Mimaride temsil, tasarımcının düşünce süreçlerini ifade etmek için kullandığı yöntemler bütünüdür. Bilgisayarın günlük kullanıma dahil olmasıyla beraber gelişen ve farklılaşan bu yöntemler, beraberinde çeşitli sorgulamaları ve yeni temsil biçimlerini geliştirmiştir. Çalışmanın odaklandığı nokta, yeni tartışılan bir kavram olan ayrık paradigması ile mimari temsil ilişkisidir. Ayrık paradigması hesaplamalı tasarım yöntemlerini kullanarak mimarlığın temel yapı taşları ve kuralları üzerinde denemeler yaparak yeni bir söylem geliştirmeyi amaçlar. Bu bağlamda çalışma iki soru etrafında şekillenmiştir: Mimaride ayrık paradigması nedir? Tasarım süreci nasıl gerçekleşir? Çalışmada, ayrık paradigması hakkındaki görüşlerin tartışılması, tasarım ve temsil ilişkisinin irdelenmesi amaçlanmıştır. Çalışma üç bölümden oluşmaktadır. Birinci bölümde, temsil kavramı tanımlanıp, 1960’lı yıllardan itibaren günümüze kadar bilgisayar ortamında temsil süreçlerinin nasıl dönüştüğü incelenmiştir. İkinci bölümde ayrık paradigması tanımlanıp, konu hakkındaki görüşlere, üretilen projelere yer verilmiştir. Aynı zamanda ayrık paradigmasının temelini oluşturan; ayrıklık, süreklilik, mereoloji kavramları tartışılmıştır. Üçüncü bölümde ise paradigmanın bilgisayar ortamındaki temsilini incelemek adına Rhino Grasshopper’da form denemeleri yapılmıştır. Çalışma, tasarım sürecinde üzerine çok düşünülmeyen parçadan bütüne olan ilişkisinin potansiyellerinin ve temsil yöntemlerinin incelemesi adına önemlidir.
{"title":"Mimarlıkta Temsilin Dönüşümünü Ayrık Paradigması Üzerinden Sorgulamak","authors":"Zeynep Sena Sancak","doi":"10.53710/jcode.1234988","DOIUrl":"https://doi.org/10.53710/jcode.1234988","url":null,"abstract":"Mimaride temsil, tasarımcının düşünce süreçlerini ifade etmek için kullandığı yöntemler bütünüdür. Bilgisayarın günlük kullanıma dahil olmasıyla beraber gelişen ve farklılaşan bu yöntemler, beraberinde çeşitli sorgulamaları ve yeni temsil biçimlerini geliştirmiştir. Çalışmanın odaklandığı nokta, yeni tartışılan bir kavram olan ayrık paradigması ile mimari temsil ilişkisidir. Ayrık paradigması hesaplamalı tasarım yöntemlerini kullanarak mimarlığın temel yapı taşları ve kuralları üzerinde denemeler yaparak yeni bir söylem geliştirmeyi amaçlar. Bu bağlamda çalışma iki soru etrafında şekillenmiştir: Mimaride ayrık paradigması nedir? Tasarım süreci nasıl gerçekleşir? Çalışmada, ayrık paradigması hakkındaki görüşlerin tartışılması, tasarım ve temsil ilişkisinin irdelenmesi amaçlanmıştır. Çalışma üç bölümden oluşmaktadır. Birinci bölümde, temsil kavramı tanımlanıp, 1960’lı yıllardan itibaren günümüze kadar bilgisayar ortamında temsil süreçlerinin nasıl dönüştüğü incelenmiştir. İkinci bölümde ayrık paradigması tanımlanıp, konu hakkındaki görüşlere, üretilen projelere yer verilmiştir. Aynı zamanda ayrık paradigmasının temelini oluşturan; ayrıklık, süreklilik, mereoloji kavramları tartışılmıştır. Üçüncü bölümde ise paradigmanın bilgisayar ortamındaki temsilini incelemek adına Rhino Grasshopper’da form denemeleri yapılmıştır. Çalışma, tasarım sürecinde üzerine çok düşünülmeyen parçadan bütüne olan ilişkisinin potansiyellerinin ve temsil yöntemlerinin incelemesi adına önemlidir.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"17 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2023-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77108707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The search for novel representation method is one of the critical components of the creative design process. Discoveries in science, such as four-dimensional (4D) spacetime, influenced artists and architects. However, existing representation techniques constrained in two-dimensional (2D) sheets for 4D spacetime for representation is evaluated as a limitation of architecture discipline. Currently, digital game environments are the potential mediums of 4D architectural representation. This study aims to decode and represent time as an entity of 4D spaces. Digital game environment provides the needed flexibility for experimenting in 4D space. Therefore, unity game engine and C# programming are used together with computer aided design (CAD) tools to generate 4D representations. 4D representations are based on two different impressions of time dimension as (1) time dilation and (2) distortion of spacetime. While time dilation is represented via motion blur (mB) script, distortion of spacetime is represented via motion trail (mT) script. As preliminary results, metrics of the time dimension in 4D spatio-temporal representations are introduced. Experimental 4D representations produced via Unity game engine and C# programming are presented to discuss the potential of game environments to be the medium of architectural representation.
