[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124697-en":3,"doc-seo-124697-105":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},124697,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation","This paper presents a methodological framework for training self-optimising, self-organising surrogate models that approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. Using two real-world datasets, the work shows that accurate approximations can be learned from relatively small data quantities. Explainable AI techniques highlight feature relevance and dependencies, and enable dataset extensions. Experiments combine four machine learning and deep learning approaches with evolutionary optimisation, validating Pareto-optimal results against ground-truth simulations and achieving low prediction error, with MAPE under 5% for one use case.","arXiv :2309 . 13 179v2 [ cs .LG] 3 Apr 2024  \nEnhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation  \nDiego Botache 1[0000−0003−1694−0307], Jens Decke 1[0000−0002−7893−1564], Winfried Ripken2[0009−0006−1926−6695], Abhinay Dornipati3 , Franz G¨otz-Hahn 1[0000−0003−3465−5040],  \nMohammed Ayeb3[0000−0001−9479−059X], and Bernhard Sick 1[0000−0001−9467−656X]  \n1 Intelligent Embedded Systems, University of Kassel, Hessen, Germany  \n{diego.botache, jens.decke, franz.goetz.hahn, [bsick](bsick}@uni-kassel.de)[}](bsick}@uni-kassel.de)[@uni-kassel.de](bsick}@uni-kassel.de)[ ](bsick}@uni-kassel.de)[https://www.uni-kassel.de/eecs/ies](https://www.uni-kassel.de/eecs/ies)  \n2 Technische Universit¨at Berlin, Berlin, Germany  \n[winfried.ripken@gmail.com](winfried.ripken@gmail.com)  \n[https://web.ml.tu-berlin.de/](https://web.ml.tu-berlin.de/)  \n3 Vehicle Systems and Fundamentals of Electrical Engineering,  \nUniversity of Kassel, Hessen, Germany  \n{abhinay.dornipati, [ayeb](ayeb}@uni-kassel.de)[}](ayeb}@uni-kassel.de)[@uni-kassel.de](ayeb}@uni-kassel.de)  \n[https://www.uni-kassel.de/eecs/fsg](https://www.uni-kassel.de/eecs/fsg)  \nAbstract. This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand of two real-world datasets, we illustrate that surrogate models can be trained on relatively small amounts of data to approximate the underlying simulations accurately. Including explainable AI techniques allow for highlighting feature relevancy or dependencies and supporting the possible extension of the used datasets.  \nOne of the datasets was created for this paper and is made publicly available for the broader scientific community. Extensive experiments combine four machine learning and deep learning algorithms with an evolutionary optimisation algorithm. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Paretooptimal results using the ground truth simulations. The results from our pipeline and a comprehensive evaluation strategy show the potential for efficiently acquiring solution candidates in multiobjective optimisation tasks by reducing the number of simulations and conserving a higher prediction accuracy, i.e., with a MAPE score under 5% for one of the presented use cases.  \nKeywords: Electric Motors · Multiobjective Optimisation · SurrogateModelling · Deep-Learning · Explainable Artificial Intelligence  \n2 D. Botache et al.  \n1 Introduction  \nMultiphysics and multiscale simulations have become crucial for the computational modelling and analysis of multiple interacting physical phenomena in technical systems. These phenomena include mechanics, fluid dynamics, heat transfer, and electromagnetics for a wide variety of applications, such as aerospace engineering, biomedical engineering, and materials science, to name a few. Incorporating multiple physical phenomena into simulations is a powerful tool for engineers, enabling them to investigate various design alternatives and parameters and enhance the depth of their decision-making during design processes. Typically, this approach involves considering competing objectives simultaneously within multiobjective optimization tasks, thereby ensuring that the final design solutions strike an optimal balance across diverse performance criteria.  \nAcquiring optimal solutions presents a significant challenge due to the complex nature of numerical models and potential nonlinear dependencies among design parameters. Moreover, constrained solution spaces yield scarce feasible solutions and require the inclusion of advanced domain knowledge of the underlying physical problem. To address these issues, we propose using surrogate models, [i.e. data-driven algorithms](i.e. data-driven algorithms), as an alternative to running computat","cbCairPS6MhUzj7N","https://ap.wps.com/l/cbCairPS6MhUzj7N","pdf",7152344,1,17,"English","en",105,"# Abstract\n# Introduction\n## Multiphysics simulation and multiobjective optimisation\n## Challenges and surrogate-model approach\n## Proposed end-to-end strategy\n## Main contributions","[{\"question\":\"What is the main goal of this paper?\",\"answer\":\"To build a framework that trains surrogate models to approximate and accelerate multiobjective optimisation in technical systems using multiphysics simulations.\"},{\"question\":\"How are the surrogate models used during optimisation?\",\"answer\":\"Surrogate ML models are trained and then applied in the optimisation task to search input parameters, after which candidate outputs are validated against ground-truth simulation results.\"},{\"question\":\"Why are explainable AI techniques included?\",\"answer\":\"They support understanding which features are relevant and how features depend on each other, and they help justify possible extensions of the datasets used.\"}]","Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation | PDF",1785893977,43,{"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},"enhancing-multi-objective-optimization-through-machine-learning-supported-multiphysics-simulation","",{"@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/enhancing-multi-objective-optimization-through-machine-learning-supported-multiphysics-simulation/124697/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of this paper?","Question",{"text":75,"@type":76},"To build a framework that trains surrogate models to approximate and accelerate multiobjective optimisation in technical systems using multiphysics simulations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the surrogate models used during optimisation?",{"text":80,"@type":76},"Surrogate ML models are trained and then applied in the optimisation task to search input parameters, after which candidate outputs are validated against ground-truth simulation results.",{"name":82,"@type":73,"acceptedAnswer":83},"Why are explainable AI techniques included?",{"text":84,"@type":76},"They support understanding which features are relevant and how features depend on each other, and they help justify possible extensions of the datasets used.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]