This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Machine Learning for Misfire Detection in a Dynamic Skip Fire Engine

Journal Article
2018-01-1158
ISSN: 1946-3936, e-ISSN: 1946-3944
Published April 03, 2018 by SAE International in United States
Machine Learning for Misfire Detection in a Dynamic Skip Fire Engine
Sector:
Citation: Chen, S., Mandal, A., Chien, L., and Ortiz-Soto, E., "Machine Learning for Misfire Detection in a Dynamic Skip Fire Engine," SAE Int. J. Engines 11(6):965-976, 2018, https://doi.org/10.4271/2018-01-1158.
Language: English

Abstract:

Dynamic skip fire (DSF) has shown significant fuel economy improvements via reduction of pumping losses that generally affect throttled spark-ignition engines. For production readiness, DSF engines must meet regulations for on-board diagnostics (OBD-II), which require detection and monitoring of misfire in all passenger vehicles powered by an internal combustion engine. Numerous misfire detection methods found in the literature, such as those using peak crankshaft angular acceleration, are generally not suitable for DSF engines due to added complexity of skipping cylinders. Specifically, crankshaft acceleration traces may change abruptly as the firing sequence changes. This article presents a novel method for misfire detection in a DSF engine using machine learning and artificial neural networks.
Two machine learning approaches are presented. The first method uses a regression-based artificial neural network to calculate expected crank acceleration from various inputs, including fire-skip sequence. The method then compares the output to measured crank acceleration to detect misfire. The second method uses an expanded neural network, which includes the measured crank acceleration as an additional input, to directly predict misfire flags. On-road validation tests of both detection algorithms were carried under steady-state and transient conditions. Results show detection rates above 95% at all tested conditions. Overall, machine learning significantly improved quality and robustness of misfire detection in DSF engines by making use of greater variety of modeling input parameters.