{"title":"A Method for Decoding and Representing Time in Fourdimensional Spaces via Digital Game Environment","authors":"Betül Uyan, S. Yazici","doi":"10.53710/jcode.1248185","DOIUrl":"https://doi.org/10.53710/jcode.1248185","url":null,"abstract":"The search for novel representation method is one of the critical components of the creative design process. Discoveries in science, such as four-dimensional (4D) spacetime, influenced artists and architects. However, existing representation techniques constrained in two-dimensional (2D) sheets for 4D spacetime for representation is evaluated as a limitation of architecture discipline. Currently, digital game environments are the potential mediums of 4D architectural representation. This study aims to decode and represent time as an entity of 4D spaces. Digital game environment provides the needed flexibility for experimenting in 4D space. Therefore, unity game engine and C# programming are used together with computer aided design (CAD) tools to generate 4D representations. 4D representations are based on two different impressions of time dimension as (1) time dilation and (2) distortion of spacetime. While time dilation is represented via motion blur (mB) script, distortion of spacetime is represented via motion trail (mT) script. As preliminary results, metrics of the time dimension in 4D spatio-temporal representations are introduced. Experimental 4D representations produced via Unity game engine and C# programming are presented to discuss the potential of game environments to be the medium of architectural representation.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"107 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2023-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76059679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The recent development of technology helps in the revolutionary war and it controls the war which is influenced by brilliant planning. The maneuver aircraft of intelligent algorithm aid the pilot to decide the particular position on the battlefield. Nowadays the hardware components of radar and missiles are widely used and the Beyond-Visual Range (BVR) is the most popular method applied in air combat. The introduction of close-range air combat maneuver decisions generates the attention of researchers in artificial intelligence. Most of the existing methods are based on autonomous aircraft focused in air combat scenario but manual air combats are widely applied in dual aircraft. Based on the factors mentioned above, a novel hierarchical maneuver decision architecture applied to a dual-aircraft close-range air combat scenario. Subsequently, the Soft Actor-Critic (SAC) algorithm is merged with competitive self-play which integrates the knowledge of sub-strategies. Further, the reinforcement learning technique is employed to achieve an approximate Nash equilibrium master strategy. The experimental results show that the hierarchical architecture exhibits good performance, symmetry, and robustness. The research generates a solution for intelligent formation of air combat in the future and guidance for Manned or unmanned aircraft cooperative combat.
