Amin Yousefpour, Mehdi Shishehbor, Zahra Zanjani Foumani, Ramin Bostanabad
Abstract Anomalies are samples that significantly deviate from the rest of the data and their detection plays a major role in building machine learning models that can be reliably used in applications such as data-driven design and novelty detection. The majority of existing anomaly detection methods either are exclusively developed for (semi) supervised settings, or provide poor performance in unsupervised applications where there is no training data with labeled anomalous samples. To bridge this research gap, we introduce a robust, efficient, and interpretable methodology based on nonlinear manifold learning to detect anomalies in unsupervised settings. The essence of our approach is to learn a low-dimensional and interpretable latent representation (aka manifold) for all the data points such that normal samples are automatically clustered together and hence can be easily and robustly identified. We learn this low-dimensional manifold by designing a learning algorithm that leverages either a latent map Gaussian process (LMGP) or a deep autoencoder (AE). Our LMGP-based approach, in particular, provides a probabilistic perspective on the learning task and is ideal for high-dimensional applications with scarce data. We demonstrate the superior performance of our approach over existing technologies via multiple analytic examples and real-world datasets.
{"title":"Unsupervised Anomaly Detection via Nonlinear Manifold Learning","authors":"Amin Yousefpour, Mehdi Shishehbor, Zahra Zanjani Foumani, Ramin Bostanabad","doi":"10.1115/1.4063642","DOIUrl":"https://doi.org/10.1115/1.4063642","url":null,"abstract":"Abstract Anomalies are samples that significantly deviate from the rest of the data and their detection plays a major role in building machine learning models that can be reliably used in applications such as data-driven design and novelty detection. The majority of existing anomaly detection methods either are exclusively developed for (semi) supervised settings, or provide poor performance in unsupervised applications where there is no training data with labeled anomalous samples. To bridge this research gap, we introduce a robust, efficient, and interpretable methodology based on nonlinear manifold learning to detect anomalies in unsupervised settings. The essence of our approach is to learn a low-dimensional and interpretable latent representation (aka manifold) for all the data points such that normal samples are automatically clustered together and hence can be easily and robustly identified. We learn this low-dimensional manifold by designing a learning algorithm that leverages either a latent map Gaussian process (LMGP) or a deep autoencoder (AE). Our LMGP-based approach, in particular, provides a probabilistic perspective on the learning task and is ideal for high-dimensional applications with scarce data. We demonstrate the superior performance of our approach over existing technologies via multiple analytic examples and real-world datasets.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135591731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marco Rossoni, Matteo Pozzi, Giorgio Colombo, Marco Gribaudo, Pietro Piazzolla
Abstract Point cloud 3D models are becoming more and more popular thanks to the spreading of scanning systems employed in many fields. When used for rendering purposes, point clouds are usually displayed with their original color acquired at scan time, without considering the lighting condition of the scene where the model is placed. This leads to a lack of realism in many contexts, especially in the case of animated point clouds employed in eXtended Reality applications where it would be desirable to have the model reacting to incoming light and integrating with the surrounding environment. This paper proposes the application of Physically Based Rendering (PBR), a rendering technique widely used in Real-Time Computer Graphics applications, to animated point cloud models for reproducing specular reflections, and achieving a photo-realistic and physically accurate look under any lighting condition. Firstly, we consider the extension of commonly used animated point cloud formats, to include normal vectors, and PBR parameters, as well as the encoding of the animated environment maps required by the technique. Then, an animated point cloud model is rendered with a shader implementing the proposed PBR method. Finally, the PBR pipeline is compared to traditional renderings of the same point cloud obtained with commonly used shaders, under different lighting conditions and environments. It will be shown how the point cloud better integrates visually with its surroundings.
