Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Engineering Applicat...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Engineering Applications of Artificial Intelligence
Article . 2023 . Peer-reviewed
License: CC BY
Data sources: Crossref
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Jyväskylä University Digital Archive
Article . 2023 . Peer-reviewed
License: CC BY
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Research.fi
Article . 2023 . Peer-reviewed
Data sources: Research.fi
https://dx.doi.org/10.60692/gd...
Other literature type . 2023
Data sources: Datacite
https://dx.doi.org/10.60692/0p...
Other literature type . 2023
Data sources: Datacite
versions View all 6 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Interactive data-driven multiobjective optimization of metallurgical properties of microalloyed steels using the DESDEO framework

تحسين متعدد الأهداف تفاعلي قائم على البيانات للخصائص المعدنية للفولاذ المصنوع من السبائك الدقيقة باستخدام إطار عمل DESDEO
Authors: Saini, Bhupinder Singh; Chakrabarti, Debalay; Chakraborti, Nirupam; Shavazipour, Babooshka; Miettinen; Kaisa;

Interactive data-driven multiobjective optimization of metallurgical properties of microalloyed steels using the DESDEO framework

Abstract

Résoudre des problèmes d'optimisation multi-objectifs basés sur des données réelles implique de nombreux défis complexes. Ces défis comprennent le prétraitement des données, la modélisation des fonctions objectives, l'obtention d'une formulation significative du problème et l'aide aux décideurs pour trouver des solutions préférées à l'existence de fonctions objectives contradictoires. Dans cet article, nous abordons le problème de l'optimisation de la composition des aciers microalliés pour obtenir de bonnes propriétés mécaniques telles que la limite d'élasticité, le pourcentage d'allongement et l'énergie Charpy. Nous formulons un problème avec six fonctions objectives basées sur les données disponibles et aidons deux décideurs à trouver une solution qui les satisfasse tous les deux. Pour permettre à deux décideurs de prendre des décisions significatives pour un problème avec de nombreux objectifs, nous créons l'algorithme MultiDM/IOPIS, qui combine des algorithmes évolutifs multi-objectifs et des fonctions de scalarisation à partir de méthodes interactives d'optimisation multi-objectifs de manière novatrice. Nous utilisons le framework logiciel appelé DESDEO, un framework Python open-source pour résoudre de manière interactive des problèmes d'optimisation multiobjectifs, pour créer l'algorithme MultiDM/IOPIS. Nous fournissons un compte rendu détaillé de tous les défis rencontrés lors de la formulation et de la résolution du problème. Nous discutons et utilisons de nombreuses stratégies pour surmonter ces défis. Dans l'ensemble, nous proposons une méthodologie pour résoudre les problèmes réels liés aux données avec de multiples fonctions objectives et décideurs. Avec cette méthodologie, nous avons réussi à obtenir des compositions d'acier microalliées aux propriétés mécaniques satisfaisantes pour les deux décideurs.

Resolver problemas de optimización multiobjetivo basados en datos de la vida real implica muchos desafíos complicados. Estos desafíos incluyen el preprocesamiento de los datos, el modelado de las funciones objetivas, la obtención de una formulación significativa del problema y el apoyo a los responsables de la toma de decisiones para encontrar soluciones preferidas en la existencia de funciones objetivas en conflicto. En este artículo, abordamos el problema de optimizar la composición de los aceros microaleados para obtener buenas propiedades mecánicas como el límite elástico, el porcentaje de alargamiento y la energía Charpy. Formulamos un problema con seis funciones objetivas basadas en los datos disponibles y ayudamos a dos tomadores de decisiones a encontrar una solución que satisfaga a ambos. Para permitir que dos tomadores de decisiones tomen decisiones significativas para un problema con muchos objetivos, creamos el llamado algoritmo MultiDM/IOPIS, que combina algoritmos evolutivos multiobjetivo y funciones de escalarización de métodos interactivos de optimización multiobjetivo de maneras novedosas. Utilizamos el marco de software llamado DESDEO, un marco de Python de código abierto para resolver de forma interactiva problemas de optimización multiobjetivo, para crear el algoritmo MultiDM/IOPIS. Proporcionamos una descripción detallada de todos los desafíos que se enfrentan al formular y resolver el problema. Discutimos y utilizamos muchas estrategias para superar esos desafíos. En general, proponemos una metodología para resolver problemas basados en datos de la vida real con múltiples funciones objetivas y tomadores de decisiones. Con esta metodología, obtuvimos con éxito composiciones de acero microaleado con propiedades mecánicas que satisfacían a ambos tomadores de decisiones.