{"title":"Hierarchical reinforcement learning from competitive self-play for dual-aircraft formation air combat","authors":"Weiren Kong, D. Zhou, Ying Zhou, Yiyang Zhao","doi":"10.1093/jcde/qwad020","DOIUrl":"https://doi.org/10.1093/jcde/qwad020","url":null,"abstract":"\u0000 The recent development of technology helps in the revolutionary war and it controls the war which is influenced by brilliant planning. The maneuver aircraft of intelligent algorithm aid the pilot to decide the particular position on the battlefield. Nowadays the hardware components of radar and missiles are widely used and the Beyond-Visual Range (BVR) is the most popular method applied in air combat. The introduction of close-range air combat maneuver decisions generates the attention of researchers in artificial intelligence. Most of the existing methods are based on autonomous aircraft focused in air combat scenario but manual air combats are widely applied in dual aircraft. Based on the factors mentioned above, a novel hierarchical maneuver decision architecture applied to a dual-aircraft close-range air combat scenario. Subsequently, the Soft Actor-Critic (SAC) algorithm is merged with competitive self-play which integrates the knowledge of sub-strategies. Further, the reinforcement learning technique is employed to achieve an approximate Nash equilibrium master strategy. The experimental results show that the hierarchical architecture exhibits good performance, symmetry, and robustness. The research generates a solution for intelligent formation of air combat in the future and guidance for Manned or unmanned aircraft cooperative combat.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"1 1","pages":"830-859"},"PeriodicalIF":4.9,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77602579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The construction site is one of the most dangerous industries because the number of occupational injuries and fatalities is significantly higher compared to other industries. Proper use of personal protective equipment (PPE) by workers can reduce the risk of occupational injuries and fatalities. However, for a variety of reasons, workers tend not to wear their personal protective equipment properly. To address these issues, we propose a vision-based framework for monitoring wearing personal protective equipment. The developed framework is based on the real-time pixel-level detect model YOLACT, which employs MobileNetV3 as a backbone to lightweight the proposed framework. In addition, the framework uses DeepSORT of object tracking algorithm to interpolate frames not predicted by the model. The post-processing algorithm in our framework classifies the correlation between workers and PPE into four statuses based on the results predicted by YOLACT and the interpolated results from DeepSORT. The results showed that the fine-tuned model achieved 66.4 mAP50, and the algorithm successfully determined workers’ PPE-wearing status detection with 91.3% accuracy. This study shows the potential to prevent occupational injuries and reduce social costs by automating monitoring at construction sites in real-time.
{"title":"Deep learning-based framework for monitoring wearing personal protective equipment on construction sites","authors":"Yeoreum Lee, Seung-Hwan Jung, Kyung-Su Kang, Han-Cheol Ryu, Hanyoung Ryu","doi":"10.1093/jcde/qwad019","DOIUrl":"https://doi.org/10.1093/jcde/qwad019","url":null,"abstract":"\u0000 The construction site is one of the most dangerous industries because the number of occupational injuries and fatalities is significantly higher compared to other industries. Proper use of personal protective equipment (PPE) by workers can reduce the risk of occupational injuries and fatalities. However, for a variety of reasons, workers tend not to wear their personal protective equipment properly. To address these issues, we propose a vision-based framework for monitoring wearing personal protective equipment. The developed framework is based on the real-time pixel-level detect model YOLACT, which employs MobileNetV3 as a backbone to lightweight the proposed framework. In addition, the framework uses DeepSORT of object tracking algorithm to interpolate frames not predicted by the model. The post-processing algorithm in our framework classifies the correlation between workers and PPE into four statuses based on the results predicted by YOLACT and the interpolated results from DeepSORT. The results showed that the fine-tuned model achieved 66.4 mAP50, and the algorithm successfully determined workers’ PPE-wearing status detection with 91.3% accuracy. This study shows the potential to prevent occupational injuries and reduce social costs by automating monitoring at construction sites in real-time.