Estimating and tuning adaptive action plans for the control of smart interconnected poultry houses

• Darlan F. Klotz UTFPR http://orcid.org/0000-0002-7291-427X
• Dalcimar Casanova UTFPR https://orcid.org/0000-0002-1905-4602
• Marcelo Teixeira UTFPR https://orcid.org/0000-0002-1008-7838

DOI: https://doi.org/10.5753/sbiagro.2021.18381

Resumo

In poultry farming, the systematic choice, update, and implementation of periodic (t) action plans define the feed conversion rate (FCR[t]), which is an acceptable measure for successful production. Appropriate action plans provide tailored resources for broilers, allowing them to grow within the so-called comfort zone, without waste or lack of resources. Although the implementation of an action plan is automatic, its configuration depends on a specialist, which tends to be inefficient and result in variable FCR[t]. In this project, the specialist's perception is reproduced, to some extent, by computational intelligence. By combining deep learning and genetic algorithm techniques, we show how action plans can adapt their performance over the time, based on previous well succeeded plans. We also implement a network infrastructure to replicate our method over distributed poultry houses, for their smart, interconnected, and adaptive control. A supervision system is provided as interface to users. Experiments using real data suggest an improvement of 5% on the performance of the most productive specialist, staying close to the optimal FCR[t].

Palavras-chave: Adaptive poultry management, Artificial neural networks, Automatic control, Intelligent control, Supervision

Referências

ABPA (2021). Brazilian association of animal protein. EMBRAPA.

Acres, A. (2020). Broiler management handbook.

Botreau, R., Bracke, M., Perny, P., Butterworth, A., Capdeville, J., Van Reenen, C., and Veissier, I. (2007). Aggregation of measures to produce an overall assessment of animal welfare. Animal, 1(8):1188–1197. DOI: https://doi.org/10.1017/S1751731107000535

Gevrey, M., Dimopoulos, I., and Lek, S. (2003). Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological modelling, 160(3):249–264. DOI: https://doi.org/10.1016/S0304-3800(02)00257-0

Henriksen, S., Bilde, T., and Riber, A. B. (2016). Effects of post-hatch brooding temperature on broiler behavior, welfare, and growth. Poultry Science, 95(10):2235–2243. DOI: https://doi.org/10.3382/ps/pew224

Johansen, S. V., Bendtsen, J. D., Martin, R., Mogensen, J., et al. (2017). Data driven broiler weight forecasting using dynamic neural network models. IFAC-PapersOnLine, 50(1):5398–5403. DOI: https://doi.org/10.1016/j.ifacol.2017.08.1073

Klotz, D. F., Ribeiro, R., Enembreck, F., Denardin, G., Barbosa, M., Casanova, D., and Teixeira, M. (2020). Estimating action plans for smart poultry houses.

Ribeiro, R., Casanova, D., Teixeira, M., Wirth, A., Gomes, H. M., Borges, A. P., and Enembreck, F. (2019). Generating action plans for poultry management using artificial neural networks. Computers and Electronics in Agriculture, 161:131–140. DOI: http://dx.doi.org/10.1016/j.compag.2018.02.017

Ross (2019). 308 and 308 FF performance objectives.