A diesel engine electrical generator set (’gen-set’) was instrumented with in-cylinder indicating sensors as well as acoustic emission microphones near the engine. Air filter clogging was emulated by progressive restriction of the engine’s inlet air flow path during which comprehensive engine and acoustic data were collected. Fast Fourier Transforms (FFTs) were analyzed on the acoustic data. Dominant FFT peaks were then applied to supervised machine learning neural network analysis with MATLAB based tools. The progressive detection of the air path clogging was audibly determined with correlation coefficients greater than 95% on test data sets for various FFT minimum intensity thresholds. Further, unsupervised machine learning Self Organizing Maps (SOMs) were produced during normal-baseline operation of the engine. Application of the degrading air flow engine sound data was then applied to the normal-baseline operation SOM. The quantization error of the degraded engine data showed clear statistical differentiation from the normal operation data map. This unsupervised SOM based approach does not know the engine degradation behavior in advance, yet shows clear promise as a method to monitor and detect changing engine operation. Companion in-cylinder combustion data additionally shows the degrading nature of the engine’s combustion with progressive airflow restriction (richer and lower density combustion).
Skip Nav Destination
ASME 2018 Internal Combustion Engine Division Fall Technical Conference
November 4–7, 2018
San Diego, California, USA
Conference Sponsors:
- Internal Combustion Engine Division
ISBN:
978-0-7918-5199-9
PROCEEDINGS PAPER
Diesel Engine Acoustic Emission Airflow Clogging Diagnostics With Machine Learning
Patrick Moore,
Patrick Moore
US Naval Academy, Annapolis, MD
Search for other works by this author on:
Harrison Yosten,
Harrison Yosten
US Naval Academy, Annapolis, MD
Search for other works by this author on:
Leonard Hamilton,
Leonard Hamilton
US Naval Academy, Annapolis, MD
Search for other works by this author on:
Dianne Luning Prak
Dianne Luning Prak
US Naval Academy, Annapolis, MD
Search for other works by this author on:
Jim Cowart
US Naval Academy, Annapolis, MD
Patrick Moore
US Naval Academy, Annapolis, MD
Harrison Yosten
US Naval Academy, Annapolis, MD
Leonard Hamilton
US Naval Academy, Annapolis, MD
Dianne Luning Prak
US Naval Academy, Annapolis, MD
Paper No:
ICEF2018-9601, V002T05A008; 15 pages
Published Online:
January 3, 2019
Citation
Cowart, J, Moore, P, Yosten, H, Hamilton, L, & Luning Prak, D. "Diesel Engine Acoustic Emission Airflow Clogging Diagnostics With Machine Learning." Proceedings of the ASME 2018 Internal Combustion Engine Division Fall Technical Conference. Volume 2: Emissions Control Systems; Instrumentation, Controls, and Hybrids; Numerical Simulation; Engine Design and Mechanical Development. San Diego, California, USA. November 4–7, 2018. V002T05A008. ASME. https://doi.org/10.1115/ICEF2018-9601
Download citation file:
16
Views
0
Citations
Related Proceedings Papers
Related Articles
Diesel Engine Acoustic Emission Airflow Clogging Diagnostics With Machine Learning
J. Eng. Gas Turbines Power (July,2019)
An Analysis of Noise Characteristics of Drill Bits
J. Energy Resour. Technol (March,2012)
Comparison of Random Forest and Neural Network in Modeling the Performance and Emissions of a Natural Gas Spark Ignition Engine
J. Energy Resour. Technol (March,2022)
Related Chapters
Outlook
Closed-Cycle Gas Turbines: Operating Experience and Future Potential
Torsional Frequency Analysis of Multi-Cylinder Inline Diesel Engine Generator System
Proceedings of the 2010 International Conference on Mechanical, Industrial, and Manufacturing Technologies (MIMT 2010)
DK-Map: A Minimalistic Approach to Network Intrusion Detection
Intelligent Engineering Systems through Artificial Neural Networks, Volume 16