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"78 1","pages":"1314"},"PeriodicalIF":4.9,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81232824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mimarlığın bilgi çağına adaptasyon süreci, araçlar, yöntemler ve bilişsel süreçler bağlamında hızlı bir değişim ile gerçekleşmektedir. Sayısal tasarım olarak adlandırılan bu sürecin etkileri, mimari tasarım pedagojisinin de bu yeni tasarım yaklaşımları bağlamında değerlendirilmesini zorunlu kılmaktadır. Bu çalışmada, güncel koşul ve ihtiyaçlara uyum sağlaması hedeflenen enformel öğrenme yaklaşımlarıyla temellenen bir sayısal mimari tasarım pedagojisi modeli önerilmektedir. Çalışma tasarımcı ve tasarım arasındaki süreçlerin eylem ve kavram döngüsündeki etkileşiminin mimarlıktaki sayısal dönüşümlerle nasıl değiştiğinin irdelendiği bir literatür araştırmasıyla başlamaktadır. Bu bölümden elde edilen verilerin, sayısal tasarımın pedagojik modellerinin tasarımcı-tasarım ilişkisinde farklı döngüler içinde olması gerekliliğini vurgulaması sebebi ile, çalışmanın ikinci bölümü, bilinen pedagojik modellerden esnek ve adapte olabilir yapısı ile ayrışarak, yürütücü-öğrenci ilişkisinde alternatif yaklaşımlar sunmasıyla bu araştırmaya katkı koyacağı düşünülen enformel öğrenme üzerine tartışmaların incelenmesi ile devam etmektedir. Bu bölümde aynı zamanda, enformel öğrenmenin ele alınan yönlerinin çalışmanın metodolojisiyle ilişkisi ortaya konularak, çalışma kapsamında geliştirilen modele ilişkin yöntem de açıklanmıştır. Geliştirilen model (i) uzaklaşma - yeniden buluşma; (ii) Fiziksel ve dijital ortamlar arasında gidiş gelişlerin çoğaltılması; (iii) katı modellemeden parametrik ve üretken modellemeye kadar farklı stratejiler olmak üzere üç ana eksenden oluşmaktadır. Modelin COVID-19 pandemisi döneminde, çevrimiçi ve enformel yöntemlere göre birbirini tamamlayan üçlü bir çalıştay dizisi ile test edilme sürecinin anlatıldığı üçüncü bölümü, modelin uygulanabilirliği ve tekrarlanabilirliği bağlamında tartışıldığı sonuç bölümü takip etmektedir.
{"title":"Mimarlıkta Sayısal Tasarım Pedagojisi Bağlamında Enformel Öğrenme","authors":"Asena Kumsal ŞEN BAYRAM, Orkan Zeynel Güzelci, Sema Alaçam","doi":"10.53710/jcode.1227228","DOIUrl":"https://doi.org/10.53710/jcode.1227228","url":null,"abstract":"Mimarlığın bilgi çağına adaptasyon süreci, araçlar, yöntemler ve bilişsel süreçler bağlamında hızlı bir değişim ile gerçekleşmektedir. Sayısal tasarım olarak adlandırılan bu sürecin etkileri, mimari tasarım pedagojisinin de bu yeni tasarım yaklaşımları bağlamında değerlendirilmesini zorunlu kılmaktadır. Bu çalışmada, güncel koşul ve ihtiyaçlara uyum sağlaması hedeflenen enformel öğrenme yaklaşımlarıyla temellenen bir sayısal mimari tasarım pedagojisi modeli önerilmektedir. Çalışma tasarımcı ve tasarım arasındaki süreçlerin eylem ve kavram döngüsündeki etkileşiminin mimarlıktaki sayısal dönüşümlerle nasıl değiştiğinin irdelendiği bir literatür araştırmasıyla başlamaktadır. Bu bölümden elde edilen verilerin, sayısal tasarımın pedagojik modellerinin tasarımcı-tasarım ilişkisinde farklı döngüler içinde olması gerekliliğini vurgulaması sebebi ile, çalışmanın ikinci bölümü, bilinen pedagojik modellerden esnek ve adapte olabilir yapısı ile ayrışarak, yürütücü-öğrenci ilişkisinde alternatif yaklaşımlar sunmasıyla bu araştırmaya katkı koyacağı düşünülen enformel öğrenme üzerine tartışmaların incelenmesi ile devam etmektedir. Bu bölümde aynı zamanda, enformel öğrenmenin ele alınan yönlerinin çalışmanın metodolojisiyle ilişkisi ortaya konularak, çalışma kapsamında geliştirilen modele ilişkin yöntem de açıklanmıştır. Geliştirilen model (i) uzaklaşma - yeniden buluşma; (ii) Fiziksel ve dijital ortamlar arasında gidiş gelişlerin çoğaltılması; (iii) katı modellemeden parametrik ve üretken modellemeye kadar farklı stratejiler olmak üzere üç ana eksenden oluşmaktadır. Modelin COVID-19 pandemisi döneminde, çevrimiçi ve enformel yöntemlere göre birbirini tamamlayan üçlü bir çalıştay dizisi ile test edilme sürecinin anlatıldığı üçüncü bölümü, modelin uygulanabilirliği ve tekrarlanabilirliği bağlamında tartışıldığı sonuç bölümü takip etmektedir.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"34 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83122355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The computer revolution coming by way of data provides an innovative approach for the design of phononic crystals (PnCs) and elastic metamaterials (EMs). By establishing an analytical surrogate model for PnCs/EMs, deep learning based on artificial neural networks (ANNs) possesses the superiorities of rapidity and accuracy in design, making up for the shortcomings of traditional design methods. Here, the recent progresses on deep learning for forward prediction, parameter design, and topology design of PnCs and EMs are reviewed. The challenges and perspectives in this emerging field are also commented.