Solving real-life data-driven multiobjective optimization problems involves many complicated challenges. These challenges include preprocessing the data, modelling the objective functions, getting a meaningful formulation of the problem, and supporting decision makers to find preferred solutions in the existence of conflicting objective functions. In this paper, we tackle the problem of optimizing the composition of microalloyed steels to get good mechanical properties such as yield strength, percentage elongation, and Charpy energy. We formulate a problem with six objective functions based on data available and support two decision makers in finding a solution that satisfies them both. To enable two decision makers to make meaningful decisions for a problem with many objectives, we create the so-called MultiDM/IOPIS algorithm, which combines multiobjective evolutionary algorithms and scalarization functions from interactive multiobjective optimization methods in novel ways. We use the software framework called DESDEO, an open-source Python framework for interactively solving multiobjective optimization problems, to create the MultiDM/IOPIS algorithm. We provide a detailed account of all the challenges faced while formulating and solving the problem. We discuss and use many strategies to overcome those challenges. Overall, we propose a methodology to solve real-life data-driven problems with multiple objective functions and decision makers. With this methodology, we successfully obtained microalloyed steel compositions with mechanical properties that satisfied both decision makers.

ينطوي حل مشكلات تحسين الأهداف المتعددة القائمة على البيانات الواقعية على العديد من التحديات المعقدة. وتشمل هذه التحديات المعالجة المسبقة للبيانات، ونمذجة الوظائف الموضوعية، والحصول على صياغة ذات مغزى للمشكلة، ودعم صانعي القرار لإيجاد حلول مفضلة في وجود وظائف موضوعية متضاربة. في هذه الورقة، نتناول مشكلة تحسين تكوين الفولاذ المصنوع من السبائك الدقيقة للحصول على خصائص ميكانيكية جيدة مثل قوة الخضوع، ونسبة الاستطالة، وطاقة شاربي. نقوم بصياغة مشكلة مع ست وظائف موضوعية بناءً على البيانات المتاحة وندعم اثنين من صانعي القرار في إيجاد حل يرضيهما. لتمكين اثنين من صانعي القرار من اتخاذ قرارات ذات مغزى لمشكلة ذات أهداف عديدة، نقوم بإنشاء ما يسمى بخوارزمية MultiDM/IOPIS، التي تجمع بين الخوارزميات التطورية متعددة الأهداف ووظائف التدرج من طرق التحسين التفاعلية متعددة الأهداف بطرق جديدة. نستخدم إطار عمل البرنامج المسمى DESDEO، وهو إطار عمل بايثون مفتوح المصدر لحل مشكلات التحسين متعدد الأهداف بشكل تفاعلي، لإنشاء خوارزمية MultiDM/IOPIS. نقدم وصفًا تفصيليًا لجميع التحديات التي تمت مواجهتها أثناء صياغة المشكلة وحلها. نناقش ونستخدم العديد من الاستراتيجيات للتغلب على تلك التحديات. بشكل عام، نقترح منهجية لحل المشكلات الواقعية القائمة على البيانات مع وظائف موضوعية متعددة وصناع القرار. من خلال هذه المنهجية، نجحنا في الحصول على تركيبات فولاذية مصنوعة من السبائك الدقيقة ذات خصائص ميكانيكية ترضي صانعي القرار.

Country
Finland
Keywords

Artificial intelligence, metallurgia, open-source software, Decision analytics utilizing causal models and multiobjective optimization, interactive optimization, päätöksentukijärjestelmät, Charpy impact test, data-driven evolutionary computation, multiple decision makers, Computational Science, avoin lähdekoodi, optimointi, Artificial Intelligence, Machine learning, FOS: Mathematics, surrogate-assisted optimization, metalliseokset, Swarm Intelligence Optimization Algorithms, multiple criteria optimization, ta216, Preprocessor, ta113, Päätöksen teko monitavoitteisesti, Multi-Objective Optimization, Optimization Applications, Python (programming language), Mathematical optimization, Multiobjective Optimization Group, monitavoiteoptimointi, Computer science, Materials science, fysikaaliset ominaisuudet, Multi-objective optimization, Operating system, Computational Theory and Mathematics, Application of Genetic Programming in Machine Learning, Computer Science, Physical Sciences, Metallurgy, interaktiivisuus, Toughness, Laskennallinen tiede, Multiobjective Optimization in Evolutionary Algorithms, Mathematics

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    8
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 10%
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
8
Top 10%
Average
Top 10%
Green
hybrid