Neural information processing system for pig carcase grading in Danish slaughterhouses

Abstract

This paper describes a full-sized integrated industrial application of neural networks of considerable extent and economic importance. Since May 1991, 16 million pig carcases have been individually graded every year in the Danish meat industry using a neural information processing system (NIPS) implemented at the 31 Classification Centres (CC). A CC is an 8 × 4 × 4 metre robot which fixs the pigs on a carousel and automatically positions and inserts nine probes into the carcases. A probe records a one-dimensional image, which is processed using multilayer perceptrons, yielding meat and fat thicknesses. The thicknesses from all the probes are subsequently fed to a recurrent neural network, which locates and predicts faulty or missing thicknesses. If there are too many predicted values, the robot repeats the measurement on the corresponding probes. The recurrent network employs a non-standard training method which alters the training data as well as the weights.