{"title":"Deep learning for the design of phononic crystals and elastic metamaterials","authors":"Chen-Xu Liu, Gui-Lan Yu","doi":"10.1093/jcde/qwad013","DOIUrl":"https://doi.org/10.1093/jcde/qwad013","url":null,"abstract":"\u0000 The computer revolution coming by way of data provides an innovative approach for the design of phononic crystals (PnCs) and elastic metamaterials (EMs). By establishing an analytical surrogate model for PnCs/EMs, deep learning based on artificial neural networks (ANNs) possesses the superiorities of rapidity and accuracy in design, making up for the shortcomings of traditional design methods. Here, the recent progresses on deep learning for forward prediction, parameter design, and topology design of PnCs and EMs are reviewed. The challenges and perspectives in this emerging field are also commented.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"28 1","pages":"602-614"},"PeriodicalIF":4.9,"publicationDate":"2023-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83689550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, we develop flexible multibody dynamic-electromagnetic-structural vibration coupled analysis method to accurately predict motor vibration by considering the electromagnetic force characteristics, rotating characteristics of rotating motor motors, and their interactions at the no-load rated speed and operating speed range. The structural characteristics are accurately reflected by developing a 3-D finite element model considering the entire components of the motor. The reliability of the 3-D finite element model of the motor is verified using the impact hammer test. In addition, to consider the rotational characteristics of the rotor structure, we develop a flexible multibody dynamics model that connects the flexible rotor and the bearing with revolute joint. The vibration of the motor at the no-load rated speed is analyzed using flexible multibody dynamics-electromagnetic-structural vibration coupled analysis. Comparing the vibration test results, it is confirmed that the flexible multibody dynamics-electromagnetic-structural vibration coupled analysis result predicts the actual motor vibration more accurately than the conventional finite element analysis-based electromagnetic-structural vibration coupled analysis result. By using flexible multibody dynamics-electromagnetic-structural vibration coupled analysis in the operating speed range, it is confirmed that not only electromagnetic force harmonics but also sideband harmonics caused by rotor eccentricity induced large vibrations, and also confirmed that it accurately predicts the vibration characteristics of actual motors with rotating rotors.
{"title":"Vibration analysis of electric motors considering rotating rotor structure using flexible multibody dynamics-electromagnetic-structural vibration coupled analysis","authors":"Seunghyeon Cho, K. Jeon, Chang-wan Kim","doi":"10.1093/jcde/qwad012","DOIUrl":"https://doi.org/10.1093/jcde/qwad012","url":null,"abstract":"\u0000 In this study, we develop flexible multibody dynamic-electromagnetic-structural vibration coupled analysis method to accurately predict motor vibration by considering the electromagnetic force characteristics, rotating characteristics of rotating motor motors, and their interactions at the no-load rated speed and operating speed range. The structural characteristics are accurately reflected by developing a 3-D finite element model considering the entire components of the motor. The reliability of the 3-D finite element model of the motor is verified using the impact hammer test. In addition, to consider the rotational characteristics of the rotor structure, we develop a flexible multibody dynamics model that connects the flexible rotor and the bearing with revolute joint. The vibration of the motor at the no-load rated speed is analyzed using flexible multibody dynamics-electromagnetic-structural vibration coupled analysis. Comparing the vibration test results, it is confirmed that the flexible multibody dynamics-electromagnetic-structural vibration coupled analysis result predicts the actual motor vibration more accurately than the conventional finite element analysis-based electromagnetic-structural vibration coupled analysis result. By using flexible multibody dynamics-electromagnetic-structural vibration coupled analysis in the operating speed range, it is confirmed that not only electromagnetic force harmonics but also sideband harmonics caused by rotor eccentricity induced large vibrations, and also confirmed that it accurately predicts the vibration characteristics of actual motors with rotating rotors.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"7 1","pages":"578-588"},"PeriodicalIF":4.9,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80145722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Data-driven intelligent computational design (DICD) is a research hotspot that emerged under fast-developing artificial intelligence. It emphasizes utilizing deep learning algorithms to extract and represent the design features hidden in historical or fabricated design process data and then learn the combination and mapping patterns of these design features for design solution retrieval, generation, optimization, evaluation, etc. Due to its capability of automatically and efficiently generating design solutions and thus supporting human-in-the-loop intelligent and innovative design activities, DICD has drawn the attention of both academic and industrial fields. However, as an emerging research subject, many unexplored issues still limit the development and application of DICD, such as specific dataset building, engineering design-related feature engineering, systematic methods and techniques for DICD implementation in the entire product design process, etc. In this regard, a systematic and operable road map for DICD implementation from a full-process perspective is established, including a general workflow for DICD project planning, an overall framework for DICD project implementation, the common mechanisms and calculation principles during DICD, key enabling technologies for detailed DICD implementation, and three case scenarios of DICD application. The road map can help academic researchers to locate their specific research directions for the further development of DICD and provide operable guidance for the engineers in their specific DICD applications.
