An adaptive model-based neuro-fuzzy-fractal controller for biochemical reactors in the food industry
Patricia Melín, Oscar Castillo · 2002
We describe a computer program based on the use of neural networks and fuzzy logic for controlling bacteria growth in biochemical reactors for the food industry. This computer program is an implementation of a new method for control using neural networks techniques and a new method for automated mathematical modelling using fuzzy logic techniques. Biochemical processes are often highly non-linear and difficult to control. The problem of controlling them using conventional controllers has been widely studied. Much of the complexity in controlling any process comes from the complexity of the process being controlled. This complexity can be described in several ways. Highly nonlinear systems are difficult to control, particularly when they have complex dynamics (such as instabilities to limit cycles and chaos). Difficulties can often be presented by constraints, either on the control parameters or in the operating regime. We show mathematical models expressed as differential equations, for the simulation of bacteria growth for several types of food. The goal of constructing these models is to capture the dynamics of bacteria population in food, so as to have a way of controlling this dynamics for industrial purposes. Controlling the growth of bacteria is very important in industrial microbiology in obtaining the food products with the desired chemical and microbiological properties.