Virtual Sensors for Designing Irrigation Controllers in Greenhouses
08 Nov 2012-Sensors (Multidisciplinary Digital Publishing Institute (MDPI))-Vol. 12, Iss: 11, pp 15244-15266
TL;DR: Some effort has been made to eliminate some problems associated with grey-box models: advance phenomenon and overestimation in this paper and better results are obtained with the use of nonlinear Black-box virtual sensors.
Abstract: Monitoring the greenhouse transpiration for control purposes is currently a difficult task. The absence of affordable sensors that provide continuous transpiration measurements motivates the use of estimators. In the case of tomato crops, the availability of estimators allows the design of automatic fertirrigation (irrigation + fertilization) schemes in greenhouses, minimizing the dispensed water while fulfilling crop needs. This paper shows how system identification techniques can be applied to obtain nonlinear virtual sensors for estimating transpiration. The greenhouse used for this study is equipped with a microlysimeter, which allows one to continuously sample the transpiration values. While the microlysimeter is an advantageous piece of equipment for research, it is also expensive and requires maintenance. This paper presents the design and development of a virtual sensor to model the crop transpiration, hence avoiding the use of this kind of expensive sensor. The resulting virtual sensor is obtained by dynamical system identification techniques based on regressors taken from variables typically found in a greenhouse, such as global radiation and vapor pressure deficit. The virtual sensor is thus based on empirical data. In this paper, some effort has been made to eliminate some problems associated with grey-box models: advance phenomenon and overestimation. The results are tested with real data and compared with other approaches. Better results are obtained with the use of nonlinear Black-box virtual sensors. This sensor is based on global radiation and vapor pressure deficit (VPD) measurements. Predictive results for the three models are developed for comparative purposes.
Citations
More filters
TL;DR: The results of this study show that it is possible to apply deep-learning-based prediction models for more precisely managing greenhouse and that the accuracy of the time-based algorithm gradually decreased as prediction time increased.
80 citations
TL;DR: In this paper, an event-based predictive control system for a greenhouse irrigation process is presented, which is able to adapt the actuation rate to the state of the plant providing the efficient way of water consumption.
41 citations
TL;DR: The Bayesian Network has demonstrated to provide a good approximation of a control signal based on previous manual and control actions implemented in the same system (based on predefined setpoints), as well as on the environmental conditions.
40 citations
Cites background from "Virtual Sensors for Designing Irrig..."
...Crops use solar radiation, the CO2 concentration in the surrounding air, water and nutrients to produce biomass (roots, stems, leaves, and fruits) through the photosynthesis process....
[...]
...Humidity inside the greenhouse is another important aspect, because high humidity may produce the appearance of diseases and decrease transpiration of the crop, whereas low humidity may cause hydric stress, closing the stomata and reducing the photosynthesis due to a decrease in the CO2 assimilation....
[...]
...When the photosynthetic rates are higher, the concentration of CO2 falls below the atmospheric producing a growth deficit that is increased when the crop reaches its maximum development [26]....
[...]
...This exchange rate coupled with CO2 taken by the crop during photosynthesis determine the concentration of CO2 in the greenhouse....
[...]
...Simulation results. where t is the time, Yi are the known states at the initial time ti, f = f(t) is a nonlinear function based on mass and heat transfer balances and the multi-dimensional vectors represent, respectively, Y = Y (t) greenhouse climate state variables (mainly the inside air temperature and humidity, CO2 concentration, PAR radiation, soil surface temperature, cover temperature, and plant temperature), U = U(t) input variables (in this work natural vents and heating system), B = B(t) disturbances (outside temperature and humidity, wind speed and direction, outside radiation, and rain), V = V (t) system variables (related to transpiration, condensation, and other processes), C system constants....
[...]
TL;DR: This study has demonstrated, for the first time, that CFD analysis and a control strategy can be combined to obtain system models for monitoring the temperature in greenhouses and suggests that, generally, virtual sensing can be applied in large greenhouses for Monitoring the temperature using a 3D real-time simulator.
Abstract: Virtual sensing is crucial in order to provide feasible and economical alternatives when physical measuring instruments are not available. Developing model-based virtual sensors to calculate real-time information at each targeted location is a complex endeavor in terms of sensing technology. This paper proposes a new approach for model-based virtual sensor development using computational fluid dynamics (CFD) and control. Its main objective is to develop a three-dimensional (3D) real-time simulator using virtual sensors to monitor the temperature in a greenhouse. To conduct this study, a small-scale greenhouse was designed, modeled, and fabricated. The controller was based on the convection heat transfer equation under specific assumptions and conditions. To determine the temperature distribution in the greenhouse, a CFD analysis was conducted. Only one well-calibrated and controlled physical sensor (temperature reference) was enough for the CFD analysis. After processing the result that was obtained from the real sensor output, each virtual sensor had learned the associative transfer function that estimated the output from given input data, resulting in a 3D real-time simulator. This study has demonstrated, for the first time, that CFD analysis and a control strategy can be combined to obtain system models for monitoring the temperature in greenhouses. These findings suggest that, generally, virtual sensing can be applied in large greenhouses for monitoring the temperature using a 3D real-time simulator.
