[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126808-en":3,"doc-seo-126808-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126808,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning-based analysis of in-cylinder flow fields to predict combustion engine performance","Cycle-to-cycle variations in an optically accessible four-stroke direct-injection spark-ignition gasoline engine are studied using high-speed scanning particle image velocimetry and in-cylinder pressure measurements. Binary classifiers predict combustion cycles of high indicated mean effective pressure using in-cylinder flow features and engineered tumble features from the intake and compression stroke. Basic mid-cylinder flow features enable early prediction up to 180° crank angle before TDC. Engineered tumble features are not superior, with results independent of model type and robust to hyper-parameter selection.","Standard Article  \nMachine learning–based analysis of in-cylinder flow fields to predict combustion engine performance  \nInternational J of Engine Research 2021, Vol. 22(1) 257–272  \n􀀂 IMechE 2019  \nArticle reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/1468087419833269](DOI: 10.1177/1468087419833269)[ ](DOI: 10.1177/1468087419833269)[journals.sagepub.com/home/jer](journals.sagepub.com/home/jer)  \nAlexander Hanuschkin 1, Steffen Schober2, Johannes Bode3, J¨urgen  \nSchorr4, Benjamin B¨ohm3, Christian Kr¨uger4 and Steven Peters 1  \nAbstract  \nCycle-to-cycle variations in an optically accessible four-stroke direct injection spark-ignition gasoline engine are investigated using high-speed scanning particle image velocimetry and in-cylinder pressure measurements. Particle image velocimetry allows to measure in-cylinder flow fields at high spatial and temporal resolution. Binary classifiers are used to predict combustion cycles of high indicated mean effective pressure based on in-cylinder flow features and engineered tumble features obtained during the intake and the compression stroke. Basic in-cylinder flow features of the midcylinder plane are sufficient to predict combustion cycles of high indicated mean effective pressure as early as 180degree crank angle before the top dead center at 0degree crank angle. Engineered characteristic tumble features derived from the flow field are not superior to the basic flow features. The results are independent of the tested machine learning method (multilayer perceptron and boosted decision trees) and robust to hyper-parameter selection.  \nKeywords  \nGasoline combustion engine, cycle-to-cycle variations, high-speed scanning particle image velocimetry, binary classifier, feature importance, neural network  \nDate received: 26 July 2018; accepted: 23 January 2019  \nIntroduction  \nOptimizing combustion engines is an important field of ongoing research to increase the degree of efficiency and to reduce emissions. Cycle-to-cycle variations (CCVs) of in-cylinder flows result in significant variations of mixture distribution and lead to overall reduction in combustion performance 1–3 and increased emissions.  \nExperimentally, CCVs can be investigated on the basis of time resolved data from a few measurement locations. A single pressure sensor is commonly used, mapping the complex spatio-temporal system to a single temporal thermodynamic variable. Time-series data of CCVs have been analyzed statistically4–6 or with wavelets.7 Next-cycle predictions in homogeneous charge compression ignition (HCCI) engines are possible based on online adaptive extreme learning machines.8–10  \nOptically accessible engines allow investigations of in-cylinder processes based on spatial and time resolved data.11–14 High-speed particle image velocimetry (PIV) extracts flow dynamics in cross-sections of the  \ncombustion chamber.11 Different cross-section planes can be investigated sequentially to extract the flow in the whole volume. 15,16 These spatio-temporal data have been investigated using engineered features, 17–19 conditional statistics, 19,20 or proper orthogonal decomposition.21–23 Graftieaux et al.17 engineered a tumble feature from the flow field. Tracking the tumble trajectory over time has been successfully applied to visualize, understand, and optimize the flow in combustion engines late in the compression stroke.20 Standard statistical tools turned out to be not suitable for  \n1 Group Research, Future Technologies, Daimler AG, Stuttgart, Germany 2University of Applied Sciences Esslingen, Esslingen, Germany 3Reaktive Str¨omungen und Messtechnik, Technische Universit¨at Darmstadt, Darmstadt, Germany  \n4Group Research, Gasoline & Hybrid Powertrains, Daimler AG, Stuttgart, Germany  \nCorresponding author:  \nSteven Peters, Group Research, Future Technologies, Daimler AG, 71065 Sindelfingen, Germany.  \nEmail: [steven.peters@dai","cbCaij1WYj1nQc9l","https://ap.wps.com/l/cbCaij1WYj1nQc9l","pdf",2623989,1,16,"English","en",105,"# Abstract\n# Introduction\n## Cycle-to-cycle variations and their impact\n## Conventional experimental analysis methods\n## Optical access and PIV-based spatio-temporal data\n## Existing ML approaches in combustion research\n## ML methods for CCVs in internal combustion engines","[{\"question\":\"How are cycle-to-cycle variations measured in this study?\",\"answer\":\"Cycle-to-cycle variations are investigated using high-speed scanning particle image velocimetry to measure in-cylinder flow fields and in-cylinder pressure measurements to characterize combustion performance.\"},{\"question\":\"What model type is used to predict combustion cycles?\",\"answer\":\"Binary classifiers are used to predict combustion cycles associated with high indicated mean effective pressure from engineered features and in-cylinder flow features.\"},{\"question\":\"How early can the prediction be made relative to top dead center?\",\"answer\":\"Basic in-cylinder flow features of the midcylinder plane allow prediction as early as 180° crank angle before top dead center (0° crank angle).\"},{\"question\":\"Are engineered tumble features more effective than basic flow features?\",\"answer\":\"No. Engineered characteristic tumble features derived from the flow field are not superior to basic in-cylinder flow features, and conclusions are consistent across tested machine learning methods and hyper-parameter choices.\"}]","Machine learning-based analysis of in-cylinder flow fields to predict combustion engine performance | PDF",1785934902,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"machine-learning-based-analysis-of-in-cylinder-flow-fields-to-predict-combustion-engine-performance","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-based-analysis-of-in-cylinder-flow-fields-to-predict-combustion-engine-performance/126808/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"How are cycle-to-cycle variations measured in this study?","Question",{"text":75,"@type":76},"Cycle-to-cycle variations are investigated using high-speed scanning particle image velocimetry to measure in-cylinder flow fields and in-cylinder pressure measurements to characterize combustion performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What model type is used to predict combustion cycles?",{"text":80,"@type":76},"Binary classifiers are used to predict combustion cycles associated with high indicated mean effective pressure from engineered features and in-cylinder flow features.",{"name":82,"@type":73,"acceptedAnswer":83},"How early can the prediction be made relative to top dead center?",{"text":84,"@type":76},"Basic in-cylinder flow features of the midcylinder plane allow prediction as early as 180° crank angle before top dead center (0° crank angle).",{"name":86,"@type":73,"acceptedAnswer":87},"Are engineered tumble features more effective than basic flow features?",{"text":88,"@type":76},"No. Engineered characteristic tumble features derived from the flow field are not superior to basic in-cylinder flow features, and conclusions are consistent across tested machine learning methods and hyper-parameter choices.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,123,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":29,"slug":122},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":46,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]