Yanzhang Tong, Yan Liang, Ying Liu, Y. Hicks, Irena Spasic
Research on user experience (UX) has attracted much attention from designers. Additionally, hedonic quality can help designers understand user interaction (such as attractive, original and innovative) when they experience a product. Realising the user’s interaction state is a significant step for designers to optimise product design and service. Previous UX modelling lacks exploration in user interaction state. Also, the lack of user interaction state factor will reduce the accuracy of the UX modelling. In this paper, we explore the interaction value of online customer review and introduce a new approach to integrating hedonic quality for UX modelling. Firstly, extracting word list from online customer review; Secondly, hedonic quality words are extracted from the word list and added as a hedonic quality part to UX modelling; Thirdly, we compared the analysis result with our previous study for the conclusion. This research combines hedonic quality with UX modelling to enrich modelling in the field of UX for the first time. The proposed data collection method is superior to the traditional collection methods in hedonic quality studies. Extracting hedonic quality factors from online customer reviews can in-depth provide reflections for designers to improve their product design. Furthermore, it also explored the valuable relationship between UX and online customer reviews to provide proactive thinking in user strategy and design activities.
{"title":"Integrating Hedonic Quality for User Experience Modelling","authors":"Yanzhang Tong, Yan Liang, Ying Liu, Y. Hicks, Irena Spasic","doi":"10.1115/detc2021-69781","DOIUrl":"https://doi.org/10.1115/detc2021-69781","url":null,"abstract":"\u0000 Research on user experience (UX) has attracted much attention from designers. Additionally, hedonic quality can help designers understand user interaction (such as attractive, original and innovative) when they experience a product. Realising the user’s interaction state is a significant step for designers to optimise product design and service. Previous UX modelling lacks exploration in user interaction state. Also, the lack of user interaction state factor will reduce the accuracy of the UX modelling. In this paper, we explore the interaction value of online customer review and introduce a new approach to integrating hedonic quality for UX modelling. Firstly, extracting word list from online customer review; Secondly, hedonic quality words are extracted from the word list and added as a hedonic quality part to UX modelling; Thirdly, we compared the analysis result with our previous study for the conclusion. This research combines hedonic quality with UX modelling to enrich modelling in the field of UX for the first time. The proposed data collection method is superior to the traditional collection methods in hedonic quality studies. Extracting hedonic quality factors from online customer reviews can in-depth provide reflections for designers to improve their product design. Furthermore, it also explored the valuable relationship between UX and online customer reviews to provide proactive thinking in user strategy and design activities.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82215669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nessrine Elloumi, A. Ben Makhlouf, B. Louhichi, D. Deneux
For several years, research has been brought to reconstruct a Computer Aided Design (CAD) model from a 3D mesh or point cloud produced by scanning techniques or CAD software. This process, which recreates the geometry of a real part is called Revere Engineering (RE). In the industry, RE enables designers and engineers to virtually simulate, test and validate products before the manufacturing process. Therefore, it is common to use a reconstruction algorithm to rebuild a CAD model of a real object with high quality. This technique solves several problems of exchanging geometric models in engineering, computer vision, computer graphics, 3D animation, medical, mechanic, virtual/ augmented reality, etc. Therefore, CAD model reconstruction promotes the integration of 3D data without recopying or manual transformations and facilitates the visualization and simulation of the deformed model behavior. The aim of this work is how to rebuild a CAD model starting from a deformed mesh. The complexity of this problem requires to be split into several complementary parts. 3D surface reconstruction is considered as the most difficult step to obtain this geometric model. This paper consists in presenting an original method to reconstruct a CAD model surface (NURBS surface) starting from a triangulation (meshed surface) as a main step of the geometric model reconstruction.