随着扫描系统在各个领域的广泛应用，点云三维模型越来越受欢迎。当用于渲染目的时，点云通常以扫描时获得的原始颜色显示，而不考虑模型所在场景的照明条件。这导致在许多情况下缺乏真实感，特别是在扩展现实应用中使用的动画点云的情况下，它希望模型对入射光做出反应并与周围环境相结合。本文提出了一种广泛应用于实时计算机图形学应用的基于物理的渲染技术(physical Based Rendering, PBR)，用于动画点云模型，以再现镜面反射，并在任何光照条件下实现逼真的物理精确外观。首先，我们考虑了常用的动画点云格式的扩展，包括法向量和PBR参数，以及该技术所需的动画环境图的编码。然后，使用实现PBR方法的着色器渲染动画点云模型。最后，在不同的光照条件和环境下，将PBR管道与使用常用着色器获得的相同点云的传统渲染图进行比较。它将展示点云如何在视觉上更好地与周围环境融为一体。
{"title":"Physically-based Rendering of Animated Point Clouds for eXtended Reality","authors":"Marco Rossoni, Matteo Pozzi, Giorgio Colombo, Marco Gribaudo, Pietro Piazzolla","doi":"10.1115/1.4063559","DOIUrl":"https://doi.org/10.1115/1.4063559","url":null,"abstract":"Abstract Point cloud 3D models are becoming more and more popular thanks to the spreading of scanning systems employed in many fields. When used for rendering purposes, point clouds are usually displayed with their original color acquired at scan time, without considering the lighting condition of the scene where the model is placed. This leads to a lack of realism in many contexts, especially in the case of animated point clouds employed in eXtended Reality applications where it would be desirable to have the model reacting to incoming light and integrating with the surrounding environment. This paper proposes the application of Physically Based Rendering (PBR), a rendering technique widely used in Real-Time Computer Graphics applications, to animated point cloud models for reproducing specular reflections, and achieving a photo-realistic and physically accurate look under any lighting condition. Firstly, we consider the extension of commonly used animated point cloud formats, to include normal vectors, and PBR parameters, as well as the encoding of the animated environment maps required by the technique. Then, an animated point cloud model is rendered with a shader implementing the proposed PBR method. Finally, the PBR pipeline is compared to traditional renderings of the same point cloud obtained with commonly used shaders, under different lighting conditions and environments. It will be shown how the point cloud better integrates visually with its surroundings.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135344464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Due to the fact that rotors usually operate in a non-stationary mode with changing speeds, the conventional rotor unbalance detection method based on the stationary signal will produce a major “spectrum ambiguity issue” and affect the accuracy of rotor unbalance detection. To this end, a tacholess order tracking method based on the STFTSC algorithm is suggested in this study, where the STFTSC algorithm is developed by combining the short-time Fourier transform and the seam carving algorithm. Firstly, the STFTSC algorithm is utilized to accurately extract the instantaneous frequency (IF) of the rotor and calculate the instantaneous phase under variable-speed conditions. Subsequently, the original signal is resampled in the angular domain to transform the non-stationary time domain signal into a stable angle domain signal, eliminating the effect of the speed variations. Finally, the angular domain signal is transformed into the order domain signal, which uses the discrete Fourier transform and the discrete spectrum correction method to identify the amplitude and phase corresponding to the fundamental frequency component of the signal. The simulation results show that the IF extracted by the STFTSC algorithm has higher extraction accuracy compared with the traditional STFT spectral peak detection method and effectively eliminates the effect of speed fluctuations. A rotor dynamic-balancing experiment shows that the unbalance correction effect based on the STFTSC algorithm is remarkable, with the average unbalance amount decrease rate on the left and right sides being 90.02% and 92.56%, respectively, after a single correction.
