Download Center

Automated in-vehicle engine calibration to optimize emissions levels using machine learning

The growing concern with environmental impact is a major drive for the tighter emissions imposed on combustion engines. The compliance with those restrictions is pushing new hardware and software solutions that, nevertheless, increase system complexity leading to more iterations and hence longer development time, a risk to profitability. In this context, it is paramount to reach optimum catalytic conversion temperature earlier through calibration strategies. This is challenging though, requiring heavy efforts in terms of time and use of resources/facilities.

A promising approach to increase efficiency is the concept of virtualization via data-based engine modeling and model based calibration.

This document presents the combined automation and virtualization in vehicle for catalyst heating calibration with support by ETAS tools INCA, INCA-FLOW & ETAS ASCMO.

ETAS & BOSCH/PS applied INCA-FLOW & ETAS ASCMO for optimizing the catalytic converter heating strategy of a modern engine. The combined use of machine learning technics (ETAS ASCMO) and highly automated testing (INCA-FLOW) resulted in a estimated effort reduction of 71% on the calibration task. The resulting paper was awarded a honorable mention on “Emissions Control” category on SIMEA 2021.