[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126393-en":3,"doc-seo-126393-105":31,"detail-sidebar-cat-0-en-105":93},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126393,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Combustion Condition Identification using a Decision Tree based Machine Learning Algorithm Applied to a Model Can Combustor with High Shear Swirl Injector - Slideshare","Decision-tree-based machine learning is applied for combustion condition identification in a high-shear counter-swirled model gas-turbine combustor. The study leverages time-series analysis inspired by prior literature to classify stability-related states using experimental observations from acoustic and flame diagnostics, aiming to detect combustion condition prior to more practical configurations. The combustor uses counter-rotating high-shear swirl injectors for fuel–air mixing and flame stabilization. Experimental setup details, data acquisition approach, and combustor dynamics are provided to support preliminary investigation.","5th National Aerospace propulsion conference at IIT Madras, India, 20-22 Jan 2025  \nCombustion Condition Identi􀀂cation using a Decision tree based Machine Learning Algorithm Applied to a Model Can Combustor with High Shear Swirl Injector  \nPK Archhitha, SK Thirumalaikumaranb, Balasundaram Mohanb, Saptharshi Basu∗, b,c  \na Department of Mechanical Engineering, Indian Institute of Technology Madras, Chennai-600036, India.  \nb Department of Mechanical Engineering, Indian Institute of Science Bangalore, Karnataka-560012, India. c Interdisciplinary Centre for Energy Research, Indian Institute of Science Bangalore, Karnataka-560012, India.  \n∗ Corresponding author: e-mail: [sbasu@iisc.ac.in](sbasu@iisc.ac.in)  \nstudy [3] proposed a selective convolutional autoencoder-based deep neural network to predict thermoacoustic instability using high-speed 􀀃ame images, with the model trained to identify both stable and unstable states. Wang et al. [4] developed a deep learning model using DNN and CNN frameworkscan simultaneously predict combustion states and heat release rates with 99 .91% accuracy, demonstrating signi􀀂cant industrial potential. Another study [5] used CNNs to extract features from acoustic pressure data in a supersonic combustor, outperforming other models in classifying combustion conditions. Hernandez-Rivera et al. [6] used nonlinear time-series analysis of pressure 􀀃uctuations to calculate recurrence plot indices, which e􀀋ectively predicted the transition from combustion noise to instability.  \nIn [7], the authors used premixed blu􀀋-body stabilized 􀀃ame images to classify combustion conditions during instability. A CNN was trained to recognize spatial patterns from highspeed 􀀃ame image sequences, with instability labeled using acoustic pressure data. To capture temporal correlations, they employed Long term short Memory Recurrence Neural Networks (LSTM-RNM), resulting in a binary classi􀀂cation framework combining CNN and LSTM. Wang et al. [8] developed a pattern recognition model using logarithmic entropy multi-threshold segmentation and fuzzy pattern recognition to classify abnormal combustor conditions, outperforming other methods like self-organizing maps and support vector machines. Han et al. [9] used a stacked sparse autoencoder-based deep neural network to extract features from unlabeled 􀀃ame images and combined with loss function to improve training e􀀎ciency, achieving superior prediction accuracy. McCartney et al. [10] enhanced thermoacoustic instability prediction with supervised machine learning on dynamic pressure readings, using Hidden Markov Models and Automated Machine Learning to restore predictive power lost by traditional tools like the Hurst exponent and Auto-Regressive models. Zhou et al. [11] used deep learning to monitor combustion instabilities via timeaveraged 􀀃ame images, designing a CNN called BASIS Image Monitor (BIM) that achieved 99% accuracy in predicting thermoacoustic states and visualized statistical links between 􀀃ame images and stability using Class Activation Maps.  \nJiang et al. [12] developed a decision tree-based method to identify combustion conditions in coal-􀀂red kilns using 􀀃ame  \n5th National Aerospace propulsion conference at IIT Madras, India, 20-22 Jan 2025  \nvideo intensity. By constructing a phase space from the intensity sequence and extracting trajectory evolution and morphology distribution features, the method improved e􀀎ciency by over 5% compared to existing approaches. Zhang et al. [13] employed a neural network to predict combustion instability, simplifying it with Active Subspaces (AS) to reduce training time while maintaining accuracy. The model uses historical data and system parameters, focusing on the most signi􀀂cant variations captured by AS. In [14], the authors varied the equivalence ratio and observed signi􀀂cant changes in combustor modal dynamics. They used Jensen-Shannon complexity and permutation entropy to classify these dynamics via a k-medoids clusterin","cbCaipG5rplalxbz","https://ap.wps.com/l/cbCaipG5rplalxbz","pdf",740994,10,1,6,"English","en",105,"# Experimental Setup, Data Acquisition and Combustor Dynamics\n## Combustor Configuration and Fuel-Air Mixing\n## Flame Stabilization and Injector Geometry\n## Fuel Supply, Operating Parameters, and Data Acquisition","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To identify combustion conditions in a high-shear counter-swirled model gas-turbine combustor using a decision-tree-based machine learning approach.\"},{\"question\":\"How is flame stabilization achieved in the experiment?\",\"answer\":\"Flame stabilization is achieved at the dump plane using counter-rotating high-shear swirl injectors that promote fuel–air mixing.\"},{\"question\":\"What fuel and key injector configuration details are used?\",\"answer\":\"Methane (CH4) is used as fuel, supplied through a pressure regulator, while the injector system uses counter-swirl directions with specified swirl numbers for primary and secondary swirlers.\"}]","Combustion Condition Identification using a Decision Tree based Machine Learning Algorithm Applied to a Model Can Combustor with High Shear Swirl Injector - Slideshare | PDF",1785904822,15,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"combustion-condition-identification-using-a-decision-tree-based-machine-learning-algorithm-applied-to-a-model-can-combustor-with-high-shear-swirl-injector-slideshare","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/combustion-condition-identification-using-a-decision-tree-based-machine-learning-algorithm-applied-to-a-model-can-combustor-with-high-shear-swirl-injector-slideshare/126393/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the main goal of the study?","Question",{"text":77,"@type":78},"To identify combustion conditions in a high-shear counter-swirled model gas-turbine combustor using a decision-tree-based machine learning approach.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How is flame stabilization achieved in the experiment?",{"text":82,"@type":78},"Flame stabilization is achieved at the dump plane using counter-rotating high-shear swirl injectors that promote fuel–air mixing.",{"name":84,"@type":75,"acceptedAnswer":85},"What fuel and key injector configuration details are used?",{"text":86,"@type":78},"Methane (CH4) is used as fuel, supplied through a pressure regulator, while the injector system uses counter-swirl directions with specified swirl numbers for primary and secondary swirlers.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,121,124,129,132,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":20,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]