Bayesian Neural Models for Time-Series Prediction of CS28 Compressive Strength in Cement Manufacturing
Resumo
Dada a crescente importância da predição da resistência compressiva do cimento para o uso mais eficiente dos recursos da indústria, trabalhos recentes tem experimentado com modelos estatísticos para auxiliar o processo industrial. Esse trabalho estuda a aplicação de Aprendizagem Profunda Bayesiana para obtensão de predições robustas de resistência compressiva. Nosso trabalho é um caminho para que modelos similares possam no futuro serem integrados ao processo de tomada de decisão no chão de fábrica.
Referências
Agency, I. E. (2009). Cement Technology Roadmap: Carbon Emissions Reductions up to 2050.
Alexandrov, A., Benidis, K., Bohlke-Schneider, M., Flunkert, V., Gasthaus, J., Januschowski, T., Maddix, D. C., Rangapuram, S., Salinas, D., Schulz, J., Stella, L., Türkmen, A. C., and Wang, Y. (2019). Gluonts: Probabilistic time series models in python.
Asteriou, D. and Hall, S. (2016). ARIMA Models and the Box-Jenkins Methodology, pages 275-296.
Berriel, R., Teixeira Lopes, A., Rodrigues, A., Varejao, F., and Oliveira-Santos, T. (2017). Monthly energy consumption forecast: A deep learning approach. pages 4283-4290.
Flunkert, V., Salinas, D., and Gasthaus, J. (2017). Deepar: Probabilistic forecasting with autoregressive recurrent networks. arXiv preprint arXiv:1704.04110.
García-Casillas, P. E., Martinez, C. A., Montes, H. C., and García-Luna, A. (2007). Prediction of portland cement strength using statistical methods. Materials and Manufacturing Processes, 22(3):333-336.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org.
Green, K., Graefe, A., and Armstrong, J. (2011). Forecasting Principles, pages 527-534.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. 9:1735-80.
Khashei, M. and Bijari, M. (2010). An artificial neural network (p,d,q) model for time-series forecasting. Expert Systems with Applications, 37(1):479 - 489.
Kumar, N. and Naranje, V. (2019). Prediction of cement strength using machine learning approach. In 2019 Amity International Conference on Artificial Intelligence (AICAI), pages 239-243.
Kumar, N., Naranje, V., and Salunkhe, S. (2020). Cement strength prediction using cloud-based machine learning techniques. Journal of Structural Integrity and Maintenance, 5(4):244-251.
Laptev, N., Yosinski, J., Li, L. E., and Smyl, S. (2017). Time-series extreme event forecasting with neural networks at uber.
Maddix, D. C., Wang, Y., and Smola, A. (2018). Deep factors with gaussian processes for forecasting. arXiv preprint arXiv:1812.00098.
Marino, D. L., Amarasinghe, K., and Manic, M. (2016). Building energy load forecasting using deep neural networks. CoRR, abs/1610.09460.
Ramezanianpour, A. M. and Hooton, R. D. (2014). A study on hydration, compressive strength, and porosity of portland-limestone cement mixes containing scms. Cement and Concrete Composites, 51:1-13.
Robles, L. A., Ortega, J. C., Fu, J. S., Reed, G. D., Chow, J. C., Watson, J. G., and Moncada-Herrera, J. A. (2008). A hybrid arima and artificial neural networks model to forecast particulate matter in urban areas: The case of temuco, chile. Atmospheric Environment, 42(35):8331 - 8340.
Soroka, I. and Stern, N. (1976). Calcareous fillers and the compressive strength of portland cement. Cement and Concrete Research, 6(3):367-376.
Tsamatsoulis, D. (2014). Application of the static and dynamic models in predicting the future strength of portland cements.
Tsamatsoulis, D. (2015). Optimizing the cement compressive strength prediction by applying coupled linear models.
Zhang, Q., Yang, B., Wang, L., and Zhu, F. (2012). Predicting cement compressive strength using double-layer multi-expression programming. In 2012 Fourth International Conference on Computational and Information Sciences, pages 94-97.
