Design of wireless web-based multiplatform system for thermal environmental control of broiler facilities using fuzzy set theory

Abstract

The control and monitoring process for broiler facilities needs to be improved to mitigate or eliminate birds’ thermal stress. Thus, the objective was to develop of a fuzzy controller embedded in a microcontroller and a multiplatform web application that communicates with the fuzzy controller to control the aviary climate system. An architecture based on the Internet of Things (IoT) and agribusiness 4.0 was used to implement a fuzzy controller embedded in a microcontroller. Data were collected by temperature and humidity sensors. A multiplatform web application communicated the climate system to the fuzzy controller. This information was transmitted to the central web server via message queuing telemetry transport (MQTT). The system performed decision-making to control the aviary thermal environment of broilers ranging from one to 49 days old. The input variables of the system were the black globe-humidity index (BGHI) and the bird age. Defuzzification by the center of gravity method produced environmental ratings that were used to control the thermal environment automatically and smartly. Using the intelligent prototype produced a 98% accuracy in the validation process. This low-cost system can be used as an agribusiness 4.0 application to mitigate thermal stress conditions in aviaries and, consequently, reduce productivity losses.

Key words
artificial intelligence; automation; aviculture 40; IoT; poultry farm; thermal comfort

INTRODUCTION

Climate control systems installed in broiler facilities must enhance efficiency to attend the global food demand. Therefore, increasing poultry management, welfare and performance, and mitigating costs constitute a present challenge (Astill et al. 2020).

Worldwide, the advances in genetics, nutrition, management and technologies over the last few years have made poultry farming a significant component of the commercial sector.

However, the absence or inappropriate thermal control on the production environment, resulting in thermal conditions above or below the thermoneutral zone for poultry, is among several causes of low performance in broiler production.

Given this scenario, stakeholders have sought the application of technologies to optimize production and mitigate losses from thermal stress in all phases of bird life (Barbosa et al. 2013, Lara & Rostagno 2013, Astill et al. 2020, Nawaz et al. 2021, Cardoso et al. 2022).

A broiler in its first weeks of life is similar to a poikilothermic animal, with a body temperature that tracks thermal variations in the environment. In this phase, the bird’s thermoregulatory system is not fully developed, and the bird does not have sufficient energy reserves to adapt to variations in the thermal environment. Although these birds are homeothermic, they are affected by the thermal environment in later developmental stages, especially by the combination of high values of air temperature and relative humidity.

The air dry-bulb temperature (t_db) ranges for the thermal comfort of broiler chickens from one to 49 days of age are 32 to 35 °C, 29 to 32 °C, 26 to 29 °C, 26 to 29 °C, 20 to 23 °C, 18 to 20 °C, and 18 to 20 °C for weeks 1-7, respectively (Abreu et al. 2015, Lourençoni et al. 2015, Ferraz et al. 2017, Paulino et al. 2019, Camargo et al. 2019).

However, the most appropriate measure of thermal comfort in countries with tropical climates is the black globe-humidity index (BGHI), which reflects the combined effects of t_db, the relative air humidity (RH), the air velocity, and thermal radiation.

Several studies have shown that thermal discomfort in broiler chickens has several negative consequences for production, such as decreased feed intake, altered water consumption, reduced growth, increased heart rate, and altered feed conversion, and can even lead to bird death (Lara & Rostagno 2013, Abreu et al. 2019a, Liu et al. 2020, Ribeiro et al. 2020, Iyasere et al. 2021). Thus, suitable thermal environments must be developed for poultry production (Castro et al. 2023).

In this sense, control systems are necessary to regulate thermal variables in the breeding environment. According to Amaral et al. (2023), thermal control systems in poultry houses use the on/off method due to their simple architecture and implementation. However, a controller based on fuzzy artificial intelligence is an alternative to classical system management methods (Mohapatra & Lenka 2016, Szesz Junior et al. 2016, Huang & Zhang 2017). Artificial intelligence, through fuzzy logic (Zadeh 1965), can be used in poultry production, with satisfactory results (Bahuti et al. 2018, Amaral et al. 2023). Mirzaee-Ghaleh et al. (2015) observed high performance of fuzzy controller to control temperature and humidity in poultry facilities when compared to on/off controllers. In turn, in a simulation, Zhou & Liang (2020) found superior temperature control performance using fuzzy controllers compared with the PID controller.

Furthermore, some studies have reported the use of artificial intelligence embedded in microcontrollers to control system environments (Sreekantha & Kavya 2017, Stewart et al. 2017). However, conventionally in emerging countries, data sampling in the breeding environment occurs manually and randomly. Since the broiler management program depends on the experience and feedback information from broiler farmers (Wang et al. 2021). Thus, low-cost intelligent systems enable innovative technologies to be implemented in these countries to improve intelligent and sustainable production. Technology can improve productivity and reduce uncertainty during production.

Implementing artificial intelligence in conjunction with the Internet of Things (IoT) can benefit a variety of agrarian sectors by enhancing both the physical and management capacity of a rural property and decision-making. The IoT has been used in soil monitoring, animal monitoring, and actuator applications to control irrigation, fertilizer application, the thermal environment, and access. The data collected by the IoT can be compiled into databases for further analysis to improve decision-making and increase production efficiency (Phiri et al. 2018, Muangprathub et al. 2019). Suseendran & Balaganesh (2021), when developing a smart cattle health monitoring system using IoT sensors, found that the proposed system achieves a 4% higher package delivery rate, 14% lower delay and 12% higher residual energy than the other existing systems.

Although studies with fuzzy controllers embedded in applications are widespread in several areas of knowledge, this tool is still a novelty in relation to climate control in poultry production. Furthermore, these resources are fundamental for the implementation of poultry farming 4.0 (Ren et al. 2020), which integrates virtual and real elements to construct a system to achieve an unmanned ecosystem to enhance flexible decisions.

The objective of the present study is the development of a fuzzy controller embedded in a microcontroller and a multiplatform web application that communicates with the fuzzy controller to control the aviary climate system for raising broiler chickens.