{"title":"Data-driven intelligent computational design for products: method, techniques, and applications","authors":"Maolin Yang, P. Jiang, Tianshuo Zang, Yuhao Liu","doi":"10.1093/jcde/qwad070","DOIUrl":"https://doi.org/10.1093/jcde/qwad070","url":null,"abstract":"\u0000 Data-driven intelligent computational design (DICD) is a research hotspot that emerged under fast-developing artificial intelligence. It emphasizes utilizing deep learning algorithms to extract and represent the design features hidden in historical or fabricated design process data and then learn the combination and mapping patterns of these design features for design solution retrieval, generation, optimization, evaluation, etc. Due to its capability of automatically and efficiently generating design solutions and thus supporting human-in-the-loop intelligent and innovative design activities, DICD has drawn the attention of both academic and industrial fields. However, as an emerging research subject, many unexplored issues still limit the development and application of DICD, such as specific dataset building, engineering design-related feature engineering, systematic methods and techniques for DICD implementation in the entire product design process, etc. In this regard, a systematic and operable road map for DICD implementation from a full-process perspective is established, including a general workflow for DICD project planning, an overall framework for DICD project implementation, the common mechanisms and calculation principles during DICD, key enabling technologies for detailed DICD implementation, and three case scenarios of DICD application. The road map can help academic researchers to locate their specific research directions for the further development of DICD and provide operable guidance for the engineers in their specific DICD applications.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"27 1","pages":"1561-1578"},"PeriodicalIF":4.9,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84358677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A Goldberg polyhedron is a convex polyhedron made of hexagons and pentagons that have icosahedral rotational symmetry. Goldberg polyhedra have appeared frequently in art, architecture, and engineering. Some carbon fullerenes, inorganic cages, viruses, and proteins in nature exhibit the fundamental shapes of Goldberg polyhedra. According to Euler's polyhedron formula, an icosahedral Goldberg polyhedron always has exactly 12 pentagons. In Goldberg polyhedra, all pentagons are surrounded by hexagons only—this is known as the isolated pentagon rule (IPR). The present study systematically developed new families of cage-like structures derived from the initial topology of Goldberg polyhedra but with the 12 pentagons fused in five different arrangements and different densities of hexagonal faces. These families might be of great significance in biology and chemistry, where some non-IPR fullerenes have been created recently with chemical reactivity and properties markedly different from IPR fullerenes. Furthermore, this study has conducted an optimisation for multiple objectives and constraints, such as equal edge length, equal area, planarity, and spherical shape. The optimised configurations are highly desirable for architectural applications, where a structure with a small number of different edge lengths and planar faces may significantly reduce the fabrication cost and enable the construction of surfaces with flat panels.
