Practice ArticleNovel intelligent real-time position tracking system using FPGA and fuzzy logic

- The performance achieved by FPGA-based and software-based controllers was compared.
- FPGA-based controllers achieve better performance controlling pneumatic systems.
- There are clear evidences that there is a performance gain using FPGAs over software-based architectures.

The main aim of this paper is to test if FPGAs are able to achieve better position tracking performance than software-based soft real-time platforms. For comparison purposes, the same controller design was implemented in these architectures. A Multi-state Fuzzy Logic controller (FLC) was implemented both in a Xilinx® Virtex-II FPGA (XC2v1000) and in a soft real-time platform NI CompactRIO®-9002. The same sampling time was used. The comparative tests were conducted using a servo-pneumatic actuation system. Steady-state errors lower than 4 μm were reached for an arbitrary vertical positioning of a 6.2 kg mass when the controller was embedded into the FPGA platform. Performance gains up to 16 times in the steady-state error, up to 27 times in the overshoot and up to 19.5 times in the settling time were achieved by using the FPGA-based controller over the software-based FLC controller.