34 citations
Cites background from "Virtual Sensors for Designing Irrig..."
...proposed virtual sensors for designing irrigation controllers in greenhouses [45]....
[...]
...virtual sensors for designing irrigation controllers in greenhouses [45]....
[...]
TL;DR: In this paper, two different leaf area index models are established and compared with the evolution of the real crop determined with an electronic planimeter: (1) Considering the temperature and photosynthetically active radiation (PAR) as the main impact factors over crop growth, a TEP-LAI model based on product of thermal effectiveness and PAR is built to estimate the leaf areas index dynamics; and (2) TOM-LAI model, based on a tomato growth model is also used to estimate an explicit function of the number of leaves and vines.
33 citations
References
More filters
Book•
01 Jan 1987
TL;DR: Das Buch behandelt die Systemidentifizierung in dem theoretischen Bereich, der direkte Auswirkungen auf Verstaendnis and praktische Anwendung der verschiedenen Verfahren zur IdentifIZierung hat.
Abstract: Das Buch behandelt die Systemidentifizierung in dem theoretischen Bereich, der direkte Auswirkungen auf Verstaendnis und praktische Anwendung der verschiedenen Verfahren zur Identifizierung hat. Da ...
20,436 citations
Journal Article•
TL;DR: Progress towards a reconciliation of parallel concepts in meteorology and physiology is described, which stresses the importance of physiological restraint on the rate of transpiration from an irrigated field surrounded by dry land.
Abstract: A turgid leaf exposed to bright sunshine can transpire an amount of water several times its own weight during a summer day. Rapid evaporation is sustained by a supply of heat from the atmosphere and by a movement of water within the plant preventing the desiccation of leaf tissue. In analysis, the need for energy and the need for water have often been disassociated. Meteorologists investigating the energetics of transpiration have assumed that leaves behave like pieces of wet, green blotting paper, and plant physiologists have demonstrated mechanisms for the conduction of water at arbitrary rates unrelated to the physics of the environment. This paper describes progress towards a reconciliation of parallel concepts in meteorology and physiology. The path for the diffusion of water vapour from leaf cells to the free atmosphere is divided into two parts, one determined primarily by the size and distribution of stomata, and the other by wind speed and the aerodynamic properties of the plant surface. Diffusive resistances for single leaves and for plant communities are established from measurements in the laboratory and in the field and are then used: (i) to predict relative rates of evaporation from leaves with wet and dry surfaces; (ii) to investigate the dependence of transpiration rate on wind speed and surface roughness; (iii) to demonstrate that the relation between transpiration rate and lead area is governed by stomatal closure in leaves well shaded from sunlight; (iv) to calculate maximum rates of transpiration for different crops and climates. A final section on the convection of dry air stresses the importance of physiological restraint on the rate of transpiration from an irrigated field surrounded by dry land.
4,686 citations
Book•
01 Jan 1994
TL;DR: I. Models for Systems and Signals, physical Modelling, simulation and model applications.
Abstract: I. MODELS. 1. Systems and Models. 2. Examples of Models. 3. Models for Systems and Signals. II. PHYSICAL MODELLING. 4. Basic Principles for Physical Modelling. 5. Some Basic Physical Analogies. 6. Bond-graphs. 7. Computer Support for Physical Modelling. III. SYSTEM IDENTIFICATION. 8. Estimation of Transient Response, Spectra and Frequency Functions. 9. Parameter Estimation of Dynamical Models. 10. System Identification as Tool for Modeling. IV. SIMULATION AND MODEL APPLICATIONS. 11. Simulation. 12. Simulators. 13. Model Validation and Model Use. Appendix A: Linear Systems - Description and Properties. Appendix B: Linearization. Appendix C: Signal Spectra.
558 citations
TL;DR: In this article, a physiological model of tomato crop development and yield was developed, where a series of differential equations represented the changes in numbers and weights of leaves, fruit, and stem segments and in the areas of leaves.
Abstract: Models of the greenhouse environment and of crops are needed to determine optimal strategies for environment control in regions where new greenhouse industries are developing. In this research, a physiological model of tomato crop development and yield was developed. A series of differential equations represent the changes in numbers and weights of leaves, fruit, and stem segments and in the areas of leaves, as new organs are initiated, age, and senesce or are picked. The model uses a source-sink approach for partitioning carbohydrate into growth of different organs. An experiment was conducted in six outdoor, controlled environment, growth chambers to quantify the effects of temperature, CO2, and light on tomato growth processes for calibrating the model. The model accurately described the differences in growth and yield of tomatoes that were observed in the experiment. With additional testing, the model can be used to help determine strategic and tactical decisions concerning greenhouse environment control over practical ranges of CO2 and temperature.
222 citations
TL;DR: In this article, the effect of climate on tomato transpiration in greenhouse tomato crops has been investigated and five transpiration models have been checked against measurements, including Stanghellini's and Jolliet's models.
175 citations