{"title":"Towards a Building Techniques of a BREP Model Starting From a Meshed Surface","authors":"Nessrine Elloumi, A. Ben Makhlouf, B. Louhichi, D. Deneux","doi":"10.1115/detc2021-71724","DOIUrl":"https://doi.org/10.1115/detc2021-71724","url":null,"abstract":"\u0000 For several years, research has been brought to reconstruct a Computer Aided Design (CAD) model from a 3D mesh or point cloud produced by scanning techniques or CAD software. This process, which recreates the geometry of a real part is called Revere Engineering (RE). In the industry, RE enables designers and engineers to virtually simulate, test and validate products before the manufacturing process. Therefore, it is common to use a reconstruction algorithm to rebuild a CAD model of a real object with high quality. This technique solves several problems of exchanging geometric models in engineering, computer vision, computer graphics, 3D animation, medical, mechanic, virtual/ augmented reality, etc. Therefore, CAD model reconstruction promotes the integration of 3D data without recopying or manual transformations and facilitates the visualization and simulation of the deformed model behavior.\u0000 The aim of this work is how to rebuild a CAD model starting from a deformed mesh. The complexity of this problem requires to be split into several complementary parts. 3D surface reconstruction is considered as the most difficult step to obtain this geometric model. This paper consists in presenting an original method to reconstruct a CAD model surface (NURBS surface) starting from a triangulation (meshed surface) as a main step of the geometric model reconstruction.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76735433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Selective laser melting (SLM) is modernizing the production of highly complex metal parts across the manufacturing industry. However, achieving material homogeneity and controlling thermal deformation remain major challenges for metal-based, additive manufacturing. Therefore, adequate control systems are needed to monitor build processes, and ensure part quality throughout production. Traditionally, control designs relied on physics-based knowledge in analyzing, characterizing, and modeling complex, nonstationary patterns. Recent advancements in machine learning techniques harness the abundance of data to discover effective control designs. In this paper, we investigate the efficacy of a data-driven approach towards in-situ modeling of melt-pool geometry. Specifically, we propose a new methodology that uses a deep neural network architecture to predict melt pool geometries with linear regression models, which manifest during in-situ processes. Experimental results show that our deep neural network model with multiple input features produced 84% goodness of fit score, outperforming the model with a single feature that scored 37% for the given dataset, and the monitored regression models. These outcomes promote further investigation into new and efficient ways for acquiring real-time data from in-situ processes. Our contribution complements the way we understand properties of in-situ data, and predict patterns of melt pools, based on artificial cognition.
{"title":"Prediction of Melt Pool Geometry Using Deep Neural Networks","authors":"F. Milaat, Zhuo Yang, H. Ko, Albert T. Jones","doi":"10.1115/detc2021-69259","DOIUrl":"https://doi.org/10.1115/detc2021-69259","url":null,"abstract":"\u0000 Selective laser melting (SLM) is modernizing the production of highly complex metal parts across the manufacturing industry. However, achieving material homogeneity and controlling thermal deformation remain major challenges for metal-based, additive manufacturing. Therefore, adequate control systems are needed to monitor build processes, and ensure part quality throughout production. Traditionally, control designs relied on physics-based knowledge in analyzing, characterizing, and modeling complex, nonstationary patterns. Recent advancements in machine learning techniques harness the abundance of data to discover effective control designs. In this paper, we investigate the efficacy of a data-driven approach towards in-situ modeling of melt-pool geometry. Specifically, we propose a new methodology that uses a deep neural network architecture to predict melt pool geometries with linear regression models, which manifest during in-situ processes. Experimental results show that our deep neural network model with multiple input features produced 84% goodness of fit score, outperforming the model with a single feature that scored 37% for the given dataset, and the monitored regression models. These outcomes promote further investigation into new and efficient ways for acquiring real-time data from in-situ processes. Our contribution complements the way we understand properties of in-situ data, and predict patterns of melt pools, based on artificial cognition.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90496226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. B. Amor, Floriane Zongo, B. Louhichi, V. Brailovski, Antoine Tahan
Additive manufacturing (AM) processes are gaining popularity and are currently used in many research activities including the biomedical applications, the automotive industries and the aerospace. Laser powder bed fusion (LPBF) is an important AM process. Metallic LPBF process is experiencing significant growth, but one of the difficulties facing this growth is limited knowledge of its dimensional and geometrical performances, in addition to the inability to predict it. In this paper, we present the dimensional deviations of some LPBF-manufactured parts selected for this investigation. a uniform method was developed regarding relevant test specimens to examine dimensional deviations in order to derive dimensional tolerance values. The manufactured test specimens were measured to examine the process dimensional deviations behavior. These parts were manufactured from AlSi10Mg powder using an EOSINT M280 printer. The results show possible dimensional tolerance values that were classified from IT1 to IT11 according to the international standard ISO 286.
