Abstract: A non-invasive method to estimate internal temperature in boneless, skinless chicken meat after cooing is presented. In this work, the internal temperature of chicken breast samples, measured at approximately half the thickness, was correlated with the external temperature of the surface above and the cooling time. For the non-invasive and accurate external temperature measurement a focal planar array IR camera with spectral range of 3.4-5 $mu@m was used. At this spectral band, the interference of water vapor originated from the sample is practically eliminated. Neural networks were used to establish a correlation between internal temperature with external temperature and cooling time. To model the internal and external temperature time series a one-hidden layer feed forward layer, with three hidden nodes was used. The network was trained with 60 time series of 20 time points each one, ranging form 0 to 570 seconds. Training was conducted for 400 epochs, with learning rate 0.3. The predictions obtained were compared with a test data set to judge the performance of the network. The method has great potential for the real-time estimation of internal temperature of cooked chicken meat in industrial lines. !11
展开▼
