14.3.1 Fuzzy Control
A fuzzy logic controller (FLC) has four main components: a fuzzification interface,
a knowledge base, a decision-making logic or kernel, and a defuzzification interface
(Lee 1990a, b; Passino and Yurkovich 1997). Currently, using fuzzy logic has
become popular in many areas mainly in the area of controlled agriculture. Fuzzy
logic is used for system modeling when the information is abundant; some typical
variables are in-house and out-house temperature, humidity for both inside and
outside the greenhouse, and wind direction (Lafont and Balmat 2002; Hurtado et al.
2010). The solutions proposed are generally based on the linearization of the
process behavior around the operating points. Fuzzy logic makes possible to solve
this problem thanks to its properties as a universal approximator. Among these
techniques are found those based on the fuzzy clustering methods (Trabelsi et al.
2007; Errahmani et al. 2009). The proposed method uses in a first stage the fuzzy
clustering technique to determine both the premises and the consequent parameters
of the fuzzy Takagi–Sugeno rules. This approach has been applied to model the air
temperature and humidity inside the greenhouse. Takagi–Sugeno fuzzy rules have
been used to design a fuzzy controller for nocturnal temperature of a greenhouse
(Nachidi, et al. 2011). Also they have been used in a reasonable greenhouse crop
transpiration rate model for irrigation scheduling (Ren et al. 2011) and thereby to
achieve the best effect. Some fuzzy logic model for estimation of greenhouse crop
transpiration rate was developed (Deng and Wang 2006), this is commonly estimated from weather parameters. But also fuzzy logic has been used to model crop
behavior such as photosynthesis processes (Center and Verma 1997). Another
application in the area of greenhouses is the implementation of a control system or
control strategy using LABVIEW software based on a Takagi–Sugeno (Cepeda,
et al. 2011) control type. Another application is to control temperature inside the
greenhouse to reduce cracking in tomato fruits (Hahn 2011), relative humidity
inside the greenhouse, to adjust thermal systems, humidification, ventilation (Gates
et al. 2001; Sriraman and Mayorga 2007), air temperature (Salgado and Boaventura
Cunha 2005; Ehrlich et al.1996), or environment variables of the greenhouse climate (Bernardo et al. 2006). Some studies have used Mandani type controllers
(Javadikia et al. 2009) using MATLAB to implement controllers on/off type,
SIMULINK for temperature fuzzy control (Xu et al. 2006), others to control carbon
dioxide concentrations (Shuying et al. 2010) using gas sensors and obtaining the
desired responses, to name a few applications. Fuzzy logic controllers have been
used in combination with classical P, PD (Kolokotsa, et al. 2010), or PID controllers
in order to optimize the climate control of greenhouses (Alghannan 2000) and also
to develop an intelligent indoor environment and management system for greenhouses. A fuzzy logic controller based on a Field Programmable Gate Array for
greenhouse climate control was proposed recently (Castañeda-Miranda et al. 2006).
Also, a type-2 FLC was designed for the greenhouse environment (Abdel 2010). A
type-2 FLC is a fuzzy system that can handle rule uncertainties (Karnik et al. 1999).
The advantages of FLC on traditional feedback control systems in greenhouses
412
I. L. López-Cruz et al.
A fuzzy logic controller (FLC) has four main components: a fuzzification interface,
a knowledge base, a decision-making logic or kernel, and a defuzzification interface
(Lee 1990a, b; Passino and Yurkovich 1997). Currently, using fuzzy logic has
become popular in many areas mainly in the area of controlled agriculture. Fuzzy
logic is used for system modeling when the information is abundant; some typical
variables are in-house and out-house temperature, humidity for both inside and
outside the greenhouse, and wind direction (Lafont and Balmat 2002; Hurtado et al.
2010). The solutions proposed are generally based on the linearization of the
process behavior around the operating points. Fuzzy logic makes possible to solve
this problem thanks to its properties as a universal approximator. Among these
techniques are found those based on the fuzzy clustering methods (Trabelsi et al.
2007; Errahmani et al. 2009). The proposed method uses in a first stage the fuzzy
clustering technique to determine both the premises and the consequent parameters
of the fuzzy Takagi–Sugeno rules. This approach has been applied to model the air
temperature and humidity inside the greenhouse. Takagi–Sugeno fuzzy rules have
been used to design a fuzzy controller for nocturnal temperature of a greenhouse
(Nachidi, et al. 2011). Also they have been used in a reasonable greenhouse crop
transpiration rate model for irrigation scheduling (Ren et al. 2011) and thereby to
achieve the best effect. Some fuzzy logic model for estimation of greenhouse crop
transpiration rate was developed (Deng and Wang 2006), this is commonly estimated from weather parameters. But also fuzzy logic has been used to model crop
behavior such as photosynthesis processes (Center and Verma 1997). Another
application in the area of greenhouses is the implementation of a control system or
control strategy using LABVIEW software based on a Takagi–Sugeno (Cepeda,
et al. 2011) control type. Another application is to control temperature inside the
greenhouse to reduce cracking in tomato fruits (Hahn 2011), relative humidity
inside the greenhouse, to adjust thermal systems, humidification, ventilation (Gates
et al. 2001; Sriraman and Mayorga 2007), air temperature (Salgado and Boaventura
Cunha 2005; Ehrlich et al.1996), or environment variables of the greenhouse climate (Bernardo et al. 2006). Some studies have used Mandani type controllers
(Javadikia et al. 2009) using MATLAB to implement controllers on/off type,
SIMULINK for temperature fuzzy control (Xu et al. 2006), others to control carbon
dioxide concentrations (Shuying et al. 2010) using gas sensors and obtaining the
desired responses, to name a few applications. Fuzzy logic controllers have been
used in combination with classical P, PD (Kolokotsa, et al. 2010), or PID controllers
in order to optimize the climate control of greenhouses (Alghannan 2000) and also
to develop an intelligent indoor environment and management system for greenhouses. A fuzzy logic controller based on a Field Programmable Gate Array for
greenhouse climate control was proposed recently (Castañeda-Miranda et al. 2006).
Also, a type-2 FLC was designed for the greenhouse environment (Abdel 2010). A
type-2 FLC is a fuzzy system that can handle rule uncertainties (Karnik et al. 1999).
The advantages of FLC on traditional feedback control systems in greenhouses
412
I. L. López-Cruz et al.