Related studies

Artificial intelligence has been applied in various sectors in society, urban examples of which are the successful optimization of energy consumption in cities (Paz et al. 2016) and prediction of residential electricity consumption (Khoury et al. 2016).

Ponciano et al. (2011) reported lower errors using fuzzy systems to monitor and control the thermal environment results than from conventional methodologies for predicting variables that affect the thermal comfort of broiler chickens. Fuzzy systems control also improve conditions for animal welfare.

Damasceno et al. (2017) found that the use of fuzzy models to estimate the thermal comfort temperature for broiler chickens was a viable technique for controlling the thermal environment and minimizing productivity losses.

Agrarian studies have been developed in several areas of application, such as the use of embedded fuzzy systems to control the dispersion of feed for broiler chickens. Satisfactory results were obtained for liquid feeds in terms of all the response parameters for feed dispersion (Bala et al. 2019). Damasceno et al. (2017) concluded that fuzzy systems provide a good alternative for estimating the thermal comfort of birds to minimize production losses. Lourençoni et al. (2019) proposed a fuzzy system for the efficient prediction of the daily average feed intake, weight gain, feed conversion, and productive efficiency index of broilers. Several authors have concluded that fuzzy systems provide more accurate predictions than empirical and statistical models (Abreu et al. 2019b, Klaučo & Kvasnica 2019, Lourençoni et al. 2019, Bahuti et al. 2023). In addition, fuzzy controller can save energy consumption and increase broiler performance during the growing period when compared to the on/off controller (Lahlouh et al. 2020).

Thus, fuzzy logic has been validated as an alternative and successful methodology to support decision-making in various sectors.

Artificial intelligence has been used to monitor and control the thermal environment in aviaries. Alecrim et al. (2017) developed a fuzzy system embedded in a PIC microcontroller to supervise the aviary thermal environment and aid in decision-making on environmental control from day one to day 28 of bird life. Li et al. (2015) concluded that IoT can be reliably and economically used to monitor aviaries, using supervision and decision-making based on t_db, air humidity, and gas concentration. Pereira et al. (2020) stated that IoT provides high efficiency and speed for recording and transmission of environmental data, respectively, increasing the productivity in biosystems (Pereira et al. 2020).

Muangprathub et al. (2019) used the IoT to monitor and control a greenhouse for growing tomatoes and achieved 30% savings in water consumption and 80% savings in some nutrients used for production compared to a regular open crop. The IoT was recommended as a control tool for decision-making in precision agriculture.

The technological evolution of the IoT has enabled devices to become smarter. Thus, efficiency and savings have been increased, while minimizing human work and speeding up interactions with producers, who have been supported in decision-making and control. Research developments in this field using digital agriculture have furthered human progress (Khanna & Kaur 2019) and increased the food production supply for the ever-growing demand of the world’s population.

Nawandar & Satpute (2019) showed that the IoT has played a key role in the evolution of digital and intelligent agriculture. IoT concepts were implemented in an intelligent irrigation controller to produce savings of 67% in irrigation water consumption.

Thus, the IoT can assist as an alternative support in the modern management of various sectors of broiler chicken production to increase savings and efficiency.

MATERIALS AND METHODS

System architecture

In addition to using artificial intelligence to aid in environmental decision-making, a system was developed in this study to apply IoT technologies for the real-time transmission, access, and remote control of information.

The proposed system is composed of hardware and software. The software is the intangible logic system, wherein embedded fuzzy rules provide intelligent control using an embedded fuzzy logic library (eFLL; Kridi et al. 2013), and an algorithm is implemented using JavaScript for the other web application functions.

The physically tangible components (hardware) of the intelligent control system are circuit boards, wires, sensors, and actuators. The devices under thermal environmental control are driven using a Raspberry Pi 3 and ESP8266 microcontrollers with four actuators (relays), which can be expanded to accommodate the number of devices. A DS18B20 temperature sensor is used to measure the black globe temperature (t_bg, °C), and a Model DHT22 temperature and humidity sensor is used to measure the t_db and RH. Arduino (Arduino 2015) is used to convert the sensors signal into t_db, t_bg and RH. There is a power supply for each device, and connectors and mobile devices are used to access the web application, monitor the collected information, and provide manual control.

Different studies in the literature have used Node-RED (https://nodered.org/) for web implementations (Krause 2017, Liang et al. 2017, Davidson et al. 2019, Baig et al. 2021). This software has become a suitable tool for digital agriculture and is used in this study. As reported in the aforementioned studies, Node-RED is a technological innovation for the IoT and an open-source and multiplatform for the production sector, information transmission, and agri-industrial control.

The architecture of the proposed system is illustrated in Figure 1. The embedded algorithms control the entire system, publish to a broker (a communication intermediary) and store data in a MySQL database. Mobile devices (a smartphone, tablet or notebook) can be used to access the web application, manually control the monitored system, and supervise and make available data collected from the environment in which the devices are inserted. Users can view in real time the fuzzy rating of the fuzzy controller for the thermal environment as a function of the data collected by the fuzzy controller. Users can also turn the thermal environmental control devices on and off.

Figure 1
System architecture (Icon source: www.flaticon.com/authors/eucalyp).

System data stream

The t_db, t_bg, and RH are transmitted in the system data stream (Figure 2) via MQTT from the collectors (DHT22, DS18B20, ESP8266). The broiler flock age is provided on the web application screen. The central computer receives the variables and sends them to the actuators (relays, ESP8266). After fuzzy classification based on the BGHI and bird age, the actuators perform thermal environmental control. All of the information can be viewed on the web application screen in real time.

Figure 2
UML stream of system variables.

In this study, the BGHI developed by Buffington et al. (1981) was used. The BGHI is currently considered the most suitable index for characterizing environmental thermal comfort because the effects of the t_db, ventilation, and thermal radiation are combined into a single variable, the black globe temperature (t_bg). In addition, air humidity is account via air dew-point temperature (t_dp). The BGHI is calculated using equation 1.

$$BGHI=T_{bg}+0.36T_{dp}–330.08$$ (1)

where,

T_bg: black-globe temperature (K);

T_dp: air dew-point temperature (K).

