This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Prediction of NO x Emissions from Compression Ignition Engines Using Ensemble Learning-Based Models with Physical Interpretability
Technical Paper
2021-24-0082
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
On-board diagnostics (OBD) data contain valuable information including real-world measurements of vehicle powertrain parameters. These data can be used to gain a richer data-driven understanding of complex physical phenomena like emissions formation during combustion. In this study, we develop a physics-based machine learning framework to predict and analyze trends in engine-out NOx emissions from diesel and diesel-hybrid heavy-duty vehicles. This model differs from black-box machine learning models presented in previous literature because it incorporates engine combustion parameters that allow physical interpretation of the results. Based on chemical kinetics and the characteristics of diffusive combustion, NOx emissions from compression ignition engines primarily depend non-linearly on three parameters: adiabatic flame temperature, the oxygen concentration in the cylinder when the intake valves are closed, and combustion time duration. Here these parameters were calculated from available OBD data. Linearizing a physics-based NOx emissions prediction model provides an opportunity to evaluate several machine learning regression techniques. The results show that an ensemble learning bagging-type model like random forest regression (RFR) is highly effective in predicting engine out NOx emissions measured by the on-board NOx sensor. We also show that real-world OBD data has high heterogeneity with clustered co-occurrences of vehicle parameters. In terms of accuracy, the developed model provides an average R2 value of 0.72 and mean absolute error (MAE) of 78 ppm for different vehicle OBD datasets, an improvement of 53% and 42% respectively when compared to non-linear regression models, and provides the opportunity to interpret the results because of its linkage to physical parameters. We also perform drop-column feature sensitivity analysis for the RFR Model and compare prediction results with black-box deep neural network and non-linear regression models. Based on its high accuracy and interpretability, the developed RFR model has potential for use in on-board NOx prediction in engines of varying displacement and design.
Authors
Topic
Citation
Panneer Selvam, H., Shekhar, S., and Northrop, W., "Prediction of NOx Emissions from Compression Ignition Engines Using Ensemble Learning-Based Models with Physical Interpretability," SAE Technical Paper 2021-24-0082, 2021, https://doi.org/10.4271/2021-24-0082.Data Sets - Support Documents
| Title | Description | Download |
|---|---|---|
| Unnamed Dataset 1 | ||
| Unnamed Dataset 2 | ||
| Unnamed Dataset 3 |
Also In
References
- Kotz , A.J. , Kittelson , D.B. , Northrop , W.F. , and Schmidt , N. Realworld NOx Emissions of Transit Buses Equipped with Diesel Exhaust Aftertreatment Systems Emission Control Science and Technology 3 2 2017 153 160
- Le Cornec , C.M.A. , Molden , N. , Van Reeuwijk , M. , and Stettler , M.E.J. Modelling of Instantaneous Emissions from Diesel Vehicles with a Special Focus on NO x : Insights from Machine Learning Techniques Science of The Total Environment 737 Oct. 2020 139625
- Liu , B. , Hu , J. , Yan , F. , Turkson , R.F. et al. A Novel Optimal Support Vector Machine Ensemble Model for NOx Emissions Prediction of a Diesel Engine Measurement 92 Oct. 2016 183 192
- Oduro , S.D. , Metia , S. , Duc , H. , Hong , G. et al. Multivariate Adaptive Regression Splines Models for Vehicular Emission Prediction Visualization in Engineering 3 June 2015 13
- Li , Q. , Qiao , F. , and Yu , L. A Machine Learning Approach for Light-Duty Vehicle Idling Emission Estimation Based on Real Driving and Environmental Information Environment Pollution and Climate Change 1 Jan. 2017 1000106
- Agbulut , U. , GUrel , A.E. , and Saridemir , S. Experimental Investigation and Prediction of Performance and Emission Responses of a CI Engine Fuelled with Different Metal-Oxide Based Nanoparticles-Diesel Blends Using Different Machine Learning Algorithms Energy 215 Jan. 2021 119076