{"title":"Classification of Dimensional Deviation in Additive Manufacturing LPBF Process for AlSi10Mg Alloy According to ISO 286 and ANSI B4.2","authors":"S. B. Amor, Floriane Zongo, B. Louhichi, V. Brailovski, Antoine Tahan","doi":"10.1115/detc2021-71683","DOIUrl":"https://doi.org/10.1115/detc2021-71683","url":null,"abstract":"\u0000 Additive manufacturing (AM) processes are gaining popularity and are currently used in many research activities including the biomedical applications, the automotive industries and the aerospace. Laser powder bed fusion (LPBF) is an important AM process. Metallic LPBF process is experiencing significant growth, but one of the difficulties facing this growth is limited knowledge of its dimensional and geometrical performances, in addition to the inability to predict it. In this paper, we present the dimensional deviations of some LPBF-manufactured parts selected for this investigation. a uniform method was developed regarding relevant test specimens to examine dimensional deviations in order to derive dimensional tolerance values. The manufactured test specimens were measured to examine the process dimensional deviations behavior. These parts were manufactured from AlSi10Mg powder using an EOSINT M280 printer. The results show possible dimensional tolerance values that were classified from IT1 to IT11 according to the international standard ISO 286.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91072812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xingtong Yang, Ming Li, Liangchao Zhu, Weidong Zhong
Multi-material topology optimization problem under total mass constraint is a challenging problem owning to the incompressibility constraint on the summation of the usage of the total materials. A novel optimization approach is proposed here that utilizes the wide search space of the genetic algorithm, and greatly reduced computational effects achieved from the direct structure-performance mapping. The former optimization is carefully designed based on our recent theoretical insights, while the latter simulation is derived via a novel convolutional neural network based simulation which does not rely on any labeled simulation data but is instead designed based on a physics-informed loss function. As compared with results obtained using latest approach based on density interpolation, structures of better compliances are observed under acceptable computational costs, as demonstrated by our numerical examples.
{"title":"Evolutionary Discrete Multi-Material Topology Optimization Using CNN-Based Simulation Without Labeled Training Data","authors":"Xingtong Yang, Ming Li, Liangchao Zhu, Weidong Zhong","doi":"10.1115/detc2021-68487","DOIUrl":"https://doi.org/10.1115/detc2021-68487","url":null,"abstract":"\u0000 Multi-material topology optimization problem under total mass constraint is a challenging problem owning to the incompressibility constraint on the summation of the usage of the total materials. A novel optimization approach is proposed here that utilizes the wide search space of the genetic algorithm, and greatly reduced computational effects achieved from the direct structure-performance mapping. The former optimization is carefully designed based on our recent theoretical insights, while the latter simulation is derived via a novel convolutional neural network based simulation which does not rely on any labeled simulation data but is instead designed based on a physics-informed loss function. As compared with results obtained using latest approach based on density interpolation, structures of better compliances are observed under acceptable computational costs, as demonstrated by our numerical examples.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76858431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid development of parallelization technology over the recent decades has provided a promising avenue for the acceleration of meshfree simulation methods. One such method, peridynamics, is particularly well-suited for parallelization due to the simplicity of the operations which must occur at each material point. However, while MPI-based parallelization (Message-Passing Interface; a method for CPU-based parallelization) of peridynamic problems is commonplace, GPU parallelization of peridynamics has received far less attention. While GPU technology may have once been an inferior option to MPI parallelization for peridynamics, modern GPU cards are more than capable of handling substantially sized peridynamics problems. This paper presents the parallelization of the peridynamic method for single-card GPU computing, providing a schematic for a compact parallel approach. The resulting method is tested with CUDA on a NVIDIA Tesla P100 card with 16 GB of memory. The per-node memory requirements for each data structure used are evaluated, as well as the per-node execution times for each operation in a million-node benchmark test. This setup is shown to provide speedup factors over 200 for problems sized up to several million nodes, therefore indicating such a GPU is more than adequate for the single-card parallelization of the peridynamic method.
