Decision support system to classify the vulnerability of broiler production system to heat stress based on fuzzy logic.

In this study, we develop an artificial intelligence model to predict the vulnerability of broiler production systems (broilers and facilities) to heat conditions using a fuzzy model approach. The model was designed with a multiple-input and a single-output (MISO) approach (input: physical environment and broilers age; output: degree of vulnerability of broilers system). For the validation of the fuzzy model, two approaches were used: (1) records from the scientific literature and (2) meteorological forecasts. First, we validated the model fuzzy with data from the scientific literature; second, we validate the model with data from meteorological forecasts. Both validation approaches were performed in different scenarios of the thermal environment (comfort, discomfort, and discomfort + low heat exchange), broilers' age (21-35 days, 25-39 days, and 28-42 days), and relative cooling efficiency (0% inefficient; and 80% efficient). Then, we applied the model to predict the degree of vulnerability of the broiler system with the help of weather forecasts. The recall and precision of the fuzzy model were high (> 0.9) for the thermal comfort and thermal discomfort + low heat exchange scenarios. In contrast, the fuzzy model was moderate agreement (recall 0.45; precision 0.64) for the thermal discomfort scenario compared to the scientific literature. The application of the model with the weather forecast showed the interaction between the physical and biological systems when submitted to a thermal environment challenge. Regardless of the broilers' age, a high degree of vulnerability was observed in facilities with inefficient cooling system. The fuzzy model developed in this study was efficient to predict the vulnerability of the broiler production system to heat conditions, further, to identify the uncertain conditions associated with broilers' age, relative humidity, and the relative cooling efficiency of the facilities.

Efficiency of cooling systems in broiler houses during hot days / Eficiência dos sistemas de resfriamento em aviários durante dias quentes

ABSTRACT: This study evaluated: (1) the vulnerability of broiler houses with different cooling systems, and (2) the spatial distribution of environmental variables during hot days. Four potentially vulnerable commercial broiler houses in southern Brazil were selected according to the following parameters: absence or presence of different cooling systems, broilers older than 28 days, and outside air dry-bulb temperature over 30°C. Broiler house vulnerability was classified according to the cooling and mechanical ventilation system: cellulose pad cooling (CPC), sprinkling (SPK), fogging (FOG), and mechanical ventilation without evaporative cooling system (VTL). The air dry-bulb temperature (Tdb, °C) and relative humidity (RH, %) were recorded every 10 min. For each broiler house, we evaluated: (1) relative cooling efficiency (RCE) and (2) inside spatial distribution of microclimate variables using a geostatistical technique. The CPC and SPK did not differ (P<0.05) in RCE (81.6% and 80.7%, respectively), but both differed from FOG (23.8%) and VLT (1.87%) systems. The highest variations in indoor Tdb were recorded in the FOG (7 °C), followed by the SPK (4 °C) and CPC (3 °C). In the CPC, there was an increase in RH from the middle to the end of the broiler house near the exhaust fans. In conclusion, the relative cooling efficiency and the inside spatial distributions of environmental variables in the broiler houses were influenced by the existing cooling system.

RESUMO: Os objetivos deste estudo foram (1) comparar a vulnerabilidade de aviários com diferentes sistemas de resfriamento, e (2) avaliar a distribuição espacial interna das variáveis ambientais durante dias quentes. Quatro aviários comerciais potencialmente vulneráveis no sul do Brasil foram selecionados de acordo com os seguintes parâmetros de elegibilidade: ausência ou presença de diferentes sistemas de resfriamento; frangos de corte com mais de 28 dias de idade; e temperatura de bulbo seco do ar externa acima de 30 °C. A vulnerabilidade do aviário foi classificada de acordo com o sistema de resfriamento e ventilação mecânica, sendo: resfriamento por pad cooling (CPC), aspersão (SPK), nebulização (FOG) e ventilação mecânica sem sistema de resfriamento evaporativo (VTL). A temperatura de bulbo seco do ar (Tbs, °C) e a umidade relativa do ar (UR, %) foram coletadas por registradores de dados autônomos a cada 10 min. Para cada aviário foram avaliados: (1) eficiência relativa de resfriamento (RCE) e (2) distribuição espacial interna das variáveis ambientais por técnica de geoestatística. O CPC e SPK não diferiram (P>0,05) na RCE (81,6% e 80,7% respectivamente), mas ambos diferiram do FOG (23,8%) e VLT (1,87%). As maiores variações na Tbs do ar interno foram registradas no FOG (7 °C), seguido pelo SPK (4 °C) e CPC (3 °C). No CPC, houve um aumento da umidade relativa do meio para o final do aviário, próximo aos exaustores. Em conclusão, a eficiência relativa de resfriamento, assim como a distribuição espacial das variáveis ambientais internas foram influenciadas pelo sistema de resfriamento de cada aviário.