Dilute Combustion Control Using Spiking Neural Networks
Abstract
Dilute combustion with exhaust gas recirculation (EGR) in spark-ignition engines presents a cost-effective method for achieving higher levels of engine efficiency. At high levels of EGR, however, cycle-to-cycle variability (CCV) of the combustion process is exacerbated by sporadic occurrences of misfires and partial burns. Previous studies have shown that temporal deterministic patterns emerge at such conditions and certain combustion cycles have a significant influence over future events. Due to the complexity of the combustion process and the nature of CCV, harnessing all the deterministic information for control purposes has remained challenging even with physics based 0-D, 1-D, and high-fidelity computational fluid dynamics (CFD) models. In this study, we present a data-driven approach to optimize the combustion process by controlling CCV adjusting the cycle-to-cycle fuel injection quantity. Readily available data from in-cylinder pressure was used to train a spiking neural network (SNN) which learns the optimal way to manage fuel injection in order to reduce CCV while maintaining acceptable levels of fuel consumption. SNNs are particularly well suited for powertrain control applications due to their ability to be deployed on FPGA-based neuromorphic hardware which are small, inexpensive, and have a low power demand. The high-performance computing (HPC) resources of Oak Ridgemore »
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- OSTI Identifier:
- 1785202
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- SAE Technical Paper Series
- Additional Journal Information:
- Journal Volume: 2021; Journal Issue: 01; Journal ID: ISSN 0148-7191
- Publisher:
- SAE International
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 33 ADVANCED PROPULSION SYSTEMS
Citation Formats
Maldonado Puente, Bryan, Kaul, Brian, Schuman, Catherine, Young, Steven, and Mitchell, Parker. Dilute Combustion Control Using Spiking Neural Networks. United States: N. p., 2021.
Web. doi:10.4271/2021-01-0534.
Maldonado Puente, Bryan, Kaul, Brian, Schuman, Catherine, Young, Steven, & Mitchell, Parker. Dilute Combustion Control Using Spiking Neural Networks. United States. https://doi.org/10.4271/2021-01-0534
Maldonado Puente, Bryan, Kaul, Brian, Schuman, Catherine, Young, Steven, and Mitchell, Parker. Tue .
"Dilute Combustion Control Using Spiking Neural Networks". United States. https://doi.org/10.4271/2021-01-0534. https://www.osti.gov/servlets/purl/1785202.
@article{osti_1785202,
title = {Dilute Combustion Control Using Spiking Neural Networks},
author = {Maldonado Puente, Bryan and Kaul, Brian and Schuman, Catherine and Young, Steven and Mitchell, Parker},
abstractNote = {Dilute combustion with exhaust gas recirculation (EGR) in spark-ignition engines presents a cost-effective method for achieving higher levels of engine efficiency. At high levels of EGR, however, cycle-to-cycle variability (CCV) of the combustion process is exacerbated by sporadic occurrences of misfires and partial burns. Previous studies have shown that temporal deterministic patterns emerge at such conditions and certain combustion cycles have a significant influence over future events. Due to the complexity of the combustion process and the nature of CCV, harnessing all the deterministic information for control purposes has remained challenging even with physics based 0-D, 1-D, and high-fidelity computational fluid dynamics (CFD) models. In this study, we present a data-driven approach to optimize the combustion process by controlling CCV adjusting the cycle-to-cycle fuel injection quantity. Readily available data from in-cylinder pressure was used to train a spiking neural network (SNN) which learns the optimal way to manage fuel injection in order to reduce CCV while maintaining acceptable levels of fuel consumption. SNNs are particularly well suited for powertrain control applications due to their ability to be deployed on FPGA-based neuromorphic hardware which are small, inexpensive, and have a low power demand. The high-performance computing (HPC) resources of Oak Ridge National Laboratory were used to run an evolutionary-based training approach for choosing the best SNN configuration that minimizes the size of the network while achieving the desired goal. The neuromorphic hardware with the optimized SNN deployed was connected to the rapid prototyping engine control system for real-time control implementation and tested on a single cylinder version of a GM LNF 4-cylinder engine. The results show a significant reduction of CCV with a small percentage of additional fuel used to stabilize the charge.},
doi = {10.4271/2021-01-0534},
journal = {SAE Technical Paper Series},
number = 01,
volume = 2021,
place = {United States},
year = {Tue Apr 06 00:00:00 EDT 2021},
month = {Tue Apr 06 00:00:00 EDT 2021}
}