On the usage of acoustic properties combined with an artificial neural network – A new approach of determining presence of dairy fouling

Fouling and cleaning in heat exchangers are severe and costly issues in food processing. In this study, a new pattern recognition method for detecting fouling on stainless steel is presented. It is based on a combination of ultrasonic parameters and a multilayer perceptron feed forward neural network. Chosen acoustic parameters change significantly with fouling compared with tap water as standard. When fouling is present echo energy of echo 2 increases up to 73.84%, characteristic acoustic impedance shows 1.802 ± 0.169 MRayl (17.54% higher than impedance for water), and logarithmic decrement seems to decrease. These acoustic parameters have been combined in an artificial neural network (ANN) with one hidden layer and back propagation algorithm to disentangle error proneness of single parameters and increase detection stability. After training with 400 and validation of 250 of 1000 samples, the ANN displayed an accuracy of 98.58% for fouling presence/absence.