The implementation of poultry houses with enhanced control over environmental variables represents a solution to the growing demands for production and animal welfare. This study assessed the internal environment of dark-house poultry houses for broilers on a weekly basis throughout a production cycle. Data were collected over six weeks, from March to April 2016 involving 40,000 Cobb500^TM broilers. A Hobo^® datalogger continuously monitored the temperature (°C), relative humidity (%), dew point temperature (°C), and black globe temperature (°C) at 15 min intervals. The indices analyzed included the temperature and humidity index (THI), the black globe and humidity index (BGHI), and enthalpy (H). In the first week, both the THI and BGHI indicated favorable conditions for the birds, with the THI ranging from 72.4 to 80 and the BGHI from 77 to 81.6. Between the second and fifth weeks, the THI conditions varied between thermal comfort and discomfort, from 56.6 to 72. In the sixth week, all indices indicated discomfort, reflecting increased metabolism and population density. The dark-house system demonstrated a feed efficiency of 51%, an accumulated mortality rate of 1.97%, and a total production of 99,873 kg of meat. The study highlights the importance of continuously monitoring and adjusting environmental conditions to optimize production and enhance bird welfare.

Due to a number of factors involving the thermal environment of a broiler cutting installation and its interaction with the physiological and productive responses of birds, artificial intelligence has been shown to be an interesting methodology to assist in the decision-making process. For this reason, the main aim of this work was to develop an artificial neural network (ANN) to predict feed conversion (FC), water consumption (Cwater), and cloacal temperature (tclo) of broilers submitted to different air dry-bulb temperatures (24, 27, 30, and 33ºC) and durations (1, 2, 3, and 4 days) of thermal stress in the second week of the production cycle. Relative humidity and wind speed were fixed at 60% and 0.2 ms-1 , respectively. The experimental data were used for the development of an ANN with supervised training using the Levenberg-Marquardt backpropagation algorithm. The ANN consisted of three input layers one hidden, and three output with sigmoidal tangent transfer functions with values between-1 and 1. The developed ANN has adequate predictive capacity, with coefficients of determination (R 2) for tclo, FC, and Cwater of 0.79, 0.87, and 0.97, respectively. In this way, the proposed ANN can be used as a support for decision-making to trigger poultry heating systems for broiler breeding.

The cloacal and surface temperatures are important physiological parameters to quantify the thermal comfort of animals, its variations may occur as a function of thermal variables. In this context, the goal of the present study was to evaluate the cloacal (t_clo) and surface (t_sur) temperatures of Cobb 500^® broilers, in the second week of life, subjected to different air dry-bulb temperature (24, 27, 30 and 33 °C) and stress durations (1, 2, 3 and 4 days). The experiment was carried out in four climate-controlled wind tunnels. Air relative humidity and air velocity were set at 60% and 0.2 m s-1, respectively. The t_clo and t_sur were measured daily through digital thermometer and thermographic camera, respectively. Analysis of variance and Scott Knott mean test at 5% probability were applied to the data. The results indicate that the stress by low air temperature (24 and 27 °C) resulted decreased of t_clo and t_sur (p0.05, Scott-Knott test) compared to the control treatment (30 °C). Acclimation of broilers to thermal stress occurred from the second day of stress.

This study aimed to compare fuzzy systems with different configurations to predict the surface temperature (t_s) of broiler chickens subjected to different intensities and durations of thermal challenges in the second week of life. Data on the t_s of broiler chickens aged 8 to 11 days were acquired by infrared thermography and subjected to combinations of four dry-bulb temperatures (t_db) (24, 27, 30, and 33 °C) and four durations of thermal challenges (DTC) (1, 2, 3, or 4 days). The input variables of the fuzzy systems were t_db and DTC, and the output variable was t_s. The Mamdani inference method involving five defuzzification methods [center of gravity (centroid), bisector of the area (bisector), largest of maximum (lom), middle of maximum (mom), and smallest of maximum (som)], and Sugeno inference with two defuzzification methods [weighted average (wtaver) and weighted sum (wtsum)] were evaluated. For both inference methods, triangular and Gaussian pertinence functions were tested for input and output variables, except for Sugeno inference, which used singletons functions as output variables. While developing fuzzy systems, different configurations must be compared, and the system with smaller simulation errors should be selected.

Broiler chickens submitted to different intensities and durations of thermal stress are subject to variation in cloacal temperature and, consequently, to a decrease in performance. Given the complexity of these interactions, artificial intelligence is a useful methodology for decision-making. Thus, this study aimed to assess and predict, by means of a fuzzy model, the cloacal temperature of broiler chickens submitted to thermal stress in the second week of life, with varying durations and intensities, in climatized wind tunnels. Mamdani's inference and defuzzification methods by means of the center of gravity were used. One hundred and twenty rules were elaborated. The developed fuzzy model was used to predict the cloacal temperature of broiler chickens on the day of thermal stress as a function of air dry-bulb temperature (°C), stress duration (days), and the number of days after thermal stress. Cloacal temperature values simulated by the fuzzy model showed standard deviations and percentage errors lower than 0.02 and 0.08%, respectively, when compared to those obtained experimentally.