Steering assistance: food processing application

The know-how developed by a company's employees is often a real asset. This know-how can remain stable over time, growing richer or, on the contrary, regressing if this knowledge is not formalized. It may therefore be essential for the company to capitalize on this know-how in a way that enables it to be exploited in the future, or even passed on to other employees. Corporate memory" thus concerns, a priori, all sectors of the economy, and several approaches to capitalizing on knowledge have been taken. Examples include: Usinor-Sacilor, for the development of an IT tool to optimize blast furnace operation based on the knowledge held by blast furnace operators (SACHEM system); SNCF, for the development of damage detection guides for tunnels, bridges, etc.EDF and Cemagref to monitor and diagnose dam failures (Vigie BarragesÒ CD-Rom), CEA to capitalize on knowledge and experience acquired in the field of nuclear reactors (REX project).

In the food industry, the operators who run the process are generally key players in product quality control, and their expertise is one of the company's assets. There are two main reasons for this.

On the one hand, there are not always direct or indirect instrumental measurements available to assess the properties of a product during the manufacturing process. The development or use of measuring devices is difficult because of the :

• the product itself: food products are elaborate biological products whose nature and composition may vary over time; moreover, they are not always homogeneous, and the evaluation system must take account of this heterogeneity;

• sensors and measuring instruments :

  • sensors must be cleanable, and it is desirable that they be non-invasive and non-destructive,

  • they must meet stringent requirements, such as cleanability or operation in very humid environments,

  • the operation of certain measuring devices may require personnel trained in their use,

  • a number of measurement systems cannot be used directly online because response times are too long,

  • criteria of cost, metrological characteristics (accuracy, precision, speed...) and development time must be taken into account.

On the other hand, food processes are generally not robust to variations in raw material characteristics, for example. Our understanding of the interactions between product and process is often incomplete, due in part to the often complicated sequence of reactions involving a variety of physico-chemical and/or biological mechanisms. All these points make...