The air dew-point is the temperature at which water vapor in the ambient air condenses into its liquid state in the form of small droplets, called dew. Following Wilhelm (1976), the air dew-point temperature (t_dp, °C) can be calculated using equations 2 and 3, for t_db between 0 and 50 °C and -50 °C and 0 °C, respectively. The current air vapor pressure (e) is estimated using Wilhelm’s (1976) mathematical model as a function of RH.

$$t_{dp}=6.983+14.38\bullet ln(e)+1.079·[lne{]}^2$$ (2)

$$t_{dp}=5.994+12.41\bullet ln(e)+0.4273[lne{]}^2$$ (3)

where,

t_dp: air dew-point temperature (°C);

e: current air vapor pressure (kPa).

Preparation of fuzzy sets

Mamdani-type fuzzy logic was adopted, and trapezoidal membership functions were used to represent the BGHI intervals and the bird age in days (Figure 3). In the literature, triangular, trapezoidal, and Gaussian membership functions have been used in fuzzy systems to satisfactorily predict the average daily feed intake, weight gain, feed conversion, and productive efficiency index of chickens (Abreu et al. 2015, Alecrim et al. 2017, Lourençoni et al. 2019, Amaral et al. 2023).

Figure 3
Fuzzy membership functions applied to input variables: (a) black globe-humidity index (BGHI) and (b) bird age (A).

The values used to construct the trapezoidal and triangular membership functions for the BGHI, bird age, and fuzzy score are listed in Tables I, II, and III, respectively. The following limits were defined for each membership function, the initial lower limit (LL_i), the initial upper limit (UL_i), the final upper limit (UL_f), and the final lower limit (LL_f).

Table I
Values for fuzzy input membership functions for black globe-humidity index (BGHI).

Function	Type	LLi	ULi	ULf	LLf
BGHI1	Trapezoidal	60.0	60.0	65.0	67.0
BGHI2	Trapezoidal	65.0	68.0	69.4	71.0
BGHI3	Trapezoidal	68.8	70.5	76.6	78.0
BGHI4	Trapezoidal	75.0	77.0	83.6	84.4
BGHI5	Trapezoidal	82.0	86.0	120.0	120.0

Table II
Values for fuzzy input membership functions for bird age (A).

Function	Type	LLi	ULi	ULf	LLf
A1	Trapezoidal	1	1	7	8
A2	Trapezoidal	7	8	21	22
A3	Trapezoidal	21	22	49	49

Table III
Values for fuzzy output membership functions for thermal environment.

Function	Type	LLi	ULi	ULf	LLf
VC	Trapezoidal	0	0	8	16
C	Triangular	13	- -	25	38
F	Triangular	33	- -	45	58
H	Triangular	55	- -	66	78
VH	Trapezoidal	73	90	150	150

The adopted BGHI fuzzy sets were divided based on intervals from the literature to define the thermal comfort for broilers for the first seven weeks of a broiler’s life (Oliveira et al. 2006, Alecrim et al. 2017, Oliveira Júnior et al. 2018). And for the bird age, the fuzzy sets were adopted based on birds’ life stages (Lourençoni et al. 2019). Thus, five and three classes were defined, respectively, to BGHI and bird age.

As for the input variables, trapezoidal membership functions were also adopted for the output variables of the thermal environment classification, but along with triangular (Figure 4). Defuzzification was performed using the center of gravity method, wherein all of the possible outputs are considered to transform the fuzzy set created through inference into a numerical value. Thus, a score for the thermal environment is obtained in terms of linguistic variables: very cold (VC), cold (C), comfortable (F), hot (H), and very hot (VH), which are defined as a function of air dry-bulb temperature and the BGHI cited in the literature.

Figure 4
Fuzzy output membership functions for thermal environment classification.

Rules were generated based on literature data and the experience of help of experts with experience in fuzzy logic and animal ambience for over ten years, who were chosen according to the methodology proposed by Cornelissen et al. (2003) that has applied by other authors (Alecrim et al. 2017, Ferraz et al. 2017, Hernández-Julio et al. 2020).

The linguistic terms were assigned according to the combinations of BGHI and bird age, as listed in Table IV. The fifteen generated rules were converted into a programming language appropriate for the eFLL (Kridi et al. 2013) and embedded in the ESP8266 microcontroller.

Table IV
System of fuzzy inference rules for variables of black globe-humidity index (BGHI) and bird age (A).

Age (days)	BGHIi
	1	2	3	4	5
A1	VC	VC	C	F	H
A2	VC	C	F	H	VH
A3	C	F	H	VH	VH

The performance of the fuzzy system embedded in the microcontroller was compared to that implemented in MATLAB. One hundred and fifty scenarios, consisting of random combinations of the BGHI and the bird age were generated and used as input data to both systems. After processing, the thermal environment scores simulated by the two systems were compared, and the percentage accuracy of the embedded fuzzy system was calculated.

Hardware development

Data acquisition module

The acquisition module is made up of the following components: Model DS18B20 digital sensors that measure t_bg; Model DHT22 sensors that measures the t_db and RH; an ESP8266 microcontroller and case for protection; and a USB cable to connect to a 5 V power supply. The digital temperature sensors communicate via a one-wire bus: a unique-64 bit code enables the identification of several DS18B20 sensors so that multiple sensors can be connected (Maxim Integrated Products 2019).

The DHT22 sensor (Model RHT03 or AM2302), collects RH values ranging from 0 to 100 (%) for temperatures ranging from -40 to 80 °C, with an accuracy of 2%. For t_db the accuracy is ±0.5 °C. The sensor comes calibrated from the factory and is compatible with the microcontroller. The sensor adjustment coefficients are internally stored (Jazizadeh & Jung 2018).

Sensor calibration

The measurement sensors for t_db (DHT22), t_bg (DS18B20 installed in the geometric center of a black globe), and the RH (DHT22) were calibrated using the sensors in a TGD-400 thermal stress meter (Instrutherm) as a reference. The TGD-400 has an accuracy of ±0.5 °C, ±0.5 °C, and ±4% for t_db, t_bg, and RH, respectively.

The aforementioned variables were measured in a climate-controlled wind tunnel by the sensors used in the developed controller and the TGD-400 thermal stress meter as a reference. The t_db values in the tested thermal environments were 16, 20, 24, 28, 32, and 36 °C. The reference device was used to measure a corresponding RH value in the tunnel at the time that each temperature data point was collected.

The sensor measurements were compared by calculating the mean values, absolute errors (AE), percentage errors (PE), and the coefficient of determination (R2) of the data, and the t-test was applied.

Thermal environment control actuator module (relays and control receiver)

The actuator module is composed of four (110 V/220 V) relays, which can control equipment with electrical currents up to 10 A. The relays are activated using a five-volt signal, which is supplied by the ESP8266 microcontroller upon receipt of a command via MQTT from the Raspberry Pi 3 central processor to drive a connected device. Appropriate contactors may be used if the device to be operated requires an electrical current above 10 A.

The actuator module can drive thermal environment control devices (heaters, fans and the water pump of an evaporative cooling system for wetting porous pads or misting/fogging), when action is needed upon classification of the aviary environment.

Data center and web server (Raspberry Pi)

The Raspberry Pi 3 is selected as the web and data persistence server for its smallness and appropriate functionality for the system architecture, at a viable cost.

The Wi-Fi router is used for wireless communication among the smart controller architecture devices using the MQTT protocol.

The hardware voltage is provided by external sources of 5 V for the Raspberry Pi and microcontrollers and 12 V for the Wi-Fi router.

Software development

Web application deployment

The eFLL (Kridi et al. 2013) was used to embed the 15 fuzzy rules that were generated using expert knowledge.

A broker was implemented in the Raspberry Pi 3 to receive information via MQTT, store the information in the MySQL database, and update the mobile devices connected to the intelligent control system architecture in real time.

The decision-making of the system is performed using an intelligent system embedded in the microcontroller based on rules, where the BGHI and bird age are input variables. Based on these input variables, fuzzy logic performs fuzzification, followed by defuzzification to return a numerical value that is the translation of the fuzzy processing output (Mendel 1995). This numerical value is used to classify the environment in terms of linguistic variables (VC, C, F, H, and VH). The control system uses the rating to decide whether to act on the climatization system, which can be turned on or off in real time, and to inform all of the clients connected to the web server of the action.

Application screens

The main screen of the implemented web application is accessed by a desktop device (Figure 5), which presents real-time information on the measurements of the thermal environment and the respective classification. When accessed by a portable device (e.g.: smartphone), the application responds and automatically adapts to any resolution (size) of the display.

Figure 5
Web application screen.

RESULTS AND DISCUSSION

Sensor calibration

No significant differences (p>0.05, t-test) were found for t_db, RH and t_bg between the postcalibration (measured by DHT22 and DS18B20 sensors and corrected through calibration equations) and reference (measured by TGD-400 sensor) values (Table V).

Table V
Mean, standard deviation, and statistical analysis of air dry-bulb temperature (t_db), black-globe temperature (t_bg) and relative air humidity (RH).

	Measurement sensors		Reference sensor	Statistical indices
Variable	DS18B20	DHT22	TGD-400	AE (ºC)	PE (%)	Std. t-test
tdb (ºC)	-	26.74 ± 7.10	26.06 ± 6.83	0.71 ± 0.44	2.67 ± 1.45	NS
RH (%)	-	64.69 ± 9.47	64.69 ± 9.75	1.77 ± 1.49	2.69 ± 2.15	NS
tbg (ºC)	24.60 ± 5.96	-	24.60 ± 6.02	0.57 ± 0.57	2.43 ± 2.49	NS

The t_db and RH values measured by the DHT22 sensor were corrected by fitting a linear regression equation (Figure 6a, b), which had R2 values of 0.9969 and 0.9437, respectively. Similar to t_db and RH results, the average values of t_bg measured in the proposed controller were closer to the reference sensor measurements (Table V), with R2 of 0.9819 (Figure 6c). The calibration-adjusted equations and profiles in the data are shown in Figure 6.

Figure 6
Correlations between (a) air dry-bulb temperature (t_db) (measured by DHT22), (b) air relative humidity (RH) (measured by DHT22) and (c) black globe temperature (t_bg) (measured by DS18B20) and TGD-400 (calibration reference) sensors.

Lahlouh et al. (2020) observed tha the fuzzy methodology is combined with a proportional, integral and derivative (PID) controller have fewer errors than those with on/off systems. In this aspect, Gao et al. (2022) developed a fuzzy PID controller for chick brooder house, and obtained R², EA and EP of 0.7634, 1.32 and 4.2%, respectively, among the simulated t_db values and measured experimentally. In turn, the R², EA and EP indicators between the simulated and measured values and RH were 0.9740, 1.91% and 3.66%, respectively. Thus, the results of the system proposed in this research indicate efficiency, since Gao et al. (2022) concluded that their controller achieved accuracy.

System architecture

The prototype implemented as an application in agribusiness 4.0 uses artificial intelligence to supervise and monitor the thermal environment for broiler thermal comfort and provides more advanced architecture and technologies than low-cost hardware and software reported in the literature (Alecrim et al. 2017, Camargo et al. 2019).

The prototype adopted the BGHI as the thermal comfort parameter from the first to the last week of the birds’ life (42 days). The BGHI was calculated in real time and implemented through 15 fuzzy rules. After defuzzification, a decision was made that was used to control the aviary thermal environment.

Unlike studies performed on poultry control and supervision (Szesz Junior et al. 2016, Alecrim et al. 2017, Lorencena et al. 2019), the proposed web application in this research adopts the existing technologies of agribusiness 4.0, the IoT, and open-source tools. Information for clients connected to the Raspberry Pi 3 server is updated in real time, and the data is saved to a MySQL database. The server thus functions as a datalogger, while controlling the aviary thermal environment.

