019, Proceedings, Part III 26, p. 462-474, 2019.
Behie, SW., Pasman, HJ., Khan, FI., Shell, K., Alarfaj, A., El-Kady, AH., & Hernandez, M. Leadership 4.0: The changing landscape of industry man-agement in the smart digital era. Process Safety and Environmental Protec-tion. No. 172, p. 317-328, 2023.
Cao, Y., Dang, Z., Wu, F., Xu, X., & Zhou, F. Probabilistic Electricity Demand Forecasting with Transformer-Guided State Space Model. In 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engi-neering (AUTEEE). p. 964-969 IEEE, 2022.
Chandriah, KK., & Naraganahalli, RV. RNN/LSTM with modified Adam opti-mizer in deep learning approach for automobile spare parts demand fore-casting. Multimedia Tools and Applications. No. 17, Vol. 80, p. 26145-26159, 2021.
Elamir, EA. On Uses of Mean Absolute Deviation: Shape Exploring and Dis-tribution Function Estimation. arXiv preprint arXiv:2206.09196. 2022.
Hodson, TO. Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development Discussions. p. 1-10, 2022.
Kaushik, M., & Guleria, N. The impact of pandemic COVID-19 in workplace. European Journal of Business and Management. No. 15, Vol. 12, p. 1-10, 2020.
Karunasingha, DS. Root mean square error or mean absolute error? Use their ratio as well. Information Sciences. Vol. 585, p. 609-29, 2022.
Kilimci, ZH., Akyuz, AO., Uysal, M., Akyokus, S., Uysal, MO., Atak Bulbul, B., & Ekmis, MA. An improved demand forecasting model using deep learning approach and proposed decision integration strategy for supply chain. Com-plexity. Vol. 2019, Article ID 9067367, 15 pages, 2019.
Koohfar, S., Woldemariam, W., & Kumar, A. Prediction of Electric Vehicles Charging Demand: A Transformer-Based Deep Learning Approach. Sus-tainability. No. 3, Vol. 15, p. 2105, 2023.
Körner, P., Kronenberg, R., Genzel, S., & Bernhofer, C. Introducing Gradient Boosting as a universal gap filling tool for meteorological time series. Mete-orol. Z. No. 5, Vol. 27, p. 369-376, 2018.
Nazir, A., Shaikh, A. K., Shah, A. S., & Khalil, A. Forecasting energy con-sumption demand of customers in smart grid using Temporal Fusion Trans-former (TFT). Results in Engineering, Vol. 17, 2023.
Novoszel, L., & Wakolbinger, T. Meta-analysis of supply chain disruption re-search. Operations research forum (2022). Cham: Springer International Publishing. No. 1, Vol. 3, p. 10, 2022.
Saptaningtyas, WW., & Rahayu, DK. A proposed model for food manufactur-ing in smes: Facing industry 5.0. Proceedings of the 5th NA International Conference on Industrial Engineering and Operations Management Detroit, Michigan, USA, August 10 - 14, 2020. p. 1653-1661, 2020.
Seyedan, M., & Mafakheri, F. Predictive big data analytics for supply chain demand forecasting: methods, applications, and research opportuni-ties, Journal of Big Data. No. 1, Vol. 7, p. 1-22, 2020.
Temizhan, E., Mirtagioglu, H., & Mendes, M. Which correlation coefficient should be used for investigating relations between quantitative variables. American Academic Scientific Research Journal for Engineering, Technolo-gy, and Sciences. Vol. 85, p. 265-277, 2022.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, AN., Kaiser, Ł., & Polosukhin, I. Attention is all you need. Advances in Neural In-formation Processing Systems 30 (NIPS 2017). Vol. 30, 2017.
Vo, TT., Le, PH., Nguyen, NT., Nguyen, TL., & Do, NH. Demand Forecasting and Inventory Prediction for Apparel Product using the ARIMA and Fuzzy EPQ Model. Journal of Engineering Science & Technology Review. No. 2, Vol. 14, p. 80-89, 2021.
Wang, L., Mykityshyn, A., Johnson, C., & Cheng, J. Flight demand forecast-ing with transformers. In AIAA AVIATION Forum 2022. p. 3708, 2022.
Wang, T., Li, Y., Chang, W., & Zhou, S. A bagging ensemble learning traffic demand prediction model based on improved LSTM and transformer. Third International Conference on Computer Science and Communication Tech-nology (ICCSCT 2022). Vol. 12506, p. 469–477, 2022.
Wu, B., Wang, L., & Zeng, YR. Interpretable tourism demand forecasting with temporal fusion transformers amid COVID-19. Applied Intelligence. No. 11, Vol. 53, p. 14493-14514, 2023.
Yi, S., Chen, X., & Tang, C. Tsformer: Time series transformer for tourism de-mand forecasting. arXiv preprint arXiv:2107.10977, 2021.
Zhang, GP., Xia, Y., & Xie, M. Intermittent demand forecasting with transform-er neural networks. Annals of Operations Research. p. 1-22, 2023.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada. 
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx