Neuro-Fuzzy Genetic Algorithms for monitoring in a production system

In this paper, our interest is focused on monitoring in production systems. The motivation behind this investigation is the need of presenting hybrid approach of Neuro-Fuzzy Genetic for the optimal learning, which allows getting the required performance measures. The presence of Neuro- Fuzzy algorithms which may involving elegantly the set of features extraction are defined in terms of membership function, where as Genetic Algorithms are proposed to optimize the set of rules, in order to design supervised classification systems by generating fuzzy if-then rules. The learning process is based on two algorithms: Levenberg-Marquardt (TRAINLM) and Gradient Descent (TRAINGDA). Then, the proposed algorithms performances are verified and analyzed through an industrial application of agro-alimentary unit called AURES dairy for the city of Batna. The simulation results show that the proposed approach performs the best when Levenberg-Marquardt is used as a learning algorithm.