This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Hybridizing Unsupervised Clustering Methods for In-Cylinder Vortex Motion Analysis under Different Swirl Ratio Conditions
Technical Paper
2021-01-0425
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Event:
SAE WCX Digital Summit
Language:
English
Abstract
Large-scale vortex motion could enhance the fuel-air mixing and the combustion stability inside a direct-injection engine. For in-cylinder vortex motion analysis, detection of the vortex features is usually a challenging task because of large cyclic variations of vortex structure, number, and locations. In previous study, K-means clustering has been successfully applied to detect the vortex features and quantify the cyclic variations. However, K-means algorithm is somewhat limited in analyzing the complex flow with multiple vortex zones and vortex merging. Therefore, we propose a hybrid clustering method which blends in two clustering algorithms, namely, Gaussian mixture model (GMM) clustering and K-means clustering, to optimize the analysis of vortex classification, vortex zone detection, and cyclic variation quantification under different flow conditions. In this study, in-cylinder flow fields with varying degrees of swirling behavior were recorded by high-speed particle image velocimetry (PIV) under high and low swirl ratio conditions. Owing to the probability density contour feature of GMM, the clustering results show that the hybrid clustering method improves the accuracy of vortex classification and vortex zone detection, especially for low swirl cases where there exist large cluster overlaps. Additionally, this hybrid clustering method is able to retain the quantification of cyclic variations by blending K-means clustering to quantify the distance. In summary, the transient features and cyclic variations of the in-cylinder vortex motion under different swirl ratio conditions can be accurately revealed by this hybrid clustering method.
Authors
- Fengnian Zhao - UM-SJTU JI - Shanghai Jiao Tong University
- Mengqi Liu - UM-SJTU JI - Shanghai Jiao Tong University
- Weihan Fan - UM-SJTU JI - Shanghai Jiao Tong University
- Jiajin Wu - UM-SJTU JI - Shanghai Jiao Tong University
- Junxiang Zhang - UM-SJTU JI - Shanghai Jiao Tong University
- David Hung - UM-SJTU JI - Shanghai Jiao Tong University
Topic
Citation
Zhao, F., Liu, M., Fan, W., Wu, J. et al., "Hybridizing Unsupervised Clustering Methods for In-Cylinder Vortex Motion Analysis under Different Swirl Ratio Conditions," SAE Technical Paper 2021-01-0425, 2021, https://doi.org/10.4271/2021-01-0425.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 | ||
Unnamed Dataset 2 |
Also In
References
- Mittal , M. , Hung , D. , Zhu , G. , and Schock , H. High-speed flow and Combustion Visualization to Study the Effects Of Charge Motion Control on Fuel Spray Development and Combustion Inside a Direct-injection Spark-ignition Engine SAE Int. J. Engines 4 1469 1480 2011 https://doi.org/10.4271/2011-01-1213
- Porpatham , E. , Ramesh , A. , and Nagalingam , B. Effect of Swirl on the Performance and Combustion of a Biogas Fuelled Spark Ignition Engine Energy Convers. Manage, 76 463 471 2013 10.1016/j.enconman.2013.07.071
- Wang , T. , Li , W. , Jia , M. , Liu , D. et al. Large-eddy Simulation of in-cylinder flow in a DISI Engine with Charge Motion Control Valve: Proper Orthogonal Decomposition Analysis and Cyclic Variation Appl. Therm. Eng. 75 561 574 2015 10.1016/j.applthermaleng.2014.10.081
- Reuss , D. Cyclic Variability of Large-scale Turbulent Structures in Directed and Undirected IC Engine flows SAE Technical Paper 2000-01-0246 2000 https://doi.org/10.4271/2000-01-0246
- Druault , P. , Guibert , P. , and Alizon , F. Use of Proper Orthogonal Decomposition for Time Interpolation from PIV data. Application to the Cycle-to-cycle Variation Analysis of in-cylinder Engine Flows Exp. Fluids 39 1009 1023 2005 10.1007/s00348-005-0035-3
- Chen , H. , Reuss , D. , and Sick , V. On the Use and Interpretation of Proper Orthogonal Decomposition of in-cylinder Engine Flows Measurement Science and Technology 23 8 085302 2012 10.1088/0957-0233/23/8/085302
