Neural Processing Letters

, Volume 24, Issue 3, pp 241–260 | Cite as

A Neuro-Dynamic Programming-Based Optimal Controller for Tomato Seedling Growth in Greenhouse Systems

  • J. Pucheta
  • H. Patiño
  • R. Fullana
  • C. Schugurensky
  • B. Kuchen


This work proposes a neuro-dynamic programming-based optimal controller to guide the growth of tomato seedling crops by manipulating its environmental conditions in a greenhouse. The neurocontroller manages the growth development of the crop, while minimizing a predefined cost function that considers the operative costs and the final state errors under physical constraints on process variables and actuator signals. The aim is to guide the growth of tomato seedlings by controlling the microclimate of the greenhouse. The design process of the neurocontroller considers the nonlinear dynamic behavior of the crop-greenhouse system model and the real climate data. Simulations of the proposed approach allow for contrasting its performance against those of other strategies for tomato seedling crop development subject to various climatic conditions.


greenhouse control systems intelligent agriculture neuro-dynamic programming neurocontrollers optimal control 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barto A.G., Bradtke S.J., Singh S.P. (1995): Learning to act using real-time dynamic programming. Artificial Intelligence 72, 81–138CrossRefGoogle Scholar
  2. 2.
    Bellman R., Dreyfus S. (1962).: Applied Dynamic Programming. Princenton University Press, PrincetonMATHGoogle Scholar
  3. 3.
    Bertsekas, D.: Dynamic Programming and Optimal Control, Athena Scientific, Belmont, MA, vols. I and II, 1995.Google Scholar
  4. 4.
    Bertsekas D., and Tsitsiklis J. (1996).: Neuro-dynamic programming. Athena Scientific, Belmont, MAMATHGoogle Scholar
  5. 5.
    Bishop C. (1995). Neural Networks for Pattern Recognition. University Press of Oxford, OxfordMATHGoogle Scholar
  6. 6.
    Casti J. and Larson R. (1978). Principles of Dynamic Programming. Marcel Dekker Inc, New YorkMATHGoogle Scholar
  7. 7.
    Enns R. and Jennie Si. (2003): Helicopter trimming and tracking control using direct neural dynamic programming. IEEE Transactions on Neural Networks, 14(4): 929–939CrossRefGoogle Scholar
  8. 8.
    Fullana, R. and Schugurensky, C.: Constrained Systems Optimization by Using Iterative Dynamic Programming (In Spanish), Anales de la VIII RPIC, Mar del Plata, 1999.Google Scholar
  9. 9.
    Goudriaan J. (1986): A simple and fast numerical method for the computation of daily totals of crop photosynthesis. Agricultural and Forest Meteorology 38, 251–255CrossRefGoogle Scholar
  10. 10.
    Gutman P.O., Lindberg P.O., Ioslovich I. and Seginer I. (1993): A non-linear optimal greenhouse control problem solved by linear programming. Journal of Agricultural Engineering Research 55, 335–351CrossRefGoogle Scholar
  11. 11.
    Hwang, Y. and Jones, J. W.: Optimizing temperature and CO2 in subtropical greenhouses, International Winter Meeting of the ASAE. Paper No. 93–3504, 1993.Google Scholar
  12. 12.
    Ioslovich I., Seginer I., Gutman P.O., and Borshchevsky M. (1995): Suboptimal CO2 enrichment of greenhouses. Journal of Agricultural Engineering Research 60, 117–136CrossRefGoogle Scholar
  13. 13.
    Jones J.W., Dayan E., Allen L.H., van Keulen H., Challa H. (1991): A dynamic tomato growth and yield model (TOMGRO). Transaction ASAE 34, 663–672Google Scholar
  14. 14.
