Prediction of Engine-Out Emissions Using Deep Convolutional Neural Networks
- 6 April 2021
- journal article
- research article
- Published by SAE International in SAE International Journal of Advances and Current Practices in Mobility
- Vol. 3 (6), 2863-2871
- https://doi.org/10.4271/2021-01-0414
Abstract
Analysis-driven pre-calibration of a modern automotive engine is extremely valuable in significantly reducing hardware investments and accelerating engine designs compliant with stricter emission regulations. Advanced modelling tools, such as a Virtual Engine Model (VEM) using Computational Fluid Dynamics (CFD), are often used within the framework of a Design of Experiments for Powertrain Engineering (DEPE) with the goal of streamlining significant portions of the calibration process. The success of the methodology largely relies on the accuracy of analytical predictions, especially engine-out emissions. Results show excellent agreements in engine performance parameters (with R2 > 98%) and good agreements in NOx and combustion noise (with R2 > 87%), while the Carbon Monoxide (CO), Unburned Hydrocarbons (HC) and Smoke emissions predictions remain a challenge even with a large n-heptane mechanism consisting of 144 species and 900 reactions and refined mesh resolution. In this study, a Machine Learning (ML) approach is presented to correlate in-cylinder images of Equivalence Ratio, Temperature, Velocity field and Turbulent Kinetic Energy (TKE) at Exhaust Valve Opening (EVO) to engine-out emissions of CO, HC and Smoke measured experimentally. The images generated from CFD simulations and experimentally measured emissions data were used to train a deep Convolutional Neural Network (CNN) based on the VGG16 architecture. The prediction performance of the trained model was evaluated on held-out data. The deep learning model led to a significant improvement in prediction of all emissions species and captured the qualitative trends as well. This model could be used as an emissions prediction sub-model in the Virtual Engine Model framework leading to significantly lower computational costs by avoiding the use of expensive chemistry solvers. Gradient-weighted Regression Activation Mapping (Grad-RAMS) was used to draw insights into image features that had a strong influence on the emissions predictions.Keywords
This publication has 13 references indexed in Scilit:
- Steady-State Calibration of a Diesel Engine in Computational Fluid Dynamics Using a Graphical Processing Unit-Based Chemistry SolverJournal of Engineering for Gas Turbines and Power, 2018
- Toward the accurate prediction of soot in engine applicationsInternational Journal of Engine Research, 2018
- Machine Learning for Misfire Detection in a Dynamic Skip Fire EngineSAE International Journal of Engines, 2018
- Development of a simulation result management and prediction system using machine learning techniquesInternational Journal of Data Mining and Bioinformatics, 2017
- Machine learning-based metamodels for sawing simulationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Machine Learning in Simulation-Based AnalysisPublished by Association for Computing Machinery (ACM) ,2015
- A chemical mechanism for low to high temperature oxidation of n-dodecane as a component of transportation fuel surrogatesCombustion and Flame, 2014
- Modeling the Effect of Injector Nozzle-Hole Layout on Diesel Engine Fuel Consumption and EmissionsJournal of Engineering for Gas Turbines and Power, 2008
- Mechanism of the Smokeless Rich Diesel Combustion by Reducing TemperatureSAE International Journal of Advances and Current Practices in Mobility, 2001