Author:

Keywords:

Water Intake, Broiler Chicken

Abstract:

In broiler production, technical and health related problems can have a strong negative effect on the production results. In two experiments with Ross 308 broilers, data of water intake was collected every 5 minutes. Based on the data of the first experiment, an input-output model was developed and tested, to model the water intake as response to the light input. Using this model, an online prediction could be made on the water intake. Actual water intake was compared against the online prediction to signal small (> 15%) and large (> 25%) negative deviations. In the second experiment a number of technical disturbances were induced, in order to validate the model-based detection of the algorithm. 80% of the intentional and unintentional disturbances could be detected using the model. The results have shown a high potential of using water intake for the monitoring of broiler production over a complete growing period.