Modeling of the temperature distribution of a greenhouse using finite element differential neural networks

Juan Carlos Bello-Robles; Ofelia Begovich; Javier Ruiz; Rita Quetziquel Fuentes-Aguilar

Kybernetika (2018)

  • Volume: 54, Issue: 5, page 1033-1048
  • ISSN: 0023-5954

Abstract

top
Most of the existing works in the literature related to greenhouse modeling treat the temperature within a greenhouse as homogeneous. However, experimental data show that there exists a temperature spatial distribution within a greenhouse, and this gradient can produce different negative effects on the crop. Thus, the modeling of this distribution will allow to study the influence of particular climate conditions on the crop and to propose new temperature control schemes that take into account the spatial distribution of the temperature. In this work, a Finite Element Differential Neural Network (FE-DNN) is proposed to model a distributed parameter system with a measurable disturbance input. The learning laws for the FE-DNN are derived by means of Lyapunov's stability analysis and a bound for the identification error is obtained. The proposed neuro identifier is then employed to model the temperature distribution of a greenhouse prototype using data measured inside the greenhouse, and showing good results.

How to cite

top

Bello-Robles, Juan Carlos, et al. "Modeling of the temperature distribution of a greenhouse using finite element differential neural networks." Kybernetika 54.5 (2018): 1033-1048. <http://eudml.org/doc/294154>.

@article{Bello2018,
abstract = {Most of the existing works in the literature related to greenhouse modeling treat the temperature within a greenhouse as homogeneous. However, experimental data show that there exists a temperature spatial distribution within a greenhouse, and this gradient can produce different negative effects on the crop. Thus, the modeling of this distribution will allow to study the influence of particular climate conditions on the crop and to propose new temperature control schemes that take into account the spatial distribution of the temperature. In this work, a Finite Element Differential Neural Network (FE-DNN) is proposed to model a distributed parameter system with a measurable disturbance input. The learning laws for the FE-DNN are derived by means of Lyapunov's stability analysis and a bound for the identification error is obtained. The proposed neuro identifier is then employed to model the temperature distribution of a greenhouse prototype using data measured inside the greenhouse, and showing good results.},
author = {Bello-Robles, Juan Carlos, Begovich, Ofelia, Ruiz, Javier, Fuentes-Aguilar, Rita Quetziquel},
journal = {Kybernetika},
keywords = {differential neural networks; distributed parameter systems; greenhouse temperature modeling},
language = {eng},
number = {5},
pages = {1033-1048},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Modeling of the temperature distribution of a greenhouse using finite element differential neural networks},
url = {http://eudml.org/doc/294154},
volume = {54},
year = {2018},
}

TY - JOUR
AU - Bello-Robles, Juan Carlos
AU - Begovich, Ofelia
AU - Ruiz, Javier
AU - Fuentes-Aguilar, Rita Quetziquel
TI - Modeling of the temperature distribution of a greenhouse using finite element differential neural networks
JO - Kybernetika
PY - 2018
PB - Institute of Information Theory and Automation AS CR
VL - 54
IS - 5
SP - 1033
EP - 1048
AB - Most of the existing works in the literature related to greenhouse modeling treat the temperature within a greenhouse as homogeneous. However, experimental data show that there exists a temperature spatial distribution within a greenhouse, and this gradient can produce different negative effects on the crop. Thus, the modeling of this distribution will allow to study the influence of particular climate conditions on the crop and to propose new temperature control schemes that take into account the spatial distribution of the temperature. In this work, a Finite Element Differential Neural Network (FE-DNN) is proposed to model a distributed parameter system with a measurable disturbance input. The learning laws for the FE-DNN are derived by means of Lyapunov's stability analysis and a bound for the identification error is obtained. The proposed neuro identifier is then employed to model the temperature distribution of a greenhouse prototype using data measured inside the greenhouse, and showing good results.
LA - eng
KW - differential neural networks; distributed parameter systems; greenhouse temperature modeling
UR - http://eudml.org/doc/294154
ER -