    Jones, J. W.: Crop growth, development and production modeling. In: Proc. of the on Automated Agriculture for the 21st Century, ASAE, pp. 447–457, Illinois, Chicago, 16–17 December 1991.Google Scholar
  15. 15.
    Lapilli, S., Fullana, R., Schugurensky, C. and Pucheta, J.: Algebraic Model of Temperature for a Greenhouse. Control algorithms Modelo algebraico de temperatura de un Algoritmos de control (In Spanish), IX RPIC, Santa Fe Argentina, 2001.Google Scholar
  16. 16.
    Lewis F. and Syrmos V. (1995). Optimal Control. Wiley Inc, New YorkMATHGoogle Scholar
  17. 17.
    Nørgaard, M.: Neural network based system identification toolbox. Tech. Report. 97- E- 851, Department of Automation, Technical University of Denmark, Denmark, 1997.Google Scholar
  18. 18.
    Oppenheim, A., Willsky, A. and Hamid Nawab, S.: Signals and Systems, 2nd (edn). Prentice-Hall Inc, Englewood Cliffs, NJ, pp. 168–170, 1998.Google Scholar
  19. 19.
    Patiño D., Carelli R. and Kuchen B.R. (2002): Neural networks for advanced control of robot manipulators. IEEE Transactions on Neural Networks 13(2): 343–354CrossRefGoogle Scholar
  20. 20.
    Patiño D. and Liu D. (2000): Neural network-based model reference adaptive control system. IEEE Transactions Systems, Man, Cybernertics Part B 30, 198–206CrossRefGoogle Scholar
  21. 21.
    Pucheta, J. A.: Optimal Trajectories Generation and Control for Crop Growth Guidance in A Greenhouse. Generación De Trayectorias Optimas Y Control Para Guiar El Desarrollo De Cultivos En Invernaderos (In Spanish). Msc. theses. ISBN 950-605-299-9. Editorial Fundación Universidad Nacional De San Juan, 2002.Google Scholar
  22. 22.
    Pucheta, J. A., Schugurensky, C., Fullanay, R. and Lapilli, S.: Optimización del costo operativo de un sistema cultivo-invernadero Operative cost Optimization of a crop-greenhouse system, (In Spanish), IX Rpic. Santa Fe, Argentina, 2001.Google Scholar
  23. 23.
    Pucheta J.A., Schugurensky C., Fullana R., Patiño H. and Kuchen B. (2005): Optimal greenhouse control of tomato seedling crops. Computers and Electronics in Agriculture 50(1): 70–82CrossRefGoogle Scholar
  24. 24.
    Seginer I., Shina G., Albright, L.D., and Marsh L.S. (1991): Optimal temperature set-points for greenhouse lettuces. Journal of Agriculture Engineering Research 49, 209–226CrossRefGoogle Scholar
  25. 25.
    Seginer I. and McClendon R.W. (1992): Methods for optimal control of the greenhouse environment. Transactions of the ASAE. 35(4): 1299–1307Google Scholar
  26. 26.
    Sutton, R. S.: Temporal Credit Assignment in Reinforcement Learning, PhD thesis, of Massachusetts, Amherst, MA, 1984.Google Scholar
  27. 27.
    Sutton R.S. (1988): Learning to predict by the method of temporal differences. Machine 3, 9–44Google Scholar
  28. 28.
    Sutton R. and Barto A. (1998). Reinforcement Learning: An Introduction. MIT Press, Cambridge, MAGoogle Scholar
  29. 29.
    Werbos P.J. (1977): Advanced forecasting methods for global crisis warning and models of intelligence. General Systems Yearbook 22, 25–38Google Scholar
  30. 30.
    Werbos P.J. (1992). Approximate dynamic programming for real-time control and neural Handbook of Intelligent Control, White and Sofge, (edn.) Van Nostrand, New YorkGoogle Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • J. Pucheta
    • 1
  • H. Patiño
    • 1
  • R. Fullana
    • 1
  • C. Schugurensky
    • 1
  • B. Kuchen
    • 1
  1. 1.Facultad de Ingeniería, Instituto de AutomáticaUniversidad Nacional de San JuanSan JuanArgentina

Personalised recommendations