{"title":"A tacholess order tracking method based on the STFTSC algorithm for rotor unbalance fault diagnosis under variable-speed conditions","authors":"Binyun Wu, Liang Hou, Shaojie Wang, Xiaozhen Lian","doi":"10.1115/1.4063401","DOIUrl":"https://doi.org/10.1115/1.4063401","url":null,"abstract":"Abstract Due to the fact that rotors usually operate in a non-stationary mode with changing speeds, the conventional rotor unbalance detection method based on the stationary signal will produce a major “spectrum ambiguity issue” and affect the accuracy of rotor unbalance detection. To this end, a tacholess order tracking method based on the STFTSC algorithm is suggested in this study, where the STFTSC algorithm is developed by combining the short-time Fourier transform and the seam carving algorithm. Firstly, the STFTSC algorithm is utilized to accurately extract the instantaneous frequency (IF) of the rotor and calculate the instantaneous phase under variable-speed conditions. Subsequently, the original signal is resampled in the angular domain to transform the non-stationary time domain signal into a stable angle domain signal, eliminating the effect of the speed variations. Finally, the angular domain signal is transformed into the order domain signal, which uses the discrete Fourier transform and the discrete spectrum correction method to identify the amplitude and phase corresponding to the fundamental frequency component of the signal. The simulation results show that the IF extracted by the STFTSC algorithm has higher extraction accuracy compared with the traditional STFT spectral peak detection method and effectively eliminates the effect of speed fluctuations. A rotor dynamic-balancing experiment shows that the unbalance correction effect based on the STFTSC algorithm is remarkable, with the average unbalance amount decrease rate on the left and right sides being 90.02% and 92.56%, respectively, after a single correction.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135878952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Augmented Reality (AR) enhances the user's perception of the real environment by superimposing virtual images generated by computers. These virtual images provide additional visual information that complements the real-world view. AR systems are rapidly gaining popularity in various manufacturing fields such as training, maintenance, assembly, and robot programming. In some AR applications, it is crucial for the invisible virtual environment to be precisely aligned with the physical environment to ensure that human users can accurately perceive the virtual augmentation in conjunction with their real surroundings. The process of achieving this accurate alignment is known as calibration. During some robotics applications using AR, we observed instances of misalignment in the visual representation within the designated workspace. This misalignment can potentially impact the accuracy of the robot's operations during the task. Based on previous research on AR-assisted robot programming systems, this work investigates the sources of misalignment errors and presents a simple and efficient calibration procedure to reduce the misalignment accuracy in general video see-through AR systems. To accurately superimpose virtual information onto the real environment, it is necessary to identify the sources and propagation of errors. In this work, we outline the linear transformation and projection of each point from the virtual world space to the virtual screen coordinates. An offline calibration method is introduced to determine the offset matrix from the Head-Mounted Display (HMD) to the camera, and experiments are conducted to validate the improvement achieved through the calibration process.
{"title":"A Global Correction Framework for Camera Registration in Video See-Through Augmented Reality Systems","authors":"Wenhao Yang, Yunbo Zhang","doi":"10.1115/1.4063350","DOIUrl":"https://doi.org/10.1115/1.4063350","url":null,"abstract":"\u0000 Augmented Reality (AR) enhances the user's perception of the real environment by superimposing virtual images generated by computers. These virtual images provide additional visual information that complements the real-world view. AR systems are rapidly gaining popularity in various manufacturing fields such as training, maintenance, assembly, and robot programming. In some AR applications, it is crucial for the invisible virtual environment to be precisely aligned with the physical environment to ensure that human users can accurately perceive the virtual augmentation in conjunction with their real surroundings. The process of achieving this accurate alignment is known as calibration. During some robotics applications using AR, we observed instances of misalignment in the visual representation within the designated workspace. This misalignment can potentially impact the accuracy of the robot's operations during the task. Based on previous research on AR-assisted robot programming systems, this work investigates the sources of misalignment errors and presents a simple and efficient calibration procedure to reduce the misalignment accuracy in general video see-through AR systems. To accurately superimpose virtual information onto the real environment, it is necessary to identify the sources and propagation of errors. In this work, we outline the linear transformation and projection of each point from the virtual world space to the virtual screen coordinates. An offline calibration method is introduced to determine the offset matrix from the Head-Mounted Display (HMD) to the camera, and experiments are conducted to validate the improvement achieved through the calibration process.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48143893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A 3D model is a storage method that can accurately describe the objective world. However, the establishment of a 3D model requires a lot of acquisition resources in details, and a precise 3D model often consumes abundant storage space. To eliminate these drawback, we propose a 3D data super-resolution model named three dimension slice reconstruction model(3DSR) that use low resolution 3D data as input to acquire a high resolution result instantaneously and accurately, shortening time and storage when building a precise 3D model. To boost the efficiency and accuracy of deep learning model, the 3D data is split as multiple slices. The 3DSR processes the slice to high resolution 2D image, and reconstruct the image as high resolution 3D data. 3D data slice-up method and slice-reconstruction method are designed to maintain the main features of 3D data. Meanwhile, a pre-trained deep 2D convolution neural network is utilized to expand the resolution of 2D image, which achieve superior performance. Our method saving the time to train deep learning model and computation time when improve the resolution. Furthermore, our model can achieve better performance even less data is utilized to train the model.
