In recent times, artificial intelligence applications in the field of dynamic systems control have proved to be an efficient tool for the improvement of processes. Programmable Logic Controller-based control systems are found in the vast majority of industrial automation systems. In this paper, a fuzzy controller approach is proposed to enhance the design of industrial control systems using commercial PLCs. The fuzzy controller is tuned by artificial intelligent techniques, and the performances of different fuzzy controller-tuning methods are compared, including the metaheuristic ones. The results shown in this paper validate the proposal that metaheuristics tuning methods of fuzzy controller have better performance in intelligent automation.

No abstract

The application of automation techniques to water pump systems, combined with modern control techniques, has been increasing the hydraulic and energy efficiency of such systems. In this context, the objective of this work is to present an intelligent method of flow control based on Brain’s Emotional Learning (BELBIC), which will be applied to an experimental workbench of a pumping system, located in the Energy Efficiency and Energy Quality Laboratory (LEEQE) at Federal University of Pernambuco (UFPE). The parameters of this controller are optimized with a particle swarm optimization (PSO) technique with minimization of Integral Absolute Error (IAE). Initial tests were performed in a computational environment so that the system’s performance could be pre-tested, thereby the dynamics of the system was modeled from real data generated in the process. The experimental results were obtained through the implementation of this control system in a programmable logic controller (PLC), which was the device responsible for all the automation of the workbench previously mentioned. The data of this workbench were collected using a supervisory system exclusively developed for this work. These data were then used to analyze the performance of the proposed control system, which demonstrated that its behavior was efficient.