Dual-Bridge SENT Processor with AI-based Genetic Algorithm Calibration for Automotive Applications

View at publisher Summarise with VIRAT
Authors: Uiseok Jeong, Junmin Lee, Dongsun Kim
Cited by: 0
References: 2

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper presents an AI-based dual-bridge sensor signal processor (SSP) with a genetic calibration engine for automotive applications. The proposed SSP integrates a dual differential bridge front-end, high-resolution ADCs, and a digital compensation unit that applies a genetic algorithm (GA)–based optimization using virtual data generation (VDG). Unlike conventional progressive polynomial calibration (PPC) methods that require many calibration points and long fitting times, the proposed VDG–GA approach automatically generates virtual calibration data from limited measurements and derives optimal polynomial coefficients to minimize sensor error. The final coefficients are stored in non-volatile memory (NVM) and applied during startup to ensure accurate, temperature-independent pressure outputs. Experimental results demonstrate that the proposed AI-based calibration reduces error by approximately 45% and calibration time by 30% compared to the PPC method, enabling sustainable and efficient mass production of functionally safe automotive sensor systems.

Fields of Study & Subjects

Sensor Technology and Measurement Systems Advanced Sensor Technologies Research Analog and Mixed-Signal Circuit Design

Publication details

Journal / source
International Conference on Consumer Electronics
Pages
1–5
Publication date
3 February 2026
Language
EN