- Shin , S. , Lee , Y. , Kim , M. , Park , J. et al. Deep Neural Network Model with Bayesian Hyperparameter Optimization for Prediction of NO x at Transient Conditions in a Diesel Engine Engineering Applications of Artificial Intelligence 94 Sept. 2020 103761
- Wang , Y. , Yu , Y. , and Li , J. Predicting the Transient NO x Emissions of the Diesel Vehicle Based on LSTM Neural Networks 2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) 261 264 Dec. 2020
- Yu , Y. , Wang , Y. , Li , J. , Fu , M. et al. A Novel Deep Learning Approach to Predict the Instantaneous NO x Emissions from Diesel Engine IEEE Access 9 2021 11002 11013
- Warey , A. , Gao , J. , and Grover , R. Prediction of Engine-Out Emissions Using Deep Convolutional Neural Networks SAE Technical Paper 2021-01-0414 2021 https://doi.org/10.4271/2021-01-0414
- Barredo Arrieta , A. , Díaz-Rodríguez , N. , Del Ser , J. , Bennetot , A. et al. Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges Toward Responsible AI Information Fusion 58 June 2020 82 115
- Mendes-Moreira , J. , Soares , C. , Jorge , A.M. , and Sousa , J.F.D. Ensemble Approaches for Regression: A Survey ACM Computing Surveys 45 1 Dec. 2012 1 40
- Kaneko , H. and Funatsu , K. Applicability Domain Based on Ensemble Learning in Classification and Regression Analyses Journal of Chemical Information and Modeling 54 Sept. 2014 2469 2482
- Qiu , X. , Zhang , L. , Ren , Y. , Suganthan , P.N. et al. Ensemble Deep Learning for Regression and Time Series Forecasting 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL) 1 6 Dec. 2014
- Ahmad , M.W. , Mourshed , M. , and Rezgui , Y. Trees Vs Neurons: Comparison Between Random Forest and ANN for High-Resolution Prediction of Building Energy Consumption Energy and Buildings 147 July 2017 77 89
- Perrotta , F. , Parry , T. , and Neves , L.C. Application of Machine Learning for Fuel Consumption Modelling of Trucks 2017 IEEE International Conference on Big Data (Big Data) 3810 3815 Dec. 2017
- Massoud , R. , Bellotti , F. , Berta , R. , Gloria , A.D. et al. Exploring Fuzzy Logic and Random Forest for Car Drivers’ Fuel Consumption Estimation in IoT-Enabled Serious Games 2019 IEEE 14th International Symposium on Autonomous Decentralized System (ISADS) 1 7 Apr. 2019 2640-7485
- Li , Z. , Yim , S.H.-L. , and Ho , K.-F. High Temporal Resolution Prediction of Street-Level PM2.5 and NO x Concentrations Using Machine Learning Approach Journal of Cleaner Production 268 Sept. 2020 121975
- Ullah , I. , Liu , K. , Yamamoto , T. , Zahid , M. et al. Electric Vehicle Energy Consumption Prediction Using Stacked Generalization: An Ensemble Learning Approach International Journal of Green Energy 0 Feb.2021 1 14 https://doi.org/10.1080/15435075.2021.1881902
- Panneer Selvam , H. , Li , Y. , Wang , P. , Northrop , W.F. , and Shekhar , S. Vehicle Emissions Prediction with Physics-Aware AI Models: Preliminary Results PGAI-AAAI-20 2021
- Panneer Selvam , H. , Li , Y. , Wang , P. , Northrop , W.F. Vehicle Emissions Prediction with Physics-Aware AI Models: Technical Report Retrieved from the University of Minnesota Digital Conservancy 2020 https://hdl.handle.net/11299/216628
- Liviu-Constantin , S. , and Daniela-Elena , M. Simplified Mechanism Used to Estimate the NO x Emission of Diesel Engine Proceedings of the 2nd International Conference on Manufacturing Engineering, Quality and Production Systems 978 960 2010
- Fleet DNA https://www.nrel.gov/transportation/fleettest-fleet-dna.html 2020
- Svetnik , V. , Liaw , A. , Tong , C. , Culberson , J.C. et al. Random Forest: A classification and Regression Tool for Compound Classification and QSAR Modeling Journal of Chemical Information and Computer Sciences 43 Nov. 2003 1947 1958
- Pedregosa , F. , Varoquaux , G. , Gramfort , A. , Michel , V. et al. Scikit-Learn: Machine learning in Python Journal of Machine Learning Research 12 2011 2825 2830
- Burman , P. A Comparative Study of Ordinary Cross-Validation, V- Fold Cross-Validation and the Repeated Learning-Testing Methods Biometrika 76 3 1989 503 514
- https://stats.stackexchange.com/users/182882/david https://stats.stackexchange.com/q/313455