FPGA Realization of ANFIS Controller Using a Proposed Digital Design

Abstract

The design and realization of Adaptive Neuro-Fuzzy Inference System (ANFIS) controller based on Field Programmable Gate Array (FPGA) is presented in this paper. The controller intended to control the temperature of medical oven. A novel design of digital ANFIS is presented here for the implementation process. Different controllers are designed and their results are compared using MATLAB program to show the ANFIS superiority. The designed controllers tested for cell cultures application at 37.5. A reduction is made for the designed digital ANFIS due to the used FPGA limitations. The reduced design minimizes the utilized slices from 366% to 3% and LUTs from 364% to 3%. The reduced design reached an optimum size for this controller to utilize a smallest memory size. A real-time FPGA implementation of the proposed digital ANFIS have been done and verified through Xilinx ISE 14.6 using the VHDL language. The VHDL code for the controller is produced, aggregated and downloaded on the FPGA Spartan 3A/AN FPGA kit. A comparison between the simulation and implementation results is made. The matching between these results proves the effectiveness and robustness of the proposed digital ANFIS and the excellent performance of the FPGA based controller.

Implementation of Robotic Navigation Algorithms Using Partial Reconfiguration on Zynq SoC

“…To provide fault tolerance, Cobleigh et al presented tree -structured self-adaptation models for such mobile robots (13). In response to observed conditions, Gafni et al [1] presented an architectural style for real-time systems in which dynamic reconfiguration is implemented via a synchronous control task (14). The author has proposed comparison of various Biological Inspired algorithms the navigation over static and dynamic condition is analysed (for single and multiple robot systems) and it has been observed that the reactive approaches are more robust and perform well in all terrain when compared to classical approaches (15).…”

FPGA implementation in mobile robot applications: State of the art review

“…The use of neural networks is widespread in scientific literature and engineering practice. Abbas Issa et al(Issa et al, 2021) presented a reconfigurable insightful controller for mobile robots. Programming known as reconfigurable control framework, was used to modify the structure of the control system, and the FPGA chip was used in the planning and implementation of the controller.…”