References

top
  1. Aguilar-Leal, O., Fuentes, R.Q., Chairez, I., Garcia, A., Huegel, J. C., 10.1016/j.asoc.2016.01.004, Applied Soft Computing 43 (2016), 663-642. DOI10.1016/j.asoc.2016.01.004
  2. Baille, A., Kittas, C., Katsoulas, N., 10.1016/s0168-1923(01)00216-7, Agricultural Forest Meteorology 107 (2001), 4, 293-306. DOI10.1016/s0168-1923(01)00216-7
  3. Chairez, I., Fuentes, R., Poznyak, A., Poznyak, T., Escudero, M., Viana, L., 10.1080/00207721.2010.495187, Int. J. Systems Sci. 43 (2012), 2, 296-307. MR2862244DOI10.1080/00207721.2010.495187
  4. Chen, J., Cai, Y., Xu, F., Hu, H., Ai, Q., 10.1155/2014/712740, Advances Mechanical Engrg. 6 (2014), 712-740. DOI10.1155/2014/712740
  5. Evans, L. C., Partial Differential Equations., American Mathematical Soc., 2010. MR2597943
  6. Fargues, J., Smits, N., Rougier, M., Boulard, T., Ridray, G., Lagier, J., Jeannequin, B., Fatnassi, H., Mermier, M., 10.1016/j.biocontrol.2004.12.008, Biolog. Control 32 (2005), 3, 461-472. DOI10.1016/j.biocontrol.2004.12.008
  7. Ferreira, P. M., Faria, E. A., Ruano, A. E., 10.1016/s0925-2312(01)00620-8, Neurocomputing 43 (2002), 1, 51-75. DOI10.1016/s0925-2312(01)00620-8
  8. Fuentes, R., Poznyak, A., Chairez, I., Franco, M., Poznyak, T., 10.1142/s1793962310000304, Int. J. Model. Simul. Sci. Comput. 1 (2010), 4, 485-508. DOI10.1142/s1793962310000304
  9. Hasni, A., Taibi, R., Draoui, B., Boulard, T., 10.1016/j.egypro.2011.05.043, Energy Procedia 6 (2011), 371-380. DOI10.1016/j.egypro.2011.05.043
  10. Kwon, Y. W., Bang, H., 10.1201/9781315275949, CRC Press, 2000. MR2134653DOI10.1201/9781315275949
  11. Perez-Cruz, J. H., Alanis, A., Rubio, J., Pacheco, J., 10.1155/2012/529176, J. Appl. Math. 2012 (2012), 1-20. MR2910916DOI10.1155/2012/529176
  12. Perez-Gonzalez, A., Begovich, O., Ruiz-León, J., Modeling of a greenhouse prototype using PSO algorithm based on a LabView TM application., In: Proc. 2014 International Conference on Electrical Engineering, Computing Science and Automatic Control 1-6. 
  13. Poznyak, A. S., Sanchez, E. N., Wen, Y., 10.1142/4703, World Scientific, 2001. DOI10.1142/4703
  14. Salgado, P., Cunha, J. B., 10.1016/j.conengprac.2004.05.007, Control Engrg. Practice 13 (2005), 5, 613-628. DOI10.1016/j.conengprac.2004.05.007
  15. Strauss, W. A., Partial Differential Equations: An Introduction., John Wiley and Sons Inc, 2007. MR2398759
  16. Zhang, X. M., Han, Q. L., 10.1109/tnn.2011.2147331, IEEE Trans. Neural Networks 22 (2011), 8, 1180-1192. MR3465626DOI10.1109/tnn.2011.2147331
  17. Zhang, X. M., Han, Q. L., 10.1109/tnnls.2017.2661862, IEEE Trans. Neural Networks Learning Systems 29 (2018), 4, 1376-1381. DOI10.1109/tnnls.2017.2661862
  18. Zienkiewicz, O. C., Taylor, R. L., Zhu, J. Z, The Finite Element Method: Its Basis and Fundamentals., Elsevier Butterworth-Heinemann, 2005. MR3292660

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.