Kybernetika 54 no. 5, 1033-1048, 2018

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

Juan Carlos Bello-Robles, Ofelia Begovich, Javier Ruiz-León and Rita Quetziquel Fuentes-AguilarDOI: 10.14736/kyb-2018-5-1033

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.

Keywords:

differential neural networks, distributed parameter systems, greenhouse temperature modeling

Classification:

93C95, 93C20

paper.pdf

References:

  1. O. Aguilar-Leal, R.Q. Fuentes, I. Chairez, A. Garcia and J. C. Huegel: Distributed parameter system identification using finite element differential neural networks. Applied Soft Computing 43 (2016), 663-642.   DOI:10.1016/j.asoc.2016.01.004
  2. A. Baille, C. Kittas and N. Katsoulas: Influence of whitening on greenhouse microclimate and crop energy partitioning. Agricultural Forest Meteorology 107 (2001), 4, 293-306.   DOI:10.1016/s0168-1923(01)00216-7
  3. I. Chairez, R. Fuentes, A. Poznyak, T. Poznyak, M. Escudero and L. Viana: DNN-state identification of 2D distributed parameter systems. Int. J. Systems Sci. 43 (2012), 2, 296-307.   DOI:10.1080/00207721.2010.495187
  4. J. Chen, Y. Cai, F. Xu, H. Hu and Q. Ai: Analysis and optimization of the fan-pad evaporative cooling system for greenhouse based on CFD. Advances Mechanical Engrg. 6 (2014), 712-740.   DOI:10.1155/2014/712740
  5. L. C. Evans: Partial Differential Equations. American Mathematical Soc., 2010.   CrossRef
  6. J. Fargues, N. Smits, M. Rougier, T. Boulard, G. Ridray, J. Lagier, B. Jeannequin, H. Fatnassi and M. Mermier: Effect of microclimate heterogeneity and ventilation system on entomopathogenic hyphomycete infection of Trialeurodes vaporariorum (Homoptera: Aleyrodidae) in Mediterranean greenhouse tomato. Biolog. Control 32 (2005), 3, 461-472.   DOI:10.1016/j.biocontrol.2004.12.008
  7. P. M. Ferreira, E. A. Faria and A. E. Ruano: Neural network models in greenhouse air temperature prediction. Neurocomputing 43 (2002), 1, 51-75.   DOI:10.1016/s0925-2312(01)00620-8
  8. R. Fuentes, A. Poznyak, I. Chairez, M. Franco and T. Poznyak: Continuous neural networks applied to identify a class of uncertain parabolic partial differential equations. Int. J. Model. Simul. Sci. Comput. 1 (2010), 4, 485-508.   DOI:10.1142/s1793962310000304
  9. A. Hasni, R. Taibi, B. Draoui and T. Boulard: Optimization of greenhouse climate model parameters using particle swarm optimization and genetic algorithms. Energy Procedia 6 (2011), 371-380.   DOI:10.1016/j.egypro.2011.05.043
  10. Y. W. Kwon and H. Bang: The Finite Element Method Using MATLAB. CRC Press, 2000.   DOI:10.1201/9781315275949
  11. J. H. Perez-Cruz, A. Alanis, J. Rubio and J. Pacheco: System identification using multilayer differential neural networks: a new result. J. Appl. Math. 2012 (2012), 1-20.   DOI:10.1155/2012/529176
  12. A. Perez-Gonzalez, O. Begovich and J. Ruiz-León: 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.   CrossRef
  13. A. S. Poznyak, E. N. Sanchez and Y. Wen: Differential Neural Networks for Robust Nonlinear Control: Identification, State Estimation and Trajectory Tracking. World Scientific, 2001.   DOI:10.1142/4703
  14. P. Salgado and J. B. Cunha: Greenhouse climate hierarchical fuzzy modelling. Control Engrg. Practice 13 (2005), 5, 613-628.   DOI:10.1016/j.conengprac.2004.05.007
  15. W. A. Strauss: Partial Differential Equations: An Introduction. John Wiley and Sons Inc, 2007.   CrossRef
  16. X. M. Zhang and Q. L. Han: Global asymptotic stability for a class of generalized neural networks with interval time-varying delays. IEEE Trans. Neural Networks 22 (2011), 8, 1180-1192.   DOI:10.1109/tnn.2011.2147331
  17. X. M. Zhang and Q. L. Han: State estimation for static neural networks with time-varying delays based on an improved reciprocally convex inequality. IEEE Trans. Neural Networks Learning Systems 29 (2018), 4, 1376-1381.   DOI:10.1109/tnnls.2017.2661862
  18. O. C. Zienkiewicz, R. L. Taylor and J. Z Zhu: The Finite Element Method: Its Basis and Fundamentals. Elsevier Butterworth-Heinemann, 2005.   CrossRef