{"title":"New families of cage-like structures based on Goldberg polyhedra with non-isolated pentagons","authors":"A. R. javan, Yuanpeng Liu, Y. Xie","doi":"10.1093/jcde/qwad005","DOIUrl":"https://doi.org/10.1093/jcde/qwad005","url":null,"abstract":"\u0000 A Goldberg polyhedron is a convex polyhedron made of hexagons and pentagons that have icosahedral rotational symmetry. Goldberg polyhedra have appeared frequently in art, architecture, and engineering. Some carbon fullerenes, inorganic cages, viruses, and proteins in nature exhibit the fundamental shapes of Goldberg polyhedra. According to Euler's polyhedron formula, an icosahedral Goldberg polyhedron always has exactly 12 pentagons. In Goldberg polyhedra, all pentagons are surrounded by hexagons only—this is known as the isolated pentagon rule (IPR). The present study systematically developed new families of cage-like structures derived from the initial topology of Goldberg polyhedra but with the 12 pentagons fused in five different arrangements and different densities of hexagonal faces. These families might be of great significance in biology and chemistry, where some non-IPR fullerenes have been created recently with chemical reactivity and properties markedly different from IPR fullerenes. Furthermore, this study has conducted an optimisation for multiple objectives and constraints, such as equal edge length, equal area, planarity, and spherical shape. The optimised configurations are highly desirable for architectural applications, where a structure with a small number of different edge lengths and planar faces may significantly reduce the fabrication cost and enable the construction of surfaces with flat panels.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"3 1","pages":"527-538"},"PeriodicalIF":4.9,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76995164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A vertically articulated robot with 6-degrees of freedom (DoF), called a general-purpose robot, can perform a myriad of different tasks within a workspace. This paper newly presents a probabilistic framework for the reliable optimal design of gearboxes used in general-purpose industrial robots, which considers random use conditions. To account for random use conditions, the start and end positions of a single motion profile are described as the random variable, which is statistically modeled as a uniform distribution based on the assumption that we have no information about the robot use pattern. Then, each sample of the random variable is converted to the corresponding motion profile by using an on-line trajectory planner. Monte Carlo simulation is implemented for the uncertainty propagation analysis, due to the heuristic feature of the on-line trajectory planner. In the design optimization formulation, the peak torque constraint and maximum bending moment constraint are described in a probabilistic manner. The system-level lifetime is calculated by combining component scale factors. The effectiveness of the proposed framework is demonstrated by examining a case study of a gearbox size problem for a 6-DoF serial industrial robot. The benefits of this study are as follows: Firstly, the proposed framework can evaluate the performance considering random use conditions. Secondly, torque reliability and bending moment reliability are newly proposed to ensure the dynamic performance of an industrial robot. Thirdly, the system-level lifetime by combining component scale factors gives more user-oriented and intuitive measure in an industrial robot design.
{"title":"Probabilistic framework for reliable optimal design of gearboxes in general-purpose industrial robots considering random use conditions","authors":"Jin-gyun Park, Heonjun Yoon, B. Youn","doi":"10.1093/jcde/qwad007","DOIUrl":"https://doi.org/10.1093/jcde/qwad007","url":null,"abstract":"\u0000 A vertically articulated robot with 6-degrees of freedom (DoF), called a general-purpose robot, can perform a myriad of different tasks within a workspace. This paper newly presents a probabilistic framework for the reliable optimal design of gearboxes used in general-purpose industrial robots, which considers random use conditions. To account for random use conditions, the start and end positions of a single motion profile are described as the random variable, which is statistically modeled as a uniform distribution based on the assumption that we have no information about the robot use pattern. Then, each sample of the random variable is converted to the corresponding motion profile by using an on-line trajectory planner. Monte Carlo simulation is implemented for the uncertainty propagation analysis, due to the heuristic feature of the on-line trajectory planner. In the design optimization formulation, the peak torque constraint and maximum bending moment constraint are described in a probabilistic manner. The system-level lifetime is calculated by combining component scale factors. The effectiveness of the proposed framework is demonstrated by examining a case study of a gearbox size problem for a 6-DoF serial industrial robot. The benefits of this study are as follows: Firstly, the proposed framework can evaluate the performance considering random use conditions. Secondly, torque reliability and bending moment reliability are newly proposed to ensure the dynamic performance of an industrial robot. Thirdly, the system-level lifetime by combining component scale factors gives more user-oriented and intuitive measure in an industrial robot design.","PeriodicalId":48611,"journal":{"name":"Journal of Computational Design and Engineering","volume":"48 1","pages":"539-548"},"PeriodicalIF":4.9,"publicationDate":"2023-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73235400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：