Çolak, A. (2006). A new model for the estimation of compressive strength of portland cement concrete. Cement and Concrete Research, 36(7):1409-1413.
Alexandrov, A., Benidis, K., Bohlke-Schneider, M., Flunkert, V., Gasthaus, J., Januschowski, T., Maddix, D. C., Rangapuram, S., Salinas, D., Schulz, J., Stella, L., Türkmen, A. C., and Wang, Y. (2019). Gluonts: Probabilistic time series models in python.
Asteriou, D. and Hall, S. (2016). ARIMA Models and the Box-Jenkins Methodology, pages 275-296.
Berriel, R., Teixeira Lopes, A., Rodrigues, A., Varejao, F., and Oliveira-Santos, T. (2017). Monthly energy consumption forecast: A deep learning approach. pages 4283-4290.
Flunkert, V., Salinas, D., and Gasthaus, J. (2017). Deepar: Probabilistic forecasting with autoregressive recurrent networks. arXiv preprint arXiv:1704.04110.
García-Casillas, P. E., Martinez, C. A., Montes, H. C., and García-Luna, A. (2007). Prediction of portland cement strength using statistical methods. Materials and Manufacturing Processes, 22(3):333-336.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org.
Green, K., Graefe, A., and Armstrong, J. (2011). Forecasting Principles, pages 527-534.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. 9:1735-80.
Khashei, M. and Bijari, M. (2010). An artificial neural network (p,d,q) model for time-series forecasting. Expert Systems with Applications, 37(1):479 - 489.
Kumar, N. and Naranje, V. (2019). Prediction of cement strength using machine learning approach. In 2019 Amity International Conference on Artificial Intelligence (AICAI), pages 239-243.
Kumar, N., Naranje, V., and Salunkhe, S. (2020). Cement strength prediction using cloud-based machine learning techniques. Journal of Structural Integrity and Maintenance, 5(4):244-251.
Laptev, N., Yosinski, J., Li, L. E., and Smyl, S. (2017). Time-series extreme event forecasting with neural networks at uber.
Maddix, D. C., Wang, Y., and Smola, A. (2018). Deep factors with gaussian processes for forecasting. arXiv preprint arXiv:1812.00098.
Marino, D. L., Amarasinghe, K., and Manic, M. (2016). Building energy load forecasting using deep neural networks. CoRR, abs/1610.09460.
Ramezanianpour, A. M. and Hooton, R. D. (2014). A study on hydration, compressive strength, and porosity of portland-limestone cement mixes containing scms. Cement and Concrete Composites, 51:1-13.
Robles, L. A., Ortega, J. C., Fu, J. S., Reed, G. D., Chow, J. C., Watson, J. G., and Moncada-Herrera, J. A. (2008). A hybrid arima and artificial neural networks model to forecast particulate matter in urban areas: The case of temuco, chile. Atmospheric Environment, 42(35):8331 - 8340.
Soroka, I. and Stern, N. (1976). Calcareous fillers and the compressive strength of portland cement. Cement and Concrete Research, 6(3):367-376.
Tsamatsoulis, D. (2014). Application of the static and dynamic models in predicting the future strength of portland cements.
Tsamatsoulis, D. (2015). Optimizing the cement compressive strength prediction by applying coupled linear models.
Zhang, Q., Yang, B., Wang, L., and Zhu, F. (2012). Predicting cement compressive strength using double-layer multi-expression programming. In 2012 Fourth International Conference on Computational and Information Sciences, pages 94-97.
Çolak, A. (2006). A new model for the estimation of compressive strength of portland cement concrete. Cement and Concrete Research, 36(7):1409-1413.
Publicado
28/11/2022
Como Citar
LIRA, Thiago I. A.; FINGER, Marcelo.
Bayesian Neural Models for Time-Series Prediction of CS28 Compressive Strength in Cement Manufacturing. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 19. , 2022, Campinas/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 660-669.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2022.227165.