The system uses the Wi-Fi network and the MQTT protocol for communication among devices. In turn, the VPN manages information security to intelligently control the aviary thermal environment. Thus, the system enables remote automated control and production monitoring through mobile devices. The improved management of the installed aviary thermal environment control systems thus optimizes production. This system is a viable, more technologized, and smart alternative for precision agriculture. Villa-Henriksen et al. (2020) stated that the viability is one of challenges of IoT systems and highlighted the importance of academic research for solving or reducing the issues.

The embedded fuzzy system was found to perform reliably (98% accuracy) by comparison to MATLAB simulations for thermal environment classification. The proposed system can thus be applied in intelligent aviaries. The use of this control system with Arduino and IoT is a viable and low-cost solution to facilitate the updating of the poultry industry and the digital transformation for the migration of intelligent production.

Future studies can be done to incorporate more variables that can be collected in modern broiler farms to efficiently and effectively estimate welfare and production efficiency. Several studies used fuzzy logic as a tool for predicting physiological and productive responses (Omomule et al. 2020, Amaral et al. 2023, Bahuti et al. 2023), in order to act as decision support systems and to be embedded in controllers. This way, it will be possible to adjust decisions related to chicken management, improving health and well-being, and promoting adequate environmental control. Because, according to Marcone et al. (2022), animal welfare conditions must be obtained by combining environmental thermal variables with animal-based indicators.

CONCLUSIONS

An embedded fuzzy controller, which consists of hardware, a web application, and a web server, is proposed in this study. The proposed controller is implemented on a small Raspberry Pi 3 computer to serve as a low-cost alternative for the intelligent control of an aviary thermal environment for raising broiler chickens. A statistical analysis of data collected and measured in the laboratory was used to validate the proposed controller. Thus, the validation results reinforce the efficiency, reliability, and stability of the proposed system, so that the control strategy carried out by the developed system meets the requirements for maintaining temperature and relative humidity.

References

• ABREU LHP, YANAGI JUNIOR T, BAHUTI M, LIMA RR, LOURENÇONI D & FASSANI ÉJ. 2019a. Performance of broilers submitted to different intensities and duration of thermal stress. Dyna 86(211): 131-137. https://doi.org/10.15446/dyna.v86n211.79465.
  » https://doi.org/10.15446/dyna.v86n211.79465
• ABREU LHP, YANAGI JUNIOR T, CAMPOS AT, LOURENÇONI D & BAHUTI M. 2019b. Fuzzy model for predicting cloacal temperature of broiler chickens under thermal stress. Eng Agric 39: 18-25. https://doi.org/10.1590/1809-4430-eng.agric.v39n1p18-25/2019.
  » https://doi.org/10.1590/1809-4430-eng.agric.v39n1p18-25/2019
• ABREU LHP, YANAGI JUNIOR T, FASSANI ÉJ, CAMPOS AT & LOURENÇONI D. 2015. Modelagem fuzzy do desempenho de frangos de corte, criados de 1 a 21 dias, submetidos a estresse térmico. Eng Agric 35(6): 967-978. http://dx.doi.org/10.1590/1809-4430-Eng.Agric.v35n6p967-978/2015.
  » https://doi.org/10.1590/1809-4430-Eng.Agric.v35n6p967-978/2015
• ALECRIM PD, CAMPOS AT, YANAGI JUNIOR T, FERREIRA JC & TRINDADE AA. 2017. Low cost fuzzy system applied to the control and supervision of thermal environment in poultry farms. Eng Agric 37: 194-205. https://doi.org/10.1590/1809-4430-Eng.Agric.v37n1p194-205/2017.
  » https://doi.org/10.1590/1809-4430-Eng.Agric.v37n1p194-205/2017
• AMARAL BC, BAHUTI M, YANAGI JUNIOR T, ABREU LHP, LIMA RR, CAMPOS AT & FASSANI ÉJ. 2023. Proficiencies of different fuzzy inference systems in predicting the production performance of broiler chickens. Comput Electron Agric 209: 107860. https://doi.org/10.1016/j.compag.2023.107860.
  » https://doi.org/10.1016/j.compag.2023.107860
• ARDUINO. 2015. Arduino Playground - DHTLib [WWW Document]. Nov 06, 2015, 0618 AM.
• ASTILL J, DARA RA, FRASER EDG, ROBERTS B & SHARIF S. 2020. Smart poultry management: Smart sensors, big data, and the internet of things. Comput Electron Agric 170: 105291. https://doi.org/10.1016/j.compag.2020.105291.
  » https://doi.org/10.1016/j.compag.2020.105291
• BAHUTI M, ABREU LHP, YANAGI JUNIOR T, LIMA RRD & CAMPOS AT. 2018. Performance of fuzzy inference systems to predict the surface temperature of broiler chickens. Eng Agric 38(6): 813-823. https://doi.org/10.1590/1809-4430-Eng.Agric.v38n6p813-823/2018.
  » https://doi.org/10.1590/1809-4430-Eng.Agric.v38n6p813-823/2018
• BAHUTI M, YANAGI JUNIOR T, LIMA RR, FASSANI ÉJ, RIBEIRO BPVB, CAMPOS AT & ABREU LHP. 2023. Statistical and fuzzy modeling for accurate prediction of feed intake and surface temperature of laying hens subjected to light challenges. Comput Electron Agric 211: 108050. https://doi.org/10.1016/j.compag.2023.108050.
  » https://doi.org/10.1016/j.compag.2023.108050
• BAIG MJA, IQBAL MT, JAMIL M & KHAN J. 2021. Design and implementation of an open-Source IoT and blockchain-based peer-to-peer energy trading platform using ESP32-S2, Node-Red and, MQTT protocol. Energy Rep 7: 5733-5746. https://doi.org/10.1016/j.egyr.2021.08.190.
  » https://doi.org/10.1016/j.egyr.2021.08.190
• BALA JA, OLANIYI OM, FOLORUNSO TA & ARULOGUN OT. 2019. Poultry Feed Dispensing System Control: A Case between Fuzzy Logic Controller and PID Controller. Balkan J Electr Comput Eng 7(2): 171-177. https://doi.org/10.17694/bajece.536026.
  » https://doi.org/10.17694/bajece.536026
• BARBOSA CF, CARVALHO RH, ROSSA A, SOARES AL, CORÓ FAG, SHIMOKOMAKI M & IDA EI. 2013. Commercial preslaughter blue light ambience for controlling broiler stress and meat qualities. Braz Arch Biol Technol 56: 817-821. https://doi.org/10.1590/S1516-89132013000500013.
  » https://doi.org/10.1590/S1516-89132013000500013
• BUFFINGTON DE, COLLAZO-AROCHO A, CANTON GH, PITT D, THATCHER WW & COLLIER RJ. 1981. Black Globe-Humidity Index (BGHI) as Comfort Equation for Dairy Cows. Trans ASAE 24(3): 711-0714. https://doi.org/10.13031/2013.34325.
  » https://doi.org/10.13031/2013.34325
• CAMARGO TF, SILVA RL, HIGA M, COUTINHO MR, OLIVEIRA JC & CONCEIÇÃO WADS. 2019. Thermal comfort monitoring in aviaries by a real-time data acquisition system. Rev Bras Eng Agric Ambient 23(9): 694-701. https://doi.org/10.1590/1807-1929/agriambi.v23n9p694-701.
  » https://doi.org/10.1590/1807-1929/agriambi.v23n9p694-701
• CARDOSO DM, CARDEAL PC, SOARES KR, SOUSA LS, CASTRO FLS, ARAÚJO ICS & LARA LJC. 2022. Feed form and nutritional level for rearing growing broilers in thermoneutral or heat stress environments. J Therm Biol 103: 103159. https://doi.org/10.1016/j.jtherbio.2021.103159.
  » https://doi.org/10.1016/j.jtherbio.2021.103159
• CASTRO JO, YANAGI JUNIOR T, BAHUTI M, FASSANI ÉJ & LIMA RR. 2023. Thermal comfort thresholds for Japanese quails based on performance and egg quality. Int J Biometeorol 67(2): 265-274. https://doi.org/10.1007/s00484-022-02403-1.
  » https://doi.org/10.1007/s00484-022-02403-1
• CORNELISSEN AMG, VAN DEN BERG J, KOOPS WJ & KAYMAK U. 2003. Elicitation of expert knowledge for fuzzy evaluation of agricultural production systems. Agric Ecosyst Environ 95: 1-18. https://doi.org/10.1016/S0167-8809(02)00174-3.
  » https://doi.org/10.1016/S0167-8809(02)00174-3
• DAMASCENO FA, CASSUSSE DC, ABREU LHP, SCHIASSI L & TINÔCO IFF. 2017. Effect of thermal environment on performance of broiler chickens using fuzzy modeling. Rev Ceres 64(4): 337-343. https://doi.org/10.1590/0034-737X201764040001.
  » https://doi.org/10.1590/0034-737X201764040001
• DAVIDSON C, REZWANA T & HOQUE MA. 2019. Smart Home Security Application Enabled by IoT. In: Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering. Springer, p. 46-56. https://doi.org/10.1007/978-3-030-05928-6_5.
• FERRAZ PFP, YANAGI JUNIOR T, LIMA RR, FERRAZ GAS & XIN H. 2017. Performance of chicks subjected to thermal challenge. Pesqui Agropecu Bras 52: 113-120. https://doi.org/10.1590/s0100-204x2017000200005.
  » https://doi.org/10.1590/s0100-204x2017000200005