{"title":"3D-Slice-Super-Resolution-Net: A Fast Few Shooting Learning Model for 3D Super-resolution Using Slice-up and Slice-reconstruction","authors":"Hongbin Lin, Qingfeng Xu, Handing Xu, Yanjie Xu, Yiming Zheng, Yubin Zhong, Zhenguo Nie","doi":"10.1115/1.4063275","DOIUrl":"https://doi.org/10.1115/1.4063275","url":null,"abstract":"\u0000 A 3D model is a storage method that can accurately describe the objective world. However, the establishment of a 3D model requires a lot of acquisition resources in details, and a precise 3D model often consumes abundant storage space. To eliminate these drawback, we propose a 3D data super-resolution model named three dimension slice reconstruction model(3DSR) that use low resolution 3D data as input to acquire a high resolution result instantaneously and accurately, shortening time and storage when building a precise 3D model. To boost the efficiency and accuracy of deep learning model, the 3D data is split as multiple slices. The 3DSR processes the slice to high resolution 2D image, and reconstruct the image as high resolution 3D data. 3D data slice-up method and slice-reconstruction method are designed to maintain the main features of 3D data. Meanwhile, a pre-trained deep 2D convolution neural network is utilized to expand the resolution of 2D image, which achieve superior performance. Our method saving the time to train deep learning model and computation time when improve the resolution. Furthermore, our model can achieve better performance even less data is utilized to train the model.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49111918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a self-supervised learning approach for a robot to learn spatially varying process parameter models for contact-based finishing tasks. In many finishing tasks, a part has spatially varying stiffness. Some regions of the part enable the robot to efficiently execute the task. On the other hand, some other regions on the part may require the robot to move cautiously in order to prevent damage and ensure safety. Compared to the constant process parameter models, spatially varying process parameter models are more complex and challenging to learn. Our self-supervised learning approach consists of utilizing an initial parameter space exploration method, surrogate modeling, selection of region sequencing policy, and development of process parameter selection policy. We showed that by carefully selecting and optimizing learning components, this approach enables a robot to efficiently learn spatially varying process parameter models for a given contact-based finishing task. We demonstrated the effectiveness of our approach through computational simulations and physical experiments with a robotic sanding case study. Our work shows that the learning approach that has been optimized based on task characteristics significantly outperforms an unoptimized learning approach based on the overall task completion time.
{"title":"Self-Supervised Learning of Spatially Varying Process Parameter Models for Robotic Finishing Tasks","authors":"Yeo Jung Yoon, Santosh V. Narayan, S. Gupta","doi":"10.1115/1.4063276","DOIUrl":"https://doi.org/10.1115/1.4063276","url":null,"abstract":"\u0000 This paper presents a self-supervised learning approach for a robot to learn spatially varying process parameter models for contact-based finishing tasks. In many finishing tasks, a part has spatially varying stiffness. Some regions of the part enable the robot to efficiently execute the task. On the other hand, some other regions on the part may require the robot to move cautiously in order to prevent damage and ensure safety. Compared to the constant process parameter models, spatially varying process parameter models are more complex and challenging to learn. Our self-supervised learning approach consists of utilizing an initial parameter space exploration method, surrogate modeling, selection of region sequencing policy, and development of process parameter selection policy. We showed that by carefully selecting and optimizing learning components, this approach enables a robot to efficiently learn spatially varying process parameter models for a given contact-based finishing task. We demonstrated the effectiveness of our approach through computational simulations and physical experiments with a robotic sanding case study. Our work shows that the learning approach that has been optimized based on task characteristics significantly outperforms an unoptimized learning approach based on the overall task completion time.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"1 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42064611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, advances in additive manufacturing (AM) techniques have called for a scalable fabrication framework for high-resolution designs. Despite several process-specific handful design approaches, there is a gap to fill between computer-aided design (CAD) and the manufacturing of highly detailed multi-scale materials, especially for delicate cellular materials design. This gap ought to be filled with an avenue capable of efficiently slicing multi-scale intricate designs. Most existing methods depend on the mesh representation, which is time-consuming and memory-hogging to generate. This paper proposes an adaptive direct slicing (mesh-free) pipeline that exploits the function representation (FRep) for hierarchical architected cellular materials design. To explore the capabilities of the presented approach, several sample structures with delicate architectures are fabricated using a stereolithography (SLA) printer. The computational efficiency of the proposed slicing algorithm is studied. Furthermore, the geometry frustration problem brought by the connection of distinct structures between functionally graded unit cells at the micro-scale level is also investigated.
