Fouling and cleaning of heat exchangers in food industry are severe and costly issues and of high importance. In this study, a planar heat exchanger was constructed to produce and clean milk protein fouling similar to industry. Using a combination of an ultrasonic measuring method and classification machines cleaning should be monitored online to adapt cleaning time. After reproducible fouling deposit was built, cleaning started which was monitored using an ultrasonic measuring unit. The measured ultrasonic signal was analyzed for seven acoustic features and fed together with temperature and mass flow rate (both measured) into a classification method for decision of fouling presence or absence. For classification, artificial neural network (ANN) and support vector machine (SVM) was applied displaying detection accuracies of more than 80 % (ANN) and 94 % (SVM), respectively. Besides, the slope change of the seven acoustic features was monitored with time resulting in a cleaning time of at least 21 ± 4 min. The cleaning time determined by the new sensor system is comparable with previously determined cleaning times for this setup. This study demonstrated that ultrasound based sensor systems offer a new tool to determine presence or absence of fouling and to monitor cleaning processes in the food industry with high accuracy.     «

Fouling and cleaning of heat exchangers in food industry are severe and costly issues and of high importance. In this study, a planar heat exchanger was constructed to produce and clean milk protein fouling similar to industry. Using a combination of an ultrasonic measuring method and classification machines cleaning should be monitored online to adapt cleaning time. After reproducible fouling deposit was built, cleaning started which was monitored using an ultrasonic measuring unit. The measure...     »