NEURAL-NETWORK PREDICTION MODELING FOR A CONTINUOUS, SNACK FOOD FRYING PROCESS

Automatic control is a primary concern of a continuous, snack food fry ing process. For the purpose of controlling product quality two neural network paradigms were applied to develop prediction models to deal w ith the complexity of the process. Based on the modeling assumptions o f the process, the neural network one-step-ahead and multiple-step-ahe ad predictors were established mathematically, the training algorithms for the two network predictors were developed and a procedure for net work prediction model identification was established Results of model identification and predictions of the continuous, snack food frying pr ocess were presented in one-step-ahead and multiple-step-ahead modes. Prediction models developed in this article are ready for development of control loops.