Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

VIRTUAL PRESSURE SENSOR BASED ON ION CURRENT MEASUREMENTS USING ARTIFICIAL NEURAL NETWORKS

Björnsson, Ola LU orcid and Tunestål, Per LU orcid (2024) ASME 2024 ICE Forward Conference, ICEF 2024
Abstract

In-cylinder pressure measurements serve as the gold standard for combustion diagnostics in Internal Combustion Engines. However, the associated costs render it unfeasible to equip engines with in-cylinder pressure sensors. For spark-ignited engines, using the more affordable in-cylinder ion current measurements as an alternative to the traditional pressure sensors has shown promising results for combustion diagnostics. Still, it has not been widely adopted, most likely due to concerns regarding robustness. The recent advancements in machine learning and big data have attracted significant attention. Given the strong correlation between ion current measurements and in-cylinder pressure, combined with the simplicity of collecting a large... (More)

In-cylinder pressure measurements serve as the gold standard for combustion diagnostics in Internal Combustion Engines. However, the associated costs render it unfeasible to equip engines with in-cylinder pressure sensors. For spark-ignited engines, using the more affordable in-cylinder ion current measurements as an alternative to the traditional pressure sensors has shown promising results for combustion diagnostics. Still, it has not been widely adopted, most likely due to concerns regarding robustness. The recent advancements in machine learning and big data have attracted significant attention. Given the strong correlation between ion current measurements and in-cylinder pressure, combined with the simplicity of collecting a large amount of data, ion current measurements are a good candidate for building machine learning models. In this paper, we show the feasibility of utilizing Artificial Neural Networks (ANN) to estimate the in-cylinder pressure using the ion current measurement as an input, effectively creating a virtual pressure sensor. Additionally, we calculate different combustion metrics useful for combustion diagnostics and compare them with those calculated on the measured in-cylinder pressure trace. The following combustion metrics are considered: Gross Indicated Mean Effective Pressure (IMEPg), Peak Pressure Location (PPL), maximum pressure, and heat release-based measurements such as total heat release and CA50. All of which could be estimated with good accuracy.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Artificial Neural Network, Ion Current, Virtual Pressure Sensor
host publication
Proceedings of ASME 2024 ICE Forward Conference, ICEF 2024
article number
V001T04A002
publisher
American Society Of Mechanical Engineers (ASME)
conference name
ASME 2024 ICE Forward Conference, ICEF 2024
conference location
San Antonio, United States
conference dates
2024-10-20 - 2024-10-23
external identifiers
  • scopus:85212429200
ISBN
9780791888520
DOI
10.1115/ICEF2024-140748
language
English
LU publication?
yes
id
f1216031-7b05-4bdc-98a4-e2e2bdc37a6e
date added to LUP
2025-01-24 13:20:50
date last changed
2025-04-04 14:32:15
@inproceedings{f1216031-7b05-4bdc-98a4-e2e2bdc37a6e,
  abstract     = {{<p>In-cylinder pressure measurements serve as the gold standard for combustion diagnostics in Internal Combustion Engines. However, the associated costs render it unfeasible to equip engines with in-cylinder pressure sensors. For spark-ignited engines, using the more affordable in-cylinder ion current measurements as an alternative to the traditional pressure sensors has shown promising results for combustion diagnostics. Still, it has not been widely adopted, most likely due to concerns regarding robustness. The recent advancements in machine learning and big data have attracted significant attention. Given the strong correlation between ion current measurements and in-cylinder pressure, combined with the simplicity of collecting a large amount of data, ion current measurements are a good candidate for building machine learning models. In this paper, we show the feasibility of utilizing Artificial Neural Networks (ANN) to estimate the in-cylinder pressure using the ion current measurement as an input, effectively creating a virtual pressure sensor. Additionally, we calculate different combustion metrics useful for combustion diagnostics and compare them with those calculated on the measured in-cylinder pressure trace. The following combustion metrics are considered: Gross Indicated Mean Effective Pressure (IMEP<sub>g</sub>), Peak Pressure Location (PPL), maximum pressure, and heat release-based measurements such as total heat release and CA50. All of which could be estimated with good accuracy.</p>}},
  author       = {{Björnsson, Ola and Tunestål, Per}},
  booktitle    = {{Proceedings of ASME 2024 ICE Forward Conference, ICEF 2024}},
  isbn         = {{9780791888520}},
  keywords     = {{Artificial Neural Network; Ion Current; Virtual Pressure Sensor}},
  language     = {{eng}},
  publisher    = {{American Society Of Mechanical Engineers (ASME)}},
  title        = {{VIRTUAL PRESSURE SENSOR BASED ON ION CURRENT MEASUREMENTS USING ARTIFICIAL NEURAL NETWORKS}},
  url          = {{http://dx.doi.org/10.1115/ICEF2024-140748}},
  doi          = {{10.1115/ICEF2024-140748}},
  year         = {{2024}},
}