Feed‐back Quality Control in the Baking Industry Using Fuzzy Sets

Abstract

A methodology for the closed loop control of biscuit quality during baking is proposed and was validated during several experiments. This methodology involves expert knowledge which is captured in a modular way. Three modules are involved in the control strategy of the process. The first module reproduces sensory evaluation by the operator. The second module diagnoses the state of the process with respect to quality state of biscuits. Finally, a decision module supervises the actuators of the process. Different fuzzy concepts are applied within these modules and fuzzy information is processed through the control chain. Results show that using only 11 rules, all components of quality are controlled with accuracy and robustness. This is particularly interesting in the light of the complexity of the process. Such a modular approach makes it possible to follow the evolution of quality during the process, in successive steps which are easily recorded and interpreted by experts. This approach could be envisaged as an operator decision support system.

How human expertise at industrial scale and experiments can be combined to improve food process knowledge and control

“…The "data-driven" approach requires large databases which are sometimes diYcult to build. Several examples of process control in food industry have been studied: cheese ripening , browning (Ioannou, Perrot, Curt, Mauris, & Trystram, 2004;, baking (Perrot, Trystram, Chevrie Guely, Schoesetters, & Dugre, 2000), sausage drying (Curt, Hossenlopp, Perrot, & Trystram, 2002), emulsiWcation (Curt, Allais, Perrot, Leblanc, & Trystram, 2004b), mixing (Edoura-Gaena, , peanut roasting (Davidson, Brown, & Landman, 1999), and dough mixing (Wide, 1999). These studies have shown that human knowledge can be extracted and can be modelled.…”

A decision support system to control the aeration of sponge finger batters

“…Application Method Observations Perrot et al (2000) Cookie baking Fuzzy logic Sensory properties Ruger et al (1995) Pulp drying Fuzzy logic Curt et al (2002) Sausage fermentation Fuzzy logic Sensory properties Zhang and Litchfield (1993) Grain dryer Fuzzy logic Cord (1994) Meat Blackboard architecture Davidson et al (1999) Peanut roasting Fuzzy logic Davidson and Smith (1995) Batch cooking Fuzzy logic Perrot et al (2004) Cheese ripening Fuzzy logic Sensory properties Kim and Cho (1997) Bread baking Fuzzy logic Kurz et al (2001) Beer fermentation Fuzzy logic Oishi et al (1992) Sake Fuzzy logic Linko et al (1992) Extrusion Fuzzy logic Neural modelling Cooney et al (1988) and Aynsley et al (1993) Fermentation control Expert-systems Real-time Hitzmann et al (1989) Enzyme production Expert-systems Closed loop Kashihara et al (1993) Beer fermentation Expert-systems Real-time monitoring of key variables Eerikainen et al (1994) Extrusion-cooking Ruled based hybrid real-time fuzzy ES Real-time Goyache et al (2001) Bovine carcass conformation assessment…”

“…To control a process, there is a need for tools to help the production manager and operators to take the right decision and to make that decision more reliable. Thus, it is relevant to develop methods of cooperation between humans and controllers, first to measure properties during manufacturing and then to integrate them in a feedback control of food processing to control the quality of the products (Curt, Hossenlopp, Perrot, & Trystram, 2002;Perrot et al, 2000). The feedback control loop can perform automatic control of the process, or it can act as a support decision system to assist the operator in choosing the most relevant action to apply.…”

Fuzzy concepts applied to food product quality control: A review

“…It is now a wide field of study that has seen the development of different tools over the last 10 years. Applied to the control of product quality in the food industry, it has been considered as pertinent by several authors for different applications and especially for taking into account the reasoning process, expressed in linguistic terms, of operators and experts [18,24,48,66,77,94]. Nevertheless, applications are still limited and few reviews on this topic are available.…”