{"title":"STL-Free Adaptive Slicing Scheme for Additive Manufacturing of Cellular Materials","authors":"Sina Rastegarzadeh, Jida Huang","doi":"10.1115/1.4063227","DOIUrl":"https://doi.org/10.1115/1.4063227","url":null,"abstract":"\u0000 In recent years, advances in additive manufacturing (AM) techniques have called for a scalable fabrication framework for high-resolution designs. Despite several process-specific handful design approaches, there is a gap to fill between computer-aided design (CAD) and the manufacturing of highly detailed multi-scale materials, especially for delicate cellular materials design. This gap ought to be filled with an avenue capable of efficiently slicing multi-scale intricate designs. Most existing methods depend on the mesh representation, which is time-consuming and memory-hogging to generate. This paper proposes an adaptive direct slicing (mesh-free) pipeline that exploits the function representation (FRep) for hierarchical architected cellular materials design. To explore the capabilities of the presented approach, several sample structures with delicate architectures are fabricated using a stereolithography (SLA) printer. The computational efficiency of the proposed slicing algorithm is studied. Furthermore, the geometry frustration problem brought by the connection of distinct structures between functionally graded unit cells at the micro-scale level is also investigated.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42085100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shijie Bian, Daniele Grandi, Tianyang Liu, P. Jayaraman, Karl Willis, Elliot T. Salder, Bodia Borijin, Thomas Lu, Richard Otis, Nhut Ho, Bingbing Li
To enable intelligent CAD design tools, we introduce a machine learning architecture, namely HG-CAD, that supports the automated material prediction and recommendation of assembly bodies through joint learning of body and assembly-level features using a hierarchical graph representation. Specifically, we formulate the material prediction and recommendation process as a node-level classification task over a novel hierarchical graph representation of CAD models, with a low-level graph capturing the body geometry, a high-level graph representing the assembly topology, and a batch-level mask randomization enabling contextual awareness. This enables our network to aggregate geometric and topological features from both the body and assembly levels, leading to superior performance. Qualitative and quantitative evaluation of the proposed architecture on the Fusion 360 Gallery Assembly Dataset demonstrates the feasibility of our approach, outperforming both computer vision and human baselines, while showing promise in application scenarios. The proposed HG-CAD architecture that unifies the processing, encoding, and joint learning of multi-modal CAD features can scale to large repositories, incorporating designers' knowledge into the learning process. These capabilities allow the architecture to serve as a recommendation system for design automation and a baseline for future work.
{"title":"HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in CAD","authors":"Shijie Bian, Daniele Grandi, Tianyang Liu, P. Jayaraman, Karl Willis, Elliot T. Salder, Bodia Borijin, Thomas Lu, Richard Otis, Nhut Ho, Bingbing Li","doi":"10.1115/1.4063226","DOIUrl":"https://doi.org/10.1115/1.4063226","url":null,"abstract":"\u0000 To enable intelligent CAD design tools, we introduce a machine learning architecture, namely HG-CAD, that supports the automated material prediction and recommendation of assembly bodies through joint learning of body and assembly-level features using a hierarchical graph representation. Specifically, we formulate the material prediction and recommendation process as a node-level classification task over a novel hierarchical graph representation of CAD models, with a low-level graph capturing the body geometry, a high-level graph representing the assembly topology, and a batch-level mask randomization enabling contextual awareness. This enables our network to aggregate geometric and topological features from both the body and assembly levels, leading to superior performance. Qualitative and quantitative evaluation of the proposed architecture on the Fusion 360 Gallery Assembly Dataset demonstrates the feasibility of our approach, outperforming both computer vision and human baselines, while showing promise in application scenarios. The proposed HG-CAD architecture that unifies the processing, encoding, and joint learning of multi-modal CAD features can scale to large repositories, incorporating designers' knowledge into the learning process. These capabilities allow the architecture to serve as a recommendation system for design automation and a baseline for future work.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49586545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nathaniel DeVol, Christopher Saldaña, Katherine Fu
Machine condition monitoring has been proven to reduce machine down time and increase productivity. State of the art research uses vibration monitoring for tasks such as maintenance and tool wear prediction. A less explored aspect is how vibration monitoring might be used to monitor equipment sensitive to vibration. In a manufacturing environment, one example of where this might be needed is in monitoring the vibration of optical linear encoders used in high precision machine tools and coordinate measuring machines. Monitoring the vibration of sensitive equipment presents a unique case for vibration monitoring because an accurate calculation of the maximum sustained vibration is needed, as opposed to extracting trends from the data. To do this, techniques for determining sustained peaks in vibration signals are needed. This work fills this gap by formalizing and testing methods for determining sustained vibration amplitudes. The methods are tested on simulated signals based on experimental data. Results show that processing the signal directly with the novel Expire Timer method produces the smallest amounts of error on average under various test conditions. Additionally, this method can operate in real-time on streaming vibration data.