• GAO L, ER M, LI L, WEN P, JIA Y & HUO L. 2022. Microclimate environment model construction and control strategy of enclosed laying brooder house. Poult Sci 101(6): 101843.
• HERNÁNDEZ-JULIO YF, FERRAZ PF, YANAGI JUNIOR T, BARBARI M & NIETO-BERNAL W. 2020. Fuzzy-genetic approaches to knowledge discovery and decision making: Estimation of the cloacal temperature of chicks exposed to different thermal conditions. Biosyst Eng 199: 109-120. https://doi.org/10.1016/j.biosystemseng.2020.02.005.
  » https://doi.org/10.1016/j.biosystemseng.2020.02.005
• HUANG J & ZHANG L. 2017. The big data processing platform for intelligent agriculture. In AIP Conference Proceedings 1864(1): 020033. https://doi.org/10.1063/1.4992850.
  » https://doi.org/10.1063/1.4992850
• IYASERE OS, BATESON M, BEARD AP & GUY JH. 2021. Which factor is more important: Intensity or duration of episodic heat stress on broiler chickens? J Ther Biol 99: 102981. https://doi.org/10.1016/j.jtherbio.2021.102981.
  » https://doi.org/10.1016/j.jtherbio.2021.102981
• JAZIZADEH F & JUNG W. 2018. Personalized thermal comfort inference using RGB video images for distributed HVAC control. Appl Energy 220: 829-841. https://doi.org/10.1016/j.apenergy.2018.02.049.
  » https://doi.org/10.1016/j.apenergy.2018.02.049
• KHANNA A & KAUR S. 2019. Evolution of internet of things (Iot) and its significant impact in the field of precision agriculture. Comput Electron Agric 157: 218-231. https://doi.org/10.1016/j.compag.2018.12.039.
  » https://doi.org/10.1016/j.compag.2018.12.039
• KHOURY J, MBAYED R, SALLOUM G & MONMASSON E. 2016. Predictive demand side management of a residential house under intermittent primary energy source conditions. Energy Build 112: 110-120. https://doi.org/10.1016/j.enbuild.2015.12.011.
  » https://doi.org/10.1016/j.enbuild.2015.12.011
• KLAUČO M & KVASNICA M. 2019. Model Predictive Control. In: MPC-Based Reference Governors, Advances in Industrial Control. Springer, p. 15-34. https://doi.org/10.1007/978-3-030-17405-7_3.
• KRAUSE J. 2017. Programming Web Applications with Node, Express and Pug, Programming Web Applications with Node, Express and Pug. Apress, 198 p. https://doi.org/10.1007/978-1-4842-2511-0
  » https://doi.org/10.1007/978-1-4842-2511-0
• KRIDI DS, ALVES AJO & LEMOS MVS. 2013. Desenvolvimento de uma biblioteca fuzzy para o controle autônomo de um robô móvel em ambiente desconhecido. Mostra Nacional de Robótica, p. 1.
• LAHLOUH I, RERHRHAYE F, ELAKKARY A & SEFIANI N. 2020. Experimental implementation of a new multi input multi output fuzzy-PID controller in a poultry house system. Heliyon 6(8): e04645. https://doi.org/10.1016/j.heliyon.2020.e04645.
  » https://doi.org/10.1016/j.heliyon.2020.e04645
• LARA L & ROSTAGNO M. 2013. Impact of Heat Stress on Poultry Production. Animals 3: 356-369. https://doi.org/10.3390/ani3020356.
  » https://doi.org/10.3390/ani3020356
• LI H, WANG H, YIN W, LI Y, QIAN Y & HU F. 2015. Development of a Remote Monitoring System for Henhouse Environment Based on IoT Technology. Future Internet 7: 329-341. https://doi.org/10.3390/fi7030329.
  » https://doi.org/10.3390/fi7030329
• LIANG L, ZHU L, SHANG W, FENG D & XIAO Z. 2017. Express supervision system based on NodeJS and MongoDB. In: IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS). IEEE, p. 607-612. https://doi.org/10.1109/ICIS.2017.7960064.
• LIU L, REN M, REN K, JIN Y & YAN M. 2020. Heat stress impacts on broiler performance: a systematic review and meta-analysis. Poul Sci 99(11): 6205-6211. https://doi.org/10.1016/j.psj.2020.08.019.
  » https://doi.org/10.1016/j.psj.2020.08.019
• LORENCENA MC, SOUTHIER LFP, CASANOVA D, RIBEIRO R & TEIXEIRA M. 2019. A framework for modelling, control and supervision of poultry farming. Int J Prod Res: 1-16. https://doi.org/10.1080/00207543.2019.1630768.
• LOURENÇONI D, YANAGI JUNIOR T, ABREU PG, CAMPOS AT & YANAGI SNM. 2019. Productive responses from broiler chickens raised in different commercial production systems - part I: fuzzy modeling. Eng Agric 39: 1-10. https://doi.org/10.1590/1809-4430-eng.agric.v39n1p1-10/2019.
  » https://doi.org/10.1590/1809-4430-eng.agric.v39n1p1-10/2019
• LOURENÇONI D, YANAGI JUNIOR T, OLIVEIRA DD, CAMPOS AT & LIMA RR. 2015. Condições ambientais em galpão convencional telado para galinhas poedeiras Hyline W-36. Eng Agric 35(1): 1-10. http://dx.doi.org/10.1590/1809-4430-Eng.Agric.v35n1p1-10/2015.
  » https://doi.org/10.1590/1809-4430-Eng.Agric.v35n1p1-10/2015
• MARCONE G, CARNOVALE F, ARNEY D, ROSA G & NAPOLITANO F. 2022. Relevance of animal-based indicators for the evaluation of sheep welfare as perceived by different stakeholders. Small Ruminant Res 217: 106827.
• MAXIM INTEGRATED PRODUCTS. 2019. DS18B20 Programmable Resolution 1-Wire Digital Thermometer. 20 p. Accessed: May, 2023. Available at: https://datasheets.maximintegrated.com/en/ds/DS18B20.pdf
  » https://datasheets.maximintegrated.com/en/ds/DS18B20.pdf
• MENDEL JM. 1995. Fuzzy logic systems for engineering: a tutorial. Proc IEEE 83: 345-377. https://doi.org/10.1109/5.364485.
  » https://doi.org/10.1109/5.364485
• MIRZAEE-GHALEH E, OMID M, KEYHANI A & DALVAND MJ. 2015. Comparasion of fuzzy and on/off controllers for winter season indoor climate management in a model poultry house. Comput Electron Agric 110: 187-195. https://doi.org/10.1016/j.compag.2014.11.017.
  » https://doi.org/10.1016/j.compag.2014.11.017
• MOHAPATRA AG & LENKA SK. 2016. Neural Network Pattern Classification and Weather Dependent Fuzzy Logic Model for Irrigation Control in WSN Based Precision Agriculture. Procedia Comput Sci 78: 499-506. https://doi.org/10.1016/j.procs.2016.02.094.
  » https://doi.org/10.1016/j.procs.2016.02.094
