Evolutionary Control of Industrial Processes Using Digital Twin
Resumo
A crescente variabilidade nos processos industriais modernos exige sistemas de controle mais flexíveis, capazes de se adaptar sem reprogramações manuais tradicionalmente empregadas nesses casos. Este trabalho objetiva mostrar que é possível complementar o controle industrial com uma camada adaptativa que responda dinamicamente a novos cenários, sem necessidade de reconfiguração. Para isso, investiga a aplicação do algoritmo NEAT para treinar um modelo de inteligência artificial capaz de aprender e ajustar-se autonomamente a mudanças no ambiente produtivo, aqui modelado por meio de um gêmeo digital. Os resultados obtidos indicam que tal abordagem pode alcançar desempenho robusto frente a diferentes configurações de processo, abrindo caminho para sistemas de automação mais resilientes e autônomos.Referências
Ali, M., Liu, S., and Yang, Q. (2025). Digital twin-enabled real-time control in robotic additive manufacturing via soft actor-critic reinforcement learning. arXiv preprint arXiv:2501.18016.
CodeReclaimers (2024). Neat-python documentation. [link]. Accessed: 2025-05-26.
Fausett, L. (1994). Fundamentals of neural networks. Prentice Hall.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT Press.
Grieves, M. (2014). Digital twin: manufacturing excellence through virtual factory replication. White paper. Available online: [link].
Grus, J. (2016). Data science do zero. Alta Books.
Haykin, S. (1999). Neural networks: principles and practice. Pearson, 2 edition.
Hoel, A. (2023). Balancing pole with neat in python.
Huang, Z., Shen, Y., Li, J., Fey, M., and Brecher, C. (2021). A survey on ai-driven digital twins in industry 4.0: Smart manufacturing and advanced robotics. Sensors, 21(19):6340.
Kagermann, H., Wahlster, W., and Helbig, J. (2013). Recommendations for implementing the strategic initiative industrie 4.0. Technical report, National Academy of Science and Engineering, Frankfurt.
Khan, S. et al. (2024). Industrial ai: a 2024 review. IEEE Access, 12:12345–12356.
Lee, J., Bagheri, B., and Kao, H. A. (2015). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 3:18–23.
Liu, J. and Liu, B. (2023). Digital twin driven rl for production lines. Applied Sciences, 13(3):456.
Neuromatch Academy (2024). Neural decoding with deep learning. [link]. Accessed: 2025-05-26.
Ortiz, J. S., Quishpe, E. K., Sailema, G. X., and Guamán, N. S. (2025). Digital twin-based active learning for industrial process control and supervision in industry 4.0. Sensors, 25(7):2076.
Qi, Q. and Tao, F. (2018). Digital twin and big data towards smart manufacturing and industry 4.0: 360 degree comparison. IEEE Access, 6:3585–3593.
Qiu, H., Al-Nussairi, A. K. J., Chevinli, Z. S., Singh, N. S. S., Chyad, M. H., Yu, J., and Maesoumi, M. (2025). Integrating digital twins with neural networks for adaptive control of automotive suspension systems. Scientific Reports, 15(1):11078.
REAL GAMES (2024). Factory i/o documentation. [link]. Accessed on: 2025-04-25.
Stanley, K. O. and Miikkulainen, R. (2002). Evolving neural networks through augmenting topologies. Evolutionary Computation, 10(2):99–127.
Su, C., Tang, X., Jiang, Q., Han, Y., Wang, T., and Jiang, D. (2025). Digital twin system for manufacturing processes based on a multi-layer knowledge graph model. Scientific Reports, 15(1):12835.
Sutton, R. S. and Barto, A. G. (2018). Reinforcement learning: an introduction. The MIT Press, 2 edition.
Walmsley, T. G., Patros, P., Yu, W., Young, B. R., Burroughs, S., Apperley, M., Carson, J. K., Udugama, I. A., Aeowjaroenlap, H., Atkins, M. J., and Walmsley, M. R. W. (2024). Adaptive digital twins for energy-intensive industries and their local communities. Digital Chemical Engineering, 10:100139.
CodeReclaimers (2024). Neat-python documentation. [link]. Accessed: 2025-05-26.
Fausett, L. (1994). Fundamentals of neural networks. Prentice Hall.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT Press.
Grieves, M. (2014). Digital twin: manufacturing excellence through virtual factory replication. White paper. Available online: [link].
Grus, J. (2016). Data science do zero. Alta Books.
Haykin, S. (1999). Neural networks: principles and practice. Pearson, 2 edition.
Hoel, A. (2023). Balancing pole with neat in python.
Huang, Z., Shen, Y., Li, J., Fey, M., and Brecher, C. (2021). A survey on ai-driven digital twins in industry 4.0: Smart manufacturing and advanced robotics. Sensors, 21(19):6340.
Kagermann, H., Wahlster, W., and Helbig, J. (2013). Recommendations for implementing the strategic initiative industrie 4.0. Technical report, National Academy of Science and Engineering, Frankfurt.
Khan, S. et al. (2024). Industrial ai: a 2024 review. IEEE Access, 12:12345–12356.
Lee, J., Bagheri, B., and Kao, H. A. (2015). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 3:18–23.
Liu, J. and Liu, B. (2023). Digital twin driven rl for production lines. Applied Sciences, 13(3):456.
Neuromatch Academy (2024). Neural decoding with deep learning. [link]. Accessed: 2025-05-26.
Ortiz, J. S., Quishpe, E. K., Sailema, G. X., and Guamán, N. S. (2025). Digital twin-based active learning for industrial process control and supervision in industry 4.0. Sensors, 25(7):2076.
Qi, Q. and Tao, F. (2018). Digital twin and big data towards smart manufacturing and industry 4.0: 360 degree comparison. IEEE Access, 6:3585–3593.
Qiu, H., Al-Nussairi, A. K. J., Chevinli, Z. S., Singh, N. S. S., Chyad, M. H., Yu, J., and Maesoumi, M. (2025). Integrating digital twins with neural networks for adaptive control of automotive suspension systems. Scientific Reports, 15(1):11078.
REAL GAMES (2024). Factory i/o documentation. [link]. Accessed on: 2025-04-25.
Stanley, K. O. and Miikkulainen, R. (2002). Evolving neural networks through augmenting topologies. Evolutionary Computation, 10(2):99–127.
Su, C., Tang, X., Jiang, Q., Han, Y., Wang, T., and Jiang, D. (2025). Digital twin system for manufacturing processes based on a multi-layer knowledge graph model. Scientific Reports, 15(1):12835.
Sutton, R. S. and Barto, A. G. (2018). Reinforcement learning: an introduction. The MIT Press, 2 edition.
Walmsley, T. G., Patros, P., Yu, W., Young, B. R., Burroughs, S., Apperley, M., Carson, J. K., Udugama, I. A., Aeowjaroenlap, H., Atkins, M. J., and Walmsley, M. R. W. (2024). Adaptive digital twins for energy-intensive industries and their local communities. Digital Chemical Engineering, 10:100139.
Publicado
29/09/2025
Como Citar
SILVA, Renato Bruno; ORBOLATO, Daniela Resende Silva.
Evolutionary Control of Industrial Processes Using Digital Twin. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 22. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 333-344.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2025.12423.
