ALGORITMOS BIOINSPIRADOS OTIMIZAM CONTROLADOR COM MAPEAMENTO COGNITIVO FUZZY DE MIXER INDUSTRIAL

• DOI: 10.22533/at.ed.81823081211

• Palavras-chave: Mapas Cognitivos Fuzzy Dinâmicos; Misturador Industrial; Algoritmos Bioinspirados; Controle Inteligente.

• Keywords: Dynamic Fuzzy Cognitive Maps; Industrial Mixer; bio-inspired evolutionary algorithms. Intelligent Control.

• Abstract: : In industrial facilities, it is common to find multivariable processes with strong interactions between their variables. Additionally, there are nonlinearities and, in some cases, conflicting control objectives. In this context, this work focuses on the application of bio-inspired algorithms for the off-line optimization of a dynamic fuzzy cognitive map (DFCM) in the intelligent control of an industrial mixer. The DFCM controller is based on Hebbian learning. Bio-inspired algorithms are inspired by biological or natural processes. They are often used in optimization problems, as they can find high-quality solutions to complex problems. Some examples of bio-inspired algorithms include genetic algorithms, ant colony algorithms, and bee swarm algorithms. Fuzzy cognitive maps are machine learning models that can be used to represent the knowledge of a system. They are composed of a set of nodes that represent system variables and a set of connections that represent the relationships between those variables. The weights of the connections are used to represent the strength of the relationships. Intelligent control is a field of engineering that focuses on the use of intelligent methods to control systems. It can be used to improve the performance, reliability, and efficiency of systems. The objective of this work is to evaluate the performance of bio-inspired algorithms for the off-line optimization of a dynamic fuzzy cognitive map (DFCM) in the intelligent control of an industrial mixer. The DFCM was trained using a simulation dataset of an industrial mixer. The dataset included information about the inputs and outputs of the mixer. Bio-inspired algorithms were used to optimize the weights of the DFCM. The results showed that bio-inspired algorithms were able to improve the performance of the DFCM. The optimized DFCM was able to achieve a more uniform mixture than the non-optimized DFCM. This work showed that bio-inspired algorithms can be used to improve the performance of dynamic fuzzy cognitive maps (DFCMs) in the intelligent control of industrial mixers. This paper ends with a conclusion and addresses future work.