Decision support system design using the operator skill to control cheese ripening––application of the fuzzy symbolic approach

Abstract

In food industries, managing sensory properties from the fabrication stage in an automatic framework constitutes a key issue for companies but is no easy task. It is an open field of research in which few studies have been carried out. Therefore, we propose to integrate the operator skill using a fuzzy symbolic approach. More precisely, the aim of our study is to present an application of such an approach to the development of a support system dedicated to help the operator on-line during cheese ripening. The information delivered by the support system, on the basis of sensory instantaneous measurements, is the global change in the cheese at each time step in comparison to a standard trajectory of ripening. The results are relevant to the control of the sensory properties of the products at the fabrication stage. Thus, the model follows the sensory trajectory of the cheese during ripening and helps the operator to diagnose and control it. It is validated on a data set of 106 points at a level of 97% and 80% for respectively a sensitivity of 3.5 and 1.75 days for a response time of the process of at mean 2 days. It opens an interesting road of cooperation between operators and food process control systems.