近几十年来并行化技术的迅速发展为加速无网格仿真方法提供了一条很有前途的途径。其中一种方法，周动力学，特别适合于并行化，因为操作简单，必须发生在每个材料点。然而，当基于mpi的并行化(消息传递接口;(一种基于cpu的并行化方法)的周期动力学问题是司空见惯的，GPU的周期动力学并行化受到的关注远远不够。虽然GPU技术可能曾经是MPI并行化的次等选择，但现代GPU卡能够处理大量大小的periddynamics问题。本文介绍了单卡GPU计算的动态并行化方法，为紧凑的并行化方法提供了一个原理图。该方法在具有16gb内存的NVIDIA Tesla P100卡上使用CUDA进行了测试。评估所使用的每个数据结构的每个节点内存需求，以及百万节点基准测试中每个操作的每个节点执行时间。这种设置可以为多达数百万个节点的问题提供超过200倍的加速系数，因此表明这样的GPU对于periddynamic方法的单卡并行化来说绰绰有余。
{"title":"A Single-Card GPU Implementation of Peridynamics","authors":"John Bartlett, D. Storti","doi":"10.1115/detc2021-68032","DOIUrl":"https://doi.org/10.1115/detc2021-68032","url":null,"abstract":"\u0000 The rapid development of parallelization technology over the recent decades has provided a promising avenue for the acceleration of meshfree simulation methods. One such method, peridynamics, is particularly well-suited for parallelization due to the simplicity of the operations which must occur at each material point. However, while MPI-based parallelization (Message-Passing Interface; a method for CPU-based parallelization) of peridynamic problems is commonplace, GPU parallelization of peridynamics has received far less attention. While GPU technology may have once been an inferior option to MPI parallelization for peridynamics, modern GPU cards are more than capable of handling substantially sized peridynamics problems. This paper presents the parallelization of the peridynamic method for single-card GPU computing, providing a schematic for a compact parallel approach. The resulting method is tested with CUDA on a NVIDIA Tesla P100 card with 16 GB of memory. The per-node memory requirements for each data structure used are evaluated, as well as the per-node execution times for each operation in a million-node benchmark test. This setup is shown to provide speedup factors over 200 for problems sized up to several million nodes, therefore indicating such a GPU is more than adequate for the single-card parallelization of the peridynamic method.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78084288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Cucinotta, R. Mineo, M. Raffaele, Fabio Salmeri
Lattice structures made by means of Additive Manufacturing are more and more used in several fields of application. In particular, reticular Titanium alloy bodies are used in biomechanics as fusion devices, due to their biocompatibility and lightweight characteristics. Although these structures have been extensively investigated, it is currently not possible to predict their behavior easily. Indeed, due to the high number of degrees of freedom of the lattice structures, it is usually required to conduct extensive experimental campaigns in order to anticipate the mechanical behavior of complex components. The present study proposes a method to predict the run-out in an intervertebral cervical cage based on experimental tests conducted on a similar cage and using Finite Element simulations. The cages were made of Ti-6Al-4V ELI by means of Electron Beam Melting. The experimental tests were carried out in accordance with the appropriate ASTM standards. The numerical simulations were consistent with the experimental results and showed a very good agreement. This methodology helped to identify the most critical issues and to verify a new cage without a second test campaign, which allows both cost and time savings.
{"title":"Assessment of the Run-Out of an Intervertebral Cervical Cage Fabricated by Additive Manufacturing Using Electron Beam Melting","authors":"F. Cucinotta, R. Mineo, M. Raffaele, Fabio Salmeri","doi":"10.1115/detc2021-70241","DOIUrl":"https://doi.org/10.1115/detc2021-70241","url":null,"abstract":"\u0000 Lattice structures made by means of Additive Manufacturing are more and more used in several fields of application. In particular, reticular Titanium alloy bodies are used in biomechanics as fusion devices, due to their biocompatibility and lightweight characteristics. Although these structures have been extensively investigated, it is currently not possible to predict their behavior easily. Indeed, due to the high number of degrees of freedom of the lattice structures, it is usually required to conduct extensive experimental campaigns in order to anticipate the mechanical behavior of complex components.\u0000 The present study proposes a method to predict the run-out in an intervertebral cervical cage based on experimental tests conducted on a similar cage and using Finite Element simulations. The cages were made of Ti-6Al-4V ELI by means of Electron Beam Melting. The experimental tests were carried out in accordance with the appropriate ASTM standards. The numerical simulations were consistent with the experimental results and showed a very good agreement.\u0000 This methodology helped to identify the most critical issues and to verify a new cage without a second test campaign, which allows both cost and time savings.","PeriodicalId":23602,"journal":{"name":"Volume 2: 41st Computers and Information in Engineering Conference (CIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87904518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：