USE OF ARTIFICIAL NEURAL NETWORK FOR INDUSTRIAL PREDICTION OF FINAL TEMPERATURE OF CHICKEN CARCASSES

In this work, an artificial neural network (ANN) was used to predict the final temperature of chicken carcasses in an industrial scale. For this purpose, temperatures of chicken carcasses were obtained in a slaughterhouse at the end of the cooling process. The variables considered to influence the temperature of carcasses were average carcass weight, prechiller and chillers velocities, prechiller and chillers average temperatures, the absence or presence of bubbles in prechiller and chiller and bubbles intensity, which were considered as input for the ANN. For training and validation of the feed forward neural network, the above inputs were combined to minimize the weighted sum of the squares of the residues, being tested 10 transfer functions, three training algorithms and two different architectures. The best result was obtained using an ANN composed of two hidden layer (10 nodes in each layer), radial bias as transfer function and gradient descent backpropagation algorithm for training. Using this architecture, the regression coefficient was 0.9265. Even with many variables affecting the industrial cooling process of the chicken carcasses, the ANN developed showed satisfactory fitting of the final temperature of chicken carcasses. This model can be further used for optimization purposes, improving the process quality of chicken carcasses as well as process profitability.