This content is not included in your SAE MOBILUS subscription, or you are not logged in.
A Machine Learning Modeling Approach for High Pressure Direct Injection Dual Fuel Compressed Natural Gas Engines
ISSN: 0148-7191, e-ISSN: 2688-3627
Published September 15, 2020 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
The emissions and efficiency of modern internal combustion engines need to be improved to reduce their environmental impact. Many strategies to address this (e.g., alternative fuels, exhaust gas aftertreatment, novel injection systems, etc.) require engine calibrations to be modified, involving extensive experimental data collection. A new approach to modeling and data collection is proposed to expedite the development of these new technologies and to reduce their upfront cost. This work evaluates a Gaussian Process Regression, Artificial Neural Network and Bayesian Optimization based strategy for the efficient development of machine learning models, intended for engine optimization and calibration. The objective of this method is to minimize the size of the required experimental data set and reduce the associated data collection cost for engine modeling.
This technique is demonstrated by generating engine performance models for a Dual Fuel High Pressure Direct Injection (HPDI) CNG Engine. Models are generated for the emissions and performance of a pilot ignited, direct injection, natural gas engine using only typical control inputs (e.g.: speed, injection timings, and fuel and air pressures). This modeling technique is first demonstrated on a full-factorial data set collected over a narrow operating space and then compared to a much coarser data set collected over a much larger space using the Box-Behnken approach.
Ten sets of neural network and Gaussian process regression models were generated for each engine output. The aggregated model results demonstrate that the machine learning models perform very well for the full factorial data set with correlation coefficients generally over 0.8 and normalized root mean square errors generally under 10%, while the response surface model is unable to characterize the outputs due to the size of the data. While there is a loss in performance using the coarser Box-Behnken data set, the machine learning methods do show some strong results for certain outputs. Models for NOX, CO2, O2, Peak Cylinder Pressure, EQR and Gross Indicated Power have R2 greater than 0.8 and normalized root mean square errors less than 20%. In general, Gaussian process regression shows the higher performing results with less performance variation over multiple tests compared to the neural network models. With further study, this method could enable the rapid evaluation and implementation of technologies and fuels for emission reduction.
CitationKarpinski-Leydier, M., Nagamune, R., and Kirchen, P., "A Machine Learning Modeling Approach for High Pressure Direct Injection Dual Fuel Compressed Natural Gas Engines," SAE Technical Paper 2020-01-2017, 2020, https://doi.org/10.4271/2020-01-2017.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
|[Unnamed Dataset 2]|
|[Unnamed Dataset 3]|
|[Unnamed Dataset 4]|
|[Unnamed Dataset 5]|
|[Unnamed Dataset 6]|
|[Unnamed Dataset 7]|
|[Unnamed Dataset 8]|
- Guzzella, L., and Onder, C.H. , Introduction to Modeling and Control of Internal Combustion Engine Systems. Journal of Chemical Information and Modeling. Vol. 53 (Berlin, Heidelberg: Springer Berlin Heidelberg, 2010). https://doi.org/10.1007/978-3-642-10775-7.
- Yusaf, T.F., Buttsworth, D.R., Saleh, K.H., and Yousif, B.F. , “CNG-Diesel Engine Performance and Exhaust Emission Analysis with the Aid of Artificial Neural Network,” Applied Energy 87(5):1661-1669, 2010, https://doi.org/10.1016/j.apenergy.2009.10.009.
- Friedrich, C., Auer, M., and Stiesch, G. , “Model Based Calibration Techniques for Medium Speed Engine Optimization: Investigations on Common Modeling Approaches for Modeling of Selected Steady State Engine Outputs,” SAE International Journal of Engines 9(4):2016-01-2156, 2016, https://doi.org/10.4271/2016-01-2156.
- Mohammadhassani, J., Dadvand, A., Khalilarya, S., and Solimanpur, M. , “Prediction and Reduction of Diesel Engine Emissions Using a Combined ANN-ACO Method,” Applied Soft Computing Journal 34:139-150, 2015, https://doi.org/10.1016/j.asoc.2015.04.059.
- Lotfan, S., Ghiasi, R.A., Fallah, M., and Sadeghi, M.H. , “ANN-Based Modeling and Reducing Dual-Fuel Engine ’ s Challenging Emissions by Multi-Objective Evolutionary Algorithm NSGA-II,” Applied Energy 175:91-99, 2016, https://doi.org/10.1016/j.apenergy.2016.04.099.
- Roy, S., Das, A.K., Bhadouria, V.S., Mallik, S.R. et al. , “Adaptive-Neuro Fuzzy Inference System (ANFIS) Based Prediction of Performance and Emission Parameters of a CRDI Assisted Diesel Engine under CNG Dual-Fuel Operation,” Journal of Natural Gas Science and Engineering 27:274-283, 2015, https://doi.org/10.1016/j.jngse.2015.08.065.
- Shi, Y., and Reitz, R.D. , “Assessment of Multiobjective Genetic Algorithms With Different Niching Strategies and Regression Methods for Engine Optimization and Design,” Journal of Engineering for Gas Turbines and Power 132(5):052801, 2010, https://doi.org/10.1115/1.4000144.
- Johri, R., and Filipi, Z. , “Neuro-Fuzzy Model Tree Approach to Virtual Sensing of Transient Diesel Soot and NOx Emissions,” 15(8):918-927, 2014, https://doi.org/10.1177/1468087413492962.
- Faghani, E. , Effect of Injection Strategies on Particulate Matter Emissions From HPDI Natural-Gas Engines (University of British Columbia, 2015), https://doi.org/10.14288/1.0220518.
- Mariani, C., Viviana, S.H.O., dos Santos Coelho, L., and Domingues, E. , 2019, “Pressure Prediction of a Spark Ignition Single Cylinder Engine Using Optimized Extreme Learning Machine Models.” Applied Energy 249 (November 2018): 204-21. https://doi.org/10.1016/j.apenergy.2019.04.126.
- Azmin, M., Farraen, R.K.S., Rutledge, J., and Winward, E. , “Using a Statistical Machine Learning Tool for Diesel Engine Air Path Calibration,” SAE Technical Paper 2014-01-2391, 2014, https://doi.org/10.4271/2014-01-2391.
- Ouelette, P., Goudie, D., and McTaggart-Cowan, G. , 2016, “Progress in the Development of Natural Gas High Pressure Direct Injection for Euro VI Heavy-Duty Trucks,” in ATZ International Motor Congress, Springer Vieweg, Wiesbaden, pp. 591-607.
- Singh, A.P. , “Characterization and System Level Study of Air Addition in a Pilot Ignited Direct Injection Natural Gas Engine,” . In: Electronic Theses and Dissertations (ETDs) 2008+. T, (University of British Columbia, 2019). http://dx.doi.org/10.14288/1.0376211.
- Robinson, T.J. , “Box-Behnken Designs,” . In: Wiley StatsRef: Statistics Reference Online, (2014), https://doi.org/10.1002/9781118445112.stat04101.
- Darío Baptista, F., Rodrigues, S., and Morgado-Dias, F. , “Performance comparison of ANN training algorithms for classification,” . In: 2013 IEEE 8th International Symposium on Intelligent Signal Processing, (Funchal, 2013), 115-120.
- Rasmussen, C., and Williams, C. , 2006, “Gaussian Processes for Machine Learning.”
- Frazier, P.I. , 2018, “A Tutorial on Bayesian Optimization,” July. http://arxiv.org/abs/1807.02811.