Neuro-fuzzy sensor´s linearization based FPGA

Nonlinear sensors and digital solutions are used in many embedded system designs. As the input/output characteristic of most sensors is nonlinear in nature, obtaining data from a nonlinear sensor by using an optimized device has always been a design challenge. This paper aims to propose a new Adapive Neuro-Fuzzy Inference System (ANFIS) digital architecture based Field Programmable Gate Array (FPGA) to linearize the sensor´s characteristic. The ANFIS linearizer in synthesized and optimized in view to digital linearization. The performance of the developed architecture is examined with comparison to ANFIS software model and with two other designed architectures based FPGA using classical techniques. The results show the successful of the proposed architecture by demonstrating the capability of the operation to linearize a temperature sensor characteristic.