• MUANGPRATHUB J, BOONNAM N, KAJORNKASIRAT S, LEKBANGPONG N, WANICHSOMBAT A & NILLAOR P. 2019. IoT and agriculture data analysis for smart farm. Comput Electron Agric 156: 467-474. https://doi.org/10.1016/j.compag.2018.12.011.
  » https://doi.org/10.1016/j.compag.2018.12.011
• NAWANDAR NK & SATPUTE VR. 2019. IoT based low cost and intelligent module for smart irrigation system. Comput Electron Agric 162: 979-990. https://doi.org/10.1016/j.compag.2019.05.027.
  » https://doi.org/10.1016/j.compag.2019.05.027
• NAWAZ AH, AMOAH K, LENG QY, ZHENG JA, ZHANG WL & ZHANG L. 2021. Poultry response to heat stress: its physiological, metabolic, and genetic implications on meat production and quality including strategies to improve broiler production in a warming world. Front Vet Sci 8: 699081. https://doi.org/10.3389/fvets.2021.699081.
  » https://doi.org/10.3389/fvets.2021.699081
• OLIVEIRA JÚNIOR AJ, SOUZA SRL, CRUZ VF, VICENTIN TA & GLAVINA ASG. 2018. Development of an android APP to calculate thermal comfort indexes on animals and people. Comput Electron Agric 151: 175-184. https://doi.org/10.1016/j.compag.2018.05.014.
  » https://doi.org/10.1016/j.compag.2018.05.014
• OLIVEIRA RD, DONZELE JL, ABREU MD, FERREIRA RA, VAZ RGMV & CELLA PS. 2006. Efeitos da temperatura e da umidade relativa sobre o desempenho e o rendimento de cortes nobres de frangos de corte de 1 a 49 dias de idade. Rev Bras Zootecn 35(3): 797-803. https://doi.org/10.1590/S1516-35982006000300023.
  » https://doi.org/10.1590/S1516-35982006000300023
• OMOMULE TG, AJAYI OO & OROGUN AO. 2020. Fuzzy prediction and pattern analysis of poultry egg production. Comput Electron Agric 171: 105301. https://doi.org/10.1016/j.compag.2020.105301.
  » https://doi.org/10.1016/j.compag.2020.105301
• PAULINO MTF, OLIVEIRA EM, GRIESER DO & TOLEDO JB. 2019. Criação de frangos de corte e acondicionamento térmico em suas instalações: Revisão. Pubvet 13(2): 1-14. https://doi.org/10.31533/pubvet.v13n3a280.1-14.
  » https://doi.org/10.31533/pubvet.v13n3a280.1-14
• PAZ JF, BAJO J, RODRÍGUEZ S, VILLARRUBIA G & CORCHADO JM. 2016. Intelligent system for lighting control in smart cities. Inf Sci 372: 241-255. https://doi.org/10.1016/j.ins.2016.08.045.
  » https://doi.org/10.1016/j.ins.2016.08.045
• PEREIRA WF, FONSECA LS, PUTTI FF, GÓES BC & NAVES LP. 2020. Environmental monitoring in a poultry farm using an instrument developed with the internet of things concept. Comput Electron Agric 170: 105257. https://doi.org/10.1016/j.compag.2020.105257.
  » https://doi.org/10.1016/j.compag.2020.105257
• PHIRI H, KUNDA D & PHIRI J. 2018. An IoT Smart Broiler Farming Model for Low Income Farmers. Int J Recent Contrib Eng, Sci & IT 6: 95. https://doi.org/10.3991/ijes.v6i3.9287.
  » https://doi.org/10.3991/ijes.v6i3.9287
• PONCIANO PF, LOPES MA, YANAGI JUNIOR T & FERRAZ GAS. 2011. Análise do ambiente para frangos por meio da lógica fuzzy: uma revisão. Arch Zootecn 60: 1-13. https://doi.org/10.21071/az.v60i232.4913.
  » https://doi.org/10.21071/az.v60i232.4913
• REN G, LIN T, YING Y, CHOWDHARY G & TING KC. 2020. Agricultural robotics research applicable to poultry production: A review. Comput Electron Agric 169: 105216. https://doi.org/10.1016/j.compag.2020.105216.
  » https://doi.org/10.1016/j.compag.2020.105216
• RIBEIRO BPVB, YANAGI JUNIOR T, OLIVEIRA DD, LIMA RR & ZANGERÔNIMO MG. 2020. Thermoneutral zone for laying hens based on environmental conditions, enthalpy and thermal comfort indexes. J Therm Biol 93: 102678. https://doi.org/10.1016/j.jtherbio.2020.102678.
  » https://doi.org/10.1016/j.jtherbio.2020.102678
• SREEKANTHA DK & KAVYA AM. 2017. Agricultural crop monitoring using IOT - a study. In: 11th International Conference on Intelligent Systems and Control (ISCO). New York: IEEE, p. 134-139. https://doi.org/10.1109/ISCO.2017.7855968.
• STEWART J, STEWART R & KENNEDY S. 2017. Internet of Things - Propagation Modelling for Precision Agriculture Applications. In: Wireless Telecommunications Symposium (WTS). New York: IEEE Xplore, p. 1-8. http://doi.ogr/10.1109/WTS.2017.7943528.
• SUSEENDRAN G & BALAGANESH D. 2021. Smart cattle health monitoring system using IoT sensors. Mater Today: Proc.
• SZESZ JUNIOR A, MONTEIRO JUNIOR M, DIAS AH, MATHIAS IM & CONTI G. 2016. Embedded system in Arduino platform with Fuzzy control to support the grain aeration decision. Cienc Rural 46: 1917-1923. https://doi.org/10.1590/0103-8478cr20141808.
  » https://doi.org/10.1590/0103-8478cr20141808
• VILLA-HENRIKSEN A, EDWARDS GTC, PESONEN LA, GREEN O & SØRENSEN CAG. 2020. Internet of Things in arable farming: Implementation, applications, challenges and potential. Biosyst Eng 191: 60-84. https://doi.org/10.1016/j.biosystemseng.2019.12.013.
  » https://doi.org/10.1016/j.biosystemseng.2019.12.013
• WANG CY, CHEN YJ & CHIEN CF. 2021. Industry 3.5 to empower smart production for poultry farming and an empirical study for broiler live weight prediction. Comput Ind Eng 151: 106931. https://doi.org/10.1016/j.cie.2020.106931.
  » https://doi.org/10.1016/j.cie.2020.106931
• WILHELM LR. 1976. Numerical calculation of psychrometric properties in SI units. Trans ASAE 19(2): 318-321. https://doi.org/10.13031/2013.36019.
  » https://doi.org/10.13031/2013.36019
• ZADEH LA. 1965. Fuzzy Sets. Control 8(3): 338-353. https://doi.org/10.1016/S0019-9958(65)90241-X.
  » https://doi.org/10.1016/S0019-9958(65)90241-X
• ZHOU Z & LIANG C. 2020. Fuzzy sliding-mode temperature-control system for soaking and germination of rice seeds. Eng Agric 40(2): 215-222. https://doi.org/10.1590/1809-4430-Eng.Agric.v40n2p215-222/2020.
  » https://doi.org/10.1590/1809-4430-Eng.Agric.v40n2p215-222/2020

Publication Dates

• Publication in this collection
  21 Mar 2025
• Date of issue
  2025

History

• Received
  12 Jan 2024
• Accepted
  16 Nov 2024