{"title":"Methods for the Automated Determination of Sustained Maximum Amplitudes in Oscillating Signals","authors":"Nathaniel DeVol, Christopher Saldaña, Katherine Fu","doi":"10.1115/1.4063130","DOIUrl":"https://doi.org/10.1115/1.4063130","url":null,"abstract":"\u0000 Machine condition monitoring has been proven to reduce machine down time and increase productivity. State of the art research uses vibration monitoring for tasks such as maintenance and tool wear prediction. A less explored aspect is how vibration monitoring might be used to monitor equipment sensitive to vibration. In a manufacturing environment, one example of where this might be needed is in monitoring the vibration of optical linear encoders used in high precision machine tools and coordinate measuring machines. Monitoring the vibration of sensitive equipment presents a unique case for vibration monitoring because an accurate calculation of the maximum sustained vibration is needed, as opposed to extracting trends from the data. To do this, techniques for determining sustained peaks in vibration signals are needed. This work fills this gap by formalizing and testing methods for determining sustained vibration amplitudes. The methods are tested on simulated signals based on experimental data. Results show that processing the signal directly with the novel Expire Timer method produces the smallest amounts of error on average under various test conditions. Additionally, this method can operate in real-time on streaming vibration data.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43002284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the past decade, human digital twins (HDTs) attracted much attention in and beyond digital twin (DT) applications. In this paper, we discuss the concept and the development of HDTs with a focus on their architecture, ethical concerns, key enabling technologies, and the opportunities of using HDTs in design. Based on the literature, we identified that data, model, and interface are three key modules in the proposed HDT architecture. Ethics is an important concern in the development and the use of the HDT from the humanities perspective. For key enabling technologies that support the functions of the HDT, we argue that the IoT infrastructure, data security, wearables, human modeling, explainable artificial intelligence, minimum viable sensing, and data visualization are strongly associated with the development of HDTs. Based on current applications, we highlight the design opportunities of using HDTs in designing products, services, and systems, as well as a design tool to facilitate the design process.
{"title":"Human digital twin, the development and impact on design","authors":"Yun-Hwa Song","doi":"10.1115/1.4063132","DOIUrl":"https://doi.org/10.1115/1.4063132","url":null,"abstract":"\u0000 In the past decade, human digital twins (HDTs) attracted much attention in and beyond digital twin (DT) applications. In this paper, we discuss the concept and the development of HDTs with a focus on their architecture, ethical concerns, key enabling technologies, and the opportunities of using HDTs in design. Based on the literature, we identified that data, model, and interface are three key modules in the proposed HDT architecture. Ethics is an important concern in the development and the use of the HDT from the humanities perspective. For key enabling technologies that support the functions of the HDT, we argue that the IoT infrastructure, data security, wearables, human modeling, explainable artificial intelligence, minimum viable sensing, and data visualization are strongly associated with the development of HDTs. Based on current applications, we highlight the design opportunities of using HDTs in designing products, services, and systems, as well as a design tool to facilitate the design process.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43914245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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：