[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119996-en":3,"doc-seo-119996-105":30,"detail-sidebar-cat-0-en-105":91},{"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},119996,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Machine Learning based Prediction of Ditching Loads - Aircraft ditching load prediction using CAE and LSTM/Koopman","Machine learning approaches are presented to predict dynamic ditching loads on aircraft fuselages. The method combines spatial load reconstruction using convolutional autoencoders with a subsequent model for transient evolution. Multiple CAE strategies are evaluated and paired either with LSTM networks or Koopman operator–based predictors. Training data are generated via an extension of the von Kármán–Wagner momentum method, whose rationale is summarized. The workflow is applied to a full-scale DLR-D150 fuselage across horizontal and vertical approach velocities at 6° incidence.","arXiv :2402 . 10724v2 [ cs .LG] 11 Oct 2024  \nMachine Learning based Prediction of Ditching Loads  \nHenning Schwarz∗ , Micha Überrück †, Jens-Peter M. Zemke ‡ and Thomas Rung §  \nHamburg University of Technology, D-21073 Hamburg, Germany  \nWe present approaches to predict dynamic ditching loads on aircraft fuselages using machine learning. The employed learning procedure is structured into two parts, the reconstruction of the spatial loads using a convolutional autoencoder (CAE) and the transient evolution of these loads in a subsequent part. Different CAE strategies are assessed and combined with either long short-term memory (LSTM) networks or Koopman operator based methods to predict the transient behaviour. The training data is compiled by an extension of the momentum method of von Karman and Wagner and the rationale of the training approach is briefly summarised.  \nThe application included refers to a full-scale fuselage of a DLR-D150 aircraft for a range of horizontal and vertical approach velocities at 6◦ incidence. Results indicate a satisfactory level of predictive agreement for all four investigated surrogate models examined, with the combination of an LSTM and a deep decoder CAE showing the best performance.  \nI. Introduction  \nDitching describes the emergency landing on water where several regulatory items have to be considered for large transport aircrafts. Resulting certification provisions are found in the EASA/FAA CS 25.563 ‘Structural ditching provisions’, CS 25.801 ‘Ditching provisions’ and CS 25.807(e)‘Ditching emergency exit for passengers’. They aim at preventing immediate injuries for occupants and limiting aircraft damages to ensure the floatation time to be long enough for the occupants to exit the aircraft safely. Ditching is either investigated by accident analysis, experiments, which are usually based on scaled model tests, or numerical simulations. Investigations are typically split into four subsequent chronological phases, i.e., an approach, impact, landing and floating (evacuation) phase, cf. Fig. 1. The impact phase is the focus of the load analysis, on which the initial conditions, such as the pitch of the aircraft, its forward and sink speeds, a possible fuel jettison or the sea state encounter angle, are the subject of optimization.  \nThe majority of investigations follow a one-way fluid-structure coupling philosophy, and are partitioned into the determination of the hydrodynamic loads obtained for a (virtually) rigid body and a subsequent assessment of the  \nCopyright © 2024 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.  \n∗ Research Associate, Institute for Fluid Dynamics and Ship Theory, Am Schwarzenberg-Campus 4, [henning.schwarz@tuhh.de](henning.schwarz@tuhh.de) (Corresponding Author)  \n†Research Associate, Institute for Fluid Dynamics and Ship Theory, Am Schwarzenberg-Campus 4, [micha.ueberrueck@tuhh.de](micha.ueberrueck@tuhh.de).  \n‡Chief Engineer, Institute of Mathematics, Am Schwarzenberg-Campus 3, [zemke@tuhh.de](zemke@tuhh.de).  \n§ Professor, Institute for Fluid Dynamics and Ship Theory, Am Schwarzenberg-Campus 4, [thomas.rung@tuhh.de](thomas.rung@tuhh.de).  \nFig. 1 Frequently employed ditching investigation phases.  \nstructural response. Model-scale ditching tests in combination with data from previously commissioned configurations are a traditional way of load analysis. Conducting model scale experiments, scaling laws and associated scaling effects have to be taken into account, and strong similarity of the load situation is hard to achieve. Because of the dominance of inertia and gravitational forces during the impact phase, experiments are usually performed using Froude-scaling for the model properties and impact conditions. Froude-scaling drastically reduces the test velocity and neglects the similarity of viscous forces. Moreover, the similarity of multi-phase aspects, i.e., cavitation and ventilation, are not considered, e.g., [1] . Seve","cbCaivLzLKnPVZNr","https://ap.wps.com/l/cbCaivLzLKnPVZNr","pdf",4696645,1,40,"English","en",105,"# Introduction\n## Ditching background and certification requirements\n## Typical investigation phases and impact-phase focus\n## Coupling philosophy and limitations of experiments\n## Numerical simulation via the DLR-Ditch method\n## Toward ML-based surrogate prediction","[{\"question\":\"What problem does the study address?\",\"answer\":\"Predicting dynamic ditching loads on aircraft fuselages during emergency water landings.\"},{\"question\":\"How is the machine learning pipeline structured?\",\"answer\":\"It reconstructs spatial load fields with convolutional autoencoders, then predicts transient load evolution using either LSTM networks or Koopman operator–based methods.\"},{\"question\":\"How is the training data generated?\",\"answer\":\"By extending the momentum method of von Kármán and Wagner, with the training approach rationale briefly summarized in the document.\"}]","Machine Learning based Prediction of Ditching Loads - Aircraft ditching load prediction using CAE and LSTM/Koopman | PDF",1785727570,101,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-based-prediction-of-ditching-loads-aircraft-ditching-load-prediction-using-cae-and-lstmkoopman","",{"@graph":36,"@context":85},[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-prediction-of-ditching-loads-aircraft-ditching-load-prediction-using-cae-and-lstmkoopman/119996/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address?","Question",{"text":75,"@type":76},"Predicting dynamic ditching loads on aircraft fuselages during emergency water landings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine learning pipeline structured?",{"text":80,"@type":76},"It reconstructs spatial load fields with convolutional autoencoders, then predicts transient load evolution using either LSTM networks or Koopman operator–based methods.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the training data generated?",{"text":84,"@type":76},"By extending the momentum method of von Kármán and Wagner, with the training approach rationale briefly summarized in the document.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":21,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]