Knock Detection with Ion Current and Vibration Sensor : A Comparative Study of Logistic Regression and Neural Networks
Björnsson, Ola LU
and Tunestål, Per
LU
(2024)
In Energies
17(22).
- Abstract
Knock detection is critical for maintaining engine performance and preventing damage in spark-ignition engines. This study explores the use of ion current and knock indicators derived from a vibration sensor ((Formula presented.)) and ion current ((Formula presented.)) to improve knock detection accuracy. Traditional threshold-based methods rely on (Formula presented.), but they are susceptible to mechanical noise and cylinder variations. In this work, we applied both logistic regression and neural networks, including fully connected (FCNN) and convolutional neural networks (CNN), to classify knock events based on these indicators. The CNN models used ion current as the primary input, with an extended version incorporating both ... (More)
Knock detection is critical for maintaining engine performance and preventing damage in spark-ignition engines. This study explores the use of ion current and knock indicators derived from a vibration sensor ((Formula presented.)) and ion current ((Formula presented.)) to improve knock detection accuracy. Traditional threshold-based methods rely on (Formula presented.), but they are susceptible to mechanical noise and cylinder variations. In this work, we applied both logistic regression and neural networks, including fully connected (FCNN) and convolutional neural networks (CNN), to classify knock events based on these indicators. The CNN models used ion current as the primary input, with an extended version incorporating both (Formula presented.) and (Formula presented.) into the fully connected layers. The models were evaluated using area under the curve (AUC) as the primary performance metric. The results show that the CNN model with additional inputs outperformed the other models, achieving a better and more consistent performance across cylinders. The dual-input logistic regression and CNN models demonstrated reduced cylinder-to-cylinder variation in classification performance, providing a more consistent knock detection accuracy across all cylinders. These findings suggest that combining ion current and knock indicators enhances knock detection reliability, offering a robust solution for real-time applications in engine control systems.
(Less)
- author
- Björnsson, Ola
LU
and Tunestål, Per
LU
- organization
- publishing date
- 2024-11
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- ion current, knock detection, machine learning
- in
- Energies
- volume
- 17
- issue
- 22
- article number
- 5693
- publisher
- MDPI AG
- external identifiers
-
- scopus:85210286324
- ISSN
- 1996-1073
- DOI
- 10.3390/en17225693
- language
- English
- LU publication?
- yes
- id
- 2290feed-d141-4e0f-a16d-9227776b3d65
- date added to LUP
- 2025-01-15 11:43:41
- date last changed
- 2025-06-19 14:36:50
@article{2290feed-d141-4e0f-a16d-9227776b3d65,
abstract = {{<p>Knock detection is critical for maintaining engine performance and preventing damage in spark-ignition engines. This study explores the use of ion current and knock indicators derived from a vibration sensor ((Formula presented.)) and ion current ((Formula presented.)) to improve knock detection accuracy. Traditional threshold-based methods rely on (Formula presented.), but they are susceptible to mechanical noise and cylinder variations. In this work, we applied both logistic regression and neural networks, including fully connected (FCNN) and convolutional neural networks (CNN), to classify knock events based on these indicators. The CNN models used ion current as the primary input, with an extended version incorporating both (Formula presented.) and (Formula presented.) into the fully connected layers. The models were evaluated using area under the curve (AUC) as the primary performance metric. The results show that the CNN model with additional inputs outperformed the other models, achieving a better and more consistent performance across cylinders. The dual-input logistic regression and CNN models demonstrated reduced cylinder-to-cylinder variation in classification performance, providing a more consistent knock detection accuracy across all cylinders. These findings suggest that combining ion current and knock indicators enhances knock detection reliability, offering a robust solution for real-time applications in engine control systems.</p>}},
author = {{Björnsson, Ola and Tunestål, Per}},
issn = {{1996-1073}},
keywords = {{ion current; knock detection; machine learning}},
language = {{eng}},
number = {{22}},
publisher = {{MDPI AG}},
series = {{Energies}},
title = {{Knock Detection with Ion Current and Vibration Sensor : A Comparative Study of Logistic Regression and Neural Networks}},
url = {{http://dx.doi.org/10.3390/en17225693}},
doi = {{10.3390/en17225693}},
volume = {{17}},
year = {{2024}},
}