- Chen , H. , Xu , M. , and Hung , D. Analyzing in-cylinder Flow Evolution and Variations in a Spark-ignition Direct-injection Engine Using Phase-invariant Proper Orthogonal Decomposition Technique SAE Technical Paper 2014-01-1174 2014 https://doi.org/10.4271/2014-01-1174
- Zhuang , H. , and Hung , D. Characterization of the Effect of Intake Air Swirl Motion on Time-resolved in-cylinder Flow Field Using Quadruple Proper Orthogonal Decomposition Energy Convers. Manage 108 366 376 2016 10.1016/j.enconman.2015.10.080
- Zhao , F. , Ge , P. , Zhuang , H. , and Hung , D. Analysis of Crank Angle-resolved Vortex Characteristics Under High Swirl Condition in a Spark-ignition Direct-injection Engine J. Eng. Gas Turbines Power 140 9 092807 2018 10.1115/1.4039082
- Liu , Z. , Teh , K. , Ge , P. , Zhao , F. et al. Tumble Vortex Characterization by Complex Moments SAE Technical Paper 2018-01-0207 2018 https://doi.org/10.4271/2018-01-0207
- Zhao , F. , Hung , D. , and Wu , S. K-means Clustering-driven Detection of Time-resolved Vortex Patterns and Cyclic Variations Inside a Direct Injection Engine Appl. Therm. Eng. 180 115810 2020 10.1016/j.applthermaleng.2020.115810
- Zhao , F. , Ruan , Z. , Yue , Z. , Hung , D. et al. Time-sequenced Flow Field Prediction in an Optical Spark-ignition Direct-injection Engine Using Bidirectional Recurrent Neural Network (bi-RNN) with Long Short-term Memory Appl. Therm. Eng 173 115253 2020 10.1016/j.applthermaleng.2020.115253
- Hanuschkin , A. , Schober , S. , Bode , J. , Schorr , J. et al. Machine Learning-based Analysis of in-cylinder Flow Fields to Predict Combustion Engine Performance Int. J. Engine Res 2019 10.1177/1468087419833269
- Kodavasal , J. , Moiz , A. , Ameen , M. , and Som , S. Using Machine Learning to Analyze Factors Determining Cycle-to-cycle Variation in a Spark-ignited Gasoline Engine Journal of Energy Resources and Technology 140 10 102204 2018 10.1115/1.4040062
- Cay , Y. Prediction of a Gasoline Engine Performance with Artificial Neural Network Fuel 111 324 331 2013 10.1016/j.fuel.2012.12.040
- Yu , W. , Zhao , F. , Yang , W. , and Xu , H. Integrated Analysis of CFD Simulation Data with K-means Clustering Algorithm for Soot Formation Under Varied Combustion Conditions Appl. Therm. Eng. 153 299 305 2019 10.1016/j.applthermaleng.2019.03.011
- Satre-Meloy , A. , Diakonova , M. , and Grünewald , P. Cluster Analysis and Prediction of Residential Peak Demand Profiles Using Occupant Activity Data Appl. Energy 260 114246 2020 10.1016/j.apenergy.2019.114246
- Brandt , A. Clustering Methods to find Representative Periods for the Optimization of Energy Systems: An Initial Framework and Comparison Appl. Energy 239 1283 1293 2019 10.1016/j.apenergy.2019.02.012
- Fränti , P. , and Sieranoja , S. K-means Properties on Six Clustering Benchmark Datasets Applied Intell 48 12 4743 4759 2018 10.1007/s10489-018-1238-7
- Fränti , P. , and Sieranoja , S. How Much Can k-means be Improved by Using Better Initialization and Repeats? Pattern Recogn. 93 95 112 2019 10.1016/j.patcog.2019.04.014
- Preheim , S. , Perrotta , A. , Martin-Platero , A. , Gupta , A. et al. Distribution-based Clustering: Using Ecology to Refine the Operational Taxonomic Unit Appl Environ Microbiol 79 6593 6603 2013 10.1128/AEM.00342-13
- Xu , D. , and Tian , Y. A Comprehensive Survey of Clustering Algorithms Annals of Data Science 2 165 193 2015 10.1007/s40745-015-0040-1
- Lu , Y. , Tian , Z. , Peng , P. , Niu , J. et al. GMM Clustering for Heating Load Patterns in-depth Identification and Prediction Model Accuracy Improvement of District Heating System Energy & Buildings 190 49 60 2019 10.1016/j.enbuild.2019.02.014
- Hou , X. , Zhang , T. , Xiong , G. , Lu , Z. et al. A Novel Steganalysis Framework of Heterogeneous Images Based on GMM Clustering Signal Processing: Image Communication 29 385 399 2014 10.1016/j.image.2014.01.006
- MATLAB and Statistics and Machine Learning Toolbox Release 2020a
- Tibshirani , R. , Walther , G. , and Hastie , T. Estimating the Number of Clusters in a Data Set Via the Gap Statistic J. Roy. Stat. Soc. B 63 2 411 423 2001 10.1111/1467-9868.00293
- Steele , R. , and Raftery , A. Performance of Bayesian Model Selection Criteria for Gaussian Mixture Models 2009
- Lumley , J. Engines: An Introduction Cambridge University Press 1999